Search results for: accidents predictions

Authors: Akeel A. Shah, Tong Zhang

Abstract:

Computational approaches to learning the properties of materials are commonplace, motivated by the need to screen or design materials for a given application, e.g., semiconductors and energy storage. Experimental approaches can be both time consuming and costly. Unfortunately, computational approaches such as ab-initio electronic structure calculations and classical or ab-initio molecular dynamics are themselves can be too slow for the rapid evaluation of materials, often involving thousands to hundreds of thousands of candidates. Machine learning assisted approaches have been developed to overcome the time limitations of purely physics-based approaches. These approaches, on the other hand, require large volumes of data for training (hundreds of thousands on many standard data sets such as QM7b). This means that they are limited by how quickly such a large data set of physics-based simulations can be established. At high fidelity, such as configuration interaction, composite methods such as G4, and coupled cluster theory, gathering such a large data set can become infeasible, which can compromise the accuracy of the predictions - many applications require high accuracy, for example band structures and energy levels in semiconductor materials and the energetics of charge transfer in energy storage materials. In order to circumvent this problem, multi-fidelity approaches can be adopted, for example the Δ-ML method, which learns a high-fidelity output from a low-fidelity result such as Hartree-Fock or density functional theory (DFT). The general strategy is to learn a map between the low and high fidelity outputs, so that the high-fidelity output is obtained a simple sum of the physics-based low-fidelity and correction, Although this requires a low-fidelity calculation, it typically requires far fewer high-fidelity results to learn the correction map, and furthermore, the low-fidelity result, such as Hartree-Fock or semi-empirical ZINDO, is typically quick to obtain, For high-fidelity outputs the result can be an order of magnitude or more in speed up. In this work, a new multi-fidelity approach is developed, based on a graph convolutional network (GCN) combined with semi-supervised learning. The GCN allows for the material or molecule to be represented as a graph, which is known to improve accuracy, for example SchNet and MEGNET. The graph incorporates information regarding the numbers of, types and properties of atoms; the types of bonds; and bond angles. They key to the accuracy in multi-fidelity methods, however, is the incorporation of low-fidelity output to learn the high-fidelity equivalent, in this case by learning their difference. Semi-supervised learning is employed to allow for different numbers of low and high-fidelity training points, by using an additional GCN-based low-fidelity map to predict high fidelity outputs. It is shown on 4 different data sets that a significant (at least one order of magnitude) increase in accuracy is obtained, using one to two orders of magnitude fewer low and high fidelity training points. One of the data sets is developed in this work, pertaining to 1000 simulations of quinone molecules (up to 24 atoms) at 5 different levels of fidelity, furnishing the energy, dipole moment and HOMO/LUMO.

Keywords: .materials screening, computational materials, machine learning, multi-fidelity, graph convolutional network, semi-supervised learning

Procedia PDF Downloads 39

Authors: Ammar Alali, Mahmoud Abughaban

Abstract:

Cost reduction and drilling optimization is the goal of many drilling operators. Historically, stuck pipe incidents were a major segment of non-productive time (NPT) associated costs. Traditionally, stuck pipe problems are part of the operations and solved post-sticking. However, the real key to savings and success is in predicting the stuck pipe incidents and avoiding the conditions leading to its occurrences. Previous attempts in stuck-pipe predictions have neglected the local geology of the problem. The proposed predictive tool utilizes geophysical data processing techniques and Machine Learning (ML) algorithms to predict drilling activities events in real-time using surface drilling data with minimum computational power. The method combines two types of analysis: (1) real-time prediction, and (2) cause analysis. Real-time prediction aggregates the input data, including historical drilling surface data, geological formation tops, and petrophysical data, from wells within the same field. The input data are then flattened per the geological formation and stacked per stuck-pipe incidents. The algorithm uses two physical methods (stacking and flattening) to filter any noise in the signature and create a robust pre-determined pilot that adheres to the local geology. Once the drilling operation starts, the Wellsite Information Transfer Standard Markup Language (WITSML) live surface data are fed into a matrix and aggregated in a similar frequency as the pre-determined signature. Then, the matrix is correlated with the pre-determined stuck-pipe signature for this field, in real-time. The correlation used is a machine learning Correlation-based Feature Selection (CFS) algorithm, which selects relevant features from the class and identifying redundant features. The correlation output is interpreted as a probability curve of stuck pipe incidents prediction in real-time. Once this probability passes a fixed-threshold defined by the user, the other component, cause analysis, alerts the user of the expected incident based on set pre-determined signatures. A set of recommendations will be provided to reduce the associated risk. The validation process involved feeding of historical drilling data as live-stream, mimicking actual drilling conditions, of an onshore oil field. Pre-determined signatures were created for three problematic geological formations in this field prior. Three wells were processed as case studies, and the stuck-pipe incidents were predicted successfully, with an accuracy of 76%. This accuracy of detection could have resulted in around 50% reduction in NPT, equivalent to 9% cost saving in comparison with offset wells. The prediction of stuck pipe problem requires a method to capture geological, geophysical and drilling data, and recognize the indicators of this issue at a field and geological formation level. This paper illustrates the efficiency and the robustness of the proposed cross-disciplinary approach in its ability to produce such signatures and predicting this NPT event.

Keywords: drilling optimization, hazard prediction, machine learning, stuck pipe

Procedia PDF Downloads 226

Authors: Ramiz M. Shubbar, Dong In Lee, Hatem A. Gzar, Arthur S. Rood

Abstract:

Air pollution is one of the biggest environmental problems in Baghdad, Iraq. The Daura refinery located nearest the center of Baghdad, represents the largest industrial area, which transmits enormous amounts of pollutants, therefore study the gaseous pollutants and particulate matter are very important to the environment and the health of the workers in refinery and the people whom leaving in areas around the refinery. Actually, some studies investigated the studied area before, but it depended on the basic Gaussian equation in a simple computer programs, however, that kind of work at that time is very useful and important, but during the last two decades new largest production units were added to the Daura refinery such as, PU_3 (Power unit_3 (Boiler 11&12)), CDU_1 (Crude Distillation unit_70000 barrel_1), and CDU_2 (Crude Distillation unit_70000 barrel_2). Therefore, it is necessary to use new advanced model to study air pollution at the region for the new current years, and calculation the monthly emission rate of pollutants through actual amounts of fuel which consumed in production unit, this may be lead to accurate concentration values of pollutants and the behavior of dispersion or transport in study area. In this study to the best of author’s knowledge CALPUFF model was used and examined for first time in Iraq. CALPUFF is an advanced non-steady-state meteorological and air quality modeling system, was applied to investigate the pollutants concentration of SO2, NO2, CO, and PM1-10μm, at areas adjacent to Daura refinery which located in the center of Baghdad in Iraq. The CALPUFF modeling system includes three main components: CALMET is a diagnostic 3-dimensional meteorological model, CALPUFF (an air quality dispersion model), CALPOST is a post processing package, and an extensive set of preprocessing programs produced to interface the model to standard routinely available meteorological and geophysical datasets. The targets of this work are modeling and simulation the four pollutants (SO2, NO2, CO, and PM1-10μm) which emitted from Daura refinery within one year. Emission rates of these pollutants were calculated for twelve units includes thirty plants, and 35 stacks by using monthly average of the fuel amount consumption at this production units. Assess the performance of CALPUFF model in this study and detect if it is appropriate and get out predictions of good accuracy compared with available pollutants observation. CALPUFF model was investigated at three stability classes (stable, neutral, and unstable) to indicate the dispersion of the pollutants within deferent meteorological conditions. The simulation of the CALPUFF model showed the deferent kind of dispersion of these pollutants in this region depends on the stability conditions and the environment of the study area, monthly, and annual averages of pollutants were applied to view the dispersion of pollutants in the contour maps. High values of pollutants were noticed in this area, therefore this study recommends to more investigate and analyze of the pollutants, reducing the emission rate of pollutants by using modern techniques and natural gas, increasing the stack height of units, and increasing the exit gas velocity from stacks.

Keywords: CALPUFF, daura refinery, Iraq, pollutants

Procedia PDF Downloads 197

Authors: Antonella Falanga, Armando Cartenì

Abstract:

Today, an unprecedented amount of data coming from several sources, including mobile devices, sensors, tracking systems, and online platforms, characterizes our lives. The term “big data” not only refers to the quantity of data but also to the variety and speed of data generation. These data hold valuable insights that, when extracted and analyzed, facilitate informed decision-making. The 4Vs of big data - velocity, volume, variety, and value - highlight essential aspects, showcasing the rapid generation, vast quantities, diverse sources, and potential value addition of these kinds of data. This surge of information has revolutionized many sectors, such as business for improving decision-making processes, healthcare for clinical record analysis and medical research, education for enhancing teaching methodologies, agriculture for optimizing crop management, finance for risk assessment and fraud detection, media and entertainment for personalized content recommendations, emergency for a real-time response during crisis/events, and also mobility for the urban planning and for the design/management of public and private transport services. Big data's pervasive impact enhances societal aspects, elevating the quality of life, service efficiency, and problem-solving capacities. However, during this transformative era, new challenges arise, including data quality, privacy, data security, cybersecurity, interoperability, the need for advanced infrastructures, and staff training. Within the transportation sector (the one investigated in this research), applications span planning, designing, and managing systems and mobility services. Among the most common big data applications within the transport sector are, for example, real-time traffic monitoring, bus/freight vehicle route optimization, vehicle maintenance, road safety and all the autonomous and connected vehicles applications. Benefits include a reduction in travel times, road accidents and pollutant emissions. Within these issues, the proper transport demand estimation is crucial for sustainable transportation planning. Evaluating the impact of sustainable mobility policies starts with a quantitative analysis of travel demand. Achieving transportation decarbonization goals hinges on precise estimations of demand for individual transport modes. Emerging technologies, offering substantial big data at lower costs than traditional methods, play a pivotal role in this context. Starting from these considerations, this study explores the usefulness impact of big data within transport demand estimation. This research focuses on leveraging (big) data collected during the COVID-19 pandemic to estimate the evolution of the mobility demand in Italy. Estimation results reveal in the post-COVID-19 era, more than 96 million national daily trips, about 2.6 trips per capita, with a mobile population of more than 37.6 million Italian travelers per day. Overall, this research allows us to conclude that big data better enhances rational decision-making for mobility demand estimation, which is imperative for adeptly planning and allocating investments in transportation infrastructures and services.

Keywords: big data, cloud computing, decision-making, mobility demand, transportation

Procedia PDF Downloads 62

Authors: Iman Farasat, Howard M. Salis

Abstract:

Engineered genetic circuits reprogram cellular behavior to act as living computers with applications in detecting cancer, creating self-controlling artificial tissues, and dynamically regulating metabolic pathways. Phenemenological models are often used to simulate and design genetic circuit behavior towards a desired behavior. While such models assume that each circuit component’s function is modular and independent, even small changes in a circuit (e.g. a new promoter, a change in transcription factor expression level, or even a new media) can have significant effects on the circuit’s function. Here, we use statistical thermodynamics to account for the several factors that control transcriptional regulation in bacteria, and experimentally demonstrate the model’s accuracy across 825 measurements in several genetic contexts and hosts. We then employ our first principles model to design, experimentally construct, and characterize a family of signal amplifying genetic circuits (genetic OpAmps) that expand the dynamic range of cell sensors. To develop these models, we needed a new approach to measuring the in vivo binding free energies of transcription factors (TFs), a key ingredient of statistical thermodynamic models of gene regulation. We developed a new high-throughput assay to measure RNA polymerase and TF binding free energies, requiring the construction and characterization of only a few constructs and data analysis (Figure 1A). We experimentally verified the assay on 6 TetR-homolog repressors and a CRISPR/dCas9 guide RNA. We found that our binding free energy measurements quantitatively explains why changing TF expression levels alters circuit function. Altogether, by combining these measurements with our biophysical model of translation (the RBS Calculator) as well as other measurements (Figure 1B), our model can account for changes in TF binding sites, TF expression levels, circuit copy number, host genome size, and host growth rate (Figure 1C). Model predictions correctly accounted for how these 8 factors control a promoter’s transcription rate (Figure 1D). Using the model, we developed a design framework for engineering multi-promoter genetic circuits that greatly reduces the number of degrees of freedom (8 factors per promoter) to a single dimensionless unit. We propose the Ptashne (Pt) number to encapsulate the 8 co-dependent factors that control transcriptional regulation into a single number. Therefore, a single number controls a promoter’s output rather than these 8 co-dependent factors, and designing a genetic circuit with N promoters requires specification of only N Pt numbers. We demonstrate how to design genetic circuits in Pt number space by constructing and characterizing 15 2-repressor OpAmp circuits that act as signal amplifiers when within an optimal Pt region. We experimentally show that OpAmp circuits using different TFs and TF expression levels will only amplify the dynamic range of input signals when their corresponding Pt numbers are within the optimal region. Thus, the use of the Pt number greatly simplifies the genetic circuit design, particularly important as circuits employ more TFs to perform increasingly complex functions.

Keywords: transcription factor, synthetic biology, genetic circuit, biophysical model, binding energy measurement

Procedia PDF Downloads 473

Authors: Kamyar Tolouei, Ehsan Moosavi

Abstract:

In open-pit mines, the long-term production scheduling optimization problem (LTPSOP) is a complicated problem that contains constraints, large datasets, and uncertainties. Uncertainty in the output is caused by several geological, economic, or technical factors. Due to its dimensions and NP-hard nature, it is usually difficult to find an ideal solution to the LTPSOP. The optimal schedule generally restricts the ore, metal, and waste tonnages, average grades, and cash flows of each period. Past decades have witnessed important measurements of long-term production scheduling and optimal algorithms since researchers have become highly cognizant of the issue. In fact, it is not possible to consider LTPSOP as a well-solved problem. Traditional production scheduling methods in open-pit mines apply an estimated orebody model to produce optimal schedules. The smoothing result of some geostatistical estimation procedures causes most of the mine schedules and production predictions to be unrealistic and imperfect. With the expansion of simulation procedures, the risks from grade uncertainty in ore reserves can be evaluated and organized through a set of equally probable orebody realizations. In this paper, to synthesize grade uncertainty into the strategic mine schedule, a stochastic integer programming framework is presented to LTPSOP. The objective function of the model is to maximize the net present value and minimize the risk of deviation from the production targets considering grade uncertainty simultaneously while satisfying all technical constraints and operational requirements. Instead of applying one estimated orebody model as input to optimize the production schedule, a set of equally probable orebody realizations are applied to synthesize grade uncertainty in the strategic mine schedule and to produce a more profitable and risk-based production schedule. A mixture of metaheuristic procedures and mathematical methods paves the way to achieve an appropriate solution. This paper introduced a hybrid model between the augmented Lagrangian relaxation (ALR) method and the metaheuristic algorithm, the Harris Hawks optimization (HHO), to solve the LTPSOP under grade uncertainty conditions. In this study, the HHO is experienced to update Lagrange coefficients. Besides, a machine learning method called Random Forest is applied to estimate gold grade in a mineral deposit. The Monte Carlo method is used as the simulation method with 20 realizations. The results specify that the progressive versions have been considerably developed in comparison with the traditional methods. The outcomes were also compared with the ALR-genetic algorithm and ALR-sub-gradient. To indicate the applicability of the model, a case study on an open-pit gold mining operation is implemented. The framework displays the capability to minimize risk and improvement in the expected net present value and financial profitability for LTPSOP. The framework could control geological risk more effectively than the traditional procedure considering grade uncertainty in the hybrid model framework.

Keywords: grade uncertainty, metaheuristic algorithms, open-pit mine, production scheduling optimization

Procedia PDF Downloads 105

Authors: Amanda Kavner, Richard Lamb

Abstract:

Faster growth in science and technology of other nations may make staying globally competitive more difficult without shifting focus on how science is taught in US classes. An integral part of learning science involves visual and spatial thinking since complex, and real-world phenomena are often expressed in visual, symbolic, and concrete modes. The primary barrier to spatial thinking and visual literacy in Science, Technology, Engineering, and Math (STEM) fields is representational competence, which includes the ability to generate, transform, analyze and explain representations, as opposed to generic spatial ability. Although the relationship is known between the foundational visual literacy and the domain-specific science literacy, science literacy as a function of science learning is still not well understood. Moreover, the need for a more reliable measure is necessary to design resources which enhance the fundamental visuospatial cognitive processes behind scientific literacy. To support the improvement of students’ representational competence, first visualization skills necessary to process these science representations needed to be identified, which necessitates the development of an instrument to quantitatively measure visual literacy. With such a measure, schools, teachers, and curriculum designers can target the individual skills necessary to improve students’ visual literacy, thereby increasing science achievement. This project details the development of an artificial neural network capable of measuring science literacy using functional Near-Infrared Spectroscopy (fNIR) data. This data was previously collected by Project LENS standing for Leveraging Expertise in Neurotechnologies, a Science of Learning Collaborative Network (SL-CN) of scholars of STEM Education from three US universities (NSF award 1540888), utilizing mental rotation tasks, to assess student visual literacy. Hemodynamic response data from fNIRsoft was exported as an Excel file, with 80 of both 2D Wedge and Dash models (dash) and 3D Stick and Ball models (BL). Complexity data were in an Excel workbook separated by the participant (ID), containing information for both types of tasks. After changing strings to numbers for analysis, spreadsheets with measurement data and complexity data were uploaded to RapidMiner’s TurboPrep and merged. Using RapidMiner Studio, a Gradient Boosted Trees artificial neural network (ANN) consisting of 140 trees with a maximum depth of 7 branches was developed, and 99.7% of the ANN predictions are accurate. The ANN determined the biggest predictors to a successful mental rotation are the individual problem number, the response time and fNIR optode #16, located along the right prefrontal cortex important in processing visuospatial working memory and episodic memory retrieval; both vital for science literacy. With an unbiased measurement of science literacy provided by psychophysiological measurements with an ANN for analysis, educators and curriculum designers will be able to create targeted classroom resources to help improve student visuospatial literacy, therefore improving science literacy.

Keywords: artificial intelligence, artificial neural network, machine learning, science literacy, neuroscience

Procedia PDF Downloads 119

Authors: E. Mosiniewicz-Szablewska, P. Suchocki, P. C. Morais

Abstract:

Despite the significant progress in cancer treatment, there is a need to search for new therapeutic methods in order to minimize side effects. Chemotherapy, the main current method of treating cancer, is non-selective and has a number of limitations. Toxicity to healthy cells is undoubtedly the biggest problem limiting the use of many anticancer drugs. The problem of how to kill cancer without harming a patient can be solved by using organic selenium (IV) compounds. Organic selenium (IV) compounds are a new class of materials showing a strong anticancer activity. They are first organic compounds containing selenium at the +4 oxidation level and therefore they eliminate the multidrug-resistance for all tumor cell lines tested so far. These materials are capable of selectively killing cancer cells without damaging the healthy ones. They are obtained by the incorporation of selenous acid (H2SeO3) into molecules of fatty acids of sunflower oil and therefore, they are inexpensive to manufacture. Attaching these compounds to magnetic carriers enables their precise delivery directly to the tumor area and the simultaneous application of the magnetic hyperthermia, thus creating a huge opportunity to effectively get rid of the tumor without any side effects. Polylactic-co-glicolic acid (PLGA) nanocapsules loaded with maghemite (-Fe2O3) nanoparticles and organic selenium (IV) compounds are successfully prepared by nanoprecipitation method. In vitro antitumor activity of the nanocapsules were evidenced using murine melanoma (B16-F10), oral squamos carcinoma (OSCC) and murine (4T1) and human (MCF-7) breast lines. Further exposure of these cells to an alternating magnetic field increased the antitumor effect of nanocapsules. Moreover, the nanocapsules presented antitumor effect while not affecting normal cells. Magnetic properties of the nanocapsules were investigated by means of dc magnetization, ac susceptibility and electron spin resonance (ESR) measurements. The nanocapsules presented a typical superparamagnetic behavior around room temperature manifested itself by the split between zero field-cooled/field-cooled (ZFC/FC) magnetization curves and the absence of hysteresis on the field-dependent magnetization curve above the blocking temperature. Moreover, the blocking temperature decreased with increasing applied magnetic field. The superparamagnetic character of the nanocapsules was also confirmed by the occurrence of a maximum in temperature dependences of both real ′(T) and imaginary ′′ (T) components of the ac magnetic susceptibility, which shifted towards higher temperatures with increasing frequency. Additionally, upon decreasing the temperature the ESR signal shifted to lower fields and gradually broadened following closely the predictions for the ESR of superparamagnetoc nanoparticles. The observed superparamagnetic properties of nanocapsules enable their simple manipulation by means of magnetic field gradient, after introduction into the blood stream, which is a necessary condition for their use as magnetic drug carriers. The observed anticancer and superparamgnetic properties show that the magnetic nanocapsules loaded with organic selenium (IV) compounds should be considered as an effective material system for magnetic drug delivery and magnetohyperthermia inductor in antitumor therapy.

Keywords: cancer treatment, magnetic drug delivery system, nanomaterials, nanotechnology

Procedia PDF Downloads 204

Authors: Armin Nabaei, M. Omair Ahmad, M. N. S. Swamy

Abstract:

Many facial expression and emotion recognition methods in the traditional approaches of using LDA, PCA, and EBGM have been proposed. In recent years deep learning models have provided a unique platform addressing by automatically extracting the features for the detection of facial expression and emotions. However, deep networks require large training datasets to extract automatic features effectively. In this work, we propose an efficient emotion detection algorithm using face images when only small datasets are available for training. We design a deep network whose feature extraction capability is enhanced by utilizing several parallel modules between the input and output of the network, each focusing on the extraction of different types of coarse features with fined grained details to break the symmetry of produced information. In fact, we leverage long range dependencies, which is one of the main drawback of CNNs. We develop this work by introducing a Dynamic Soft-Margin SoftMax.The conventional SoftMax suffers from reaching to gold labels very soon, which take the model to over-fitting. Because it’s not able to determine adequately discriminant feature vectors for some variant class labels. We reduced the risk of over-fitting by using a dynamic shape of input tensor instead of static in SoftMax layer with specifying a desired Soft- Margin. In fact, it acts as a controller to how hard the model should work to push dissimilar embedding vectors apart. For the proposed Categorical Loss, by the objective of compacting the same class labels and separating different class labels in the normalized log domain.We select penalty for those predictions with high divergence from ground-truth labels.So, we shorten correct feature vectors and enlarge false prediction tensors, it means we assign more weights for those classes with conjunction to each other (namely, “hard labels to learn”). By doing this work, we constrain the model to generate more discriminate feature vectors for variant class labels. Finally, for the proposed optimizer, our focus is on solving weak convergence of Adam optimizer for a non-convex problem. Our noteworthy optimizer is working by an alternative updating gradient procedure with an exponential weighted moving average function for faster convergence and exploiting a weight decay method to help drastically reducing the learning rate near optima to reach the dominant local minimum. We demonstrate the superiority of our proposed work by surpassing the first rank of three widely used Facial Expression Recognition datasets with 93.30% on FER-2013, and 16% improvement compare to the first rank after 10 years, reaching to 90.73% on RAF-DB, and 100% k-fold average accuracy for CK+ dataset, and shown to provide a top performance to that provided by other networks, which require much larger training datasets.

Keywords: computer vision, facial expression recognition, machine learning, algorithms, depp learning, neural networks

Procedia PDF Downloads 74

Authors: Sylvie Michel, Sylvie Gerbaix, Marc Bidan

Abstract:

Artificial intelligence (AI) can be held accountable for its detrimental impacts. This question gains heightened relevance given AI's pervasive reach across various domains, magnifying its power and potential. The expanding influence of AI raises fundamental ethical inquiries, primarily centering on biases, responsibility, and transparency. This encompasses discriminatory biases arising from algorithmic criteria or data, accidents attributed to autonomous vehicles or other systems, and the imperative of transparent decision-making. This article aims to stimulate reflection on AI accountability, denoting the necessity to elucidate the effects it generates. Accountability comprises two integral aspects: adherence to legal and ethical standards and the imperative to elucidate the underlying operational rationale. The objective is to initiate a reflection on the obstacles to this "accountability," facing the challenges of the complexity of artificial intelligence's system and its effects. Then, this article proposes to mobilize Edgar Morin's complex thought to encompass and face the challenges of this complexity. The first contribution is to point out the challenges posed by the complexity of A.I., with fractional accountability between a myriad of human and non-human actors, such as software and equipment, which ultimately contribute to the decisions taken and are multiplied in the case of AI. Accountability faces three challenges resulting from the complexity of the ethical issues combined with the complexity of AI. The challenge of the non-neutrality of algorithmic systems as fully ethically non-neutral actors is put forward by a revealing ethics approach that calls for assigning responsibilities to these systems. The challenge of the dilution of responsibility is induced by the multiplicity and distancing between the actors. Thus, a dilution of responsibility is induced by a split in decision-making between developers, who feel they fulfill their duty by strictly respecting the requests they receive, and management, which does not consider itself responsible for technology-related flaws. Accountability is confronted with the challenge of transparency of complex and scalable algorithmic systems, non-human actors self-learning via big data. A second contribution involves leveraging E. Morin's principles, providing a framework to grasp the multifaceted ethical dilemmas and subsequently paving the way for establishing accountability in AI. When addressing the ethical challenge of biases, the "hologrammatic" principle underscores the imperative of acknowledging the non-ethical neutrality of algorithmic systems inherently imbued with the values and biases of their creators and society. The "dialogic" principle advocates for the responsible consideration of ethical dilemmas, encouraging the integration of complementary and contradictory elements in solutions from the very inception of the design phase. Aligning with the principle of organizing recursiveness, akin to the "transparency" of the system, it promotes a systemic analysis to account for the induced effects and guides the incorporation of modifications into the system to rectify deviations and reintroduce modifications into the system to rectify its drifts. In conclusion, this contribution serves as an inception for contemplating the accountability of "artificial intelligence" systems despite the evident ethical implications and potential deviations. Edgar Morin's principles, providing a lens to contemplate this complexity, offer valuable perspectives to address these challenges concerning accountability.

Keywords: accountability, artificial intelligence, complexity, ethics, explainability, transparency, Edgar Morin

Procedia PDF Downloads 63

Authors: Festus Okotie

Abstract:

Nigeria is the giant of Africa with great and diverse transport potentials yet to be fully tapped into and explored.it is the most populated nation in Africa with nearly 200 million people, the sixth largest oil producer overall and largest oil producer in Africa with proven oil and gas reserves of 37 billion barrels and 192 trillion cubic feet, over 300 square kilometers of arable land and significant deposits of largely untapped minerals. A world bank indicator which measures trading across border ranked Nigeria at 183 out of 185 countries in 2017 and although different governments in the past made efforts through different interventions such as 2007 ports reforms led by Ngozi Okonjo-Iweala, a former minister of Finance and world bank managing director also attempted to resolve some of the challenges such as infrastructure shortcomings, policy and regulatory inconsistencies, overlapping functions and duplicated roles among the different MDA’S. It is one of the fundamental structures smart nations and cities are using to improve the living conditions of its citizens and achieving sustainability. Examples of some of its benefits includes tracking high pedestrian areas, traffic patterns, railway stations, planning and scheduling bus times, it also enhances interoperability, creates alerts of transport situation and has swift capacity to share information among the different platforms and transport modes. It also offers a comprehensive approach to risk management, putting emergency procedures and response capabilities in place, identifying dangers, including vandalism or violence, fare evasion, and medical emergencies. The Nigerian transport system is urgently in need of modern infrastructures such as ITS. Smart city transport technology helps cities to function productively, while improving services for businesses and lives of is citizens. This technology has the ability to improve travel across traditional modes of transport, such as cars and buses, with immediate benefits for city dwellers and also helps in managing transport systems such as dangerous weather conditions, heavy traffic, and unsafe speeds which can result in accidents and loss of lives. Intelligent transportation systems help in traffic control such as permitting traffic lights to react to changing traffic patterns, instead of working on a fixed schedule in traffic. Intelligent transportation systems is very important in Nigeria’s transportation sector and so would require trained personnel to drive its efficiency to greater height because the purpose of introducing it is to add value and at the same time reduce motor vehicle miles and traffic congestion which is a major challenge around Tin can island and Apapa Port, a major transportation hub in Nigeria. The need for the federal government, state governments, houses of assembly to organise a national transportation workshop to begin the process of addressing the challenges in our nation’s transport sector is highly expedient and so bills that will facilitate the implementation of policies to promote intelligent transportation systems needs to be sponsored because of its potentials to create thousands of jobs for our citizens, provide farmers with better access to cities and a better living condition for Nigerians.

Keywords: intelligent, transport, system, Nigeria

Procedia PDF Downloads 116

Authors: T. C. C. Soo, S. Bhassu

Abstract:

Unlike the common presence of both innate and adaptive immunity in vertebrates, crustaceans, in particular, shrimps, have been discovered to possess only innate immunity. This further emphasizes the importance of innate immunity within shrimps in pathogenic resistance. Under the study of pathogenic immune challenge, different shrimp species actually exhibit varying degrees of immune resistance towards the same pathogen. Furthermore, even within the same shrimp species, different batches of challenged shrimps can have different strengths of immune defence. Several important pathways are activated within shrimps during pathogenic infection. One of them is JAK-STAT pathway that is activated during bacterial, viral and fungal infections by which STAT(Signal Transducer and Activator of Transcription) gene is the core element of the pathway. Based on theory of Central Dogma, the genomic information is transmitted in the order of DNA, RNA and protein. This study is focused in uncovering the important evolutionary patterns present within the DNA (non-coding region) and RNA (coding region). The three shrimp species involved are Macrobrachium rosenbergii, Penaeus monodon and Litopenaeus vannamei which all possess commercial significance. The shrimp species were challenged with a famous penaeid shrimp virus called white spot syndrome virus (WSSV) which can cause serious lethality. Tissue samples were collected during time intervals of 0h, 3h, 6h, 12h, 24h, 36h and 48h. The DNA and RNA samples were then extracted using conventional kits from the hepatopancreas tissue samples. PCR technique together with designed STAT gene conserved primers were utilized for identification of the STAT coding sequences using RNA-converted cDNA samples and subsequent characterization using various bioinformatics approaches including Ramachandran plot, ProtParam and SWISS-MODEL. The varying levels of immune STAT gene activation for the three shrimp species during WSSV infection were confirmed using qRT-PCR technique. For one sample, three biological replicates with three technical replicates each were used for qRT-PCR. On the other hand, DNA samples were important for uncovering the structural variations within the genomic region of STAT gene which would greatly assist in understanding the STAT protein functional variations. The partially-overlapping primers technique was used for the genomic region sequencing. The evolutionary inferences and event predictions were then conducted through the Bayesian Inference method using all the acquired coding and non-coding sequences. This was supplemented by the construction of conventional phylogenetic trees using Maximum likelihood method. The results showed that adaptive evolution caused STAT gene sequence mutations between different shrimp species which led to evolutionary divergence event. Subsequently, the divergent sites were correlated to the differing expressions of STAT gene. Ultimately, this study assists in knowing the shrimp species innate immune variability and selection of disease resistant shrimps for breeding purpose. The deeper understanding of STAT gene evolution from the perspective of both purifying and adaptive approaches not only can provide better immunological insight among shrimp species, but also can be used as a good reference for immunological studies in humans or other model organisms.

Keywords: gene evolution, JAK-STAT pathway, immunology, STAT gene

Procedia PDF Downloads 150

Authors: Nuno Biga

Abstract:

Artificial Intelligence (AI) has the potential to transform management into several impactful ways. It allows machines to interpret information to find patterns in big data and learn from context analysis, optimize operations, make predictions sensitive to each specific situation and support data-driven decision making. The introduction of an 'artificial brain' in organization also enables learning through complex information and data provided by those who train it, namely its users. The "Assisted-BIGAMES" version of the Accident & Emergency (A&E) simulator introduces the concept of a "Virtual Assistant" (VA) sensitive to context, that provides users useful suggestions to pursue the following operations such as: a) to relocate workstations in order to shorten travelled distances and minimize the stress of those involved; b) to identify in real time existing bottleneck(s) in the operations system so that it is possible to quickly act upon them; c) to identify resources that should be polyvalent so that the system can be more efficient; d) to identify in which specific processes it may be advantageous to establish partnership with other teams; and e) to assess possible solutions based on the suggested KPIs allowing action monitoring to guide the (re)definition of future strategies. This paper is built on the BIGAMES© simulator and presents the conceptual AI model developed and demonstrated through a pilot project (BIG-AI). Each Virtual Assisted BIGAME is a management simulator developed by the author that guides operational and strategic decision making, providing users with useful information in the form of management recommendations that make it possible to predict the actual outcome of different alternative management strategic actions. The pilot project developed incorporates results from 12 editions of the BIGAME A&E that took place between 2017 and 2022 at AESE Business School, based on the compilation of data that allows establishing causal relationships between decisions taken and results obtained. The systemic analysis and interpretation of data is powered in the Assisted-BIGAMES through a computer application called "BIGAMES Virtual Assistant" (VA) that players can use during the Game. Each participant in the VA permanently asks himself about the decisions he should make during the game to win the competition. To this end, the role of the VA of each team consists in guiding the players to be more effective in their decision making, through presenting recommendations based on AI methods. It is important to note that the VA's suggestions for action can be accepted or rejected by the managers of each team, as they gain a better understanding of the issues along time, reflect on good practice and rely on their own experience, capability and knowledge to support their own decisions. Preliminary results show that the introduction of the VA provides a faster learning of the decision-making process. The facilitator designated as “Serious Game Controller” (SGC) is responsible for supporting the players with further analysis. The recommended actions by the SGC may differ or be similar to the ones previously provided by the VA, ensuring a higher degree of robustness in decision-making. Additionally, all the information should be jointly analyzed and assessed by each player, who are expected to add “Emotional Intelligence”, an essential component absent from the machine learning process.

Keywords: artificial intelligence, gamification, key performance indicators, machine learning, management simulators, serious games, virtual assistant

Procedia PDF Downloads 104

Authors: Bin Shi, Mouhab Meshreki, Grégoire Bazin, Helmi Attia

Abstract:

Large monolithic components are widely used in the aerospace industry in order to reduce airplane weight. Milling is an important operation in manufacturing of the monolithic parts. More than 90% of the material could be removed in the milling operation to obtain the final shape. This results in low rigidity and post-machining distortion. The post-machining distortion is the deviation of the final shape from the original design after releasing the clamps. It is a major challenge in machining of the monolithic parts, which costs billions of economic losses every year. Three sources are directly related to the part distortion, including initial residual stresses (RS) generated from previous manufacturing processes, machining-induced RS and thermal load generated during machining. A finite element model was developed to simulate a milling process and predicate the post-machining distortion. In this study, a rolled-aluminum plate AA7175 with a thickness of 60 mm was used for the raw block. The initial residual stress distribution in the block was measured using a layer-removal method. A stress-mapping technique was developed to implement the initial stress distribution into the part. It is demonstrated that this technique significantly accelerates the simulation time. Machining-induced residual stresses on the machined surface were measured using MTS3000 hole-drilling strain-gauge system. The measured RS was applied on the machined surface of a plate to predict the distortion. The predicted distortion was compared with experimental results. It is found that the effect of the machining-induced residual stress on the distortion of a thick plate is very limited. The distortion can be ignored if the wall thickness is larger than a certain value. The RS generated from the thermal load during machining is another important factor causing part distortion. Very limited number of research on this topic was reported in literature. A coupled thermo-mechanical FE model was developed to evaluate the thermal effect on the plastic deformation of a plate. A moving heat source with a feed rate was used to simulate the dynamic cutting heat in a milling process. When the heat source passed the part surface, a small layer was removed to simulate the cutting operation. The results show that for different feed rates and plate thicknesses, the plastic deformation/distortion occurs only if the temperature exceeds a critical level. It was found that the initial residual stress has a major contribution to the part distortion. The machining-induced stress has limited influence on the distortion for thin-wall structure when the wall thickness is larger than a certain value. The thermal load can also generate part distortion when the cutting temperature is above a critical level. The developed numerical model was employed to predict the distortion of a frame part with complex structures. The predictions were compared with the experimental measurements, showing both are in good agreement. Through optimization of the position of the part inside the raw plate using the developed numerical models, the part distortion can be significantly reduced by 50%.

Keywords: modelling, monolithic parts, optimization, post-machining distortion, residual stresses

Procedia PDF Downloads 54

Authors: Pinzhe Zhao

Abstract:

This study focuses on predicting university students' cheating tendencies using psychological traits and machine learning techniques. Academic dishonesty is a significant issue that compromises the integrity and fairness of educational institutions. While much research has been dedicated to detecting cheating behaviors after they have occurred, there is limited work on predicting such tendencies before they manifest. The aim of this research is to develop a model that can identify students who are at higher risk of engaging in academic misconduct, allowing for earlier interventions to prevent such behavior. Psychological factors are known to influence students' likelihood of cheating. Research shows that traits such as test anxiety, moral reasoning, self-efficacy, and achievement motivation are strongly linked to academic dishonesty. High levels of anxiety may lead students to cheat as a way to cope with pressure. Those with lower self-efficacy are less confident in their academic abilities, which can push them toward dishonest behaviors to secure better outcomes. Students with weaker moral judgment may also justify cheating more easily, believing it to be less wrong under certain conditions. Achievement motivation also plays a role, as students driven primarily by external rewards, such as grades, are more likely to cheat compared to those motivated by intrinsic learning goals. In this study, data on students’ psychological traits is collected through validated assessments, including scales for anxiety, moral reasoning, self-efficacy, and motivation. Additional data on academic performance, attendance, and engagement in class are also gathered to create a more comprehensive profile. Using machine learning algorithms such as Random Forest, Support Vector Machines (SVM), and Long Short-Term Memory (LSTM) networks, the research builds models that can predict students’ cheating tendencies. These models are trained and evaluated using metrics like accuracy, precision, recall, and F1 scores to ensure they provide reliable predictions. The findings demonstrate that combining psychological traits with machine learning provides a powerful method for identifying students at risk of cheating. This approach allows for early detection and intervention, enabling educational institutions to take proactive steps in promoting academic integrity. The predictive model can be used to inform targeted interventions, such as counseling for students with high test anxiety or workshops aimed at strengthening moral reasoning. By addressing the underlying factors that contribute to cheating behavior, educational institutions can reduce the occurrence of academic dishonesty and foster a culture of integrity. In conclusion, this research contributes to the growing body of literature on predictive analytics in education. It offers a approach by integrating psychological assessments with machine learning to predict cheating tendencies. This method has the potential to significantly improve how academic institutions address academic dishonesty, shifting the focus from punishment after the fact to prevention before it occurs. By identifying high-risk students and providing them with the necessary support, educators can help maintain the fairness and integrity of the academic environment.

Keywords: academic dishonesty, cheating prediction, intervention strategies, machine learning, psychological traits, academic integrity

Procedia PDF Downloads 20

Authors: Michael Josef Schwerer

Abstract:

Background: Analyzing any aircraft accident is mandatory based on the regulations of the International Civil Aviation Organization and the respective country’s criminal prosecution authorities. Legal medicine investigations are unavoidable when fatalities involve the flight crew or when doubts arise concerning the pilot’s aeromedical health status before the event. As a result of frequently tremendous blunt and sharp force trauma along with the impact of the aircraft to the ground, consecutive blast or fire exposition of the occupants or putrefaction of the dead bodies in cases of delayed recovery, relevant findings can be masked or destroyed and therefor being inaccessible in standard pathology practice comprising just forensic autopsy and histopathology. Such cases are of considerable risk of remaining unsolved without legal consequences for those responsible. Further, no lessons can be drawn from these scenarios to improve flight safety and prevent future mishaps. Aims and Methods: To learn from previously unsolved aircraft accidents, re-evaluations of the investigation files and modern molecular pathology studies were performed. Genetic testing involved predominantly PCR-based analysis of gene regulation, studying DNA promotor methylations, RNA transcription and posttranscriptional regulation. In addition, the presence or absence of infective agents, particularly DNA- and RNA-viruses, was studied. Technical adjustments of molecular genetic procedures when working with archived sample material were necessary. Standards for the proper interpretation of the respective findings had to be settled. Results and Discussion: Additional molecular genetic testing significantly contributes to the quality of forensic pathology assessment in aviation mishaps. Previously undetected cardiotropic viruses potentially explain e.g., a pilot’s sudden incapacitation resulting from cardiac failure or myocardial arrhythmia. In contrast, negative results for infective agents participate in ruling out concerns about an accident pilot’s fitness to fly and the aeromedical examiner’s precedent decision to issue him or her an aeromedical certificate. Care must be taken in the interpretation of genetic testing for pre-existing diseases such as hypertrophic cardiomyopathy or ischemic heart disease. Molecular markers such as mRNAs or miRNAs, which can establish these diagnoses in clinical patients, might be misleading in-flight crew members because of adaptive changes in their tissues resulting from repeated mild hypoxia during flight, for instance. Military pilots especially demonstrate significant physiological adjustments to their somatic burdens in flight, such as cardiocirculatory stress and air combat maneuvers. Their non-pathogenic alterations in gene regulation and expression will likely be misinterpreted for genuine disease by inexperienced investigators. Conclusions: The growing influence of molecular pathology on legal medicine practice has found its way into aircraft accident investigation. As appropriate quality standards for laboratory work and data interpretation are provided, forensic genetic testing supports the medico-legal analysis of aviation mishaps and potentially reduces the number of unsolved events in the future.

Keywords: aviation medicine, aircraft accident investigation, forensic pathology, molecular pathology

Procedia PDF Downloads 44

Authors: Bidzina Matsaberidze, Anna Sikharulidze, Gia Sirbiladze, Bezhan Ghvaberidze

Abstract:

In the modern world emergency management decision support systems are actively used by state organizations, which are interested in extreme and abnormal processes and provide optimal and safe management of supply needed for the civil and military facilities in geographical areas, affected by disasters, earthquakes, fires and other accidents, weapons of mass destruction, terrorist attacks, etc. Obviously, these kinds of extreme events cause significant losses and damages to the infrastructure. In such cases, usage of intelligent support technologies is very important for quick and optimal location-transportation of emergency service in order to avoid new losses caused by these events. Timely servicing from emergency service centers to the affected disaster regions (response phase) is a key task of the emergency management system. Scientific research of this field takes the important place in decision-making problems. Our goal was to create an expert knowledge-based intelligent support system, which will serve as an assistant tool to provide optimal solutions for the above-mentioned problem. The inputs to the mathematical model of the system are objective data, as well as expert evaluations. The outputs of the system are solutions for Fuzzy Multi-Objective Emergency Location-Transportation Problem (FMOELTP) for disasters’ regions. The development and testing of the Intelligent Support System were done on the example of an experimental disaster region (for some geographical zone of Georgia) which was generated using a simulation modeling. Four objectives are considered in our model. The first objective is to minimize an expectation of total transportation duration of needed products. The second objective is to minimize the total selection unreliability index of opened humanitarian aid distribution centers (HADCs). The third objective minimizes the number of agents needed to operate the opened HADCs. The fourth objective minimizes the non-covered demand for all demand points. Possibility chance constraints and objective constraints were constructed based on objective-subjective data. The FMOELTP was constructed in a static and fuzzy environment since the decisions to be made are taken immediately after the disaster (during few hours) with the information available at that moment. It is assumed that the requests for products are estimated by homeland security organizations, or their experts, based upon their experience and their evaluation of the disaster’s seriousness. Estimated transportation times are considered to take into account routing access difficulty of the region and the infrastructure conditions. We propose an epsilon-constraint method for finding the exact solutions for the problem. It is proved that this approach generates the exact Pareto front of the multi-objective location-transportation problem addressed. Sometimes for large dimensions of the problem, the exact method requires long computing times. Thus, we propose an approximate method that imposes a number of stopping criteria on the exact method. For large dimensions of the FMOELTP the Estimation of Distribution Algorithm’s (EDA) approach is developed.

Keywords: epsilon-constraint method, estimation of distribution algorithm, fuzzy multi-objective combinatorial programming problem, fuzzy multi-objective emergency location/transportation problem

Procedia PDF Downloads 321

Authors: Brooklyn Rushton, Michelle Rutty, Natalie Knowles, Daniel Scott

Abstract:

As people are increasingly on the search for extraordinary experiences and connections with nature, adventure tourism is experiencing significant growth and providing tourists with life-changing experiences. Unlike built attraction-based tourism, adventure tourism relies entirely on natural heritage, which leaves communities dependent on adventure tourism extremely vulnerable to environmental and climatic changes. A growing body of evidence suggests that global climate change will influence the future of adventure tourism and mountain outdoor recreation opportunities on a global scale. Across Canada, more specifically, climate change is broadly anticipated to present risks for winter-snow sports, while opportunities are anticipated to arise for green season activities. These broad seasonal shifts do not account for the indirect impacts of climate change on adventure tourism, such as the cost of adaptation or the increase of natural hazards and the associated likelihood of accidents. While some research has examined the impact of climate change on natural environments that adventure tourism relies on, a very small body of research has specifically focused on guides’ perspectives or included hard adventure tourism activities. The guiding industry is unique, as guides are trained through an elegant blend of art and science to make decisions based on experience, observation, and intuition. While quantitative research can monitor change in natural environments, guides local knowledge can provide eye-witness accounts and outline what environmental changes mean for the future sustainability of adventure tourism. This research will capture the extensive knowledge of mountain guides to better understand the implications of climate change for mountain adventure and potential adaptive responses for the adventure tourism industry. This study uses a structured online survey with open and close-ended questions that will be administered using Qualtrics (an online survey platform). This survey is disseminated to current members of the Association of Canadian Mountain Guides (ACMG). Participation in this study will be exclusive to members of the ACMG operating in the outdoor guiding streams. The 25 survey questions are organized into four sections: demographic and professional operation (9 questions), physical change (4 questions), climate change perception (6 questions), and climate change adaptation (6 questions). How mountain guides perceive and respond to climate change is important knowledge for the future of the expanding adventure tourism industry. Results from this study are expected to provide important information to mountain destinations on climate change vulnerability and adaptive capacity. Expected results of this study include guides insight into: (1) experience-safety relevant observed physical changes in guided regions (i.e. glacial coverage, permafrost coverage, precipitation, temperature, and slope instability) (2) changes in hazards within the guiding environment (i.e. avalanches, rockfall, icefall, forest fires, flooding, and extreme weather events), (3) existing and potential adaptation strategies, and (4) key information and other barriers for adaptation. By gaining insight from the knowledge of mountain guides, this research can help the tourism industry at large understand climate risk and create adaptation strategies to ensure the resiliency of the adventure tourism industry.

Keywords: adventure tourism, climate change, environmental change, mountain hazards

Procedia PDF Downloads 191

Authors: Gregor Vidmar, Rožle Repič, Boštjan Lesar, Miha Humar

Abstract:

The study investigates the impact of cracks in surface coatings on moisture content (MC) and related fungal growth in window frames made of thermally modified (TM) and native Norway spruce using hygrothermal simulations for Ljubljana, Slovenia. Comprehensive validation against field test data confirmed the numerical model's predictions, demonstrating similar trends in MC changes over the investigated four years. Various established mould growth models (isopleth, VTT, bio hygrothermal) did not appropriately reflect differences between the spruce types because they do not consider material moisture content, leading to the main conclusion that TM spruce is more resistant to moisture-related issues. Wood's MC influences fungal decomposition, typically occurring above 25% - 30% MC, with some fungi growing at lower MC under conducive conditions. Surface coatings cannot wholly prevent water penetration, which becomes significant when the coating is damaged. This study investigates the detrimental effects of surface coating cracks on wood moisture absorption, comparing TM spruce and native spruce window frames. Simulations were conducted for undamaged and damaged coatings (from 1 mm to 9 mm wide cracks) on window profiles as well as for uncoated profiles. Sorption curves were also measured up to 95% of the relative humidity. MC was measured in the frames exposed to actual climatic conditions and compared to simulated data for model validation. The study utilizes a simplified model of the bottom frame part due to convergence issues with simulations of the whole frame. TM spruce showed about 4% lower MC content compared to native spruce. Simulations showed that a 3 mm wide crack in native spruce coatings for the north orientation poses significant moisture risks, while a 9 mm wide crack in TM spruce coatings remains acceptable furthermore in the case of uncoated TM spruce could be acceptable. In addition, it seems that large enough cracks may cause even worse moisture dynamics compared to uncoated native spruce profiles. The absorption curve comes out to be the far most influential parameter, and the next one is density. Existing mould growth models need to be upgraded to reflect wood material differences accurately. Due to the lower sorption curve of TM spruce, in reality, higher RH values are obtained under the same boundary conditions, which implies a more critical situation according to these mould growth models. Still, it does not reflect the difference in materials, especially under external exposure conditions. Even if different substrate categories in the isopleth and bio-hygrothermal model or different sensitivity material classes for standard and TM wood are used, it does not necessarily change the expected trends; thus, models with MC being the inherent part of the models should be introduced. Orientation plays a crucial role in moisture dynamics. Results show that for similar moisture dynamics, for Norway spruce, the crack could be about 2 mm wider on the south than on the north side. In contrast, for TM spruce, orientation isn't as important, compared to other material properties. The study confirms the enhanced suitability of TM spruce for window frames in terms of moisture resistance and crack tolerance in surface coatings.

Keywords: hygrothermal simulations, mould growth, surface coating, thermally modified wood, window frame

Procedia PDF Downloads 34

Authors: Dilnee D. Suraweera, Tim Groom, Brian Chung, Brendan Bond, Andrew Schipp, Marc E. Nicolas

Abstract:

Pyrethrum (Tanacetum cinerariifolium) is a perennial plant belongs to family Asteraceae. This is cultivated commercially for extraction of natural insecticide pyrethrins, which accumulates in their flower head achenes. Approximately 94% of the pyrethrins are produced within secretory ducts and trichomes of achenes of the mature pyrethrum flower. This is the most widely used botanical insecticide in the world and Australia is the current largest pyrethrum producer in the world. Rainfall in pyrethrum growing regions in Australia during pyrethrum flowering period, in late spring and early summer is significantly less. Due to lack of adequate soil moisture and under elevated temperature conditions during post-anthesis period, resulting in yield reductions. Therefore, understanding of yield responses of pyrethrum to irrigation is important for Pyrethrum as a commercial crop. Irrigation management has been identified as a key area of pyrethrum crop management strategies that could be manipulated to increase yield. Pyrethrum is a comparatively drought tolerant plant and it has some ability to survive in dry conditions due to deep rooting. But in dry areas and in dry seasons, the crop cannot reach to its full yield potential without adequate soil moisture. Therefore, irrigation is essential during the flowering period prevent crop water stress and maximise yield. Irrigation during the water deficit period results in an overall increased rate of water uptake and growth by the plant which is essential to achieve the maximum yield benefits from commercial crops. The effects of irrigation treatments applied at post-anthesis period on pyrethrum yield responses were studied in two irrigation methods. This was conducted in a first harvest commercial pyrethrum field in Waubra, Victoria, during 2012/2013 season. Drip irrigation and overhead sprinkler irrigation treatments applied during whole flowering period were compared with ‘rainfed’ treatment in relation to flower yield and pyrethrin yield responses. The results of this experiment showed that the application of 180mm of irrigation throughout the post-anthesis period, from early flowering stages to physiological maturity under drip irrigation treatment increased pyrethrin concentration by 32%, which combined with the 95 % increase in the flower yield to give a total pyrethrin yield increase of 157%, compared to the ‘rainfed’ treatment. In contrast to that overhead sprinkler irrigation treatment increased pyrethrin concentration by 19%, which combined with the 60 % increase in the flower yield to give a total pyrethrin yield increase of 91%, compared to the ‘rainfed’ treatment. Irrigation treatments applied throughout the post-anthesis period significantly increased flower yield as a result of enhancement of number of flowers and flower size. Irrigation provides adequate soil moisture for flower development in pyrethrum which slows the rate of flower development and increases the length of the flowering period, resulting in a delayed crop harvest (11 days) compared to the ‘rainfed’ treatment. Overall, irrigation has a major impact on pyrethrin accumulation which increases the rate and duration of pyrethrin accumulation resulting in higher pyrethrin yield per flower at physiological maturity. The findings of this study will be important for future yield predictions and to develop advanced agronomic strategies to maximise pyrethrin yield in pyrethrum.

Keywords: achene, drip irrigation, overhead irrigation, pyrethrin

Procedia PDF Downloads 409

Authors: Soheila Sadeghi

Abstract:

Accurate cost prediction is essential for effective project management and decision-making in the construction industry. This study aims to develop a cost prediction model for construction projects using Machine Learning techniques and Particle Swarm Optimization (PSO). The research utilizes a comprehensive dataset containing project cost estimates, actual costs, resource details, and project performance metrics from a road reconstruction project. The methodology involves data preprocessing, feature selection, and the development of an Artificial Neural Network (ANN) model optimized using PSO. The study investigates the impact of various input features, including cost estimates, resource allocation, and project progress, on the accuracy of cost predictions. The performance of the optimized ANN model is evaluated using metrics such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and R-squared. The results demonstrate the effectiveness of the proposed approach in predicting project costs, outperforming traditional benchmark models. The feature selection process identifies the most influential variables contributing to cost variations, providing valuable insights for project managers. However, this study has several limitations. Firstly, the model's performance may be influenced by the quality and quantity of the dataset used. A larger and more diverse dataset covering different types of construction projects would enhance the model's generalizability. Secondly, the study focuses on a specific optimization technique (PSO) and a single Machine Learning algorithm (ANN). Exploring other optimization methods and comparing the performance of various ML algorithms could provide a more comprehensive understanding of the cost prediction problem. Future research should focus on several key areas. Firstly, expanding the dataset to include a wider range of construction projects, such as residential buildings, commercial complexes, and infrastructure projects, would improve the model's applicability. Secondly, investigating the integration of additional data sources, such as economic indicators, weather data, and supplier information, could enhance the predictive power of the model. Thirdly, exploring the potential of ensemble learning techniques, which combine multiple ML algorithms, may further improve cost prediction accuracy. Additionally, developing user-friendly interfaces and tools to facilitate the adoption of the proposed cost prediction model in real-world construction projects would be a valuable contribution to the industry. The findings of this study have significant implications for construction project management, enabling proactive cost estimation, resource allocation, budget planning, and risk assessment, ultimately leading to improved project performance and cost control. This research contributes to the advancement of cost prediction techniques in the construction industry and highlights the potential of Machine Learning and PSO in addressing this critical challenge. However, further research is needed to address the limitations and explore the identified future research directions to fully realize the potential of ML-based cost prediction models in the construction domain.

Keywords: cost prediction, construction projects, machine learning, artificial neural networks, particle swarm optimization, project management, feature selection, road reconstruction

Procedia PDF Downloads 58

Authors: Alper T. Celebi, Ali Beskok

Abstract:

Electroosmotic (EO) slip flows in nanochannels are investigated using non-equilibrium molecular dynamics (MD) simulations, and the results are compared with analytical solution of Poisson-Boltzmann and Stokes (PB-S) equations with slip contribution. The ultimate objective of this study is to show that well-known continuum flow model can accurately predict the EO velocity profiles in nanochannels using the slip lengths and apparent viscosities obtained from force-driven flow simulations performed at various liquid-wall interaction strengths. EO flow of aqueous NaCl solution in silicon nanochannels are simulated under realistic electrochemical conditions within the validity region of Poisson-Boltzmann theory. A physical surface charge density is determined for nanochannels based on dissociations of silanol functional groups on channel surfaces at known salt concentration, temperature and local pH. First, we present results of density profiles and ion distributions by equilibrium MD simulations, ensuring that the desired thermodynamic state and ionic conditions are satisfied. Next, force-driven nanochannel flow simulations are performed to predict the apparent viscosity of ionic solution between charged surfaces and slip lengths. Parabolic velocity profiles obtained from force-driven flow simulations are fitted to a second-order polynomial equation, where viscosity and slip lengths are quantified by comparing the coefficients of the fitted equation with continuum flow model. Presence of charged surface increases the viscosity of ionic solution while the velocity-slip at wall decreases. Afterwards, EO flow simulations are carried out under uniform electric field for different liquid-wall interaction strengths. Velocity profiles present finite slips near walls, followed with a conventional viscous flow profile in the electrical double layer that reaches a bulk flow region in the center of the channel. The EO flow enhances with increased slip at the walls, which depends on wall-liquid interaction strength and the surface charge. MD velocity profiles are compared with the predictions from analytical solutions of the slip modified PB-S equation, where the slip length and apparent viscosity values are obtained from force-driven flow simulations in charged silicon nano-channels. Our MD results show good agreements with the analytical solutions at various slip conditions, verifying the validity of PB-S equation in nanochannels as small as 3.5 nm. In addition, the continuum model normalizes slip length with the Debye length instead of the channel height, which implies that enhancement in EO flows is independent of the channel height. Further MD simulations performed at different channel heights also shows that the flow enhancement due to slip is independent of the channel height. This is important because slip enhanced EO flow is observable even in micro-channels experiments by using a hydrophobic channel with large slip and high conductivity solutions with small Debye length. The present study provides an advanced understanding of EO flows in nanochannels. Correct characterization of nanoscale EO slip flow is crucial to discover the extent of well-known continuum models, which is required for various applications spanning from ion separation to drug delivery and bio-fluidic analysis.

Keywords: electroosmotic flow, molecular dynamics, slip length, velocity-slip

Procedia PDF Downloads 157

Authors: Danlei Yang, Luofeng Huang

Abstract:

The integration of digital twin technology with renewable energy systems offers an innovative approach to predicting and optimising performance throughout the entire lifecycle. A digital twin is a continuously updated virtual replica of a real-world entity, synchronised with data from its physical counterpart and environment. Many digital twin companies today claim to have mature digital twin products, but their focus is primarily on equipment visualisation. However, the core of a digital twin should be its model, which can mirror, shadow, and thread with the real-world entity, which is still underdeveloped. For a floating solar energy system, a digital twin model can be defined in three aspects: (a) the physical floating solar energy system along with environmental factors such as solar irradiance and wave dynamics, (b) a digital model powered by artificial intelligence (AI) algorithms, and (c) the integration of real system data with the AI-driven model and a user interface. The experimental setup for the floating solar energy system, is designed to replicate real-ocean conditions of floating solar installations within a controlled laboratory environment. The system consists of a water tank that simulates an aquatic surface, where a floating catamaran structure supports a solar panel. The solar simulator is set up in three positions: one directly above and two inclined at a 45° angle in front and behind the solar panel. This arrangement allows the simulation of different sun angles, such as sunrise, midday, and sunset. The solar simulator is positioned 400 mm away from the solar panel to maintain consistent solar irradiance on its surface. Stability for the floating structure is achieved through ropes attached to anchors at the bottom of the tank, which simulates the mooring systems used in real-world floating solar applications. The floating solar energy system's sensor setup includes various devices to monitor environmental and operational parameters. An irradiance sensor measures solar irradiance on the photovoltaic (PV) panel. Temperature sensors monitor ambient air and water temperatures, as well as the PV panel temperature. Wave gauges measure wave height, while load cells capture mooring force. Inclinometers and ultrasonic sensors record heave and pitch amplitudes of the floating system’s motions. An electric load measures the voltage and current output from the solar panel. All sensors collect data simultaneously. Artificial neural network (ANN) algorithms are central to developing the digital model, which processes historical and real-time data, identifies patterns, and predicts the system’s performance in real time. The data collected from various sensors are partly used to train the digital model, with the remaining data reserved for validation and testing. The digital twin model combines the experimental setup with the ANN model, enabling monitoring, analysis, and prediction of the floating solar energy system's operation. The digital model mirrors the functionality of the physical setup, running in sync with the experiment to provide real-time insights and predictions. It provides useful industrial benefits, such as informing maintenance plans as well as design and control strategies for optimal energy efficiency. In long term, this digital twin will help improve overall solar energy yield whilst minimising the operational costs and risks.

Keywords: digital twin, floating solar energy system, experiment setup, artificial intelligence

Procedia PDF Downloads 6

Authors: André Python

Abstract:

To this day, terrorism persists as a worldwide threat, exemplified by the recent deadly attacks in January 2015 in Paris and the ongoing massacres perpetrated by ISIS in Iraq and Syria. In response to this threat, states deploy various counterterrorism measures, the cost of which could be reduced through effective preventive measures. In order to increase the efficiency of preventive measures, policy-makers may benefit from accurate predictive models that are able to capture the complex spatial dynamics of terrorism occurring at a local scale. Despite empirical research carried out at country-level that has confirmed theories explaining the diffusion processes of terrorism across space and time, scholars have failed to assess diffusion’s theories on a local scale. Moreover, since scholars have not made the most of recent statistical modelling approaches, they have been unable to build up predictive models accurate in both space and time. In an effort to address these shortcomings, this research suggests a novel approach to systematically assess the theories of terrorism’s diffusion on a local scale and provide a predictive model of the local spatial dynamics of terrorism worldwide. With a focus on the lethal terrorist events that occurred after 9/11, this paper addresses the following question: why and how does lethal terrorism diffuse in space and time? Based on geolocalised data on worldwide terrorist attacks and covariates gathered from 2002 to 2013, a binomial spatio-temporal point process is used to model the probability of terrorist attacks on a sphere (the world), the surface of which is discretised in the form of Delaunay triangles and refined in areas of specific interest. Within a Bayesian framework, the model is fitted through an integrated nested Laplace approximation - a recent fitting approach that computes fast and accurate estimates of posterior marginals. Hence, for each location in the world, the model provides a probability of encountering a lethal terrorist attack and measures of volatility, which inform on the model’s predictability. Diffusion processes are visualised through interactive maps that highlight space-time variations in the probability and volatility of encountering a lethal attack from 2002 to 2013. Based on the previous twelve years of observation, the location and lethality of terrorist events in 2014 are statistically accurately predicted. Throughout the global scope of this research, local diffusion processes such as escalation and relocation are systematically examined: the former process describes an expansion from high concentration areas of lethal terrorist events (hotspots) to neighbouring areas, while the latter is characterised by changes in the location of hotspots. By controlling for the effect of geographical, economical and demographic variables, the results of the model suggest that the diffusion processes of lethal terrorism are jointly driven by contagious and non-contagious factors that operate on a local scale – as predicted by theories of diffusion. Moreover, by providing a quantitative measure of predictability, the model prevents policy-makers from making decisions based on highly uncertain predictions. Ultimately, this research may provide important complementary tools to enhance the efficiency of policies that aim to prevent and combat terrorism.

Keywords: diffusion process, terrorism, spatial dynamics, spatio-temporal modeling

Procedia PDF Downloads 350

Authors: A. J. Al-Graitti, G. A. Khalid, P. Berthelson, A. Mason-Jones, R. Prabhu, M. D. Jones

Abstract:

Motor vehicle related pedestrian road traffic collisions are a major road safety challenge, since they are a leading cause of death and serious injury worldwide, contributing to a third of the global disease burden. The auto rickshaw, which is a common form of urban transport in many developing countries, plays a major transport role, both as a vehicle for hire and for private use. The most common auto rickshaws are quite unlike ‘typical’ four-wheel motor vehicle, being typically characterised by three wheels, a non-tilting sheet-metal body or open frame construction, a canvas roof and side curtains, a small drivers’ cabin, handlebar controls and a passenger space at the rear. Given the propensity, in developing countries, for auto rickshaws to be used in mixed cityscapes, where pedestrians and vehicles share the roadway, the potential for auto rickshaw impacts with pedestrians is relatively high. Whilst auto rickshaws are used in some Western countries, their limited number and spatial separation from pedestrian walkways, as a result of city planning, has not resulted in significant accident statistics. Thus, auto rickshaws have not been subject to the vehicle impact related pedestrian crash kinematic analyses and/or injury mechanics assessment, typically associated with motor vehicle development in Western Europe, North America and Japan. This study presents a parametric analysis of auto rickshaw related pedestrian impacts by computational simulation, using a Finite Element model of an auto rickshaw and an LS-DYNA 50^th percentile male Hybrid III Anthropometric Test Device (dummy). Parametric variables include auto rickshaw impact velocity, auto rickshaw impact region (front, centre or offset) and relative pedestrian impact position (front, side and rear). The output data of each impact simulation was correlated against reported injury metrics, Head Injury Criterion (front, side and rear), Neck injury Criterion (front, side and rear), Abbreviated Injury Scale and reported risk level and adds greater understanding to the issue of auto rickshaw related pedestrian injury risk. The parametric analyses suggest that pedestrians are subject to a relatively high risk of injury during impacts with an auto rickshaw at velocities of 20 km/h or greater, which during some of the impact simulations may even risk fatalities. The present study provides valuable evidence for informing a series of recommendations and guidelines for making the auto rickshaw safer during collisions with pedestrians. Whilst it is acknowledged that the present research findings are based in the field of safety engineering and may over represent injury risk, compared to “Real World” accidents, many of the simulated interactions produced injury response values significantly greater than current threshold curves and thus, justify their inclusion in the study. To reduce the injury risk level and increase the safety of the auto rickshaw, there should be a reduction in the velocity of the auto rickshaw and, or, consideration of engineering solutions, such as retro fitting injury mitigation technologies to those auto rickshaw contact regions which are the subject of the greatest risk of producing pedestrian injury.

Keywords: auto rickshaw, finite element analysis, injury risk level, LS-DYNA, pedestrian impact

Procedia PDF Downloads 194

Authors: Zachary Blanks, Solomon Sonya

Abstract:

Poaching presents a serious threat to endangered animal species, environment conservations, and human life. Additionally, some poaching activity has even been linked to supplying funds to support terrorist networks elsewhere around the world. Consequently, agencies dedicated to protecting wildlife habitats have a near intractable task of adequately patrolling an entire area (spanning several thousand kilometers) given limited resources, funds, and personnel at their disposal. Thus, agencies need predictive tools that are both high-performing and easily implementable by the user to help in learning how the significant features (e.g. animal population densities, topography, behavior patterns of the criminals within the area, etc) interact with each other in hopes of abating poaching. This research develops a classification model using machine learning algorithms to aid in forecasting future attacks that is both easy to train and performs well when compared to other models. In this research, we demonstrate how data imputation methods (specifically predictive mean matching, gradient boosting, and random forest multiple imputation) can be applied to analyze data and create significant predictions across a varied data set. Specifically, we apply these methods to improve the accuracy of adopted prediction models (Logistic Regression, Support Vector Machine, etc). Finally, we assess the performance of the model and the accuracy of our data imputation methods by learning on a real-world data set constituting four years of imputed data and testing on one year of non-imputed data. This paper provides three main contributions. First, we extend work done by the Teamcore and CREATE (Center for Risk and Economic Analysis of Terrorism Events) research group at the University of Southern California (USC) working in conjunction with the Department of Homeland Security to apply game theory and machine learning algorithms to develop more efficient ways of reducing poaching. This research introduces ensemble methods (Random Forests and Stochastic Gradient Boosting) and applies it to real-world poaching data gathered from the Ugandan rain forest park rangers. Next, we consider the effect of data imputation on both the performance of various algorithms and the general accuracy of the method itself when applied to a dependent variable where a large number of observations are missing. Third, we provide an alternate approach to predict the probability of observing poaching both by season and by month. The results from this research are very promising. We conclude that by using Stochastic Gradient Boosting to predict observations for non-commercial poaching by season, we are able to produce statistically equivalent results while being orders of magnitude faster in computation time and complexity. Additionally, when predicting potential poaching incidents by individual month vice entire seasons, boosting techniques produce a mean area under the curve increase of approximately 3% relative to previous prediction schedules by entire seasons.

Keywords: ensemble methods, imputation, machine learning, random forests, statistical analysis, stochastic gradient boosting, wildlife protection

Procedia PDF Downloads 291

Authors: A. Kolendo

Abstract:

Pacific Islands are one of the most vulnerable areas to climate change. Sea level rise and accelerating storm surge continuously threaten the communities' habitats on low-lying atolls. With scientific predictions of encroaching tides on their land, the Islanders have been informed about the need for future relocation planning. However, some communities oppose such retreat strategies through the reasoning that comprehends current climatic changes through the lenses of the biblical ark of Noah. This parable states God's promise never to flood the Earth again and never deprive people of their land and habitats. Several interpretations of this parable emerged in Oceania, prompting either climate action or denial. Resistance to relocation planning expressed through Christian thoughts led religion to be perceived as a barrier to dialogue between the Islanders and scientists. Since climate change concerns natural processes, the attitudes towards environmental stewardship prompt the communities' responses to it; some Christian teachings indicate humanity's responsibility over the environment, whereas others ascertain the people's dominion, which prompts resistance and sometimes denial. With church denominations and their various environmental standpoints, competing responses to climate change emerged in Oceania. Before miss-ionization, traditional knowledge had guided the environmental sphere, influencing current Christian teachings. Each atoll characterizes a distinctive manner of traditional knowledge; however, the unique relationship with nature unites all islands. The interconnectedness between the land, sea and people indicates the integrity between the communities and their environments. Such a factor influences the comprehension of Noah's story in the context of climate change that threatens their habitats. Pacific Islanders experience climate change through the slow disappearance of their homelands. However, the Western world perceives it as a global issue that will affect the population in the long-term perspective. Therefore, the Islanders seek to comprehend this global phenomenon in a local context that reads climate change as the Great Deluge. Accordingly, the safety measures that this parable promotes compensate for the danger of climate change. The rainbow covenant gives hope in God's promise never to flood the Earth again. At the same time, Noah's survival relates to the Islanders' current situation. Since these communities have the lowest carbon emissions rate, their contribution to anthropogenic climate change is scarce. Therefore, the lack of environmental sin would contextualize them as contemporary Noah with the ultimate survival of sea level rise. This study aims to defy religion constituting a barrier through secondary data analysis from a risk compensation perspective. Instead, religion is portrayed as a source of knowledge that enables comprehension of the communities' situation. By demonstrating that the Pacific Islanders utilize Noah's story as a vessel for coping with the danger of climate change, the study argues that religion provides safety measures that compensate for the future projections of land's disappearance. The purpose is to build a bridge between religious communities and scientific bodies and ultimately bring an understanding of two diverse perspectives. By addressing the practical challenges of interdisciplinary research with faith-based systems, this study uplifts the voices of communities and portrays their experiences expressed through Christian thoughts.

Keywords: Christianity, climate change, existential threat, Pacific Islands, story of Noah

Procedia PDF Downloads 95

Authors: M. Reza Hashemi, Chris Small, Scott Hayward

Abstract:

The Northeast Coast of the US faces damaging effects of coastal flooding and winds due to Atlantic tropical and extratropical storms each year. Historically, several large storm events have produced substantial levels of damage to the region; most notably of which were the Great Atlantic Hurricane of 1938, Hurricane Carol, Hurricane Bob, and recently Hurricane Sandy (2012). The objective of this study was to develop an integrated modeling system that could be used as a forecasting/hindcasting tool to evaluate and communicate the risk coastal communities face from these coastal storms. This modeling system utilizes the ADvanced CIRCulation (ADCIRC) model for storm surge predictions and the Simulating Waves Nearshore (SWAN) model for the wave environment. These models were coupled, passing information to each other and computing over the same unstructured domain, allowing for the most accurate representation of the physical storm processes. The coupled SWAN-ADCIRC model was validated and has been set up to perform real-time forecast simulations (as well as hindcast). Modeled storm parameters were then passed to a coastal risk assessment tool. This tool, which is generic and universally applicable, generates spatial structural damage estimate maps on an individual structure basis for an area of interest. The required inputs for the coastal risk model included a detailed information about the individual structures, inundation levels, and wave heights for the selected region. Additionally, calculation of wind damage to structures was incorporated. The integrated coastal risk assessment system was then tested and applied to Charlestown, a small vulnerable coastal town along the southern shore of Rhode Island. The modeling system was applied to Hurricane Sandy and a synthetic storm. In both storm cases, effect of natural dunes on coastal risk was investigated. The resulting damage maps for the area (Charlestown) clearly showed that the dune eroded scenarios affected more structures, and increased the estimated damage. The system was also tested in forecast mode for a large Nor’Easters: Stella (March 2017). The results showed a good performance of the coupled model in forecast mode when compared to observations. Finally, a nearshore model XBeach was then nested within this regional grid (ADCIRC-SWAN) to simulate nearshore sediment transport processes and coastal erosion. Hurricane Irene (2011) was used to validate XBeach, on the basis of a unique beach profile dataset at the region. XBeach showed a relatively good performance, being able to estimate eroded volumes along the beach transects with a mean error of 16%. The validated model was then used to analyze the effectiveness of several erosion mitigation methods that were recommended in a recent study of coastal erosion in New England: beach nourishment, coastal bank (engineered core), and submerged breakwater as well as artificial surfing reef. It was shown that beach nourishment and coastal banks perform better to mitigate shoreline retreat and coastal erosion.

Keywords: ADCIRC, coastal flooding, storm surge, coastal risk assessment, living shorelines

Procedia PDF Downloads 116

Authors: Zhiwu Zheng, Prakhar Kumar, Sigurd Wagner, Naveen Verma, James C. Sturm

Abstract:

Soft robots have drawn great interest recently due to a rich range of possible shapes and motions they can take on to address new applications, compared to traditional rigid robots. Large-area electronics (LAE) provides a unique platform for creating soft robots by leveraging thin-film technology to enable the integration of a large number of actuators, sensors, and control circuits on flexible sheets. However, the rich shapes and motions possible, especially when interacting with complex environments, pose significant challenges to forming well-generalized and robust models necessary for robot design and control. In this work, we describe an analytical model for predicting the shape and locomotion of a flexible (steel-foil-based) piezoelectric-actuated 2D robot based on Euler-Bernoulli beam theory. It is nominally (unpowered) lying flat on the ground, and when powered, its shape is controlled by an array of piezoelectric thin-film actuators. Key features of the models are its ability to incorporate the significant effects of gravity on the shape and to precisely predict the spatial distribution of friction against the contacting surfaces, necessary for determining inchworm-type motion. We verified the model by developing a distributed discrete element representation of a continuous piezoelectric actuator and by comparing its analytical predictions to discrete-element robot simulations using PyBullet. Without gravity, predicting the shape of a sheet with a linear array of piezoelectric actuators at arbitrary voltages is straightforward. However, gravity significantly distorts the shape of the sheet, causing some segments to flatten against the ground. Our work includes the following contributions: (i) A self-consistent approach was developed to exactly determine which parts of the soft robot are lifted off the ground, and the exact shape of these sections, for an arbitrary array of piezoelectric voltages and configurations. (ii) Inchworm-type motion relies on controlling the relative friction with the ground surface in different sections of the robot. By adding torque-balance to our model and analyzing shear forces, the model can then determine the exact spatial distribution of the vertical force that the ground is exerting on the soft robot. Through this, the spatial distribution of friction forces between ground and robot can be determined. (iii) By combining this spatial friction distribution with the shape of the soft robot, in the function of time as piezoelectric actuator voltages are changed, the inchworm-type locomotion of the robot can be determined. As a practical example, we calculated the performance of a 5-actuator system on a 50-µm thick steel foil. Piezoelectric properties of commercially available thin-film piezoelectric actuators were assumed. The model predicted inchworm motion of up to 200 µm per step. For independent verification, we also modelled the system using PyBullet, a discrete-element robot simulator. To model a continuous thin-film piezoelectric actuator, we broke each actuator into multiple segments, each of which consisted of two rigid arms with appropriate mass connected with a 'motor' whose torque was set by the applied actuator voltage. Excellent agreement between our analytical model and the discrete-element simulator was shown for both for the full deformation shape and motion of the robot.

Keywords: analytical modeling, piezoelectric actuators, soft robot locomotion, thin-film technology

Procedia PDF Downloads 180

Authors: Ainura Tursunalieva, Irene Hudson

Abstract:

Continuous improvement of both the quality and safety of health care is an important goal in Australia and internationally. The intensive care unit (ICU) receives patients with a wide variety of and severity of illnesses. Accurately identifying patients at risk of developing complications or dying is crucial to increasing healthcare efficiency. Thus, it is essential for clinicians and researchers to have a robust framework capable of evaluating the risk profile of a patient. ICU scoring systems provide such a framework. The Acute Physiology and Chronic Health Evaluation III and the Simplified Acute Physiology Score II are ICU scoring systems frequently used for assessing the severity of acute illness. These scoring systems collect multiple risk factors for each patient including physiological measurements then render the assessment outcomes of individual risk factors into a single numerical value. A higher score is related to a more severe patient condition. Furthermore, the Mortality Probability Model II uses logistic regression based on independent risk factors to predict a patient’s probability of mortality. An important overlooked limitation of SAPS II and MPM II is that they do not, to date, include interaction terms between a patient’s vital signs. This is a prominent oversight as it is likely there is an interplay among vital signs. The co-existence of certain conditions may pose a greater health risk than when these conditions exist independently. One barrier to including such interaction terms in predictive models is the dimensionality issue as it becomes difficult to use variable selection. We propose an innovative scoring system which takes into account a dependence structure among patient’s vital signs, such as systolic and diastolic blood pressures, heart rate, pulse interval, and peripheral oxygen saturation. Copulas will capture the dependence among normally distributed and skewed variables as some of the vital sign distributions are skewed. The estimated dependence parameter will then be incorporated into the traditional scoring systems to adjust the points allocated for the individual vital sign measurements. The same dependence parameter will also be used to create an alternative copula-based model for predicting a patient’s probability of mortality. The new copula-based approach will accommodate not only a patient’s trajectories of vital signs but also the joint dependence probabilities among the vital signs. We hypothesise that this approach will produce more stable assessments and lead to more time efficient and accurate predictions. We will use two data sets: (1) 250 ICU patients admitted once to the Chui Regional Hospital (Kyrgyzstan) and (2) 37 ICU patients’ agitation-sedation profiles collected by the Hunter Medical Research Institute (Australia). Both the traditional scoring approach and our copula-based approach will be evaluated using the Brier score to indicate overall model performance, the concordance (or c) statistic to indicate the discriminative ability (or area under the receiver operating characteristic (ROC) curve), and goodness-of-fit statistics for calibration. We will also report discrimination and calibration values and establish visualization of the copulas and high dimensional regions of risk interrelating two or three vital signs in so-called higher dimensional ROCs.

Keywords: copula, intensive unit scoring system, ROC curves, vital sign dependence

Procedia PDF Downloads 152