Search results for: vector quantization

Authors: Zahra Mohajer, Afsaneh Soltani

Abstract:

Doping is a major issue in competitive sports and is favored by vast groups of athletes. The feeling of being higher-ranking than others and gaining fame has caused many athletes to misuse drugs. The definition of doping is to use prohibited substances and/or methods that help physical or mental performances or both. Doping counts as the illegal use of chemical substances or drugs, excessive amounts of physiological substances to increase the performance at or out of competition or even the use of inappropriate medications to treat an injury to gain the ability to participate in a competition. The International Olympic Committee (IOC) and World Anti-Doping Agency (WADA) have forbidden these substances to ensure fair and equal competition and also the health of the competitors. As of 2004 WADA has published an international list of illegal substances used for doping, which is updated annually. In the process of the Genome Project scientists have gained the ability to treat numerous diseases by gene therapy, which may result in bodily performance increase and therefore a potential opportunity to misuse by some athletes. Gene doping is defined as the non-therapeutic direct and indirect genetic modifications using genetic materials that can improve the performances in sports events. Biosynthetic drugs are a form of indirect genetic engineering. The method can be performed in three ways such as injecting the DNA directly into the muscle, inserting the genetically engineered cells, or transferring the DNA using a virus as a vector. Erythropoietin is a hormone majorly released by the kidney and in small amounts by the liver. Its function is to stimulate the erythropoiesis and therefore the more production of red blood cells (RBC) which causes an increase in Hemoglobin (Hb). During this process, the oxygen delivery to muscles will increase, which will improve athletic performance and postpone exhaustion. There are ways to increase the oxygen transferred to muscles such as blood transfusion, stimulating the production of red blood cells by using Erythropoietin (EPO), and also using allosteric effectors of Hemoglobin. EPO can either be injected as a protein or can be inserted into the cells as the gene which encodes EPO. Adeno-associated viruses have been employed to deliver the EPO gene to the cells. Employing the genes that naturally exist in the human body such as the EPO gene can reduce the risk of detecting gene doping. The first research about blood doping was conducted in 1947. The study has shown that an increase in hematocrit (HCT) up to 55% following homologous transfusion makes it more unchallenging for the body to perform the exercise at the altitude. Thereafter athletes’ attraction to blood infusion escalated. Also, a study has demonstrated that by reinfusing their own blood 4 weeks after being drawn, three men have shown a rise in Hb level which improved the oxygen uptake, and a delay in exhaustion. The list of performance-enhancing drugs is published by WADA annually and includes the following drugs: anabolic agents, hormones, Beta-2 agonists, Beta-blockers, Diuretics, Stimulants, narcotics, cannabinoids, and corticosteroids.

Keywords: doping, PEDs, sports, WADA

Procedia PDF Downloads 80

Authors: Noura Al Akkari, Aurélie Foucquier, Sylvain Lespinats

Abstract:

Load monitoring is a management process for energy consumption towards energy savings and energy efficiency. Non Intrusive Load Monitoring (NILM) is one method of load monitoring used for disaggregation purposes. NILM is a technique for identifying individual appliances based on the analysis of the whole residence data retrieved from the main power meter of the house. Our NILM framework starts with data acquisition, followed by data preprocessing, then event detection, feature extraction, then general appliance modeling and identification at the final stage. The event detection stage is a core component of NILM process since event detection techniques lead to the extraction of appliance features. Appliance features are required for the accurate identification of the household devices. In this research work, we aim at developing a new event detection methodology with accurate load disaggregation to extract appliance features. Time-domain features extracted are used for tuning general appliance models for appliance identification and classification steps. We use unsupervised algorithms such as Dynamic Time Warping (DTW). The proposed method relies on detecting areas of operation of each residential appliance based on the power demand. Then, detecting the time at which each selected appliance changes its states. In order to fit with practical existing smart meters capabilities, we work on low sampling data with a frequency of (1/60) Hz. The data is simulated on Load Profile Generator software (LPG), which was not previously taken into consideration for NILM purposes in the literature. LPG is a numerical software that uses behaviour simulation of people inside the house to generate residential energy consumption data. The proposed event detection method targets low consumption loads that are difficult to detect. Also, it facilitates the extraction of specific features used for general appliance modeling. In addition to this, the identification process includes unsupervised techniques such as DTW. To our best knowledge, there exist few unsupervised techniques employed with low sampling data in comparison to the many supervised techniques used for such cases. We extract a power interval at which falls the operation of the selected appliance along with a time vector for the values delimiting the state transitions of the appliance. After this, appliance signatures are formed from extracted power, geometrical and statistical features. Afterwards, those formed signatures are used to tune general model types for appliances identification using unsupervised algorithms. This method is evaluated using both simulated data on LPG and real-time Reference Energy Disaggregation Dataset (REDD). For that, we compute performance metrics using confusion matrix based metrics, considering accuracy, precision, recall and error-rate. The performance analysis of our methodology is then compared with other detection techniques previously used in the literature review, such as detection techniques based on statistical variations and abrupt changes (Variance Sliding Window and Cumulative Sum).

Keywords: electrical disaggregation, DTW, general appliance modeling, event detection

Procedia PDF Downloads 43

Authors: Abderrhamane Jarou, Dominique Sauter, Christophe Aubrun

Abstract:

Over the past decade, the growing demand for energy efficiency in buildings has attracted the attention of the control community. Failures in HVAC (heating, ventilation and air conditioning) systems in buildings can have a significant impact on the desired and expected energy performance of buildings and on the user's comfort as well. FTC is a recent technology area that studies the adaptation of control algorithms to faulty operating conditions of a system. The application of Fault-Tolerant Control (FTC) in HVAC systems has gained attention in the last two decades. The objective is to maintain the variations in system performance due to faults within an acceptable range with respect to the desired nominal behavior. This paper considers the so-called active approach, which is based on fault and identification scheme combined with a control reconfiguration algorithm that consists in determining a new set of control parameters so that the reconfigured performance is "as close as possible, "in some sense, to the nominal performance. Thermal models of buildings and their HVAC systems are described by non-linear (usually bi-linear) equations. Most of the works carried out so far in FDI (fault diagnosis and isolation) or FTC consider a linearized model of the studied system. However, this model is only valid in a reduced range of variation. This study presents a new fault diagnosis (FD) algorithm based on a bilinear observer for the detection and accurate estimation of the magnitude of the HVAC system failure. The main contribution of the proposed FD algorithm is that instead of using specific linearized models, the algorithm inherits the structure of the actual bilinear model of the building thermal dynamics. As an immediate consequence, the algorithm is applicable to a wide range of unpredictable operating conditions, i.e., weather dynamics, outdoor air temperature, zone occupancy profile. A bilinear fault detection observer is proposed for a bilinear system with unknown inputs. The residual vector in the observer design is decoupled from the unknown inputs and, under certain conditions, is made sensitive to all faults. Sufficient conditions are given for the existence of the observer and results are given for the explicit computation of observer design matrices. Dedicated observer schemes (DOS) are considered for sensor FDI while unknown input bilinear observers are considered for actuator or system components FDI. The proposed strategy for FTC works as follows: At a first level, FDI algorithms are implemented, making it also possible to estimate the magnitude of the fault. Once the fault is detected, the fault estimation is then used to feed the second level and reconfigure the control low so that that expected performances are recovered. This paper is organized as follows. A general structure for fault-tolerant control of buildings is first presented and the building model under consideration is introduced. Then, the observer-based design for Fault Diagnosis of bilinear systems is studied. The FTC approach is developed in Section IV. Finally, a simulation example is given in Section V to illustrate the proposed method.

Keywords: bilinear systems, fault diagnosis, fault-tolerant control, multi-zones building

Procedia PDF Downloads 146

Authors: Iliuta Cumpanasu, Veronica Oana Cumpanasu

Abstract:

This paper focuses on studying the conjunction between the new emerged theory of “Memory Effect” in Irregular Migration and Related Criminality and the notion of securitization, and its impact on border management, bringing about a scientific advancement in the field by identifying the patterns corresponding to the linkage of the two concepts, for the first time, and developing a theoretical explanation, with respect to the effects of the non-military threats on border security. Over recent years, irregular migration has experienced a significant increase worldwide. The U.N.'s refugee agency reports that the number of displaced people is at its highest ever - surpassing even post-World War II numbers when the world was struggling to come to terms with the most devastating event in history. This is also the fresh reality within the core studied coordinate, the Balkan Route of Irregular Migration, which starts from Asia and Africa and continues to Turkey, Greece, North Macedonia or Bulgaria, Serbia, and ends in Romania, where thousands of migrants find themselves in an irregular situation concerning their entry to the European Union, with its important consequences concerning the related criminality. The data from the past six years was collected by making use of semi-structured interviews with experts in the field of migration and desk research within some organisations involved in border security, pursuing the gathering of genuine insights from the aforementioned field, which was constantly addressed the existing literature and subsequently subjected to the mixed methods of analysis, including the use of the Vector Auto-Regression estimates model. Thereafter, the analysis of the data followed the processes and outcomes in Grounded Theory, and a new Substantive Theory emerged, explaining how the phenomena of irregular migration and cross-border criminality are the decisive impetus for implementing the concept of securitization in border management by using the proposed pattern. The findings of the study are therefore able to capture an area that has not yet benefitted from a comprehensive approach in the scientific community, such as the seasonality, stationarity, dynamics, predictions, or the pull and push factors in Irregular Migration, also highlighting how the recent ‘Pandemic’ interfered with border security. Therefore, the research uses an inductive revelatory theoretical approach which aims at offering a new theory in order to explain a phenomenon, triggering a practically handy contribution for the scientific community, research institutes or Academia and also usefulness to organizational practitioners in the field, among which UN, IOM, UNHCR, Frontex, Interpol, Europol, or national agencies specialized in border security. The scientific outcomes of this study were validated on June 30, 2021, when the author defended his dissertation for the European Joint Master’s in Strategic Border Management, a two years prestigious program supported by the European Commission and Frontex Agency and a Consortium of six European Universities and is currently one of the research objectives of his pending PhD research at the West University Timisoara.

Keywords: migration, border, security, memory effect

Procedia PDF Downloads 54

Authors: Noura Al Akkari, Aurélie Foucquier, Sylvain Lespinats

Abstract:

Load monitoring is a management process for energy consumption towards energy savings and energy efficiency. Non Intrusive Load Monitoring (NILM) is one method of load monitoring used for disaggregation purposes. NILM is a technique for identifying individual appliances based on the analysis of the whole residence data retrieved from the main power meter of the house. Our NILM framework starts with data acquisition, followed by data preprocessing, then event detection, feature extraction, then general appliance modeling and identification at the final stage. The event detection stage is a core component of NILM process since event detection techniques lead to the extraction of appliance features. Appliance features are required for the accurate identification of the household devices. In this research work, we aim at developing a new event detection methodology with accurate load disaggregation to extract appliance features. Time-domain features extracted are used for tuning general appliance models for appliance identification and classification steps. We use unsupervised algorithms such as Dynamic Time Warping (DTW). The proposed method relies on detecting areas of operation of each residential appliance based on the power demand. Then, detecting the time at which each selected appliance changes its states. In order to fit with practical existing smart meters capabilities, we work on low sampling data with a frequency of (1/60) Hz. The data is simulated on Load Profile Generator software (LPG), which was not previously taken into consideration for NILM purposes in the literature. LPG is a numerical software that uses behaviour simulation of people inside the house to generate residential energy consumption data. The proposed event detection method targets low consumption loads that are difficult to detect. Also, it facilitates the extraction of specific features used for general appliance modeling. In addition to this, the identification process includes unsupervised techniques such as DTW. To our best knowledge, there exist few unsupervised techniques employed with low sampling data in comparison to the many supervised techniques used for such cases. We extract a power interval at which falls the operation of the selected appliance along with a time vector for the values delimiting the state transitions of the appliance. After this, appliance signatures are formed from extracted power, geometrical and statistical features. Afterwards, those formed signatures are used to tune general model types for appliances identification using unsupervised algorithms. This method is evaluated using both simulated data on LPG and real-time Reference Energy Disaggregation Dataset (REDD). For that, we compute performance metrics using confusion matrix based metrics, considering accuracy, precision, recall and error-rate. The performance analysis of our methodology is then compared with other detection techniques previously used in the literature review, such as detection techniques based on statistical variations and abrupt changes (Variance Sliding Window and Cumulative Sum).

Keywords: general appliance model, non intrusive load monitoring, events detection, unsupervised techniques;

Procedia PDF Downloads 46

Authors: Alexander Norbach

Abstract:

The script in this paper describes the use of advanced simulation environment using electronic systems (Microcontroller, Operational Amplifiers, and FPGA). The simulation may be used for all dynamic systems with the diffusion and the ionisation behaviour also. By additionally required observer structure, the system works with parallel real-time simulation based on diffusion model and the state-space representation for other dynamics. The proposed deposited model may be used for electrodynamic effects, including ionising effects and eddy current distribution also. With the script and proposed method, it is possible to calculate the spatial distribution of the electromagnetic fields in real-time. For further purpose, the spatial temperature distribution may be used also. With upon system, the uncertainties, unknown initial states and disturbances may be determined. This provides the estimation of the more precise system states for the required system, and additionally, the estimation of the ionising disturbances that occur due to radiation effects. The results have shown that a system can be also developed and adopted specifically for space systems with the real-time calculation of the radiation effects only. Electronic systems can take damage caused by impacts with charged particle flux in space or radiation environment. In order to be able to react to these processes, it must be calculated within a shorter time that ionising radiation and dose is present. All available sensors shall be used to observe the spatial distributions. By measured value of size and known location of the sensors, the entire distribution can be calculated retroactively or more accurately. With the formation, the type of ionisation and the direct effect to the systems and thus possible prevent processes can be activated up to the shutdown. The results show possibilities to perform more qualitative and faster simulations independent of kind of systems space-systems and radiation environment also. The paper gives additionally an overview of the diffusion effects and their mechanisms. For the modelling and derivation of equations, the extended current equation is used. The size K represents the proposed charge density drifting vector. The extended diffusion equation was derived and shows the quantising character and has similar law like the Klein-Gordon equation. These kinds of PDE's (Partial Differential Equations) are analytically solvable by giving initial distribution conditions (Cauchy problem) and boundary conditions (Dirichlet boundary condition). For a simpler structure, a transfer function for B- and E- fields was analytically calculated. With known discretised responses g₁(k·Ts) and g₂(k·Ts), the electric current or voltage may be calculated using a convolution; g₁ is the direct function and g₂ is a recursive function. The analytical results are good enough for calculation of fields with diffusion effects. Within the scope of this work, a proposed model of the consideration of the electromagnetic diffusion effects of arbitrary current 'waveforms' has been developed. The advantage of the proposed calculation of diffusion is the real-time capability, which is not really possible with the FEM programs available today. It makes sense in the further course of research to use these methods and to investigate them thoroughly.

Keywords: advanced observer, electrodynamics, systems, diffusion, partial differential equations, solver

Procedia PDF Downloads 101

Authors: Jeronimo Cox, Tomonari Furukawa

Abstract:

Magnetometers have become more popular in inertial measurement units (IMU) for their ability to correct estimations using the earth's magnetic field. Accelerometer and gyroscope-based packages fail with dead-reckoning errors accumulated over time. Localization in robotic applications with magnetometer-inclusive IMUs has become popular as a way to track the odometry of slower-speed robots. With high-speed motions, the accumulated error increases over smaller periods of time, making them difficult to track with IMU. Tracking a high-speed motion is especially difficult with limited observability. Visual obstruction of motion leaves motion-tracking cameras unusable. When motions are too dynamic for estimation techniques reliant on the observability of the gravity vector, the use of magnetometers is further justified. As available magnetometer calibration methods are limited with the assumption that background magnetic fields are uniform, estimation in nonuniform magnetic fields is problematic. Hard iron distortion is a distortion of the magnetic field by other objects that produce magnetic fields. This kind of distortion is often observed as the offset from the origin of the center of data points when a magnetometer is rotated. The magnitude of hard iron distortion is dependent on proximity to distortion sources. Soft iron distortion is more related to the scaling of the axes of magnetometer sensors. Hard iron distortion is more of a contributor to the error of attitude estimation with magnetometers. Indoor environments or spaces inside ferrite-based structures, such as building reinforcements or a vehicle, often cause distortions with proximity. As positions correlate to areas of distortion, methods of magnetometer localization include the production of spatial mapping of magnetic field and collection of distortion signatures to better aid location tracking. The goal of this paper is to compare magnetometer methods that don't need pre-productions of magnetic field maps. Mapping the magnetic field in some spaces can be costly and inefficient. Dynamic measurement fusion is used to track the motion of a multi-link system with us. Conventional calibration by data collection of rotation at a static point, real-time estimation of calibration parameters each time step, and using two magnetometers for determining local hard iron distortion are compared to confirm the robustness and accuracy of each technique. With opposite-facing magnetometers, hard iron distortion can be accounted for regardless of position, Rather than assuming that hard iron distortion is constant regardless of positional change. The motion measured is a repeatable planar motion of a two-link system connected by revolute joints. The links are translated on a moving base to impulse rotation of the links. Equipping the joints with absolute encoders and recording the motion with cameras to enable ground truth comparison to each of the magnetometer methods. While the two-magnetometer method accounts for local hard iron distortion, the method fails where the magnetic field direction in space is inconsistent.

Keywords: motion tracking, sensor fusion, magnetometer, state estimation

Procedia PDF Downloads 50

Authors: George Zhou, Yunchan Chen, Candace Chien

Abstract:

Kidney replacement therapy is the current standard of care for end-stage renal diseases. In-center or home hemodialysis remains an integral component of the therapeutic regimen. Arteriovenous fistulas (AVF) make up the vascular circuit through which blood is filtered and returned. Naturally, AVF patency determines whether adequate clearance and filtration can be achieved and directly influences clinical outcomes. Our aim was to build a deep learning model for automated AVF stenosis screening based on the sound of blood flow through the AVF. A total of 311 patients with AVF were enrolled in this study. Blood flow sounds were collected using a digital stethoscope. For each patient, blood flow sounds were collected at 6 different locations along the patient’s AVF. The 6 locations are artery, anastomosis, distal vein, middle vein, proximal vein, and venous arch. A total of 1866 sounds were collected. The blood flow sounds are labeled as “patent” (normal) or “stenotic” (abnormal). The labels are validated from concurrent ultrasound. Our dataset included 1527 “patent” and 339 “stenotic” sounds. We show that blood flow sounds vary significantly along the AVF. For example, the blood flow sound is loudest at the anastomosis site and softest at the cephalic arch. Contextualizing the sound with location metadata significantly improves classification performance. How to encode and incorporate categorical metadata is an active area of research1. Herein, we study ordinal (i.e., integer) encoding schemes. The numerical representation is concatenated to the flattened feature vector. We train a vision transformer (ViT) on spectrogram image representations of the sound and demonstrate that using scalar multiples of our integer encodings improves classification performance. Models are evaluated using a 10-fold cross-validation procedure. The baseline performance of our ViT without any location metadata achieves an AuROC and AuPRC of 0.68 ± 0.05 and 0.28 ± 0.09, respectively. Using the following encodings of Artery:0; Arch: 1; Proximal: 2; Middle: 3; Distal 4: Anastomosis: 5, the ViT achieves an AuROC and AuPRC of 0.69 ± 0.06 and 0.30 ± 0.10, respectively. Using the following encodings of Artery:0; Arch: 10; Proximal: 20; Middle: 30; Distal 40: Anastomosis: 50, the ViT achieves an AuROC and AuPRC of 0.74 ± 0.06 and 0.38 ± 0.10, respectively. Using the following encodings of Artery:0; Arch: 100; Proximal: 200; Middle: 300; Distal 400: Anastomosis: 500, the ViT achieves an AuROC and AuPRC of 0.78 ± 0.06 and 0.43 ± 0.11. respectively. Interestingly, we see that using increasing scalar multiples of our integer encoding scheme (i.e., encoding “venous arch” as 1,10,100) results in progressively improved performance. In theory, the integer values do not matter since we are optimizing the same loss function; the model can learn to increase or decrease the weights associated with location encodings and converge on the same solution. However, in the setting of limited data and computation resources, increasing the importance at initialization either leads to faster convergence or helps the model escape a local minimum.

Keywords: arteriovenous fistula, blood flow sounds, metadata encoding, deep learning

Procedia PDF Downloads 51

Authors: Yuli Hou, Jianping Sun, Mengdan Gao, Hui Liu, Ling Qin, Ang Li, Dongfu Li, Yonghong Zhang, Yan Zhao

Abstract:

Background and Aims: Interferon-induced transmembrane protein 3 (IFITM3) is a component of ISG (Interferon-Stimulated Gene) family. IFITM3 has been recognized as a key signal molecule regulating cell growth in some tumors. However, the function of IFITM3 rs12252-CC genotype in the hepatocellular carcinoma (HCC) remains unknown to author’s best knowledge. A cohort study was employed to clarify the relationship between IFITM3 rs12252-CC genotype and HCC progression, and cellular experiments were used to investigate the correlation of function of IFITM3 and the progress of HCC. Methods: 336 candidates were enrolled in study, including 156 with HBV related HCC and 180 with chronic Hepatitis B infections or liver cirrhosis. Polymerase chain reaction (PCR) was employed to determine the gene polymorphism of IFITM3. The functions of IFITM3 were detected in PLC/PRF/5 cell with different treated:LV-IFITM3 transfected with lentivirus to knockdown the expression of IFITM3 and LV-NC transfected with empty lentivirus as negative control. The IFITM3 expression, proliferation and migration were detected by Quantitative reverse transcription polymerase chain reaction (qRT-PCR), QuantiGene Plex 2.0 assay, western blotting, immunohistochemistry, Cell Counting Kit(CCK)-8 and wound healing respectively. Six samples (three infected with empty lentiviral as control; three infected with LV-IFITM3 vector lentiviral as experimental group ) of PLC/PRF/5 were sequenced at BGI (Beijing Genomics Institute, Shenzhen,China) using RNA-seq technology to identify the IFITM3-related signaling pathways and chose PI3K/AKT pathway as related signaling to verify. Results: The patients with HCC had a significantly higher proportion of IFITM3 rs12252-CC compared with the patients with chronic HBV infection or liver cirrhosis. The distribution of CC genotype in HCC patients with low differentiation was significantly higher than that in those with high differentiation. Patients with CC genotype found with bigger tumor size, higher percentage of vascular thrombosis, higher distribution of low differentiation and higher 5-year relapse rate than those with CT/TT genotypes. The expression of IFITM3 was higher in HCC tissues than adjacent normal tissues, and the level of IFITM3 was higher in HCC tissues with low differentiation and metastatic than high/medium differentiation and without metastatic. Higher RNA level of IFITM3 was found in CC genotype than TT genotype. In PLC/PRF/5 cell with knockdown, the ability of cell proliferation and migration was inhibited. Analysis RNA sequencing and verification of RT-PCR found out the phosphatidylinositol 3-kinase/protein kinase B/mammalian target of rapamycin(PI3K/AKT/mTOR) pathway was associated with knockdown IFITM3.With the inhibition of IFITM3, the expression of PI3K/AKT/mTOR signaling pathway was blocked and the expression of vimentin was decreased. Conclusions: IFITM3 rs12252-CC with the higher expression plays a vital role in the progress of HCC by regulating HCC cell proliferation and migration. These effects are associated with PI3K/AKT/mTOR signaling pathway.

Keywords: IFITM3, interferon-induced transmembrane protein 3, HCC, hepatocellular carcinoma, PI3K/ AKT/mTOR, phosphatidylinositol 3-kinase/protein kinase B/mammalian target of rapamycin

Procedia PDF Downloads 102

Authors: Yichao Liu, Peter Fransson, Julian Heidecke, Jonas Wallin, Joacim Rockloev

Abstract:

Dengue, a mosquito-borne viral disease, poses a significant public health challenge in endemic tropical or subtropical countries, including Sri Lanka. To reveal insights into the complexity of the dynamics of this disease and study the drivers, a comprehensive model capable of both robust forecasting and insightful inference of drivers while capturing the co-circulating of several virus strains is essential. However, existing studies mostly focus on only one aspect at a time and do not integrate and carry insights across the siloed approach. While mechanistic models are developed to capture immunity dynamics, they are often oversimplified and lack integration of all the diverse drivers of disease transmission. On the other hand, purely data-driven methods lack constraints imposed by immuno-epidemiological processes, making them prone to overfitting and inference bias. This research presents a hybrid model that combines machine learning techniques with mechanistic modelling to overcome the limitations of existing approaches. Leveraging eight years of newly reported dengue case data, along with socioeconomic factors, such as human mobility, weekly climate data from 2011 to 2018, genetic data detecting the introduction and presence of new strains, and estimates of seropositivity for different districts in Sri Lanka, we derive a data-driven vector (SEI) to human (SEIR) model across 16 regions in Sri Lanka at the weekly time scale. By conducting ablation studies, the lag effects allowing delays up to 12 weeks of time-varying climate factors were determined. The model demonstrates superior predictive performance over a pure machine learning approach when considering lead times of 5 and 10 weeks on data withheld from model fitting. It further reveals several interesting interpretable findings of drivers while adjusting for the dynamics and influences of immunity and introduction of a new strain. The study uncovers strong influences of socioeconomic variables: population density, mobility, household income and rural vs. urban population. The study reveals substantial sensitivity to the diurnal temperature range and precipitation, while mean temperature and humidity appear less important in the study location. Additionally, the model indicated sensitivity to vegetation index, both max and average. Predictions on testing data reveal high model accuracy. Overall, this study advances the knowledge of dengue transmission in Sri Lanka and demonstrates the importance of incorporating hybrid modelling techniques to use biologically informed model structures with flexible data-driven estimates of model parameters. The findings show the potential to both inference of drivers in situations of complex disease dynamics and robust forecasting models.

Keywords: compartmental model, climate, dengue, machine learning, social-economic

Procedia PDF Downloads 39

Authors: Md. Samsuddin Ansari, Ashish Arora

Abstract:

Every year 10 million people fall ill with one of the oldest diseases known as tuberculosis, caused by Mycobacterium tuberculosis. The success of M. tuberculosis as a pathogen is because of its ability to persist in host tissues. Multidrug resistance (MDR) mycobacteria cases increase every day, which is associated with efflux pumps controlled at the level of transcription. The transcription regulators of MDR transporters in bacteria belong to one of the following four regulatory protein families: AraC, MarR, MerR, and TetR. Phenolic acid decarboxylase repressor (PadR), like a family of transcription regulators, is closely related to the MarR family. Phenolic acid decarboxylase repressor (PadR) was first identified as a transcription factor involved in the regulation of phenolic acid stress response in various microorganisms (including Mycobacterium tuberculosis H37Rv). Recently research has shown that the PadR family transcription factors are global, multifunction transcription regulators. Rv0047c is a PadR subfamily-1 protein. We are exploring the biophysical and structural characterization of Rv0047c. The Rv0047 gene was amplified by PCR using the primers containing EcoRI and HindIII restriction enzyme sites cloned in pET-NH6 vector and overexpressed in DH5α and BL21 (λDE3) cells of E. coli following purification with Ni2+-NTA column and size exclusion chromatography. We did DSC to know the thermal stability; the Tm (transition temperature) of protein is 55.29ºC, and ΔH (enthalpy change) of 6.92 kcal/mol. Circular dichroism to know the secondary structure and conformation and fluorescence spectroscopy for tertiary structure study of protein. To understand the effect of pH on the structure, function, and stability of Rv0047c we employed spectroscopy techniques such as circular dichroism, fluorescence, and absorbance measurements in a wide range of pH (from pH-2.0 to pH-12). At low and high pH, it shows drastic changes in the secondary and tertiary structure of the protein. EMSA studies showed the specific binding of Rv0047c with its own 30-bp promoter region. To determine the effect of complex formation on the secondary structure of Rv0047c, we examined the CD spectra of the complex of Rv0047c with promoter DNA of rv0047. The functional role of Rv0047c was characterized by over-expressing the Rv0047c gene under the control of hsp60 promoter in Mycobacterium tuberculosis H37Rv. We have predicted the three-dimensional structure of Rv0047c using the Swiss Model and Modeller, with validity checked by the Ramachandra plot. We did molecular docking of Rv0047c with dnaA, through PatchDock following refinement through FireDock. Through this, it is possible to easily identify the binding hot-stop of the receptor molecule with that of the ligand, the nature of the interface itself, and the conformational change undergone by the protein pattern. We are using X-crystallography to unravel the structure of Rv0047c. Overall the studies show that Rv0047c may have transcription regulation along with providing an insight into the activity of Rv0047c in the pH range of subcellular environment and helps to understand the protein-protein interaction, a novel target to kill dormant bacteria and potential strategy for tuberculosis control.

Keywords: mycobacterium tuberculosis, phenolic acid decarboxylase repressor, Rv0047c, Circular dichroism, fluorescence spectroscopy, docking, protein-protein interaction

Procedia PDF Downloads 67

Authors: Srijata Mitra, Mobina Parveen, Pranab Roy, Narayan Chandra Chattopadhyay

Abstract:

Chlorinated hydrocarbon can be a major pollution problem in groundwater as well as soil. Many people interact with these chemicals on daily accidentally or by professionally in the laboratory. One of the most common sources for Chlorinated hydrocarbon contamination of soil and groundwater are industrial effluents. The wide use and discharge of Trichloroethylene (TCE), a volatile chlorohydrocarbon from chemical industry, led to major water pollution in rural areas. TCE is an mainly used as an industrial metal degreaser in industries. Biotransformation of TCE to the potent carcinogen vinyl chloride (VC) by consortia of anaerobic bacteria might have role for the above purpose. For these reasons, the aim of current study was to isolate and characterized the genes involved in TCE metabolism and also to investigate the in silico study of those genes. To our knowledge, only one aromatic dioxygenase system, the toluene dioxygenase in Pseudomonas putida F1 has been shown to be involved in TCE degradation. This is first instance where Bacillus cereus group being used in biodegradation of trichloroethylene. A novel bacterial strain 2479 was isolated from oil depot site at Rajbandh, Durgapur (West Bengal, India) by enrichment culture technique. It was identified based on polyphasic approach and ribotyping. The bacterium was gram positive, rod shaped, endospore forming and capable of degrading trichloroethylene as the sole carbon source. On the basis of phylogenetic data and Fatty Acid Methyl Ester Analysis, strain 2479 should be placed within the genus Bacillus and species cereus. However, the present isolate (strain 2479) is unique and sharply different from the usual Bacillus strains in its biodegrading nature. Fujiwara test was done to estimate that the strain 2479 could degrade TCE efficiently. The gene for TCE biodegradation was PCR amplified from genomic DNA of Bacillus cereus 2479 by using todC1 gene specific primers. The 600bp amplicon was cloned into expression vector pUC I8 in the E. coli host XL1-Blue and expressed under the control of lac promoter and nucleotide sequence was determined. The gene sequence was deposited at NCBI under the Accession no. GU183105. In Silico approach involved predicting the physico-chemical properties of deduced Tce1 protein by using ProtParam tool. The tce1 gene contained 342 bp long ORF encoding 114 amino acids with a predicted molecular weight 12.6 kDa and the theoretical pI value of the polypeptide was 5.17, molecular formula: C559H886N152O165S8, total number of atoms: 1770, aliphatic index: 101.93, instability index: 28.60, Grand Average of Hydropathicity (GRAVY): 0.152. Three differentially expressed proteins (97.1, 40 and 30 kDa) were directly involved in TCE biodegradation, found to react immunologically to the antibodies raised against TCE inducible proteins in Western blot analysis. The present study suggested that cloned gene product (TCE1) was capable of degrading TCE as verified chemically.

Keywords: cloning, Bacillus cereus, in silico analysis, TCE

Procedia PDF Downloads 365

Authors: Piotr A. Kowalski, Kasper Sapala, Wiktor Warchalowski

Abstract:

PM10 is a suspended dust that primarily has a negative effect on the respiratory system. PM10 is responsible for attacks of coughing and wheezing, asthma or acute, violent bronchitis. Indirectly, PM10 also negatively affects the rest of the body, including increasing the risk of heart attack and stroke. Unfortunately, Poland is a country that cannot boast of good air quality, in particular, due to large PM concentration levels. Therefore, based on the dense network of Airly sensors, it was decided to deal with the problem of prediction of suspended particulate matter concentration. Due to the very complicated nature of this issue, the Machine Learning approach was used. For this purpose, Convolution Neural Network (CNN) neural networks have been adopted, these currently being the leading information processing methods in the field of computational intelligence. The aim of this research is to show the influence of particular CNN network parameters on the quality of the obtained forecast. The forecast itself is made on the basis of parameters measured by Airly sensors and is carried out for the subsequent day, hour after hour. The evaluation of learning process for the investigated models was mostly based upon the mean square error criterion; however, during the model validation, a number of other methods of quantitative evaluation were taken into account. The presented model of pollution prediction has been verified by way of real weather and air pollution data taken from the Airly sensor network. The dense and distributed network of Airly measurement devices enables access to current and archival data on air pollution, temperature, suspended particulate matter PM1.0, PM2.5, and PM10, CAQI levels, as well as atmospheric pressure and air humidity. In this investigation, PM2.5, and PM10, temperature and wind information, as well as external forecasts of temperature and wind for next 24h served as inputted data. Due to the specificity of the CNN type network, this data is transformed into tensors and then processed. This network consists of an input layer, an output layer, and many hidden layers. In the hidden layers, convolutional and pooling operations are performed. The output of this system is a vector containing 24 elements that contain prediction of PM10 concentration for the upcoming 24 hour period. Over 1000 models based on CNN methodology were tested during the study. During the research, several were selected out that give the best results, and then a comparison was made with the other models based on linear regression. The numerical tests carried out fully confirmed the positive properties of the presented method. These were carried out using real ‘big’ data. Models based on the CNN technique allow prediction of PM10 dust concentration with a much smaller mean square error than currently used methods based on linear regression. What's more, the use of neural networks increased Pearson's correlation coefficient (R²) by about 5 percent compared to the linear model. During the simulation, the R² coefficient was 0.92, 0.76, 0.75, 0.73, and 0.73 for 1st, 6th, 12th, 18th, and 24th hour of prediction respectively.

Keywords: air pollution prediction (forecasting), machine learning, regression task, convolution neural networks

Procedia PDF Downloads 98

Authors: Kaomud Tyagi, Rajasree Chakraborty, Shantanu Kundu, Devkant Singha, Kailash Chandra, Vikas Kumar

Abstract:

The melon thrips, Thrips palmi is a serious pest of a wide range of agriculture crops and also act as vectors for plant viruses (genus Tospovirus, family Bunyaviridae). More molecular data on this species is required to understand the cryptic speciation and evolutionary affiliations. Mitochondrial genomes have been widely used in phylogenetic and evolutionary studies in insect. So far, mitogenomes of five thrips species (Anaphothrips obscurus, Frankliniella intonsa, Frankliniella occidentalis, Scirtothrips dorsalis and Thrips imaginis) is available in the GenBank database. In this study, we sequenced the first complete mitogenome T. palmi and compared it with available thrips mitogenomes. We assembled the mitogenome from the whole genome sequencing data generated using Illumina Hiseq2500. Annotation was performed using MITOS web-server to estimate the location of protein coding genes (PCGs), transfer RNA (tRNAs), ribosomal RNAs (rRNAs) and their secondary structures. The boundaries of PCGs and rRNAs was confirmed manually in NCBI. Phylogenetic analyses were performed using the 13 PCGs data using maximum likelihood (ML) in PAUP, and Bayesian inference (BI) in MrBayes 3.2. The complete mitogenome of T. palmi was 15,333 base pairs (bp), which was greater than the genomes of A. obscurus (14,890bp), F. intonsa (15,215 bp), F. occidentalis (14,889 bp) and S. dorsalis South Asia strain (SA1) (14,283 bp), but smaller than the genomes of T. imaginis (15,407 bp) and S. dorsalis East Asia strain (EA1) (15,343bp). Like in other thrips species, the mitochondrial genome of T. palmi was represented by 37 genes, including 13 PCGs, large and small ribosomal RNA (rrnL and rrnS) genes, 22 transfer RNA (tRNAs) genes (with one extra gene for trn-Serine) and two A+T-rich control regions (CR1 and CR2). Thirty one genes were observed on heavy (H) strand and six genes on the light (L) strand. The six tRNA genes (trnG,trnK, trnY, trnW, trnF, and trnH) were found to be conserved in all thrips species mitogenomes in their locations relative to a protein-coding or rRNA gene upstream or downstream. The gene arrangements of T. palmi is very close to T. imaginis except the rearrangements in tRNAs genes: trnR (arginine), and trnE (glutamic acid) were found to be located between cox3 and CR2 in T. imaginis which were translocated between atp6 and CR1 in T. palmi; trnL1 (Leucine) and trnS1(Serine) were located between atp6 and CR1 in T. imaginis which were translocated between cox3 and CR2 in T. palmi. The location of CR1 upstream of nad5 gene was suggested to be ancestral condition of the thrips species in subfamily Thripinae, was also observed in T. palmi. Both the Maximum likelihood (ML) and Bayesian Inference (BI) phylogenetic trees generated resulted in similar topologies. The T. palmi was clustered with T. imaginis. We concluded that more molecular data on the diverse thrips species from different hierarchical level is needed, to understand the phylogenetic and evolutionary relationships among them.

Keywords: thrips, comparative mitogenomics, gene rearrangements, phylogenetic analysis

Procedia PDF Downloads 138

Authors: Alberto Veses, Olga Sanhauja, María Soledad Callén, Tomás García

Abstract:

The appropriate use of renewable sources emerges as a decisive point to minimize the environmental impact caused by fossil fuels use. Particularly, the use of lignocellulosic biomass becomes one of the best promising alternatives since it is the only carbon-containing renewable source that can produce bioproducts similar to fossil fuels and it does not compete with food market. Among all the processes that can valorize lignocellulosic biomass, pyrolysis is an attractive alternative because it is the only thermochemical process that can produce a liquid biofuel (bio-oil) in a simple way and solid and gas fractions that can be used as energy sources to support the process. However, in order to incorporate bio-oils in current infrastructures and further process in future biorefineries, their quality needs to be improved. Introducing different low-cost catalysts and/or incorporating different polymer residues to the process are some of the new, simple and low-cost strategies that allow the user to directly obtain advanced bio-oils to be used in future biorefineries in an economic way. In this manner, from previous thermogravimetric analyses, local agricultural wastes such as grape seeds (GS) were selected as lignocellulosic biomass while, waste tires (WT) were selected as polymer residue. On the other hand, CaO was selected as low-cost catalyst based on previous experiences by the group. To reach this aim, a specially-designed fixed bed reactor using N₂ as a carrier gas was used. This reactor has the peculiarity to incorporate a vertical mobile liner that allows the user to introduce the feedstock in the oven once the selected temperature (550 ºC) is reached, ensuring higher heating rates needed for the process. Obtaining a well-defined phase distribution in the resulting bio-oil is crucial to ensure the viability to the process. Thus, once experiments were carried out, not only a well-defined two layers was observed introducing several mixtures (reaching values up to 40 wt.% of WT) but also, an upgraded organic phase, which is the one considered to be processed in further biorefineries. Radical interactions between GS and WT released during the pyrolysis process and dehydration reactions enhanced by CaO can promote the formation of better-quality bio-oils. The latter was reflected in a reduction of water and oxygen content of bio-oil and hence, a substantial increase of its heating value and its stability. Moreover, not only sulphur content was reduced from solely WT pyrolysis but also potential and negative issues related to a strong acidic environment of conventional bio-oils were minimized due to its basic pH and lower total acid numbers. Therefore, acidic compounds obtained in the pyrolysis such as CO₂-like substances can react with the CaO and minimize acidic problems related to lignocellulosic bio-oils. Moreover, this CO₂ capture promotes H₂ production from water gas shift reaction favoring hydrogen-transfer reactions, improving the final quality of the bio-oil. These results show the great potential of grapes seeds to carry out the catalytic co-pyrolysis process with different plastic residues in order to produce a liquid bio-oil that can be considered as a high-quality renewable vector.

Keywords: advanced bio-oils, biorefinery, catalytic co-pyrolysis of biomass and waste tires, lignocellulosic biomass

Procedia PDF Downloads 208

Authors: Duncan Wallace, M-Tahar Kechadi

Abstract:

In recent years, Machine Learning (ML) approaches have been successfully applied to an analysis of patient symptom data in the context of disease diagnosis, at least where such data is well codified. However, much of the data present in Electronic Health Records (EHR) are unlikely to prove suitable for classic ML approaches. Furthermore, as scores of data are widely spread across both hospitals and individuals, a decentralized, computationally scalable methodology is a priority. The focus of this paper is to develop a method to predict outliers in an out-of-hours healthcare provision center (OOHC). In particular, our research is based upon the early identification of patients who have underlying conditions which will cause them to repeatedly require medical attention. OOHC act as an ad-hoc delivery of triage and treatment, where interactions occur without recourse to a full medical history of the patient in question. Medical histories, relating to patients contacting an OOHC, may reside in several distinct EHR systems in multiple hospitals or surgeries, which are unavailable to the OOHC in question. As such, although a local solution is optimal for this problem, it follows that the data under investigation is incomplete, heterogeneous, and comprised mostly of noisy textual notes compiled during routine OOHC activities. Through the use of Deep Learning methodologies, the aim of this paper is to provide the means to identify patient cases, upon initial contact, which are likely to relate to such outliers. To this end, we compare the performance of Long Short-Term Memory, Gated Recurrent Units, and combinations of both with Convolutional Neural Networks. A further aim of this paper is to elucidate the discovery of such outliers by examining the exact terms which provide a strong indication of positive and negative case entries. While free-text is the principal data extracted from EHRs for classification, EHRs also contain normalized features. Although the specific demographical features treated within our corpus are relatively limited in scope, we examine whether it is beneficial to include such features among the inputs to our neural network, or whether these features are more successfully exploited in conjunction with a different form of a classifier. In this section, we compare the performance of randomly generated regression trees and support vector machines and determine the extent to which our classification program can be improved upon by using either of these machine learning approaches in conjunction with the output of our Recurrent Neural Network application. The output of our neural network is also used to help determine the most significant lexemes present within the corpus for determining high-risk patients. By combining the confidence of our classification program in relation to lexemes within true positive and true negative cases, with an inverse document frequency of the lexemes related to these cases, we can determine what features act as the primary indicators of frequent-attender and non-frequent-attender cases, providing a human interpretable appreciation of how our program classifies cases.

Keywords: artificial neural networks, data-mining, machine learning, medical informatics

Procedia PDF Downloads 101

Authors: V. Mantey, N. Findlay, I. Maddox

Abstract:

The quality and quantity of global satellite data have been increasing exponentially in recent years as spaceborne systems become more affordable and the sensors themselves become more sophisticated. This is a valuable resource for many applications, including disaster management and relief. However, while more information can be valuable, the volume of data available is impossible to manually examine. Therefore, the question becomes how to extract as much information as possible from the data with limited manpower. Buildings are a key feature of interest in satellite imagery with applications including telecommunications, population models, and disaster relief. Machine learning tools are fast becoming one of the key resources to solve this problem, and models have been developed to detect buildings in optical satellite imagery. However, by and large, most models focus on affluent regions where buildings are generally larger and constructed further apart. This work is focused on the more difficult problem of detection in populated regions. The primary challenge with detecting small buildings in densely populated regions is both the spatial and spectral resolution of the optical sensor. Densely packed buildings with similar construction materials will be difficult to separate due to a similarity in color and because the physical separation between structures is either non-existent or smaller than the spatial resolution. This study finds that training models until they are overfitting the input sample can perform better in these areas than a more robust, generalized model. An overfitted model takes less time to fine-tune from a generalized pre-trained model and requires fewer input data. The model developed for this study has also been fine-tuned using existing, open-source, building vector datasets. This is particularly valuable in the context of disaster relief, where information is required in a very short time span. Leveraging existing datasets means that little to no manpower or time is required to collect data in the region of interest. The training period itself is also shorter for smaller datasets. Requiring less data means that only a few quality areas are necessary, and so any weaknesses or underpopulated regions in the data can be skipped over in favor of areas with higher quality vectors. In this study, a landcover classification model was developed in conjunction with the building detection tool to provide a secondary source to quality check the detected buildings. This has greatly reduced the false positive rate. The proposed methodologies have been implemented and integrated into a configurable production environment and have been employed for a number of large-scale commercial projects, including continent-wide DEM production, where the extracted building footprints are being used to enhance digital elevation models. Overfitted machine learning models are often considered too specific to have any predictive capacity. However, this study demonstrates that, in cases where input data is scarce, overfitted models can be judiciously applied to solve time-sensitive problems.

Keywords: building detection, disaster relief, mask-RCNN, satellite mapping

Procedia PDF Downloads 147

Authors: Anupama Singh, Papia Raj

Abstract:

Though Municipal Solid Waste (MSW) is a worldwide problem, yet its implications are enormous in developing countries, as they are unable to provide proper Municipal Solid Waste Management (MSWM) for the large volume of MSW. As a result, the collected wastes are dumped in open dumping at landfilling sites while the uncollected wastes remain strewn on the roadside, many-a-time clogging drainage. Such unsafe and inadequate management of MSW causes various public health hazards. For example, MSW directly on contact or by leachate contaminate the soil, surface water, and ground water; open burning causes air pollution; anaerobic digestion between the piles of MSW enhance the greenhouse gases i.e., carbon dioxide and methane (CO2 and CH4) into the atmosphere. Moreover, open dumping can cause spread of vector borne disease like cholera, typhoid, dysentery, and so on. Patna, the capital city of Bihar, one of the most underdeveloped provinces in India, is a unique representation of this situation. Patna has been identified as the ‘garbage city’. Over the last decade there has been an exponential increase in the quantity of MSW generation in Patna. Though a large proportion of such MSW is recyclable in nature, only a negligible portion is recycled. Plastic constitutes the major chunk of the recyclable waste. The chemical composition of plastic is versatile consisting of toxic compounds, such as, plasticizers, like adipates and phthalates. Pigmented plastic is highly toxic and it contains harmful metals such as copper, lead, chromium, cobalt, selenium, and cadmium. Human population becomes vulnerable to an array of health problems as they are exposed to these toxic chemicals multiple times a day through air, water, dust, and food. Based on analysis of health data it can be emphasized that in Patna there has been an increase in the incidence of specific diseases, such as, diarrhoea, dysentry, acute respiratory infection (ARI), asthma, and other chronic respiratory diseases (CRD). This trend can be attributed to improper MSWM. The results were reiterated through a survey (N=127) conducted during 2014-15 in selected areas of Patna. Random sampling method of data collection was used to better understand the relationship between different variables affecting public health due to exposure to MSW and lack of MSWM. The results derived through bivariate and logistic regression analysis of the survey data indicate that segregation of wastes at source, segregation behavior, collection bins in the area, distance of collection bins from residential area, and transportation of MSW are the major determinants of public health issues. Sustainable recycling is a robust method for MSWM with its pioneer concerns being environment, society, and economy. It thus ensures minimal threat to environment and ecology consequently improving public health conditions. Hence, this paper concludes that sustainable recycling would be the most viable approach to manage MSW in Patna and would eventually reduce public health hazards.

Keywords: municipal solid waste, Patna, public health, sustainable recycling

Procedia PDF Downloads 289

Authors: Arsyam Mawardi, Sony Suhandono, Azzania Fibriani, Fifi Fitriyah Masduki

Abstract:

Malaria is an infectious disease caused by Plasmodium sp. This disease has a high prevalence in Indonesia, especially in Jayapura. The vaccine that is currently being developed has not been effective in overcoming malaria. This is due to the high polymorphism in the Plasmodium genome especially in areas that encode Plasmodium surface proteins. Merozoite Surface Protein 1 (MSP1) Plasmodium falciparum is a surface protein that plays a role in the invasion process in human erythrocytes through the interaction of Glycophorin A protein receptors and sialic acid in erythrocytes with Reticulocyte Binding Proteins (RBP) and Duffy Adhesion Protein (DAP) ligands in merozoites. MSP1 can be targeted to be a specific antigen and predicted epitope area which will be used for the development of diagnostic and malaria vaccine therapy. MSP1 consists of 17 blocks, each block is dimorphic, and has been marked as the K1 and MAD20 alleles. Exceptions only in block 2, because it has 3 alleles, among others K1, MAD20 and RO33. These polymorphisms cause allelic variations and implicate the severity of patients infected P. falciparum. In addition, polymorphism of MSP1 in Jayapura isolates has not been reported so it is interesting to be further identified and projected as a specific antigen. Therefore, in this study, we analyzed the allele polymorphism as well as detected the MSP1 epitope antigen candidate on block 2 P. falciparum. Clinical samples of selected malaria patients followed the consecutive sampling method, examining malaria parasites with blood preparations on glass objects observed through a microscope. Plasmodium DNA was isolated from the blood of malarial positive patients. The block 2 MSP1 gene was amplified using PCR method and cloned using the pGEM-T easy vector then transformed to TOP'10 E.coli. Positive colonies selection was performed with blue-white screening. The existence of target DNA was confirmed by PCR colonies and DNA sequencing methods. Furthermore, DNA sequence analysis was done through alignment and formation of a phylogenetic tree using MEGA 6 software and insilico analysis using IEDB software to predict epitope candidate for P. falciparum. A total of 15 patient samples have been isolated from Plasmodium DNA. PCR amplification results show the target gene size about ± 1049 bp. The results of MSP1 nucleotide alignment analysis reveal that block 2 MSP1 genes derived from the sample of malarial patients were distributed in four different allele family groups, K1 (7), MAD20 (1), RO33 (0) and MSP1_Jayapura (10) alleles. The most commonly appears of the detected allele is MSP1_Jayapura single allele. There was no significant association between sex variables, age, the density of parasitemia and alel variation (Mann Whitney, U > 0.05), while symptomatic signs have a significant difference as a trigger of detectable allele variation (U < 0.05). In this research, insilico study shows that there is a new epitope antigen candidate from the MSP1_Jayapura allele and it is predicted to be recognized by B cells with 17 amino acid lengths in the amino acid sequence 187 to 203.

Keywords: epitope candidate, insilico analysis, MSP1 P. falciparum, polymorphism

Procedia PDF Downloads 153

Authors: Ayman Hijazi, Witold Kwapinski, J. J. Leahy

Abstract:

Finding a sustainable alternative energy to fossil fuel is an urgent need as various environmental challenges in the world arise. Therefore, formic acid (FA) decomposition has been an attractive field that lies at the center of biomass platform, comprising a potential pool of hydrogen energy that stands as a new energy vector. Liquid FA features considerable volumetric energy density of 6.4 MJ/L and a specific energy density of 5.3 MJ/Kg that qualifies it in the prime seat as an energy source for transportation infrastructure. Additionally, the increasing research interest in FA decomposition is driven by the need of in-situ H2 production, which plays a key role in the hydrogenation reactions of biomass into higher value components. It is reported elsewhere in literature that catalytic decomposition of FA is usually performed in poorly designed setup using simple glassware under magnetic stirring, thus demanding further energy investment to retain the used catalyst. it work suggests an approach that integrates designing a novel catalyst featuring magnetic property with a robust setup that minimizes experimental & measurement discrepancies. One of the most prominent active species for dehydrogenation/hydrogenation of biomass compounds is palladium. Accordingly, we investigate the potential of engrafting palladium metal onto functionalized magnetic nanoparticles as a heterogeneous catalyst to favor the production of CO-free H2 gas from FA. Using ordinary magnet to collect the spent catalyst renders core-shell magnetic nanoparticles as the backbone of the process. Catalytic experiments were performed in a jacketed batch reactor equipped with an overhead stirrer under inert medium. Through a novel approach, FA is charged into the reactor via high-pressure positive displacement pump at steady state conditions. The produced gas (H2+CO2) was measured by connecting the gas outlet to a measuring system based on the amount of the displaced water. The novelty of this work lies in designing a very responsive catalyst, pumping consistent amount of FA into a sealed reactor running at steady state mild temperatures, and continuous gas measurement, along with collecting the used catalyst without the need for centrifugation. Catalyst characterization using TEM, XRD, SEM, and CHN elemental analyzer provided us with details of catalyst preparation and facilitated new venues to alter the nanostructure of the catalyst framework. Consequently, the introduction of amine groups has led to appreciable improvements in terms of dispersion of the doped metals and eventually attaining nearly complete conversion (100%) of FA after 7 hours. The relative importance of the process parameters such as temperature (35-85°C), stirring speed (150-450rpm), catalyst loading (50-200mgr.), and Pd doping ratio (0.75-1.80wt.%) on gas yield was assessed by a Taguchi design-of-experiment based model. Experimental results showed that operating at lower temperature range (35-50°C) yielded more gas while the catalyst loading and Pd doping wt.% were found to be the most significant factors with a P-values 0.026 & 0.031, respectively.

Keywords: formic acid decomposition, green catalysis, hydrogen, mesoporous silica, process optimization, nanoparticles

Procedia PDF Downloads 14

Authors: Ayman Hijazi, Witold Kwapinski, J. J. Leahy

Abstract:

Finding a sustainable alternative energy to fossil fuel is an urgent need as various environmental challenges in the world arise. Therefore, formic acid (FA) decomposition has been an attractive field that lies at the center of the biomass platform, comprising a potential pool of hydrogen energy that stands as a distinct energy vector. Liquid FA features considerable volumetric energy density of 6.4 MJ/L and a specific energy density of 5.3 MJ/Kg that qualifies it in the prime seat as an energy source for transportation infrastructure. Additionally, the increasing research interest in FA decomposition is driven by the need for in-situ H₂ production, which plays a key role in the hydrogenation reactions of biomass into higher-value components. It is reported elsewhere in the literature that catalytic decomposition of FA is usually performed in poorly designed setups using simple glassware under magnetic stirring, thus demanding further energy investment to retain the used catalyst. Our work suggests an approach that integrates designing a distinct catalyst featuring magnetic properties with a robust setup that minimizes experimental & measurement discrepancies. One of the most prominent active species for the dehydrogenation/hydrogenation of biomass compounds is palladium. Accordingly, we investigate the potential of engrafting palladium metal onto functionalized magnetic nanoparticles as a heterogeneous catalyst to favor the production of CO-free H₂ gas from FA. Using an ordinary magnet to collect the spent catalyst renders core-shell magnetic nanoparticles as the backbone of the process. Catalytic experiments were performed in a jacketed batch reactor equipped with an overhead stirrer under an inert medium. Through a distinct approach, FA is charged into the reactor via a high-pressure positive displacement pump at steady-state conditions. The produced gas (H₂+CO₂) was measured by connecting the gas outlet to a measuring system based on the amount of the displaced water. The uniqueness of this work lies in designing a very responsive catalyst, pumping a consistent amount of FA into a sealed reactor running at steady-state mild temperatures, and continuous gas measurement, along with collecting the used catalyst without the need for centrifugation. Catalyst characterization using TEM, XRD, SEM, and CHN elemental analyzer provided us with details of catalyst preparation and facilitated new venues to alter the nanostructure of the catalyst framework. Consequently, the introduction of amine groups has led to appreciable improvements in terms of dispersion of the doped metals and eventually attaining nearly complete conversion (100%) of FA after 7 hours. The relative importance of the process parameters such as temperature (35-85°C), stirring speed (150-450rpm), catalyst loading (50-200mgr.), and Pd doping ratio (0.75-1.80wt.%) on gas yield was assessed by a Taguchi design-of-experiment based model. Experimental results showed that operating at a lower temperature range (35-50°C) yielded more gas, while the catalyst loading and Pd doping wt.% were found to be the most significant factors with P-values 0.026 & 0.031, respectively.

Keywords: formic acid decomposition, green catalysis, hydrogen, mesoporous silica, process optimization, nanoparticles

Procedia PDF Downloads 11

Authors: Patrick Cormier, Cesar Meylan, Matt Jensen, Dana Agar-Newman, Chloe Werle, Ming-Chang Tsai, Marc Klimstra

Abstract:

Sprint-derived horizontal force-velocity-power (FVP) profiles can be developed with adequate validity and reliability with satellite (GPS/GNSS) systems. However, FVP metrics are sensitive to small nuances in data processing procedures such that minor differences in defining the onset and end of the sprint could result in different FVP metric outcomes. Furthermore, in team-sports, there is a requirement for rapid analysis and feedback of results from multiple athletes, therefore developing standardized and automated methods to improve the speed, efficiency and reliability of this process are warranted. Thus, the purpose of this study was to compare different methods of sprint end detection on the development of FVP profiles from 10Hz GPS/GNSS data through goodness-of-fit and intertrial reliability statistics. Seventeen national team female soccer players participated in the FVP protocol which consisted of 2x40m maximal sprints performed towards the end of a soccer specific warm-up in a training session (1020 hPa, wind = 0, temperature = 30°C) on an open grass field. Each player wore a 10Hz Catapult system unit (Vector S7, Catapult Innovations) inserted in a vest in a pouch between the scapulae. All data were analyzed following common procedures. Variables computed and assessed were the model parameters, estimated maximal sprint speed (MSS) and the acceleration constant τ, in addition to horizontal relative force (F₀), velocity at zero (V₀), and relative mechanical power (Pmax). The onset of the sprints was standardized with an acceleration threshold of 0.1 m/s². The sprint end detection methods were: 1. Time when peak velocity (MSS) was achieved (zero acceleration), 2. Time after peak velocity drops by -0.4 m/s, 3. Time after peak velocity drops by -0.6 m/s, and 4. When the integrated distance from the GPS/GNSS signal achieves 40-m. Goodness-of-fit of each sprint end detection method was determined using the residual sum of squares (RSS) to demonstrate the error of the FVP modeling with the sprint data from the GPS/GNSS system. Inter-trial reliability (from 2 trials) was assessed utilizing intraclass correlation coefficients (ICC). For goodness-of-fit results, the end detection technique that used the time when peak velocity was achieved (zero acceleration) had the lowest RSS values, followed by -0.4 and -0.6 velocity decay, and 40-m end had the highest RSS values. For intertrial reliability, the end of sprint detection techniques that were defined as the time at (method 1) or shortly after (method 2 and 3) when MSS was achieved had very large to near perfect ICC and the time at the 40 m integrated distance (method 4) had large to very large ICCs. Peak velocity was reached at 29.52 ± 4.02-m. Therefore, sport scientists should implement end of sprint detection either when peak velocity is determined or shortly after to improve goodness of fit to achieve reliable between trial FVP profile metrics. Although, more robust processing and modeling procedures should be developed in future research to improve sprint model fitting. This protocol was seamlessly integrated into the usual training which shows promise for sprint monitoring in the field with this technology.

Keywords: automated, biomechanics, team-sports, sprint

Procedia PDF Downloads 89

Authors: Antonio Boggia, Luisa Paolotti, Gianluca Massei, Lucia Rocchi, Elaine Pace, Maria Attard

Abstract:

The aim of this paper is to present a methodology and a computer model for sustainability assessment based on the integration of Multi-criteria Decision Analysis (MCDA) with a Geographic Information System (GIS). It presents the result of a study for the implementation of a model for measuring sustainability to address the policy actions for the improvement of sustainability at territory level. The aim is to rank areas in order to understand the specific technical and/or financial support that is required to develop sustainable growth. Assessing sustainable development is a multidimensional problem: economic, social and environmental aspects have to be taken into account at the same time. The tool for a multidimensional representation is a proper set of indicators. The set of indicators must be integrated into a model, that is an assessment methodology, to be used for measuring sustainability. The model, developed by the Environmental Laboratory of the University of Perugia, is called GeoUmbriaSUIT. It is a calculation procedure developed as a plugin working in the open-source GIS software QuantumGIS. The multi-criteria method used within GeoUmbriaSUIT is the algorithm TOPSIS (Technique for Order Preference by Similarity to Ideal Design), which defines a ranking based on the distance from the worst point and the closeness to an ideal point, for each of the criteria used. For the sustainability assessment procedure, GeoUmbriaSUIT uses a geographic vector file where the graphic data represent the study area and the single evaluation units within it (the alternatives, e.g. the regions of a country, or the municipalities of a region), while the alphanumeric data (attribute table), describe the environmental, economic and social aspects related to the evaluation units by means of a set of indicators (criteria). The use of the algorithm available in the plugin allows to treat individually the indicators representing the three dimensions of sustainability, and to compute three different indices: environmental index, economic index and social index. The graphic output of the model allows for an integrated assessment of the three dimensions, avoiding aggregation. The presence of separate indices and graphic output make GeoUmbriaSUIT a readable and transparent tool, since it doesn’t produce an aggregate index of sustainability as final result of the calculations, which is often cryptic and difficult to interpret. In addition, it is possible to develop a “back analysis”, able to explain the positions obtained by the alternatives in the ranking, based on the criteria used. The case study presented is an assessment of the level of sustainability in the six regions of Malta, an island state in the middle of the Mediterranean Sea and the southernmost member of the European Union. The results show that the integration of MCDA-GIS is an adequate approach for sustainability assessment. In particular, the implemented model is able to provide easy to understand results. This is a very important condition for a sound decision support tool, since most of the time decision makers are not experts and need understandable output. In addition, the evaluation path is traceable and transparent.

Keywords: GIS, multi-criteria analysis, sustainability assessment, sustainable development

Procedia PDF Downloads 243

Authors: Mayank Gupta, Siba Prasad Samal, Vasu Kakkirala

Abstract:

The internet world and its priorities have changed considerably in the last decade. Browsing on smart phones has increased manifold and is set to explode much more. Users spent considerable time browsing different websites, that gives a great deal of insight into user’s preferences. Instead of plain information classifying different aspects of browsing like Bookmarks, History, and Download Manager into useful categories would improve and enhance the user’s experience. Most of the classification solutions are server side that involves maintaining server and other heavy resources. It has security constraints and maybe misses on contextual data during classification. On device, classification solves many such problems, but the challenge is to achieve accuracy on classification with resource constraints. This on device classification can be much more useful in personalization, reducing dependency on cloud connectivity and better privacy/security. This approach provides more relevant results as compared to current standalone solutions because it uses content rendered by browser which is customized by the content provider based on user’s profile. This paper proposes a Naive Bayes based lightweight classification engine targeted for a resource constraint devices. Our solution integrates with Web Browser that in turn triggers classification algorithm. Whenever a user browses a webpage, this solution extracts DOM Tree data from the browser’s rendering engine. This DOM data is a dynamic, contextual and secure data that can’t be replicated. This proposal extracts different features of the webpage that runs on an algorithm to classify into multiple categories. Naive Bayes based engine is chosen in this solution for its inherent advantages in using limited resources compared to other classification algorithms like Support Vector Machine, Neural Networks, etc. Naive Bayes classification requires small memory footprint and less computation suitable for smartphone environment. This solution has a feature to partition the model into multiple chunks that in turn will facilitate less usage of memory instead of loading a complete model. Classification of the webpages done through integrated engine is faster, more relevant and energy efficient than other standalone on device solution. This classification engine has been tested on Samsung Z3 Tizen hardware. The Engine is integrated into Tizen Browser that uses Chromium Rendering Engine. For this solution, extensive dataset is sourced from dmoztools.net and cleaned. This cleaned dataset has 227.5K webpages which are divided into 8 generic categories ('education', 'games', 'health', 'entertainment', 'news', 'shopping', 'sports', 'travel'). Our browser integrated solution has resulted in 15% less memory usage (due to partition method) and 24% less power consumption in comparison with standalone solution. This solution considered 70% of the dataset for training the data model and the rest 30% dataset for testing. An average accuracy of ~96.3% is achieved across the above mentioned 8 categories. This engine can be further extended for suggesting Dynamic tags and using the classification for differential uses cases to enhance browsing experience.

Keywords: chromium, lightweight engine, mobile computing, Naive Bayes, Tizen, web browser, webpage classification

Procedia PDF Downloads 134

Authors: Sofia N. Gonçalves, Duarte M. S. Albuquerque, José C. F. Pereira

Abstract:

The energy transition is spurred by structural changes in energy demand, supply, and prices. Microwave technology was first proposed as a faster alternative for cooking food. It was found that food heated instantly when interacting with high-frequency electromagnetic waves. The dielectric properties account for a material’s ability to absorb electromagnetic energy and dissipate this energy in the form of heat. Many energy-intense industries could benefit from electromagnetic heating since many of the raw materials are dielectric at high temperatures. Limestone sedimentary rock is a dielectric material intensively used in the cement industry to produce unslaked lime. A numerical 3D model was implemented in COMSOL Multiphysics to study the limestone continuous processing under microwave heating. The model solves the two-way coupling between the Energy equation and Maxwell’s equations as well as the coupling between heat transfer and chemical interfaces. Complementary, a controller was implemented to optimize the overall heating efficiency and control the numerical model stability. This was done by continuously matching the cavity impedance and predicting the required energy for the system, avoiding energy inefficiencies. This controller was developed in MATLAB and successfully fulfilled all these goals. The limestone load influence on thermal decomposition and overall process efficiency was the main object of this study. The procedure considered the Verification and Validation of the chemical kinetics model separately from the coupled model. The chemical model was found to correctly describe the chosen kinetic equation, and the coupled model successfully solved the equations describing the numerical model. The interaction between flow of material and electric field Poynting vector revealed to influence limestone decomposition, as a result from the low dielectric properties of limestone. The numerical model considered this effect and took advantage from this interaction. The model was demonstrated to be highly unstable when solving non-linear temperature distributions. Limestone has a dielectric loss response that increases with temperature and has low thermal conductivity. For this reason, limestone is prone to produce thermal runaway under electromagnetic heating, as well as numerical model instabilities. Five different scenarios were tested by considering a material fill ratio of 30%, 50%, 65%, 80%, and 100%. Simulating the tube rotation for mixing enhancement was proven to be beneficial and crucial for all loads considered. When uniform temperature distribution is accomplished, the electromagnetic field and material interaction is facilitated. The results pointed out the inefficient development of the electric field within the bed for 30% fill ratio. The thermal efficiency showed the propensity to stabilize around 90%for loads higher than 50%. The process accomplished a maximum microwave efficiency of 75% for the 80% fill ratio, sustaining that the tube has an optimal fill of material. Electric field peak detachment was observed for the case with 100% fill ratio, justifying the lower efficiencies compared to 80%. Microwave technology has been demonstrated to be an important ally for the decarbonization of the cement industry.

Keywords: CFD numerical simulations, efficiency optimization, electromagnetic heating, impedance matching, limestone continuous processing

Procedia PDF Downloads 141

Authors: Z. Gharaee

Abstract:

Recognizing actions performed by others is important in our daily lives since it is necessary for communicating with others in a proper way. We perceive an action by observing the kinematics of motions involved in the performance. We use our experience and concepts to make a correct recognition of the actions. Although building the action concepts is a life-long process, which is repeated throughout life, we are very efficient in applying our learned concepts in analyzing motions and recognizing actions. Experiments on the subjects observing the actions performed by an actor show that an action is recognized after only about two hundred milliseconds of observation. In this study, hierarchical action recognition architecture is proposed by using growing grid layers. The first-layer growing grid receives the pre-processed data of consecutive 3D postures of joint positions and applies some heuristics during the growth phase to allocate areas of the map by inserting new neurons. As a result of training the first-layer growing grid, action pattern vectors are generated by connecting the elicited activations of the learned map. The ordered vector representation layer receives action pattern vectors to create time-invariant vectors of key elicited activations. Time-invariant vectors are sent to second-layer growing grid for categorization. This grid creates the clusters representing the actions. Finally, one-layer neural network developed by a delta rule labels the action categories in the last layer. System performance has been evaluated in an experiment with the publicly available MSR-Action3D dataset. There are actions performed by using different parts of human body: Hand Clap, Two Hands Wave, Side Boxing, Bend, Forward Kick, Side Kick, Jogging, Tennis Serve, Golf Swing, Pick Up and Throw. The growing grid architecture was trained by applying several random selections of generalization test data fed to the system during on average 100 epochs for each training of the first-layer growing grid and around 75 epochs for each training of the second-layer growing grid. The average generalization test accuracy is 92.6%. A comparison analysis between the performance of growing grid architecture and self-organizing map (SOM) architecture in terms of accuracy and learning speed show that the growing grid architecture is superior to the SOM architecture in action recognition task. The SOM architecture completes learning the same dataset of actions in around 150 epochs for each training of the first-layer SOM while it takes 1200 epochs for each training of the second-layer SOM and it achieves the average recognition accuracy of 90% for generalization test data. In summary, using the growing grid network preserves the fundamental features of SOMs, such as topographic organization of neurons, lateral interactions, the abilities of unsupervised learning and representing high dimensional input space in the lower dimensional maps. The architecture also benefits from an automatic size setting mechanism resulting in higher flexibility and robustness. Moreover, by utilizing growing grids the system automatically obtains a prior knowledge of input space during the growth phase and applies this information to expand the map by inserting new neurons wherever there is high representational demand.

Keywords: action recognition, growing grid, hierarchical architecture, neural networks, system performance

Procedia PDF Downloads 131

Authors: Rahbel Rahman, Rogério Meireles Pinto, Margareth Santos Zanchetta

Abstract:

Background: Existing shortcomings of current health-service delivery include poor teamwork, competencies that do not address consumer needs, and episodic rather than continuous care. Brazil’s Sistema Único de Saúde (Unified Health System, UHS) is acknowledged worldwide as a model for delivering community-based care through Estratégia Saúde da Família (FHS; Family Health Strategy) interdisciplinary teams, comprised of Community Health Agents (in Portuguese, Agentes Comunitário de Saude, ACS), nurses, and physicians. FHS teams are mandated to collectively offer clinical care, disease prevention services, vector control, health surveillance and social services. Our study compares medical providers (nurses and physicians) and community-based providers (ACS) on their perceptions of work environment, professional skills, cognitive capacities and job context. Global health administrators and policy makers can leverage on similarities and differences across care providers to develop interprofessional training for community-based primary care. Methods: Cross-sectional data were collected from 168 ACS, 62 nurses and 32 physicians in Brazil. We compared providers’ demographic characteristics (age, race, and gender) and job context variables (caseload, work experience, work proximity to community, the length of commute, and familiarity with the community). Providers perceptions were compared to their work environment (work conditions and work resources), professional skills (consumer-input, interdisciplinary collaboration, efficacy of FHS teams, work-methods and decision-making autonomy), and cognitive capacities (knowledge and skills, skill variety, confidence and perseverance). Descriptive and bi-variate analysis, such as Pearson Chi-square and Analysis of Variance (ANOVA) F-tests, were performed to draw comparisons across providers. Results: Majority of participants were ACS (64%); 24% nurses; and 12% physicians. Majority of nurses and ACS identified as mixed races (ACS, n=85; nurses, n=27); most physicians identified as males (n=16; 52%), and white (n=18; 58%). Physicians were less likely to incorporate consumer-input and demonstrated greater decision-making autonomy than nurses and ACS. ACS reported the highest levels of knowledge and skills but the least confidence compared to nurses and physicians. ACS, nurses, and physicians were efficacious that FHS teams improved the quality of health in their catchment areas, though nurses tend to disagree that interdisciplinary collaboration facilitated their work. Conclusion: To our knowledge, there has been no study comparing key demographic and cognitive variables across ACS, nurses and physicians in the context of their work environment and professional training. We suggest that global health systems can leverage upon the diverse perspectives of providers to implement a community-based primary care model grounded in interprofessional training. Our study underscores the need for in-service trainings to instill reflective skills of providers, improve communication skills of medical providers and curative skills of ACS. Greater autonomy needs to be extended to community based providers to offer care integral to addressing consumer and community needs.

Keywords: global health systems, interdisciplinary health teams, community health agents, community-based care

Procedia PDF Downloads 205

Authors: V. V. Fomin, A. P. Mikhailovich, E. M. Agapitov, V. E. Rogachev, E. A. Kostousova, E. S. Perekhodova

Abstract:

Ground-level landscape photos can be used as a source of objective data on woody vegetation and vegetation dynamics. We proposed a method for processing, analyzing, and presenting ground photographs, which has the following advantages: 1) researcher has to form holistic representation of the study area in form of a set of interlapping ground-level landscape photographs; 2) it is necessary to define or obtain characteristics of the landscape, objects, and phenomena present on the photographs; 3) it is necessary to create new or supplement existing textual descriptions and annotations for the ground-level landscape photographs; 4) single or multiple ground-level landscape photographs can be used to develop specialized geoinformation layers, schematic maps or thematic maps; 5) it is necessary to determine quantitative data that describes both images as a whole, and displayed objects and phenomena, using algorithms for automated image analysis. It is suggested to match each photo with a polygonal geoinformation layer, which is a sector consisting of areas corresponding with parts of the landscape visible in the photos. Calculation of visibility areas is performed in a geoinformation system within a sector using a digital model of a study area relief and visibility analysis functions. Superposition of the visibility sectors corresponding with various camera viewpoints allows matching landscape photos with each other to create a complete and wholesome representation of the space in question. It is suggested to user-defined data or phenomenons on the images with the following superposition over the visibility sector in the form of map symbols. The technology of geoinformation layers’ spatial superposition over the visibility sector creates opportunities for image geotagging using quantitative data obtained from raster or vector layers within the sector with the ability to generate annotations in natural language. The proposed method has proven itself well for relatively open and clearly visible areas with well-defined relief, for example, in mountainous areas in the treeline ecotone. When the polygonal layers of visibility sectors for a large number of different points of photography are topologically superimposed, a layer of visibility of sections of the entire study area is formed, which is displayed in the photographs. Also, as a result of this overlapping of sectors, areas that did not appear in the photo will be assessed as gaps. According to the results of this procedure, it becomes possible to obtain information about the photos that display a specific area and from which points of photography it is visible. This information may be obtained either as a query on the map or as a query for the attribute table of the layer. The method was tested using repeated photos taken from forty camera viewpoints located on Ray-Iz mountain massif (Polar Urals, Russia) from 1960 until 2023. It has been successfully used in combination with other ground-based and remote sensing methods of studying the climate-driven dynamics of woody vegetation in the Polar Urals. Acknowledgment: This research was collaboratively funded by the Russian Ministry for Science and Education project No. FEUG-2023-0002 (image representation) and Russian Science Foundation project No. 24-24-00235 (automated textual description).

Keywords: woody, vegetation, repeated, photographs

Procedia PDF Downloads 22

Authors: David F. Nettleton, Elodie Bugnicourt, Christian Wasiak, Alejandro Rosales

Abstract:

In this presentation, preliminary results are given for the modeling and calibration of two different industrial winding MIMO (Multiple Input Multiple Output) processes using machine learning techniques. In contrast to previous approaches which have typically used ‘black-box’ linear statistical methods together with a definition of the mechanical behavior of the process, we use non-linear machine learning algorithms together with a ‘white-box’ rule induction technique to create a supervised model of the fitting error between the expected and real force measures. The final objective is to build a precise model of the winding process in order to control de-tension of the material being wound in the first case, and the friction of the material passing through the die, in the second case. Case 1, Tension Control of a Winding Process. A plastic web is unwound from a first reel, goes over a traction reel and is rewound on a third reel. The objectives are: (i) to train a model to predict the web tension and (ii) calibration to find the input values which result in a given tension. Case 2, Friction Force Control of a Micro-Pullwinding Process. A core+resin passes through a first die, then two winding units wind an outer layer around the core, and a final pass through a second die. The objectives are: (i) to train a model to predict the friction on die2; (ii) calibration to find the input values which result in a given friction on die2. Different machine learning approaches are tested to build models, Kernel Ridge Regression, Support Vector Regression (with a Radial Basis Function Kernel) and MPART (Rule Induction with continuous value as output). As a previous step, the MPART rule induction algorithm was used to build an explicative model of the error (the difference between expected and real friction on die2). The modeling of the error behavior using explicative rules is used to help improve the overall process model. Once the models are built, the inputs are calibrated by generating Gaussian random numbers for each input (taking into account its mean and standard deviation) and comparing the output to a target (desired) output until a closest fit is found. The results of empirical testing show that a high precision is obtained for the trained models and for the calibration process. The learning step is the slowest part of the process (max. 5 minutes for this data), but this can be done offline just once. The calibration step is much faster and in under one minute obtained a precision error of less than 1x10-3 for both outputs. To summarize, in the present work two processes have been modeled and calibrated. A fast processing time and high precision has been achieved, which can be further improved by using heuristics to guide the Gaussian calibration. Error behavior has been modeled to help improve the overall process understanding. This has relevance for the quick optimal set up of many different industrial processes which use a pull-winding type process to manufacture fibre reinforced plastic parts. Acknowledgements to the Openmind project which is funded by Horizon 2020 European Union funding for Research & Innovation, Grant Agreement number 680820

Keywords: data model, machine learning, industrial winding, calibration

Procedia PDF Downloads 212

Authors: Xingyu Gao, Qiang Wu

Abstract:

Patents play a crucial role in protecting innovation and intellectual property. Early prediction of the impact of artificial intelligence (AI) patents helps researchers and companies allocate resources and make better decisions. Understanding the key factors that influence patent impact can assist researchers in gaining a better understanding of the evolution of AI technology and innovation trends. Therefore, identifying highly impactful patents early and providing support for them holds immeasurable value in accelerating technological progress, reducing research and development costs, and mitigating market positioning risks. Despite the extensive research on AI patents, accurately predicting their early impact remains a challenge. Traditional methods often consider only single factors or simple combinations, failing to comprehensively and accurately reflect the actual impact of patents. This paper utilized the artificial intelligence patent database from the United States Patent and Trademark Office and the Len.org patent retrieval platform to obtain specific information on 35,708 AI patents. Using six machine learning models, namely Multiple Linear Regression, Random Forest Regression, XGBoost Regression, LightGBM Regression, Support Vector Machine Regression, and K-Nearest Neighbors Regression, and using early indicators of patents as features, the paper comprehensively predicted the impact of patents from three aspects: technical, social, and economic. These aspects include the technical leadership of patents, the number of citations they receive, and their shared value. The SHAP (Shapley Additive exPlanations) metric was used to explain the predictions of the best model, quantifying the contribution of each feature to the model's predictions. The experimental results on the AI patent dataset indicate that, for all three target variables, LightGBM regression shows the best predictive performance. Specifically, patent novelty has the greatest impact on predicting the technical impact of patents and has a positive effect. Additionally, the number of owners, the number of backward citations, and the number of independent claims are all crucial and have a positive influence on predicting technical impact. In predicting the social impact of patents, the number of applicants is considered the most critical input variable, but it has a negative impact on social impact. At the same time, the number of independent claims, the number of owners, and the number of backward citations are also important predictive factors, and they have a positive effect on social impact. For predicting the economic impact of patents, the number of independent claims is considered the most important factor and has a positive impact on economic impact. The number of owners, the number of sibling countries or regions, and the size of the extended patent family also have a positive influence on economic impact. The study primarily relies on data from the United States Patent and Trademark Office for artificial intelligence patents. Future research could consider more comprehensive data sources, including artificial intelligence patent data, from a global perspective. While the study takes into account various factors, there may still be other important features not considered. In the future, factors such as patent implementation and market applications may be considered as they could have an impact on the influence of patents.

Keywords: patent influence, interpretable machine learning, predictive models, SHAP

Procedia PDF Downloads 17