Search results for: distributed algorithms

Authors: F. Tang, S. Boskovich, A. Raheja, Z. Aliyazicioglu, S. Bhandari, N. Tsuchiya

Abstract:

Calpoly Autonomous Transportation Experience (CATE) is a driverless vehicle that we are developing to provide safe, accessible, and efficient transportation of passengers throughout the Cal Poly Pomona campus for events such as orientation tours. Unlike the other self-driving vehicles that are usually developed to operate with other vehicles and reside only on the road networks, CATE will operate exclusively on walk-paths of the campus (potentially narrow passages) with pedestrians traveling from multiple locations. Safety becomes paramount as CATE operates within the same environment as pedestrians. As driverless vehicles assume greater roles in today’s transportation, this project will contribute to autonomous driving with pedestrian traffic in a highly dynamic environment. The CATE project requires significant interdisciplinary work. Researchers from mechanical engineering, electrical engineering and computer science are working together to attack the problem from different perspectives (hardware, software and system). In this abstract, we describe the software aspects of the project, with a focus on the requirements and the major components. CATE shall provide a GUI interface for the average user to interact with the car and access its available functionalities, such as selecting a destination from any origin on campus. We have developed an interface that provides an aerial view of the campus map, the current car location, routes, and the goal location. Users can interact with CATE through audio or manual inputs. CATE shall plan routes from the origin to the selected destination for the vehicle to travel. We will use an existing aerial map for the campus and convert it to a spatial graph configuration where the vertices represent the landmarks and edges represent paths that the car should follow with some designated behaviors (such as stay on the right side of the lane or follow an edge). Graph search algorithms such as A* will be implemented as the default path planning algorithm. D* Lite will be explored to efficiently recompute the path when there are any changes to the map. CATE shall avoid any static obstacles and walking pedestrians within some safe distance. Unlike traveling along traditional roadways, CATE’s route directly coexists with pedestrians. To ensure the safety of the pedestrians, we will use sensor fusion techniques that combine data from both lidar and stereo vision for obstacle avoidance while also allowing CATE to operate along its intended route. We will also build prediction models for pedestrian traffic patterns. CATE shall improve its location and work under a GPS-denied situation. CATE relies on its GPS to give its current location, which has a precision of a few meters. We have implemented an Unscented Kalman Filter (UKF) that allows the fusion of data from multiple sensors (such as GPS, IMU, odometry) in order to increase the confidence of localization. We also noticed that GPS signals can easily get degraded or blocked on campus due to high-rise buildings or trees. UKF can also help here to generate a better state estimate. In summary, CATE will provide on-campus transportation experience that coexists with dynamic pedestrian traffic. In future work, we will extend it to multi-vehicle scenarios.

Keywords: driverless vehicle, path planning, sensor fusion, state estimate

Procedia PDF Downloads 143

Authors: Meena Agrawal, Chaitanya P. Agrawal

Abstract:

The power systems are transforming and becoming smarter with innovations in technologies to enable embark simultaneously upon the sustainable energy needs, rising environmental concerns, economic benefits and quality requirements. The advantages provided by inter-connection of renewable energy resources are becoming more viable and dependable with the smart controlling technologies. The limitation of most renewable resources have their diversity and intermittency causing problems in power quality, grid stability, reliability, security etc. is being cured by these efforts. A necessitate of optimal energy management by intelligent Micro-Grids at the distribution end of the power system has been accredited to accommodate sustainable renewable Distributed Energy Resources on large scale across the power grid. All over the world Smart Grids are emerging now as foremost concern infrastructure upgrade programs. The hardware setup includes NI cRIO 9022, Compact Reconfigurable Input Output microcontroller board connected to the PC on a LAN router with three hardware modules. The Real-Time Embedded Controller is reconfigurable controller device consisting of an embedded real-time processor controller for communication and processing, a reconfigurable chassis housing the user-programmable FPGA, Eight hot-swappable I/O modules, and graphical LabVIEW system design software. It has been employed for signal analysis, controls and acquisition and logging of the renewable sources with the LabVIEW Real-Time applications. The employed cRIO chassis controls the timing for the module and handles communication with the PC over the USB, Ethernet, or 802.11 Wi-Fi buses. It combines modular I/O, real-time processing, and NI LabVIEW programmable. In the presented setup, the Analog Input Module NI 9205 five channels have been used for input analog voltage signals from renewable energy sources and NI 9227 four channels have been used for input analog current signals of the renewable sources. For switching actions based on the programming logic developed in software, a module having Electromechanical Relays (single-pole single throw) with 4-Channels, electrically isolated and LED indicating the state of that channel have been used for isolating the renewable Sources on fault occurrence, which is decided by the logic in the program. The module for Ethernet based Data Acquisition Interface ENET 9163 Ethernet Carrier, which is connected on the LAN Router for data acquisition from a remote source over Ethernet also has the module NI 9229 installed. The LabVIEW platform has been employed for efficient data acquisition, monitoring and control. Control logic utilized in program for operation of the hardware switching Related to Fault Relays has been portrayed as a flowchart. A communication system has been successfully developed amongst the sources and loads connected on different computers using Hypertext transfer protocol, HTTP or Ethernet Local Stacked area Network TCP/IP protocol. There are two main I/O interfacing clients controlling the operation of the switching control of the renewable energy sources over internet or intranet. The paper presents experimental results of the briefed setup for intelligent control of the micro-grid for renewable energy sources, besides the control of Micro-Grid with data acquisition and control hardware based on a microcontroller with visual program developed in LabVIEW.

Keywords: data acquisition and control, LabVIEW, microcontroller cRIO, Smart Micro-Grid

Procedia PDF Downloads 333

Authors: P. Ramesh, Aby Joseph, Arya G. Lal, U. S. Aji

Abstract:

Integration of distributed green renewable energy sources in addition with battery energy storage is an inevitable requirement in a smart grid environment. To achieve this, an Intelligent Green Energy Management System (i-GEMS) needs to be incorporated to ensure coordinated operation between supply and load demand based on the hierarchy of Renewable Energy Sources (RES), battery energy storage and distribution grid. A bi-directional energy harvester is an integral component facilitating Intelligent Green Energy Management System (i-GEMS) and it is required to meet the technical challenges mentioned as follows: (1) capability for bi-directional mode of operation (buck/boost) (2) reduction of circuit parasitic to suppress voltage spikes (3) converter startup problem (4) high frequency magnetics (5) higher power density (6) mode transition issues during battery charging and discharging. This paper is focused to address the above mentioned issues and targeted to design, develop and implement a bi-directional energy harvester with galvanic isolation. In this work, the hardware architecture for bi-directional energy harvester rated 3.5 kW is developed with Isolated Full Bridge Boost Converter (IFBBC) as well as Dual Active Bridge (DAB) Converter configuration using modular power electronics hardware which is identical for both solar PV array and battery energy storage. In IFBBC converter, the current fed full bridge circuit is enabled and voltage fed full bridge circuit is disabled through Pulse Width Modulation (PWM) pulses for boost mode of operation and vice-versa for buck mode of operation. In DAB converter, all the switches are in active state so as to adjust the phase shift angle between primary full bridge and secondary full bridge which in turn decides the power flow directions depending on modes (boost/buck) of operation. Here, the control algorithm is developed to ensure the regulation of the common DC link voltage and maximum power extraction from the renewable energy sources depending on the selected mode (buck/boost) of operation. The circuit analysis and simulation study are conducted using PSIM 9.0 in three scenarios which are - 1.IFBBC with passive clamp, 2. IFBBC with active clamp, 3. DAB converter. In this work, a common hardware prototype for bi-directional energy harvester with 3.5 kW rating is built for IFBBC and DAB converter configurations. The power circuit is equipped with right choice of MOSFETs, gate drivers with galvanic isolation, high frequency transformer, filter capacitors, and filter boost inductor. The experiment was conducted for IFBBC converter with passive clamp under boost mode and the prototype confirmed the simulation results showing the measured efficiency as 88% at 2.5 kW output power. The digital controller hardware platform is developed using floating point microcontroller TMS320F2806x from Texas Instruments. The firmware governing the operation of the bi-directional energy harvester is written in C language and developed using code composer studio. The comprehensive analyses of the power circuit design, control strategy for battery charging/discharging under buck/boost modes and comparative performance evaluation using simulation and experimental results will be presented.

Keywords: bi-directional energy harvester, dual active bridge, isolated full bridge boost converter, intelligent green energy management system, maximum power point tracking, renewable energy sources

Procedia PDF Downloads 140

Authors: Pablo Oteiza, Ricardo Alvarez, Mehrdad Pirnia, Fuat Can

Abstract:

To effectively combat climate change, many countries around the world have committed to a decarbonisation of their electricity, along with promoting a large-scale integration of renewable energy sources (RES). While this trend represents a unique opportunity to effectively combat climate change, achieving a sound and cost-efficient energy transition towards low-carbon power systems poses significant challenges for the multi-year Transmission Network Expansion Planning (TNEP) problem. The objective of the multi-year TNEP is to determine the necessary network infrastructure to supply the projected demand in a cost-efficient way, considering the evolution of the new generation mix, including the integration of RES. The rapid integration of large-scale RES increases the variability and uncertainty in the power system operation, which in turn increases short-term flexibility requirements. To meet these requirements, flexible generating technologies such as energy storage systems must be considered within the TNEP as well, along with proper models for capturing the operational challenges of future power systems. As a consequence, TNEP formulations are becoming more complex and difficult to solve, especially for its application in realistic-sized power system models. To meet these challenges, there is an increasing need for developing efficient algorithms capable of solving the TNEP problem with reasonable computational time and resources. In this regard, a promising research area is the use of artificial intelligence (AI) techniques for solving large-scale mixed-integer optimization problems, such as the TNEP. In particular, the use of AI along with mathematical optimization strategies based on decomposition has shown great potential. In this context, this paper presents an efficient algorithm for solving the multi-year TNEP problem. The algorithm combines AI techniques with Column Generation, a traditional decomposition-based mathematical optimization method. One of the challenges of using Column Generation for solving the TNEP problem is that the subproblems are of mixed-integer nature, and therefore solving them requires significant amounts of time and resources. Hence, in this proposal we solve a linearly relaxed version of the subproblems, and trained a binary classifier that determines the value of the binary variables, based on the results obtained from the linearized version. A key feature of the proposal is that we integrate the binary classifier into the optimization algorithm in such a way that the optimality of the solution can be guaranteed. The results of a study case based on the HRP 38-bus test system shows that the binary classifier has an accuracy above 97% for estimating the value of the binary variables. Since the linearly relaxed version of the subproblems can be solved with significantly less time than the integer programming counterpart, the integration of the binary classifier into the Column Generation algorithm allowed us to reduce the computational time required for solving the problem by 50%. The final version of this paper will contain a detailed description of the proposed algorithm, the AI-based binary classifier technique and its integration into the CG algorithm. To demonstrate the capabilities of the proposal, we evaluate the algorithm in case studies with different scenarios, as well as in other power system models.

Keywords: integer optimization, machine learning, mathematical decomposition, transmission planning

Procedia PDF Downloads 83

Authors: Eduardo Rodrigues, Gisela Mendes, José M. Torres, José E. Sousa

Abstract:

In the sequence of the liberalisation of the electricity sector a progressive engagement of consumers has been considered and targeted by sector regulatory policies. With the objective of promoting market competition while protecting consumers interests, by transferring some of the upstream benefits to the end users while reaching a fair distribution of system costs, different market models to value consumers’ demand flexibility at the energy community level are envisioned. Local Energy and Flexibility Markets (LEFM) involve stakeholders interested in providing or procure local flexibility for community, services and markets’ value. Under the scope of DOMINOES, a European research project supported by Horizon 2020, the local market concept developed is expected to: • Enable consumers/prosumers empowerment, by allowing them to value their demand flexibility and Distributed Energy Resources (DER); • Value local liquid flexibility to support innovative distribution grid management, e.g., local balancing and congestion management, voltage control and grid restoration; • Ease the wholesale market uptake of DER, namely small-scale flexible loads aggregation as Virtual Power Plants (VPPs), facilitating Demand Response (DR) service provision; • Optimise the management and local sharing of Renewable Energy Sources (RES) in Medium Voltage (MV) and Low Voltage (LV) grids, trough energy transactions within an energy community; • Enhance the development of energy markets through innovative business models, compatible with ongoing policy developments, that promote the easy access of retailers and other service providers to the local markets, allowing them to take advantage of communities’ flexibility to optimise their portfolio and subsequently their participation in external markets. The general concept proposed foresees a flow of market actions, technical validations, subsequent deliveries of energy and/or flexibility and balance settlements. Since the market operation should be dynamic and capable of addressing different requests, either prioritising balancing and prosumer services or system’s operation, direct procurement of flexibility within the local market must also be considered. This paper aims to highlight the research on the definition of suitable DR models to be used by the Distribution System Operator (DSO), in case of technical needs, and by the retailer, mainly for portfolio optimisation and solve unbalances. The models to be proposed and implemented within relevant smart distribution grid and microgrid validation environments, are focused on day-ahead and intraday operation scenarios, for predictive management and near-real-time control respectively under the DSO’s perspective. At local level, the DSO will be able to procure flexibility in advance to tackle different grid constrains (e.g., demand peaks, forecasted voltage and current problems and maintenance works), or during the operating day-to-day, to answer unpredictable constraints (e.g., outages, frequency deviations and voltage problems). Due to the inherent risks of their active market participation retailers may resort to DR models to manage their portfolio, by optimising their market actions and solve unbalances. The interaction among the market actors involved in the DR activation and in flexibility exchange is explained by a set of sequence diagrams for the DR modes of use from the DSO and the energy provider perspectives. • DR for DSO’s predictive management – before the operating day; • DR for DSO’s real-time control – during the operating day; • DR for retailer’s day-ahead operation; • DR for retailer’s intraday operation.

Keywords: demand response, energy communities, flexible demand, local energy and flexibility markets

Procedia PDF Downloads 98

Authors: Jan C. Droste, Justine Burns, Nithin Narayan

Abstract:

Introduction: Life-threatening detrimental effects of inappropriate adrenaline (epinephrine) administration, e.g., by giving the wrong dose, in the context of anaphylaxis management is well documented in the medical literature. Half of the fatal anaphylactic reactions in the UK are iatrogenic, and the median time to a cardio-respiratory arrest can be as short as 5 minutes. It is therefore imperative that hospital doctors of all grades have active and accurate knowledge of the correct route, site, and dosage of administration of adrenaline. Given this time constraint and the potential fatal outcome with inappropriate management of anaphylaxis, it is alarming that surveys over the last 15 years have repeatedly shown only a minority of doctors to have accurate knowledge of adrenaline administration as recommended by the UK Resuscitation Council guidelines (2008 updated 2012). This comparison of survey results of the medical workforce over several years in a small NHS District General Hospital was conducted in order to establish the effect of the employment of multiple educational methods regarding adrenaline administration in anaphylaxis in adults. Methods: Between 2010 and 2017, several education methods and tools were used to repeatedly inform the medical workforce (doctors and advanced clinical practitioners) in a single district general hospital regarding the treatment of anaphylaxis in adults. Whilst the senior staff remained largely the same cohort, junior staff had changed fully in every survey. Examples included: (i) Formal teaching -in Grand Rounds; during the junior doctors’ induction process; advanced life support courses (ii) In-situ simulation training performed by the clinical skills simulation team –several ad hoc sessions and one 3-day event in 2017 visiting 16 separate clinical areas performing an acute anaphylaxis scenario using actors- around 100 individuals from multi-disciplinary teams were involved (iii) Hospital-wide distribution of the simulation event via the Trust’s Simulation Newsletter (iv) Laminated algorithms were attached to the 'crash trolleys' (v) A short email 'alert' was sent to all medical staff 3 weeks prior to the survey detailing the emergency treatment of anaphylaxis (vi) In addition, the performance of the surveys themselves represented a teaching opportunity when gaps in knowledge could be addressed. Face to face surveys were carried out in 2010 ('pre-intervention), 2015, and 2017, in the latter two occasions including advanced clinical practitioners (ACP). All surveys consisted of convenience samples. If verbal consent to conduct the survey was obtained, the medical practitioners' answers were recorded immediately on a data collection sheet. Results: There was a sustained improvement in the knowledge of the medical workforce from 2010 to 2017: Answers improved regarding correct drug by 11% (84%, 95%, and 95%); the correct route by 20% (76%, 90%, and 96%); correct site by 40% (43%, 83%, and 83%) and the correct dose by 45% (27%, 54%, and 72%). Overall, knowledge of all components -correct drug, route, site, and dose-improved from 13% in 2010 to 62% in 2017. Conclusion: This survey comparison shows knowledge of the medical workforce regarding adrenaline administration for treatment of anaphylaxis in adults can be considerably improved by employing a variety of educational methods.

Keywords: adrenaline, anaphylaxis, epinephrine, medical education, patient safety

Procedia PDF Downloads 127

Authors: Yunwei Tang, Linhai Jing, Hui Li, Qingjie Liu, Xiuxia Li, Qi Yan, Haifeng Ding

Abstract:

The giant panda (Ailuropoda melanoleuca) is an endangered species, mainly live in central China, where bamboos act as the main food source of wild giant pandas. Knowledge of spatial distribution of bamboos therefore becomes important for identifying the habitat of giant pandas. There have been ongoing studies for mapping bamboos and other tree species using remote sensing. WorldView-2 (WV-2) is the first high resolution commercial satellite with eight Multi-Spectral (MS) bands. Recent studies demonstrated that WV-2 imagery has a high potential in classification of tree species. The advanced classification techniques are important for utilising high spatial resolution imagery. It is generally agreed that object-based image analysis is a more desirable method than pixel-based analysis in processing high spatial resolution remotely sensed data. Classifiers that use spatial information combined with spectral information are known as contextual classifiers. It is suggested that contextual classifiers can achieve greater accuracy than non-contextual classifiers. Thus, spatial correlation can be incorporated into classifiers to improve classification results. The study area is located at Wuyipeng area in Wolong, Sichuan Province. The complex environment makes it difficult for information extraction since bamboos are sparsely distributed, mixed with brushes, and covered by other trees. Extensive fieldworks in Wuyingpeng were carried out twice. The first one was on 11th June, 2014, aiming at sampling feature locations for geometric correction and collecting training samples for classification. The second fieldwork was on 11th September, 2014, for the purposes of testing the classification results. In this study, spectral separability analysis was first performed to select appropriate MS bands for classification. Also, the reflectance analysis provided information for expanding sample points under the circumstance of knowing only a few. Then, a spatially weighted object-based k-nearest neighbour (k-NN) classifier was applied to the selected MS bands to identify seven land cover types (bamboo, conifer, broadleaf, mixed forest, brush, bare land, and shadow), accounting for spatial correlation within classes using geostatistical modelling. The spatially weighted k-NN method was compared with three alternatives: the traditional k-NN classifier, the Support Vector Machine (SVM) method and the Classification and Regression Tree (CART). Through field validation, it was proved that the classification result obtained using the spatially weighted k-NN method has the highest overall classification accuracy (77.61%) and Kappa coefficient (0.729); the producer’s accuracy and user’s accuracy achieve 81.25% and 95.12% for the bamboo class, respectively, also higher than the other methods. Photos of tree crowns were taken at sample locations using a fisheye camera, so the canopy density could be estimated. It is found that it is difficult to identify bamboo in the areas with a large canopy density (over 0.70); it is possible to extract bamboos in the areas with a median canopy density (from 0.2 to 0.7) and in a sparse forest (canopy density is less than 0.2). In summary, this study explores the ability of WV-2 imagery for bamboo extraction in a mountainous region in Sichuan. The study successfully identified the bamboo distribution, providing supporting knowledge for assessing the habitats of giant pandas.

Keywords: bamboo mapping, classification, geostatistics, k-NN, worldview-2

Procedia PDF Downloads 311

Authors: Gus Calderon, Richard McCreight, Tammy Schwartz

Abstract:

Forensic analysis of community wildfire destruction in California has shown that reducing or removing flammable vegetation in proximity to buildings and structures is one of the most important wildfire defenses available to homeowners. State laws specify the requirements for homeowners to create and maintain defensible space around all structures. Unfortunately, this decades-long effort had limited success due to noncompliance and minimal enforcement. As a result, vulnerable communities continue to experience escalating human and economic costs along the wildland-urban interface (WUI). Quantifying vegetative fuels at both the community and parcel scale requires detailed imaging from an aircraft with remote sensing technology to reduce uncertainty. FireWatch has been delivering high spatial resolution (5” ground sample distance) wildfire hazard maps annually to the community of Rancho Santa Fe, CA, since 2019. FireWatch uses a multispectral imaging system mounted onboard an aircraft to create georeferenced orthomosaics and spectral vegetation index maps. Using proprietary algorithms, the vegetation type, condition, and proximity to structures are determined for 1,851 properties in the community. Secondary data processing combines object-based classification of vegetative fuels, assisted by machine learning, to prioritize mitigation strategies within the community. The remote sensing data for the 10 sq. mi. community is divided into parcels and sent to all homeowners in the form of defensible space maps and reports. Follow-up aerial surveys are performed annually using repeat station imaging of fixed GPS locations to address changes in defensible space, vegetation fuel cover, and condition over time. These maps and reports have increased wildfire awareness and mitigation efforts from 40% to over 85% among homeowners in Rancho Santa Fe. To assist homeowners fighting increasing insurance premiums and non-renewals, FireWatch has partnered with Black Swan Analytics, LLC, to leverage the multispectral imagery and increase homeowners’ understanding of wildfire risk drivers. For this study, a subsample of 100 parcels was selected to gain a comprehensive understanding of wildfire risk and the elements which can be mitigated. Geospatial data from FireWatch’s defensible space maps was combined with Black Swan’s patented approach using 39 other risk characteristics into a 4score Report. The 4score Report helps property owners understand risk sources and potential mitigation opportunities by assessing four categories of risk: Fuel sources, ignition sources, susceptibility to loss, and hazards to fire protection efforts (FISH). This study has shown that susceptibility to loss is the category residents and property owners must focus their efforts. The 4score Report also provides a tool to measure the impact of homeowner actions on risk levels over time. Resiliency is the only solution to breaking the cycle of community wildfire destruction and it starts with high-quality data and education.

Keywords: defensible space, geospatial data, multispectral imaging, Rancho Santa Fe, susceptibility to loss, wildfire risk.

Procedia PDF Downloads 106

Authors: James Brown, Stella Kortekaas, Ian Finnie, George Zhang, Christine Devine, Neil Healy

Abstract:

The use of GIS as an analysis tool for engineering decision making is now best practice in the offshore industry. GIS enables multidisciplinary data integration, analysis and visualisation which allows the presentation of large and intricate datasets in a simple map-interface accessible to all project stakeholders. Presenting integrated geoscience and geotechnical data in GIS enables decision makers to be well-informed. This paper is a successful case study of how GIS spatial analysis techniques were applied to help select the most favourable pipeline route. Routing a pipeline through any natural environment has numerous obstacles, whether they be topographical, geological, engineering or financial. Where the pipeline is subjected to external hydrostatic water pressure and is carrying pressurised hydrocarbons, the requirement to safely route the pipeline through hazardous terrain becomes absolutely paramount. This study illustrates how the application of modern, GIS-based pipeline routing techniques enabled the identification of a single most-favourable pipeline route crossing of a challenging seabed terrain. Conventional approaches to pipeline route determination focus on manual avoidance of primary constraints whilst endeavouring to minimise route length. Such an approach is qualitative, subjective and is liable to bias towards the discipline and expertise that is involved in the routing process. For very short routes traversing benign seabed topography in shallow water this approach may be sufficient, but for deepwater geohazardous sites, the need for an automated, multi-criteria, and quantitative approach is essential. This study combined multiple routing constraints using modern least-cost-routing algorithms deployed in GIS, hitherto unachievable with conventional approaches. The least-cost-routing procedure begins with the assignment of geocost across the study area. Geocost is defined as a numerical penalty score representing hazard posed by each routing constraint (e.g. slope angle, rugosity, vulnerability to debris flows) to the pipeline. All geocosted routing constraints are combined to generate a composite geocost map that is used to compute the least geocost route between two defined terminals. The analyses were applied to select the most favourable pipeline route for a potential gas development in deep water. The study area is geologically complex with a series of incised, potentially active, canyons carved into a steep escarpment, with evidence of extensive debris flows. A similar debris flow in the future could cause significant damage to a poorly-placed pipeline. Protruding inter-canyon spurs offer lower-gradient options for ascending an escarpment but the vulnerability of periodic failure of these spurs is not well understood. Close collaboration between geoscientists, pipeline engineers, geotechnical engineers and of course the gas export pipeline operator guided the analyses and assignment of geocosts. Shorter route length, less severe slope angles, and geohazard avoidance were the primary drivers in identifying the most favourable route.

Keywords: geocost, geohazard, pipeline route determination, pipeline route optimisation, spatial analysis

Procedia PDF Downloads 405

Authors: Amber Dhoot, Tarush Gupta, Andrea Gurr, William Jenkins, Sandro Pietrunti, Alexis Tang

Abstract:

Background: The COVID-19 pandemic has driven pharmacovigilance towards a new paradigm. Nowadays, more people than ever before are recognising and reporting adverse reactions from medications, treatments, and vaccines. In the modern era, with over 3.8 billion users, social media has become the most accessible medium for people to voice their opinions and so provides an opportunity to engage with more patient-centric and accessible pharmacovigilance. However, the pharmaceutical industry has been slow to incorporate social media into its modern pharmacovigilance strategy. This project aims to make social media a more effective tool in pharmacovigilance, and so reduce drug costs, improve drug safety and improve patient outcomes. This will be achieved by firstly uncovering and categorising the barriers facing the widespread adoption of social media in pharmacovigilance. Following this, the potential opportunities of social media will be explored. We will then propose realistic, practical recommendations to make social media a more effective tool for pharmacovigilance. Methodology: A comprehensive systematic literature review was conducted to produce a categorised summary of these barriers. This was followed by conducting 11 semi-structured interviews with pharmacovigilance experts to confirm the literature review findings whilst also exploring the unpublished and real-life challenges faced by those in the pharmaceutical industry. Finally, a survey of the general public (n = 112) ascertained public knowledge, perception, and opinion regarding the use of their social media data for pharmacovigilance purposes. This project stands out by offering perspectives from the public and pharmaceutical industry that fill the research gaps identified in the literature review. Results: Our results gave rise to several key analysis points. Firstly, inadequacies of current Natural Language Processing algorithms hinder effective pharmacovigilance data extraction from social media, and where data extraction is possible, there are significant questions over its quality. Social media also contains a variety of biases towards common drugs, mild adverse drug reactions, and the younger generation. Additionally, outdated regulations for social media pharmacovigilance do not align with new, modern General Data Protection Regulations (GDPR), creating ethical ambiguity about data privacy and level of access. This leads to an underlying mindset of avoidance within the pharmaceutical industry, as firms are disincentivised by the legal, financial, and reputational risks associated with breaking ambiguous regulations. Conclusion: Our project uncovered several barriers that prevent effective pharmacovigilance on social media. As such, social media should be used to complement traditional sources of pharmacovigilance rather than as a sole source of pharmacovigilance data. However, this project adds further value by proposing five practical recommendations that improve the effectiveness of social media pharmacovigilance. These include: prioritising health-orientated social media; improving technical capabilities through investment and strategic partnerships; setting clear regulatory guidelines using multi-stakeholder processes; creating an adverse drug reaction reporting interface inbuilt into social media platforms; and, finally, developing educational campaigns to raise awareness of the use of social media in pharmacovigilance. Implementation of these recommendations would speed up the efficient, ethical, and systematic adoption of social media in pharmacovigilance.

Keywords: adverse drug reaction, drug safety, pharmacovigilance, social media

Procedia PDF Downloads 81

Authors: Margarita Dufresne

Abstract:

This study devoted to development TPS for small space re-usable launchers. We have used SIRIUS design for S1 prototype. Multiphysics coupling for hypersonic reactive flow and thermos-structural analysis with and without ablation is provided by -CCM+ and COMSOL Multiphysics and FASTRAN and ACE+. Flow around hypersonic flight vehicles is the interaction of multiple shocks and the interaction of shocks with boundary layers. These interactions can have a very strong impact on the aeroheating experienced by the flight vehicle. A real gas implies the existence of a gas in equilibrium, non-equilibrium. Mach number ranged from 5 to 10 for first stage flight.The goals of this effort are to provide validation of the iterative coupling of hypersonic physics models in STAR-CCM+ and FASTRAN with COMSOL Multiphysics and ACE+. COMSOL Multiphysics and ACE+ are used for thermal structure analysis to simulate Conjugate Heat Transfer, with Conduction, Free Convection and Radiation to simulate Heat Flux from hypersonic flow. The reactive simulations involve an air chemical model of five species: N, N2, NO, O and O2. Seventeen chemical reactions, involving dissociation and recombination probabilities calculation include in the Dunn/Kang mechanism. Forward reaction rate coefficients based on a modified Arrhenius equation are computed for each reaction. The algorithms employed to solve the reactive equations used the second-order numerical scheme is obtained by a “MUSCL” (Monotone Upstream-cantered Schemes for Conservation Laws) extrapolation process in the structured case. Coupled inviscid flux: AUSM+ flux-vector splitting The MUSCL third-order scheme in STAR-CCM+ provides third-order spatial accuracy, except in the vicinity of strong shocks, where, due to limiting, the spatial accuracy is reduced to second-order and provides improved (i.e., reduced) dissipation compared to the second-order discretization scheme. initial unstructured mesh is refined made using this initial pressure gradient technique for the shock/shock interaction test case. The suggested by NASA turbulence models are the K-Omega SST with a1 = 0.355 and QCR (quadratic) as the constitutive option. Specified k and omega explicitly in initial conditions and in regions – k = 1E-6 *Uinf^2 and omega = 5*Uinf/ (mean aerodynamic chord or characteristic length). We put into practice modelling tips for hypersonic flow as automatic coupled solver, adaptative mesh refinement to capture and refine shock front, using advancing Layer Mesher and larger prism layer thickness to capture shock front on blunt surfaces. The temperature range from 300K to 30 000 K and pressure between 1e-4 and 100 atm. FASTRAN and ACE+ are coupled to provide high-fidelity solution for hot hypersonic reactive flow and Conjugate Heat Transfer. The results of both approaches meet the CIRCA wind tunnel results.

Keywords: hypersonic, first stage, high speed compressible flow, shock wave, aerodynamic heating, conugate heat transfer, conduction, free convection, radiation, fastran, ace+, comsol multiphysics, star-ccm+, thermal protection system (tps), space launcher, wind tunnel

Procedia PDF Downloads 68

Authors: Sofia Quaglia, Carmine Di Martino, Brendan Tierney

Abstract:

Artificial Intelligence (A.I.) constitutes various aspects of modern life, from the Machine Learning algorithms predicting the stocks on Wall streets to the killing of belligerents and innocents alike on the battlefield. Moreover, the end goal is to create autonomous A.I.; this means that the presence of humans in the decision-making process will be absent. The question comes naturally: when an A.I. does something wrong when its behavior is harmful to the community and its actions go against the law, which is to be held responsible? This research’s subject matter in A.I. and Robot Ethics focuses mainly on Robot Rights and its ultimate objective is to answer the questions: (i) What is the function of rights? (ii) Who is a right holder, what is personhood and the requirements needed to be a moral agent (therefore, accountable for responsibility)? (iii) Can an A.I. be a moral agent? (ontological requirements) and finally (iv) if it ought to be one (ethical implications). With the direction to answer this question, this research project was done via a collaboration between the School of Computer Science in the Technical University of Dublin that oversaw the technical aspects of this work, as well as the Department of Philosophy in the University of Milan, who supervised the philosophical framework and argumentation of the project. Firstly, it was found that all rights are positive and based on consensus; they change with time based on circumstances. Their function is to protect the social fabric and avoid dangerous situations. The same goes for the requirements considered necessary to be a moral agent: those are not absolute; in fact, they are constantly redesigned. Hence, the next logical step was to identify what requirements are regarded as fundamental in real-world judicial systems, comparing them to that of ones used in philosophy. Autonomy, free will, intentionality, consciousness and responsibility were identified as the requirements to be considered a moral agent. The work went on to build a symmetrical system between personhood and A.I. to enable the emergence of the ontological differences between the two. Each requirement is introduced, explained in the most relevant theories of contemporary philosophy, and observed in its manifestation in A.I. Finally, after completing the philosophical and technical analysis, conclusions were drawn. As underlined in the research questions, there are two issues regarding the assignment of moral agency to artificial agent: the first being that all the ontological requirements must be present and secondly being present or not, whether an A.I. ought to be considered as an artificial moral agent. From an ontological point of view, it is very hard to prove that an A.I. could be autonomous, free, intentional, conscious, and responsible. The philosophical accounts are often very theoretical and inconclusive, making it difficult to fully detect these requirements on an experimental level of demonstration. However, from an ethical point of view it makes sense to consider some A.I. as artificial moral agents, hence responsible for their own actions. When considering artificial agents as responsible, there can be applied already existing norms in our judicial system such as removing them from society, and re-educating them, in order to re-introduced them to society. This is in line with how the highest profile correctional facilities ought to work. Noticeably, this is a provisional conclusion and research must continue further. Nevertheless, the strength of the presented argument lies in its immediate applicability to real world scenarios. To refer to the aforementioned incidents, involving the murderer of innocents, when this thesis is applied it is possible to hold an A.I. accountable and responsible for its actions. This infers removing it from society by virtue of its un-usability, re-programming it and, only when properly functioning, re-introducing it successfully

Keywords: artificial agency, correctional system, ethics, natural agency, responsibility

Procedia PDF Downloads 188

Authors: Sergio Celaschi, Henrique Canavarro de Alencar, Claaudecir Biazoli

Abstract:

Effluent quality is of the highest priority for compliance with the permit limits of environmental protection agencies and ensures the protection of their local water system. Of the pollutants monitored, the biochemical oxygen demand (BOD) posed one of the greatest challenges. This work presents a solution for wastewater treatment plants - WWTP’s ability to react to different situations and meet treatment goals. Delayed BOD5 results from the lab take 7 to 8 analysis days, hindered the WWTP’s ability to react to different situations and meet treatment goals. Reducing BOD turnaround time from days to hours is our quest. Such a solution is based on a system of two BOD bioreactors associated with Digital Twin (DT) and Machine Learning (ML) methodologies via an Internet of Things (IoT) platform to monitor and control a WWTP to support decision making. DT is a virtual and dynamic replica of a production process. DT requires the ability to collect and store real-time sensor data related to the operating environment. Furthermore, it integrates and organizes the data on a digital platform and applies analytical models allowing a deeper understanding of the real process to catch sooner anomalies. In our system of continuous time monitoring of the BOD suppressed by the effluent treatment process, the DT algorithm for analyzing the data uses ML on a chemical kinetic parameterized model. The continuous BOD monitoring system, capable of providing results in a fraction of the time required by BOD5 analysis, is composed of two thermally isolated batch bioreactors. Each bioreactor contains input/output access to wastewater sample (influent and effluent), hydraulic conduction tubes, pumps, and valves for batch sample and dilution water, air supply for dissolved oxygen (DO) saturation, cooler/heater for sample thermal stability, optical ODO sensor based on fluorescence quenching, pH, ORP, temperature, and atmospheric pressure sensors, local PLC/CPU for TCP/IP data transmission interface. The dynamic BOD system monitoring range covers 2 mg/L < BOD < 2,000 mg/L. In addition to the BOD monitoring system, there are many other operational WWTP sensors. The CPU data is transmitted/received to/from the digital platform, which in turn performs analyses at periodic intervals, aiming to feed the learning process. BOD bulletins and their credibility intervals are made available in 12-hour intervals to web users. The chemical kinetics ML algorithm is composed of a coupled system of four first-order ordinary differential equations for the molar masses of DO, organic material present in the sample, biomass, and products (CO₂ and H₂O) of the reaction. This system is solved numerically linked to its initial conditions: DO (saturated) and initial products of the kinetic oxidation process; CO₂ = H₂0 = 0. The initial values for organic matter and biomass are estimated by the method of minimization of the mean square deviations. A real case of continuous monitoring of BOD wastewater effluent quality is being conducted by deploying an IoT application on a large wastewater purification system located in S. Paulo, Brazil.

Keywords: effluent treatment, biochemical oxygen demand, continuous monitoring, IoT, machine learning

Procedia PDF Downloads 72

Authors: Artur Tyliszczak, Ewa Szymanek, Maciej Marek

Abstract:

Flow through granular materials is important to a vast array of industries, for instance in construction industry where granular layers are used for bulkheads and isolators, in chemical engineering and catalytic reactors where large surfaces of packed granular beds intensify chemical reactions, or in energy production systems, where granulates are promising materials for heat storage and heat transfer media. Despite the common usage of granulates and extensive research performed in this field, phenomena occurring between granular solid elements or between solids and fluid are still not fully understood. In the present work we analyze the heat exchange process between the flowing medium (gas, liquid) and solid material inside the granular layers. We consider them as a composite of isolated solid elements and inter-granular spaces in which a gas or liquid can flow. The structure of the layer is controlled by shapes of particular granular elements (e.g., spheres, cylinders, cubes, Raschig rings), its spatial distribution or effective characteristic dimension (total volume or surface area). We will analyze to what extent alteration of these parameters influences on flow characteristics (turbulent intensity, mixing efficiency, heat transfer) inside the layer and behind it. Analysis of flow inside granular layers is very complicated because the use of classical experimental techniques (LDA, PIV, fibber probes) inside the layers is practically impossible, whereas the use of probes (e.g. thermocouples, Pitot tubes) requires drilling of holes inside the solid material. Hence, measurements of the flow inside granular layers are usually performed using for instance advanced X-ray tomography. In this respect, theoretical or numerical analyses of flow inside granulates seem crucial. Application of discrete element methods in combination with the classical finite volume/finite difference approaches is problematic as a mesh generation process for complex granular material can be very arduous. A good alternative for simulation of flow in complex domains is an immersed boundary-volume penalization (IB-VP) in which the computational meshes have simple Cartesian structure and impact of solid objects on the fluid is mimicked by source terms added to the Navier-Stokes and energy equations. The present paper focuses on application of the IB-VP method combined with large eddy simulation (LES). The flow solver used in this work is a high-order code (SAILOR), which was used previously in various studies, including laminar/turbulent transition in free flows and also for flows in wavy channels, wavy pipes and over various shape obstacles. In these cases a formal order of approximation turned out to be in between 1 and 2, depending on the test case. The current research concentrates on analyses of the flows in dense granular layers with elements distributed in a deterministic regular manner and validation of the results obtained using LES-IB method and body-fitted approach. The comparisons are very promising and show very good agreement. It is found that the size, number of elements and their distribution have huge impact on the obtained results. Ordering of the granular elements (or lack of it) affects both the pressure drop and efficiency of the heat transfer as it significantly changes mixing process.

Keywords: granular layers, heat transfer, immersed boundary method, numerical simulations

Procedia PDF Downloads 135

Authors: Ugo Galvanetto, Pirto G. Pavan, Mirco Zaccariotto

Abstract:

The discipline of Computer-integrated surgery (CIS) will provide equipment able to improve the efficiency of healthcare systems and, which is more important, clinical results. Surgeons and machines will cooperate in new ways that will extend surgeons’ ability to train, plan and carry out surgery. Patient specific CIS of the brain requires several steps: 1 - Fast generation of brain models. Based on image recognition of MR images and equipped with artificial intelligence, image recognition techniques should differentiate among all brain tissues and segment them. After that, automatic mesh generation should create the mathematical model of the brain in which the various tissues (white matter, grey matter, cerebrospinal fluid …) are clearly located in the correct positions. 2 – Reliable and fast simulation of the surgical process. Computational mechanics will be the crucial aspect of the entire procedure. New algorithms will be used to simulate the mechanical behaviour of cutting through cerebral tissues. 3 – Real time provision of visual and haptic feedback A sophisticated human-machine interface based on ergonomics and psychology will provide the feedback to the surgeon. The present work will address in particular point 2. Modelling the cutting of soft tissue in a structure as complex as the human brain is an extremely challenging problem in computational mechanics. The finite element method (FEM), that accurately represents complex geometries and accounts for material and geometrical nonlinearities, is the most used computational tool to simulate the mechanical response of soft tissues. However, the main drawback of FEM lies in the mechanics theory on which it is based, classical continuum Mechanics, which assumes matter is a continuum with no discontinuity. FEM must resort to complex tools such as pre-defined cohesive zones, external phase-field variables, and demanding remeshing techniques to include discontinuities. However, all approaches to equip FEM computational methods with the capability to describe material separation, such as interface elements with cohesive zone models, X-FEM, element erosion, phase-field, have some drawbacks that make them unsuitable for surgery simulation. Interface elements require a-priori knowledge of crack paths. The use of XFEM in 3D is cumbersome. Element erosion does not conserve mass. The Phase Field approach adopts a diffusive crack model instead of describing true tissue separation typical of surgical procedures. Modelling discontinuities, so difficult when using computational approaches based on classical continuum Mechanics, is instead easy for novel computational methods based on Peridynamics (PD). PD is a non-local theory of mechanics formulated with no use of spatial derivatives. Its governing equations are valid at points or surfaces of discontinuity, and it is, therefore especially suited to describe crack propagation and fragmentation problems. Moreover, PD does not require any criterium to decide the direction of crack propagation or the conditions for crack branching or coalescence; in the PD-based computational methods, cracks develop spontaneously in the way which is the most convenient from an energy point of view. Therefore, in PD computational methods, crack propagation in 3D is as easy as it is in 2D, with a remarkable advantage with respect to all other computational techniques.

Keywords: computational mechanics, peridynamics, finite element, biomechanics

Procedia PDF Downloads 80

Authors: Norma Binti Alias, Che Rahim Che The, Norfarizan Mohd Said, Sakinah Abdul Hanan, Akhtar Ali

Abstract:

This paper discusses on the transportation of magnetic drug targeting through blood within vessels, tissues and cells. There are three integrated mathematical models to be discussed and analyze the concentration of drug and blood flow through magnetic nanoparticles. The cell therapy brought advancement in the field of nanotechnology to fight against the tumors. The systematic therapeutic effect of Single Cells can reduce the growth of cancer tissue. The process of this nanoscale phenomena system is able to measure and to model, by identifying some parameters and applying fundamental principles of mathematical modeling and simulation. The mathematical modeling of single cell growth depends on three types of cell densities such as proliferative, quiescent and necrotic cells. The aim of this paper is to enhance the simulation of three types of models. The first model represents the transport of drugs by coupled partial differential equations (PDEs) with 3D parabolic type in a cylindrical coordinate system. This model is integrated by Non-Newtonian flow equations, leading to blood liquid flow as the medium for transportation system and the magnetic force on the magnetic nanoparticles. The interaction between the magnetic force on drug with magnetic properties produces induced currents and the applied magnetic field yields forces with tend to move slowly the movement of blood and bring the drug to the cancer cells. The devices of nanoscale allow the drug to discharge the blood vessels and even spread out through the tissue and access to the cancer cells. The second model is the transport of drug nanoparticles from the vascular system to a single cell. The treatment of the vascular system encounters some parameter identification such as magnetic nanoparticle targeted delivery, blood flow, momentum transport, density and viscosity for drug and blood medium, intensity of magnetic fields and the radius of the capillary. Based on two discretization techniques, finite difference method (FDM) and finite element method (FEM), the set of integrated models are transformed into a series of grid points to get a large system of equations. The third model is a single cell density model involving the three sets of first order PDEs equations for proliferating, quiescent and necrotic cells change over time and space in Cartesian coordinate which regulates under different rates of nutrients consumptions. The model presents the proliferative and quiescent cell growth depends on some parameter changes and the necrotic cells emerged as the tumor core. Some numerical schemes for solving the system of equations are compared and analyzed. Simulation and computation of the discretized model are supported by Matlab and C programming languages on a single processing unit. Some numerical results and analysis of the algorithms are presented in terms of informative presentation of tables, multiple graph and multidimensional visualization. As a conclusion, the integrated of three types mathematical modeling and the comparison of numerical performance indicates that the superior tool and analysis for solving the complete set of magnetic drug delivery system which give significant effects on the growth of the targeted cancer cell.

Keywords: mathematical modeling, visualization, PDE models, magnetic nanoparticle drug delivery model, drug release model, single cell effects, avascular tumor growth, numerical analysis

Procedia PDF Downloads 427

Authors: Jesus Carretero, Mario Vasile, Javier Garcia-Blas, Felix Garcia-Carballeira

Abstract:

Supporting cross-border secure and reliable exchange of data and documents and to promote data interoperability is critical for Europe to enhance sector (like eFinance, eJustice and eHealth). This work presents the status and results of the European Project MADE, a Research Project funded by Connecting Europe facility Programme, to provide secure e-invoicing and e-document exchange systems among Europe countries in compliance with the eIDAS Regulation (Regulation EU 910/2014 on electronic identification and trust services). The main goal of MADE is to develop six new AS4 Access Points and SMP in Europe to provide secure document exchanges using the eDelivery DSI (Digital Service Infrastructure) amongst both private and public entities. Moreover, the project demonstrates the feasibility and interest of the solution provided by providing several months of interoperability among the providers of the six partners in different EU countries. To achieve those goals, we have followed a methodology setting first a common background for requirements in the partner countries and the European regulations. Then, the partners have implemented access points in each country, including their service metadata publisher (SMP), to allow the access to their clients to the pan-European network. Finally, we have setup interoperability tests with the other access points of the consortium. The tests will include the use of each entity production-ready Information Systems that process the data to confirm all steps of the data exchange. For the access points, we have chosen AS4 instead of other existing alternatives because it supports multiple payloads, native web services, pulling facilities, lightweight client implementations, modern crypto algorithms, and more authentication types, like username-password and X.509 authentication and SAML authentication. The main contribution of MADE project is to open the path for European companies to use eDelivery services with cross-border exchange of electronic documents following PEPPOL (Pan-European Public Procurement Online) based on the e-SENS AS4 Profile. It also includes the development/integration of new components, integration of new and existing logging and traceability solutions and maintenance tool support for PKI. Moreover, we have found that most companies are still not ready to support those profiles. Thus further efforts will be needed to promote this technology into the companies. The consortium includes the following 9 partners. From them, 2 are research institutions: University Carlos III of Madrid (Coordinator), and Universidad Politecnica de Valencia. The other 7 (EDICOM, BIZbrains, Officient, Aksesspunkt Norge, eConnect, LMT group, Unimaze) are private entities specialized in secure delivery of electronic documents and information integration brokerage in their respective countries. To achieve cross-border operativity, they will include AS4 and SMP services in their platforms according to the EU Core Service Platform. Made project is instrumental to test the feasibility of cross-border documents eDelivery in Europe. If successful, not only einvoices, but many other types of documents will be securely exchanged through Europe. It will be the base to extend the network to the whole Europe. This project has been funded under the Connecting Europe Facility Agreement number: INEA/CEF/ICT/A2016/1278042. Action No: 2016-EU-IA-0063.

Keywords: security, e-delivery, e-invoicing, e-delivery, e-document exchange, trust

Procedia PDF Downloads 265

Authors: Jana Chakrabarti, Madhushrita Das, Ankhi Haldar, Roshni Chatterjee, Tanmoy Dey, Pubali Dhar

Abstract:

High incidences of Protein Energy Malnutrition as a consequence of low protein intake are quite prevalent among the children in developing countries. Thus prevention of under-nutrition has emerged as a critical challenge to India’s developmental Planners in recent times. Increase in population over the last decade has led to greater pressure on the existing animal protein sources. But these resources are currently declining due to persistent drought, diseases, natural disasters, high-cost of feed, and low productivity of local breeds and this decline in productivity is most evident in some developing countries. So the need of the hour is to search for efficient utilization of unconventional low-cost animal protein resources. Molluscs, as a group is regarded as under-exploited source of health-benefit molecules. Bivalve is the second largest class of phylum Mollusca. Annual harvests of bivalves for human consumption represent about 5% by weight of the total world harvest of aquatic resources. The freshwater mussel Lamellidens marginalis is widely distributed in ponds and large bodies of perennial waters in the Indian sub-continent and well accepted as food all over India. Moreover, ethno-medicinal uses of the flesh of Lamellidens among the rural people to treat hypertension have been documented. Present investigation thus attempts to evaluate the potential of Lamellidens marginalis as functional food. Mussels were collected from freshwater ponds and brought to the laboratory two days before experimentation for acclimatization in laboratory conditions. Shells were removed and fleshes were preserved at- 20oC until analysis. Tissue homogenate was prepared for proximate studies. Fatty acids and amino acids composition were analyzed. Vitamins, Minerals and Heavy metal contents were also studied. Mussel Protein hydrolysate was prepared using Alcalase 2.4 L and degree of hydrolysis was evaluated to analyze its Functional properties. Ferric Reducing Antioxidant Power (FRAP) and DPPH Antioxidant assays were performed. Anti-hypertensive property was evaluated by measuring Angiotensin Converting Enzyme (ACE) inhibition assay. Proximate analysis indicates that mussel meat contains moderate amount of protein (8.30±0.67%), carbohydrate (8.01±0.38%) and reducing sugar (4.75±0.07%), but less amount of fat (1.02±0.20%). Moisture content is quite high but ash content is very low. Phospholipid content is significantly high (19.43 %). Lipid constitutes, substantial amount of eicosapentaenoic acid (EPA) and docosahexaenoic acid (DHA) which have proven prophylactic values. Trace elements are found present in substantial amount. Comparative study of proximate nutrients between Labeo rohita, Lamellidens and cow’s milk indicates that mussel meat can be used as complementary food source. Functionality analyses of protein hydrolysate show increase in Fat absorption, Emulsification, Foaming capacity and Protein solubility. Progressive anti-oxidant and anti-hypertensive properties have also been documented. Lamellidens marginalis can thus be regarded as a functional food source as this may combine effectively with other food components for providing essential elements to the body. Moreover, mussel protein hydrolysate provides opportunities for utilizing it in various food formulations and pharmaceuticals. The observations presented herein should be viewed as a prelude to what future holds.

Keywords: functional food, functional properties, Lamellidens marginalis, protein hydrolysate

Procedia PDF Downloads 416

Authors: Ling Ai, Ziyu Zhao, Zeyu Zhou, Xiaochen Yang, Heng Zhai, Stuart Holmes

Abstract:

Optimizing the catalyst layer structure is crucial for enhancing the performance of proton exchange membrane fuel cells (PEMFCs) with low Platinum (Pt) loading. Current works focused on the utilization, durability, and site activity of Pt particles on support, and performance enhancement has been achieved by loading Pt onto porous support with different morphology, such as graphene, carbon fiber, and carbon black. Some schemes have also incorporated cost considerations to achieve lower Pt loading. However, the design of the catalyst layer (CL) structure in the membrane electrode assembly (MEA) must consider the interactions between the layers. Addressing the crucial aspects of water management, low contact resistance, and the establishment of effective three-phase boundary for MEA, multi-walled carbon nanotubes (MWCNTs) are promising CL support due to their intrinsically high hydrophobicity, high axial electrical conductivity, and potential for ordered alignment. However, the drawbacks of MWCNTs, such as strong agglomeration, wall surface chemical inertness, and unopened ends, are unfavorable for Pt nanoparticle loading, which is detrimental to MEA processing and leads to inhomogeneous CL surfaces. This further deteriorates the utilization of Pt and increases the contact resistance. Robust chemical oxidation or nitrogen doping can introduce polar functional groups onto the surface of MWCNTs, facilitating the creation of open tube ends and inducing defects in tube walls. This improves dispersibility and load capacity but reduces length and conductivity. Consequently, a trade-off exists between maintaining the intrinsic properties and the degree of functionalization of MWCNTs. In this work, MWCNTs were modified based on the operational requirements of the MEA from the viewpoint of interlayer interactions, including the search for the optimal degree of oxidation, N-doping, and micro-arrangement. MWCNT were functionalized by oxidizing, N-doping, as well as micro-alignment to achieve lower contact resistance between CL and proton exchange membrane (PEM), better hydrophobicity, and enhanced performance. Furthermore, this work expects to construct a more continuously distributed three-phase boundary by aligning MWCNT to form a locally ordered structure, which is essential for the efficient utilization of Pt active sites. Different from other chemical oxidation schemes that used HNO3:H2SO4 (1:3) mixed acid to strongly oxidize MWCNT, this scheme adopted pure HNO3 to partially oxidize MWCNT at a lower reflux temperature (80 ℃) and a shorter treatment time (0 to 10 h) to preserve the morphology and intrinsic conductivity of MWCNT. The maximum power density of 979.81 mw cm-2 was achieved by Pt loading on 6h MWCNT oxidation time (Pt-MWCNT6h). This represented a 59.53% improvement over the commercial Pt/C catalyst of 614.17 (mw cm-2). In addition, due to the stronger electrical conductivity, the charge transfer resistance of Pt-MWCNT6h in the electrochemical impedance spectroscopy (EIS) test was 0.09 Ohm cm-2, which was 48.86% lower than that of Pt/C. This study will discuss the developed catalysts and their efficacy in a working fuel cell system. This research will validate the impact of low-functionalization modification of MWCNTs on the performance of PEMFC, which simplifies the preparation challenges of CL and contributing for the widespread commercial application of PEMFCs on a larger scale.

Keywords: carbon nanotubes, electrocatalyst, membrane electrode assembly, proton exchange membrane fuel cell

Procedia PDF Downloads 68

Authors: Juan Pablo Botero Torres, Alba Avila, Luis Felipe Giraldo

Abstract:

Independent navigation and mobility through unknown spaces pose a challenge for the autonomy of visually impaired people (VIP), who have relied on the use of traditional assistive tools like the white cane and trained dogs. However, emerging visually assistive technologies (VAT) have proposed several human-machine interfaces (HMIs) that could improve VIP’s ability for self-guidance. Hereby, we introduce the design and implementation of a visually assistive device, Anajaa – Visual Substitution System (AVSS). This system integrates ultrasonic sensors with custom electronics, and computer vision models (convolutional neural networks), in order to achieve a robust system that acquires information of the surrounding space and transmits it to the user in an intuitive and efficient manner. AVSS consists of two modules: the sensing and the actuation module, which are fitted to a chest mount and belt that communicate via Bluetooth. The sensing module was designed for the acquisition and processing of proximity signals provided by an array of ultrasonic sensors. The distribution of these within the chest mount allows an accurate representation of the surrounding space, discretized in three different levels of proximity, ranging from 0 to 6 meters. Additionally, this module is fitted with an RGB-D camera used to detect potentially threatening obstacles, like staircases, using a convolutional neural network specifically trained for this purpose. Posteriorly, the depth data is used to estimate the distance between the stairs and the user. The information gathered from this module is then sent to the actuation module that creates an HMI, by the means of a 3x2 array of vibration motors that make up the tactile display and allow the system to deliver haptic feedback. The actuation module uses vibrational messages (tactones); changing both in amplitude and frequency to deliver different awareness levels according to the proximity of the obstacle. This enables the system to deliver an intuitive interface. Both modules were tested under lab conditions, and the HMI was additionally tested with a focal group of VIP. The lab testing was conducted in order to establish the processing speed of the computer vision algorithms. This experimentation determined that the model can process 0.59 frames per second (FPS); this is considered as an adequate processing speed taking into account that the walking speed of VIP is 1.439 m/s. In order to test the HMI, we conducted a focal group composed of two females and two males between the ages of 35-65 years. The subject selection was aided by the Colombian Cooperative of Work and Services for the Sightless (COOTRASIN). We analyzed the learning process of the haptic messages throughout five experimentation sessions using two metrics: message discrimination and localization success. These correspond to the ability of the subjects to recognize different tactones and locate them within the tactile display. Both were calculated as the mean across all subjects. Results show that the focal group achieved message discrimination of 70% and a localization success of 80%, demonstrating how the proposed HMI leads to the appropriation and understanding of the feedback messages, enabling the user’s awareness of its surrounding space.

Keywords: computer vision on embedded systems, electronic trave aids, human-machine interface, haptic feedback, visual assistive technologies, vision substitution systems

Procedia PDF Downloads 80

Authors: Anne Schattel, Mitja Echim, Christof Büskens

Abstract:

Trajectory planning for deep space missions has become a recent topic of great interest. Flying to space objects like asteroids provides two main challenges. One is to find rare earth elements, the other to gain scientific knowledge of the origin of the world. Due to the enormous spatial distances such explorer missions have to be performed unmanned and autonomously. The mathematical field of optimization and optimal control can be used to realize autonomous missions while protecting recourses and making them safer. The resulting algorithms may be applied to other, earth-bound applications like e.g. deep sea navigation and autonomous driving as well. The project KaNaRiA ('Kognitionsbasierte, autonome Navigation am Beispiel des Ressourcenabbaus im All') investigates the possibilities of cognitive autonomous navigation on the example of an asteroid mining mission, including the cruise phase and approach as well as the asteroid rendezvous, landing and surface exploration. To verify and test all methods an interactive, real-time capable simulation using virtual reality is developed under KaNaRiA. This paper focuses on the specific challenge of the guidance during the cruise phase of the spacecraft, i.e. trajectory optimization and optimal control, including first solutions and results. In principle there exist two ways to solve optimal control problems (OCPs), the so called indirect and direct methods. The indirect methods are being studied since several decades and their usage needs advanced skills regarding optimal control theory. The main idea of direct approaches, also known as transcription techniques, is to transform the infinite-dimensional OCP into a finite-dimensional non-linear optimization problem (NLP) via discretization of states and controls. These direct methods are applied in this paper. The resulting high dimensional NLP with constraints can be solved efficiently by special NLP methods, e.g. sequential quadratic programming (SQP) or interior point methods (IP). The movement of the spacecraft due to gravitational influences of the sun and other planets, as well as the thrust commands, is described through ordinary differential equations (ODEs). The competitive mission aims like short flight times and low energy consumption are considered by using a multi-criteria objective function. The resulting non-linear high-dimensional optimization problems are solved by using the software package WORHP ('We Optimize Really Huge Problems'), a software routine combining SQP at an outer level and IP to solve underlying quadratic subproblems. An application-adapted model of impulsive thrusting, as well as a model of an electrically powered spacecraft propulsion system, is introduced. Different priorities and possibilities of a space mission regarding energy cost and flight time duration are investigated by choosing different weighting factors for the multi-criteria objective function. Varying mission trajectories are analyzed and compared, both aiming at different destination asteroids and using different propulsion systems. For the transcription, the robust method of full discretization is used. The results strengthen the need for trajectory optimization as a foundation for autonomous decision making during deep space missions. Simultaneously they show the enormous increase in possibilities for flight maneuvers by being able to consider different and opposite mission objectives.

Keywords: deep space navigation, guidance, multi-objective, non-linear optimization, optimal control, trajectory planning.

Procedia PDF Downloads 411

Authors: Loretta Ichim, Dan Popescu, Grigore Stamatescu

Abstract:

The paper reports the collaboration between a top university from Romania and three companies for the implementation of a research project in a multidisciplinary domain, focusing on the impact and benefits both for the education and industry. The joint activities were developed under the Space Technology and Advanced Research Program (STAR), funded by the Romanian Space Agency (ROSA) for a university-industry partnership. The context was defined by linking the European Space Agency optional programs, with the development and promotion national research, with the educational and industrial capabilities in the aeronautics, security and related areas by increasing the collaboration between academic and industrial entities as well as by realizing high-level scientific production. The project name is Multisensory Robotic System for Aerial Monitoring of Critical Infrastructure Systems (MUROS), which was carried 2013-2016. The project included the University POLITEHNICA of Bucharest (coordinator) and three companies, which manufacture and market unmanned aerial systems. The project had as main objective the development of an integrated system for combined ground wireless sensor networks and UAV monitoring in various application scenarios for critical infrastructure surveillance. This included specific activities related to fundamental and applied research, technology transfer, prototype implementation and result dissemination. The core area of the contributions laid in distributed data processing and communication mechanisms, advanced image processing and embedded system development. Special focus is given by the paper to analyzing the impact the project implementation in the educational process, directly or indirectly, through the faculty members (professors and students) involved in the research team. Three main directions are discussed: a) enabling students to carry out internships at the partner companies, b) handling advanced topics and industry requirements at the master's level, c) experiments and concept validation for doctoral thesis. The impact of the research work (as the educational component) developed by the faculty members on the increasing performances of the companies’ products is highlighted. The collaboration between university and companies was well balanced both for contributions and results. The paper also presents the outcomes of the project which reveals the efficient collaboration between high education and industry: master thesis, doctoral thesis, conference papers, journal papers, technical documentation for technology transfer, prototype, and patent. The experience can provide useful practices of blending research and education within an academia-industry cooperation framework while the lessons learned represent a starting point in debating the new role of advanced research and development performing companies in association with higher education. This partnership, promoted at UE level, has a broad impact beyond the constrained scope of a single project and can develop into long-lasting collaboration while benefiting all stakeholders: students, universities and the surrounding knowledge-based economic and industrial ecosystem. Due to the exchange of experiences between the university (UPB) and the manufacturing company (AFT Design), a new project, SIMUL, under the Bridge Grant Program (Romanian executive agency UEFISCDI) was started (2016 – 2017). This project will continue the educational research for innovation on master and doctoral studies in MUROS thematic (collaborative multi-UAV application for flood detection).

Keywords: education process, multisensory robotic system, research and innovation project, technology transfer, university-industry partnership

Procedia PDF Downloads 238

Authors: Hilary Modir, Kyle Dutton, Michelle Swab, Shabnam Asghari

Abstract:

Since its emergence, the cutaneous manifestations of COVID-19 have been documented in the literature. However, the majority are case reports with significant limitations in appraisal quality, thus leaving the role of dermatological manifestations of COVID-19 erroneously underexplored. The primary aim of this review was to systematically examine clinical patterns of dermatological manifestations as reported in the literature. This study was designed as a systematic review of case reports. The inclusion criteria consisted of all published reports and articles regarding COVID-19 in English, from September 1st, 2019, until June 22nd, 2020. The population consisted of confirmed cases of COVID-19 with associated cutaneous signs and symptoms. Exclusion criteria included research in planning stages, protocols, book reviews, news articles, review studies, and policy analyses. With the collaboration of a librarian, a search strategy was created consisting of a mixture of keyword terms and controlled vocabulary. Electronic databases searched were MEDLINE via PubMed, EMBASE, CINAHL, Web of Science, LILACS, PsycINFO, WHO Global Literature on Coronavirus Disease, Cochrane Library, Campbell Collaboration, Prospero, WHO International Clinical Trials Registry Platform, Australian and New Zealand Clinical Trials Registry, U.S. Institutes of Health Ongoing Trials Register, AAD Registry, OSF preprints, SSRN, MedRxiV and BioRxiV. The study selection featured an initial pre-screening of titles and abstracts by one independent reviewer. Results were verified by re-examining a random sample of 1% of excluded articles. Eligible studies progressed for full-text review by two calibrated independent reviewers. Covidence was used to store and extract data, such as citation information and findings pertaining to COVID-19 and cutaneous signs and symptoms. Data analysis and summarization methodology reflect the framework proposed by PRISMA and recommendations set out by Cochrane and Joanna Brigg’s Institute for conducting systematic reviews. The Oxford Centre for Evidence-Based Medicine’s level of evidence was used to appraise the quality of individual studies. The literature search revealed a total of 1221 articles. After the abstract and full-text screening, only 95 studies met the eligibility criteria, proceeding to data extraction. Studies were divided into 58% case reports and 42% series. A total of 833 manifestations were reported in 723 confirmed COVID-19 cases. The most frequent lesions were 23% maculopapular, 15% urticarial and 13% pseudo-chilblains, with 46% of lesions reporting pruritus, 16% erythema, 14% pain, 12% burning sensation, and 4% edema. The most common lesion locations were 20% trunk, 19.5% lower limbs, and 17.7% upper limbs. The time to resolution of lesions was between one and twenty-one days. In conclusion, over half of the reported cutaneous presentations in COVID-19 positive patients were maculopapular, urticarial and pseudo-chilblains, with the majority of lesions distributed to the extremities and trunk. As this review’s sample size only contained COVID-19 confirmed cases with skin presentations, it becomes difficult to deduce the direct relationship between skin findings and COVID-19. However, it can be correlated that acute onset of skin lesions, such as chilblains-like, may be associated with or may warrant consideration of COVID-19 as part of the differential diagnosis.

Keywords: COVID-19, cutaneous manifestations, cutaneous signs, general dermatology, medical dermatology, Sars-Cov-2, skin and infectious disease, skin findings, skin manifestations

Procedia PDF Downloads 180

Authors: Joseph M. Rich, Vinay A. Duddalwar, Assad A. Oberai

Abstract:

Prostate adenocarcinoma is the most common cancer in males, with osseous metastases as the commonest site of metastatic prostate carcinoma (mPC). Treatment monitoring is based on the evaluation and characterization of lesions on multiple imaging studies, including Computed Tomography (CT). Monitoring of the osseous disease burden, including follow-up of lesions and identification and characterization of new lesions, is a laborious task for radiologists. Deep learning algorithms are increasingly used to perform tasks such as identification and segmentation for osseous metastatic disease and provide accurate information regarding metastatic burden. Here, nnUNet was used to produce a model which can segment CT scan images of prostate adenocarcinoma vertebral bone metastatic lesions. nnUNet is an open-source Python package that adds optimizations to deep learning-based UNet architecture but has not been extensively combined with transfer learning techniques due to the absence of a readily available functionality of this method. The IRB-approved study data set includes imaging studies from patients with mPC who were enrolled in clinical trials at the University of Southern California (USC) Health Science Campus and Los Angeles County (LAC)/USC medical center. Manual segmentation of metastatic lesions was completed by an expert radiologist Dr. Vinay Duddalwar (20+ years in radiology and oncologic imaging), to serve as ground truths for the automated segmentation. Despite nnUNet’s success on some medical segmentation tasks, it only produced an average Dice Similarity Coefficient (DSC) of 0.31 on the USC dataset. DSC results fell in a bimodal distribution, with most scores falling either over 0.66 (reasonably accurate) or at 0 (no lesion detected). Applying more aggressive data augmentation techniques dropped the DSC to 0.15, and reducing the number of epochs reduced the DSC to below 0.1. Datasets have been identified for transfer learning, which involve balancing between size and similarity of the dataset. Identified datasets include the Pancreas data from the Medical Segmentation Decathlon, Pelvic Reference Data, and CT volumes with multiple organ segmentations (CT-ORG). Some of the challenges of producing an accurate model from the USC dataset include small dataset size (115 images), 2D data (as nnUNet generally performs better on 3D data), and the limited amount of public data capturing annotated CT images of bone lesions. Optimizations and improvements will be made by applying transfer learning and generative methods, including incorporating generative adversarial networks and diffusion models in order to augment the dataset. Performance with different libraries, including MONAI and custom architectures with Pytorch, will be compared. In the future, molecular correlations will be tracked with radiologic features for the purpose of multimodal composite biomarker identification. Once validated, these models will be incorporated into evaluation workflows to optimize radiologist evaluation. Our work demonstrates the challenges of applying automated image segmentation to small medical datasets and lays a foundation for techniques to improve performance. As machine learning models become increasingly incorporated into the workflow of radiologists, these findings will help improve the speed and accuracy of vertebral metastatic lesions detection.

Keywords: deep learning, image segmentation, medicine, nnUNet, prostate carcinoma, radiomics

Procedia PDF Downloads 95

Authors: Olga Kononova, Sergey Lyapin

Abstract:

Global information society requirements are transparency and reliability of data, as well as ability to manage information resources independently; particularly to search, to analyze, to evaluate information, thereby obtaining new expertise. Moreover, it is satisfying the society information needs that increases the efficiency of the enterprise management and public administration. The study of structurally organized thematic and semantic contexts of different types, automatically extracted from unstructured data, is one of the important tasks for the application of information technologies in education, science, culture, governance and business. The objectives of this study are the contextual knowledge typologization, selection or creation of effective tools for extracting and analyzing contextual knowledge. Explication of various kinds and forms of the contextual knowledge involves the development and use full-text search information systems. For the implementation purposes, the authors use an e-library 'Humanitariana' services such as the contextual search, different types of queries (paragraph-oriented query, frequency-ranked query), automatic extraction of knowledge from the scientific texts. The multifunctional e-library «Humanitariana» is realized in the Internet-architecture in WWS-configuration (Web-browser / Web-server / SQL-server). Advantage of use 'Humanitariana' is in the possibility of combining the resources of several organizations. Scholars and research groups may work in a local network mode and in distributed IT environments with ability to appeal to resources of any participating organizations servers. Paper discusses some specific cases of the contextual knowledge explication with the use of the e-library services and focuses on possibilities of new types of the contextual knowledge. Experimental research base are science texts about 'e-government' and 'computer games'. An analysis of the subject-themed texts trends allowed to propose the content analysis methodology, that combines a full-text search with automatic construction of 'terminogramma' and expert analysis of the selected contexts. 'Terminogramma' is made out as a table that contains a column with a frequency-ranked list of words (nouns), as well as columns with an indication of the absolute frequency (number) and the relative frequency of occurrence of the word (in %% ppm). The analysis of 'e-government' materials showed, that the state takes a dominant position in the processes of the electronic interaction between the authorities and society in modern Russia. The media credited the main role in these processes to the government, which provided public services through specialized portals. Factor analysis revealed two factors statistically describing the used terms: human interaction (the user) and the state (government, processes organizer); interaction management (public officer, processes performer) and technology (infrastructure). Isolation of these factors will lead to changes in the model of electronic interaction between government and society. In this study, the dominant social problems and the prevalence of different categories of subjects of computer gaming in science papers from 2005 to 2015 were identified. Therefore, there is an evident identification of several types of contextual knowledge: micro context; macro context; dynamic context; thematic collection of queries (interactive contextual knowledge expanding a composition of e-library information resources); multimodal context (functional integration of iconographic and full-text resources through hybrid quasi-semantic algorithm of search). Further studies can be pursued both in terms of expanding the resource base on which they are held, and in terms of the development of appropriate tools.

Keywords: contextual knowledge, contextual search, e-library services, frequency-ranked query, paragraph-oriented query, technologies of the contextual knowledge extraction

Procedia PDF Downloads 357

Authors: Shuai Yuan, Minxia Shi, Xu Zhang, Jianzhi Yang, Kangqi Tian, Yuzheng Ma

Abstract:

The precise measurement of muscle activities is essential for understanding the function of various body movements. This work aims to develop a muscle magnetic field signal detection system based on mathematical analysis. Medical research has underscored that early detection of muscle atrophy, coupled with lifestyle adjustments such as dietary control and increased exercise, can significantly enhance muscle-related diseases. Currently, surface electromyography (sEMG) is widely employed in research as an early predictor of muscle atrophy. Nonetheless, the primary limitation of using sEMG to forecast muscle strength is its inability to directly measure the signals generated by muscles. Challenges arise from potential skin-electrode contact issues due to perspiration, leading to inaccurate signals or even signal loss. Additionally, resistance and phase are significantly impacted by adipose layers. The recent emergence of optically pumped magnetometers introduces a fresh avenue for bio-magnetic field measurement techniques. These magnetometers possess high sensitivity and obviate the need for a cryogenic environment unlike superconducting quantum interference devices (SQUIDs). They detect muscle magnetic field signals in the range of tens to thousands of femtoteslas (fT). The utilization of magnetometers for capturing muscle magnetic field signals remains unaffected by issues of perspiration and adipose layers. Since their introduction, optically pumped atomic magnetometers have found extensive application in exploring the magnetic fields of organs such as cardiac and brain magnetism. The optimal operation of these magnetometers necessitates an environment with an ultra-weak magnetic field. To achieve such an environment, researchers usually utilize a combination of active magnetic compensation technology with passive magnetic shielding technology. Passive magnetic shielding technology uses a magnetic shielding device built with high permeability materials to attenuate the external magnetic field to a few nT. Compared with more layers, the coils that can generate a reverse magnetic field to precisely compensate for the residual magnetic fields are cheaper and more flexible. To attain even lower magnetic fields, compensation coils designed by Biot-Savart law are involved to generate a counteractive magnetic field to eliminate residual magnetic fields. By solving the magnetic field expression of discrete points in the target region, the parameters that determine the current density distribution on the plane can be obtained through the conventional target field method. The current density is obtained from the partial derivative of the stream function, which can be represented by the combination of trigonometric functions. Optimization algorithms in mathematics are introduced into coil design to obtain the optimal current density distribution. A one-dimensional linear regression analysis was performed on the collected data, obtaining a coefficient of determination R2 of 0.9349 with a p-value of 0. This statistical result indicates a stable relationship between the peak-to-peak value (PPV) of the muscle magnetic field signal and the magnitude of grip strength. This system is expected to be a widely used tool for healthcare professionals to gain deeper insights into the muscle health of their patients.

Keywords: muscle magnetic signal, magnetic shielding, compensation coils, trigonometric functions.

Procedia PDF Downloads 55

Authors: Dongping Fang, Lian Duan, Xiaojing Yuan, Mike Xu, Allyn Klunder, Kevin Tan, Suiting Cao, Yeqing Ji

Abstract:

Accurate prediction of a medical condition with straight clinical evidence is a long-sought topic in the medical management and health insurance field. Although great progress has been made with machine learning algorithms, the medical community is still, to a certain degree, suspicious about the model's accuracy and interpretability. This paper presents an innovative hierarchical attention deep learning model to achieve good prediction and clear interpretability that can be easily understood by medical professionals. This deep learning model uses a hierarchical attention structure that matches naturally with the medical history data structure and reflects the member’s encounter (date of service) sequence. The model attention structure consists of 3 levels: (1) attention on the medical code types (diagnosis codes, procedure codes, lab test results, and prescription drugs), (2) attention on the sequential medical encounters within a type, (3) attention on the medical codes within an encounter and type. This model is applied to predict the occurrence of stage 3 chronic kidney disease (CKD3), using three years’ medical history of Medicare Advantage (MA) members from a top health insurance company. The model takes members’ medical events, both claims and electronic medical record (EMR) data, as input, makes a prediction of CKD3 and calculates the contribution from individual events to the predicted outcome. The model outcome can be easily explained with the clinical evidence identified by the model algorithm. Here are examples: Member A had 36 medical encounters in the past three years: multiple office visits, lab tests and medications. The model predicts member A has a high risk of CKD3 with the following well-contributed clinical events - multiple high ‘Creatinine in Serum or Plasma’ tests and multiple low kidneys functioning ‘Glomerular filtration rate’ tests. Among the abnormal lab tests, more recent results contributed more to the prediction. The model also indicates regular office visits, no abnormal findings of medical examinations, and taking proper medications decreased the CKD3 risk. Member B had 104 medical encounters in the past 3 years and was predicted to have a low risk of CKD3, because the model didn’t identify diagnoses, procedures, or medications related to kidney disease, and many lab test results, including ‘Glomerular filtration rate’ were within the normal range. The model accurately predicts members A and B and provides interpretable clinical evidence that is validated by clinicians. Without extra effort, the interpretation is generated directly from the model and presented together with the occurrence date. Our model uses the medical data in its most raw format without any further data aggregation, transformation, or mapping. This greatly simplifies the data preparation process, mitigates the chance for error and eliminates post-modeling work needed for traditional model explanation. To our knowledge, this is the first paper on an interpretable deep-learning model using a 3-level attention structure, sourcing both EMR and claim data, including all 4 types of medical data, on the entire Medicare population of a big insurance company, and more importantly, directly generating model interpretation to support user decision. In the future, we plan to enrich the model input by adding patients’ demographics and information from free-texted physician notes.

Keywords: deep learning, interpretability, attention, big data, medical conditions

Procedia PDF Downloads 89

Authors: Muhammad Bilal Shaikh

Abstract:

Mineral processing plants play a pivotal role in extracting valuable minerals from raw ores, contributing significantly to various industries. However, the optimization of plant throughput remains a complex challenge, necessitating innovative approaches for increased efficiency and productivity. This research paper investigates the application of Multimodal Artificial Intelligence (MAI) techniques to address this challenge, aiming to improve overall plant throughput in mineral processing operations. The integration of multimodal AI leverages a combination of diverse data sources, including sensor data, images, and textual information, to provide a holistic understanding of the complex processes involved in mineral extraction. The paper explores the synergies between various AI modalities, such as machine learning, computer vision, and natural language processing, to create a comprehensive and adaptive system for optimizing mineral processing plants. The primary focus of the research is on developing advanced predictive models that can accurately forecast various parameters affecting plant throughput. Utilizing historical process data, machine learning algorithms are trained to identify patterns, correlations, and dependencies within the intricate network of mineral processing operations. This enables real-time decision-making and process optimization, ultimately leading to enhanced plant throughput. Incorporating computer vision into the multimodal AI framework allows for the analysis of visual data from sensors and cameras positioned throughout the plant. This visual input aids in monitoring equipment conditions, identifying anomalies, and optimizing the flow of raw materials. The combination of machine learning and computer vision enables the creation of predictive maintenance strategies, reducing downtime and improving the overall reliability of mineral processing plants. Furthermore, the integration of natural language processing facilitates the extraction of valuable insights from unstructured textual data, such as maintenance logs, research papers, and operator reports. By understanding and analyzing this textual information, the multimodal AI system can identify trends, potential bottlenecks, and areas for improvement in plant operations. This comprehensive approach enables a more nuanced understanding of the factors influencing throughput and allows for targeted interventions. The research also explores the challenges associated with implementing multimodal AI in mineral processing plants, including data integration, model interpretability, and scalability. Addressing these challenges is crucial for the successful deployment of AI solutions in real-world industrial settings. To validate the effectiveness of the proposed multimodal AI framework, the research conducts case studies in collaboration with mineral processing plants. The results demonstrate tangible improvements in plant throughput, efficiency, and cost-effectiveness. The paper concludes with insights into the broader implications of implementing multimodal AI in mineral processing and its potential to revolutionize the industry by providing a robust, adaptive, and data-driven approach to optimizing plant operations. In summary, this research contributes to the evolving field of mineral processing by showcasing the transformative potential of multimodal artificial intelligence in enhancing plant throughput. The proposed framework offers a holistic solution that integrates machine learning, computer vision, and natural language processing to address the intricacies of mineral extraction processes, paving the way for a more efficient and sustainable future in the mineral processing industry.

Keywords: multimodal AI, computer vision, NLP, mineral processing, mining

Procedia PDF Downloads 65

Authors: G. Senoga, D. Nakimuli, B. Ndagire, B. Lukwago, D. Kyamagwa

Abstract:

Background: The COVID-19 epidemic affected the education sector, with some private schools closing while other children missed schooling for fear contracting COVID-19. Post COVID-19, PSIU in collaborated with Kampala City Council Authority Directorate of Education and Social Science, Water and Sanitation department, and Directorate of Public Health and Environment to improve sanitation and hygiene among pupils and staff in 50 public and private school system in Kampala city. The “Be Clean, Stay Healthy Campaign” used a behavioral change approach in educating, reinforcing and engaging learners on proper hand washing behaviors, proper toilet usage and garbage disposal. In April 2022, 40 Washa lots were constructed, to reduce the pupil - hand wash station ratio; distributed KCCA approved printed materials; oriented 50 teachers, WASH committees to execute and implement hygiene promotion. To ensure sustainability, WASH messages were memorized and practiced through hand washing songs, Pledge, prayer, Poems, Skits, Music, dance and drama, coupled with participatory, practical demonstrations using peer to peer approach, guest speakers at assemblies and in classes. This improved hygiene and sanitation practices. Premised on this, PSI conducted an end line assessment to explore the impact of a hand washing campaign in regards to improvements in hand washing practices and hand hygiene among pupils, accessibility, functionality and usage of the constructed hygiene and sanitation facilities. Method: A cross-sectional post intervention assessment using a mixed methods approach, targeting headteachers, wash committee members and pupils less <17 years was used. Quantitative approaches with a mix of open-ended questions were used in purposively selected respondents in 50 schools. Primary three to primary seven pupils were randomly selected, data was analyzed using the Statistical Package for Social Scientists (SPSS) Outcomes and Findings: 46,989 pupils (51% female), 1,127 and 524 teaching and non-teaching staff were reached by the intervention, respectively. 96% of schools trained on sanitation, sustainable water usage and hygiene constituted 17-man school WASH committees with teacher, parents and pupils representatives. (31%) of the WASH committees developed workplans, (78%) held WASH meetings monthly. This resulted into improved sanitation, water usage, waste management, proper use of toilets, and improved pupils’ health with reduced occurrences of stomach upsets, diarrhoea initially attributed to improper use of latrines and general waste management. Teachers reported reduced number of school absenteeism due to improved hygiene and general waste management at school, especially proper management of sanitary pads. School administrations response rate in purchase of hygiene equipment’s and detergents like soap improved. Regular WASH meetings in classes, teachers and community supervision ensured WASH facilities are used appropriately. Conclusion and Recommendations: Practical behaviour change innovations improves pupil’s knowledge and understanding of hygiene messages and usage. Over 70% of pupils had clear recall of key WASH Messages. There is need for continuous water flow in the Washa lots, harvesting rain water would reduce water bills while complementing National water supply coupled with increasing on Washa lots in densely populated schools.

Keywords: handwashing, hygyiene, sanitation, behaviour change

Procedia PDF Downloads 89

Authors: Asma Omri, Iheb Sifaoui, Sofiane Sayahi, Hichem Besbes

Abstract:

Future vehicle systems demand advanced capabilities, notably in-cabin life detection and driver monitoring systems, with a particular emphasis on drowsiness detection. To meet these requirements, several techniques employ artificial intelligence methods based on real-time vital sign measurements. In parallel, Frequency-Modulated Continuous-Wave (FMCW) radar technology has garnered considerable attention in the domains of healthcare and biomedical engineering for non-invasive vital sign monitoring. FMCW radar offers a multitude of advantages, including its non-intrusive nature, continuous monitoring capacity, and its ability to penetrate through clothing. In this paper, we propose a system utilizing the AWR6843AOP radar from Texas Instruments (TI) to extract precise vital sign information. The radar allows us to estimate Ballistocardiogram (BCG) signals, which capture the mechanical movements of the body, particularly the ballistic forces generated by heartbeats and respiration. These signals are rich sources of information about the cardiac cycle, rendering them suitable for heart rate estimation. The process begins with real-time subject positioning, followed by clutter removal, computation of Doppler phase differences, and the use of various filtering methods to accurately capture subtle physiological movements. To address the challenges associated with FMCW radar-based vital sign monitoring, including motion artifacts due to subjects' movement or radar micro-vibrations, Long Short-Term Memory (LSTM) networks are implemented. LSTM's adaptability to different heart rate patterns and ability to handle real-time data make it suitable for continuous monitoring applications. Several crucial steps were taken, including feature extraction (involving amplitude, time intervals, and signal morphology), sequence modeling, heart rate estimation through the analysis of detected cardiac cycles and their temporal relationships, and performance evaluation using metrics such as Root Mean Square Error (RMSE) and correlation with reference heart rate measurements. For dataset construction and LSTM training, a comprehensive data collection system was established, integrating the AWR6843AOP radar, a Heart Rate Belt, and a smart watch for ground truth measurements. Rigorous synchronization of these devices ensured data accuracy. Twenty participants engaged in various scenarios, encompassing indoor and real-world conditions within a moving vehicle equipped with the radar system. Static and dynamic subject’s conditions were considered. The heart rate estimation through LSTM outperforms traditional signal processing techniques that rely on filtering, Fast Fourier Transform (FFT), and thresholding. It delivers an average accuracy of approximately 91% with an RMSE of 1.01 beat per minute (bpm). In conclusion, this paper underscores the promising potential of FMCW radar technology integrated with artificial intelligence algorithms in the context of automotive applications. This innovation not only enhances road safety but also paves the way for its integration into the automotive ecosystem to improve driver well-being and overall vehicular safety.

Keywords: ballistocardiogram, FMCW Radar, vital sign monitoring, LSTM

Procedia PDF Downloads 72