Model-based condition monitoring (MBCM) solves the inverse problem of inferring a systems state, including possible faults, from sensor observations. Constructing these models in a knowledge-based manner following the laws of physics is hard due to the inverse nature of the problem and unknown fault types. As a result, it has become more attractive to build a model solely from past observations via machine learning (ML). Although highly promising, shortcomings of ML in the scientific domain, including physically inconsistent results and lack of interpretability, became apparent. This led to recent efforts to enhance machine learning with scientific knowledge including a combination of knowledge-based and data-driven modelling, often referred to as hybrid models. The main contributions of this work are: (1) a link of shortcomings of machine learning in CM to a lack of knowledge; (2) a categorization of unique approaches with respect to required knowledge and mechanism of incorporation that have either been applied in condition monitoring or show potential from their application to scientific problems; (3) derivation of promising research directions uncovered as vacant spaces in the categorization.
{"title":"Knowledge Incorporation for Machine Learning in Condition Monitoring: A Survey","authors":"E. Hagendorfer","doi":"10.1145/3459104.3459144","DOIUrl":"https://doi.org/10.1145/3459104.3459144","url":null,"abstract":"Model-based condition monitoring (MBCM) solves the inverse problem of inferring a systems state, including possible faults, from sensor observations. Constructing these models in a knowledge-based manner following the laws of physics is hard due to the inverse nature of the problem and unknown fault types. As a result, it has become more attractive to build a model solely from past observations via machine learning (ML). Although highly promising, shortcomings of ML in the scientific domain, including physically inconsistent results and lack of interpretability, became apparent. This led to recent efforts to enhance machine learning with scientific knowledge including a combination of knowledge-based and data-driven modelling, often referred to as hybrid models. The main contributions of this work are: (1) a link of shortcomings of machine learning in CM to a lack of knowledge; (2) a categorization of unique approaches with respect to required knowledge and mechanism of incorporation that have either been applied in condition monitoring or show potential from their application to scientific problems; (3) derivation of promising research directions uncovered as vacant spaces in the categorization.","PeriodicalId":322229,"journal":{"name":"International Symposium on Electrical, Electronics and Information Engineering","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129774067","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper is an introduction and guide to big data in the modern world, from the perspective of an information system practitioner. It will first look at the use of big data in business and industry. It describes the issues faced by organizations with big data and the new business models that have emerged because of the Internet and Web 2.0. It explores this through qualitative research involving employees directly involved in big data analyses. It also explores how big data has impacted on customer data analysis and addresses whether it is providing good value for the amount invested in the technology. It will also explain current methods of data collection through the analysis of literature. Finally, this paper will explore the ethical implications of data collection both in organizations and online, and it will then look at current research on whether the data economy itself is ethical.
{"title":"An Investigation into the Effectiveness of Big Data in Organizations, the Use of Customer Data, and the Ethical Implications of the Data Economy","authors":"Robert Polding, M. E. Dieguez","doi":"10.1145/3459104.3459201","DOIUrl":"https://doi.org/10.1145/3459104.3459201","url":null,"abstract":"This paper is an introduction and guide to big data in the modern world, from the perspective of an information system practitioner. It will first look at the use of big data in business and industry. It describes the issues faced by organizations with big data and the new business models that have emerged because of the Internet and Web 2.0. It explores this through qualitative research involving employees directly involved in big data analyses. It also explores how big data has impacted on customer data analysis and addresses whether it is providing good value for the amount invested in the technology. It will also explain current methods of data collection through the analysis of literature. Finally, this paper will explore the ethical implications of data collection both in organizations and online, and it will then look at current research on whether the data economy itself is ethical.","PeriodicalId":322229,"journal":{"name":"International Symposium on Electrical, Electronics and Information Engineering","volume":"3 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124379608","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Helio S. Esteban Villega, C. B. Pinilla, Laura Milena Prieto
This paper presents the design and simulation of two predictive controllers with different estimators on a 3 DOF helicopter. The work begins with the modeling of the helicopter, obtaining the equations using LaGrange method with a matrix form representation, including viscous friction and assuming a drive-motor with stationary behavior. With the dynamic equations defined, the next step was to obtain the identification of real parameters for the dynamic system. This was carried out using a grey box method applied in a real 3DOF Helicopter prototype built at the university. After verifying the model with the best fit-test, the controller design step begins. To have a comparison point of the advanced controller's performance, a classical PID was tuned. To use the Kalman estimator, a linearization process was achieved and verified with the respective simulation. To get the neural network estimator a NARX type of neural network was used with a layer size of 14 and with 2 delays per input and output. In the design of the MPC controller's the same weights and limitations were assumed, considering the real limitations of the prototype and keeping the reference input near to the linearization point. To get proper evaluation criteria the setting time, overshoot, noise rejection, computational time and ITAE index were the values used to determine the performance for each controller. Simulations were performed on the dynamic system, with step and random steps and tracking-trajectory. According to the obtained data in the step test, the three strategies were able to control the vehicle obtaining negligible differences. In the random step and trajectory tracking test was observed than MPC controller with a neural network estimator gets a better response without noise but, some noise levels were added and the Kalman filter gets a better rejection level. Analyzing the computation time, it was observed that the neural network estimator has the longest simulation times in comparison to the Kalman filter and the classical PID.
{"title":"Predictive Control of 3 DOF Helicopter Using a Kalman and Neural Network Estimator","authors":"Helio S. Esteban Villega, C. B. Pinilla, Laura Milena Prieto","doi":"10.1145/3459104.3459126","DOIUrl":"https://doi.org/10.1145/3459104.3459126","url":null,"abstract":"This paper presents the design and simulation of two predictive controllers with different estimators on a 3 DOF helicopter. The work begins with the modeling of the helicopter, obtaining the equations using LaGrange method with a matrix form representation, including viscous friction and assuming a drive-motor with stationary behavior. With the dynamic equations defined, the next step was to obtain the identification of real parameters for the dynamic system. This was carried out using a grey box method applied in a real 3DOF Helicopter prototype built at the university. After verifying the model with the best fit-test, the controller design step begins. To have a comparison point of the advanced controller's performance, a classical PID was tuned. To use the Kalman estimator, a linearization process was achieved and verified with the respective simulation. To get the neural network estimator a NARX type of neural network was used with a layer size of 14 and with 2 delays per input and output. In the design of the MPC controller's the same weights and limitations were assumed, considering the real limitations of the prototype and keeping the reference input near to the linearization point. To get proper evaluation criteria the setting time, overshoot, noise rejection, computational time and ITAE index were the values used to determine the performance for each controller. Simulations were performed on the dynamic system, with step and random steps and tracking-trajectory. According to the obtained data in the step test, the three strategies were able to control the vehicle obtaining negligible differences. In the random step and trajectory tracking test was observed than MPC controller with a neural network estimator gets a better response without noise but, some noise levels were added and the Kalman filter gets a better rejection level. Analyzing the computation time, it was observed that the neural network estimator has the longest simulation times in comparison to the Kalman filter and the classical PID.","PeriodicalId":322229,"journal":{"name":"International Symposium on Electrical, Electronics and Information Engineering","volume":"237 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115997440","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Each Government is must ensure adequate health and social welfare for people. The healthcare book is a document historicizing medical information related to a person. It helps doctors to make consistent diagnoses. The major concern of doctors is to ensure the inalterability of information provided by the healthcare book. Based on the major benefits that Blockchain technology offers, we use it to design a digital healthcare book system by writing smart contract with Ethereum blockchain. It guarantees data integrity and provides secure information to doctors on various medical exams, patients’ pathologies and others. It is a low-cost and safe system in cases of emergency. In addition, an Ethereum based implementation is used to verify the feasibility of our proposed system.
{"title":"Developing a Digital Healthcare Book based on the Blockchain Technology","authors":"Nelson Josias Gbètoho Saho, E. C. Ezin","doi":"10.1145/3459104.3459203","DOIUrl":"https://doi.org/10.1145/3459104.3459203","url":null,"abstract":"Each Government is must ensure adequate health and social welfare for people. The healthcare book is a document historicizing medical information related to a person. It helps doctors to make consistent diagnoses. The major concern of doctors is to ensure the inalterability of information provided by the healthcare book. Based on the major benefits that Blockchain technology offers, we use it to design a digital healthcare book system by writing smart contract with Ethereum blockchain. It guarantees data integrity and provides secure information to doctors on various medical exams, patients’ pathologies and others. It is a low-cost and safe system in cases of emergency. In addition, an Ethereum based implementation is used to verify the feasibility of our proposed system.","PeriodicalId":322229,"journal":{"name":"International Symposium on Electrical, Electronics and Information Engineering","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125754061","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A. TorresYanez, J. A. Vázquez-Feijoo, M. UrriolagoitiaCalderonG., G. Urriolagoitia-Sosa
From thermodynamics data, the kinetics of the crankshaft of a mono-cylindrical mechanism is carried on; there is not a real full kinetic analysis of this kind of crankshaft. This work has the target of offering a first step analysis for any researcher that is interested in approaching the design optimization of a combustion engine. Though this kind of engine does not have spread use today, it is still a relevant point from which to depart. This work takes some carried on experiments on an internal combustion engine adapted to work as one cylinder. With the data provided, the energy generated by the explosion is assumed and then, it is possible to know the pressure generated in the combustion chamber. The cinematics is carried on the mechanism and then the forces per cycle are obtained. Giving the pressure along the time of the proposed crankshaft, the structural behavior of the crankshaft can be simulated during a complete Otto cycle.
{"title":"Dynamics of a Mono-cylindrical Crankshaft of a Four Strokes Otto Engine","authors":"A. TorresYanez, J. A. Vázquez-Feijoo, M. UrriolagoitiaCalderonG., G. Urriolagoitia-Sosa","doi":"10.1145/3459104.3459115","DOIUrl":"https://doi.org/10.1145/3459104.3459115","url":null,"abstract":"From thermodynamics data, the kinetics of the crankshaft of a mono-cylindrical mechanism is carried on; there is not a real full kinetic analysis of this kind of crankshaft. This work has the target of offering a first step analysis for any researcher that is interested in approaching the design optimization of a combustion engine. Though this kind of engine does not have spread use today, it is still a relevant point from which to depart. This work takes some carried on experiments on an internal combustion engine adapted to work as one cylinder. With the data provided, the energy generated by the explosion is assumed and then, it is possible to know the pressure generated in the combustion chamber. The cinematics is carried on the mechanism and then the forces per cycle are obtained. Giving the pressure along the time of the proposed crankshaft, the structural behavior of the crankshaft can be simulated during a complete Otto cycle.","PeriodicalId":322229,"journal":{"name":"International Symposium on Electrical, Electronics and Information Engineering","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126208475","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The use of machine learning techniques, especially deep learning, could improve the predictions of the currently used epidemiological models for predicting Covid-19 in the short term. This information is essential for better decision making and to reduce the impacts of the disease spread in different countries. We explored the use of support vector regression (SVR) and long short-term memory networks (LSTM), the state of the art neural network architecture for time series analysis, to predict the daily incidence and prevalence for nine countries in Latin America. Our methodology and the models used can be replicated in other countries. Our main findings were: (i) there is no single best model or best hyperparameters configuration for all countries and targets; (ii) the LSTM showed an average MAE that was around 50% lower for incidence and 20% lower for prevalence when considering all countries; (iii) the LSTM showed better results for predicting incidence for most countries (Argentina, Bolivia, Brazil, Guatemala, and Haiti); (iv) the SVR showed better results for predicting prevalence for most countries (Argentina, Bolivia, Colombia, Cuba, Guatemala, and Haiti); and (v) for Brazil, the LSTM provided better results for both targets, with an MAE that was 68% lower for incidence and 73% lower for prevalence.
{"title":"An In-depth Analysis on the Use of Long Short-term Memory Networks to Predict Incidence and Prevalence of Covid-19 in Latin America","authors":"B. Barreira, Roberto Fray da Silva, C. Cugnasca","doi":"10.1145/3459104.3459167","DOIUrl":"https://doi.org/10.1145/3459104.3459167","url":null,"abstract":"The use of machine learning techniques, especially deep learning, could improve the predictions of the currently used epidemiological models for predicting Covid-19 in the short term. This information is essential for better decision making and to reduce the impacts of the disease spread in different countries. We explored the use of support vector regression (SVR) and long short-term memory networks (LSTM), the state of the art neural network architecture for time series analysis, to predict the daily incidence and prevalence for nine countries in Latin America. Our methodology and the models used can be replicated in other countries. Our main findings were: (i) there is no single best model or best hyperparameters configuration for all countries and targets; (ii) the LSTM showed an average MAE that was around 50% lower for incidence and 20% lower for prevalence when considering all countries; (iii) the LSTM showed better results for predicting incidence for most countries (Argentina, Bolivia, Brazil, Guatemala, and Haiti); (iv) the SVR showed better results for predicting prevalence for most countries (Argentina, Bolivia, Colombia, Cuba, Guatemala, and Haiti); and (v) for Brazil, the LSTM provided better results for both targets, with an MAE that was 68% lower for incidence and 73% lower for prevalence.","PeriodicalId":322229,"journal":{"name":"International Symposium on Electrical, Electronics and Information Engineering","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121253303","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The aim of this paper is to design and implement a series of actions regarding the operation of DEDA S.A. (Natural Gas Distribution Networks), based on principles of Industry 4.0. The Natural Gas Distribution sector is one of the most critical and innovative areas where Industry 4.0 can be applied, being part of critical infrastructure management. At first, company's business process architecture was developed, with the aim to export DEDA's business process and functional specifications related to the required information systems. Subsequently, company's communication network is implemented alongside the company's gas network, in coordination with the company's control room. In addition, modernization of metering system is taking place in order to exchange information between smart meters and the control room. A number of Information Systems, such as the pipeline surveillance system and the Business Intelligence system will also be installed in order to ensure communication at different levels using Cloud technologies. The implementation is expected to improve DEDA's organization, increasing customers' service level. As a result, there will be an expected increase in the operational efficiency of DEDA's network through the use of advanced technologies, in cooperation with business process modelling techniques. The effort should be continued in this direction in order to achieve even greater improvement in business processes, information systems and pipeline automation.
{"title":"Applying the Industry 4.0 in a Smart Gas Grid: The Greek Gas Distribution Network Case","authors":"N. Panayiotou, V. P. Stavrou, K. Stergiou","doi":"10.1145/3459104.3459136","DOIUrl":"https://doi.org/10.1145/3459104.3459136","url":null,"abstract":"The aim of this paper is to design and implement a series of actions regarding the operation of DEDA S.A. (Natural Gas Distribution Networks), based on principles of Industry 4.0. The Natural Gas Distribution sector is one of the most critical and innovative areas where Industry 4.0 can be applied, being part of critical infrastructure management. At first, company's business process architecture was developed, with the aim to export DEDA's business process and functional specifications related to the required information systems. Subsequently, company's communication network is implemented alongside the company's gas network, in coordination with the company's control room. In addition, modernization of metering system is taking place in order to exchange information between smart meters and the control room. A number of Information Systems, such as the pipeline surveillance system and the Business Intelligence system will also be installed in order to ensure communication at different levels using Cloud technologies. The implementation is expected to improve DEDA's organization, increasing customers' service level. As a result, there will be an expected increase in the operational efficiency of DEDA's network through the use of advanced technologies, in cooperation with business process modelling techniques. The effort should be continued in this direction in order to achieve even greater improvement in business processes, information systems and pipeline automation.","PeriodicalId":322229,"journal":{"name":"International Symposium on Electrical, Electronics and Information Engineering","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121508535","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A control algorithm based on adaptive neural networks is developed to control the navigation of a mobile autonomous ground-based explorer robot. A simulation was performed in the Matlab program to verify the operation of the algorithm, where the set of proximity sensors used by the robot for the detection and evasion of obstacles was simulated. The algorithm was developed using three neural network architectures: Adaline-type linear adaptive network, Perceptron neural network, and Feedforward neural network. The mathematical study of each of the adaptive neural network architectures proposed for the recognition of training patterns, corresponding to wall following patterns was carried out; their comparison was made and based on the results of the simulation, the one that showed the best output responses was selected to form part of the algorithm. This algorithm is in charged of the main tasks of obstacle avoidance and the target searching, generating as control outputs: the angle of rotation of the robot concerning its current position and its forward speed, to solve the problem of high difficulty concave obstacles encountered in the robot's path to the target. This is a hybrid algorithm, made up of a local path planning algorithm, in charge of obstacle wall fallowing and a global path planning algorithm, in charge of finding the final objective. This work focused on solving the problem of evasion of high difficulty concave obstacles, formed by curves in the form of a loop, also called dead-end traps, in which a situation of local minimum is presented. In this work different types of obstacles were simulated, being able to create almost any shape; the algorithm was tested with obstacles created from arrays of bars or lines forming simple corners, with obstacles such as U-shaped, snail-shaped, labyrinth-shaped, among other complicated shapes. The developed algorithm autonomously generates an obstacle-free navigation path, with a speed control of the robot, during the entire movement until reaching the final target. Besides, the simulation shows that the designed algorithm works adequately to solve the problem of concave obstacles, and compared with results of other mobile robot navigation techniques such as potential fields, diffuse controller-based techniques, and techniques based on rule learning (pure neural network); that in general, they present great limitations to solve the type of problem posed, difficult concave-type obstacles, remaining stuck in local minima or entering into infinite cycles with no exit, without reaching the final target; therefore, the robustness of the developed algorithm is shown.
{"title":"Development of a Hybrid Control Algorithm Based on Neural Networks for Mobile Autonomous Robot Navigation","authors":"E. Quintero, C. B. Pinilla","doi":"10.1145/3459104.3459125","DOIUrl":"https://doi.org/10.1145/3459104.3459125","url":null,"abstract":"A control algorithm based on adaptive neural networks is developed to control the navigation of a mobile autonomous ground-based explorer robot. A simulation was performed in the Matlab program to verify the operation of the algorithm, where the set of proximity sensors used by the robot for the detection and evasion of obstacles was simulated. The algorithm was developed using three neural network architectures: Adaline-type linear adaptive network, Perceptron neural network, and Feedforward neural network. The mathematical study of each of the adaptive neural network architectures proposed for the recognition of training patterns, corresponding to wall following patterns was carried out; their comparison was made and based on the results of the simulation, the one that showed the best output responses was selected to form part of the algorithm. This algorithm is in charged of the main tasks of obstacle avoidance and the target searching, generating as control outputs: the angle of rotation of the robot concerning its current position and its forward speed, to solve the problem of high difficulty concave obstacles encountered in the robot's path to the target. This is a hybrid algorithm, made up of a local path planning algorithm, in charge of obstacle wall fallowing and a global path planning algorithm, in charge of finding the final objective. This work focused on solving the problem of evasion of high difficulty concave obstacles, formed by curves in the form of a loop, also called dead-end traps, in which a situation of local minimum is presented. In this work different types of obstacles were simulated, being able to create almost any shape; the algorithm was tested with obstacles created from arrays of bars or lines forming simple corners, with obstacles such as U-shaped, snail-shaped, labyrinth-shaped, among other complicated shapes. The developed algorithm autonomously generates an obstacle-free navigation path, with a speed control of the robot, during the entire movement until reaching the final target. Besides, the simulation shows that the designed algorithm works adequately to solve the problem of concave obstacles, and compared with results of other mobile robot navigation techniques such as potential fields, diffuse controller-based techniques, and techniques based on rule learning (pure neural network); that in general, they present great limitations to solve the type of problem posed, difficult concave-type obstacles, remaining stuck in local minima or entering into infinite cycles with no exit, without reaching the final target; therefore, the robustness of the developed algorithm is shown.","PeriodicalId":322229,"journal":{"name":"International Symposium on Electrical, Electronics and Information Engineering","volume":"79 10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131204597","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Defending against threats in today's world requires the latest technology. One of the promising methods for solving problems is biometric. The algorithm of operation of optoelectronic biometric security systems, the task of which is to assess the emotional response of a person to a specific test object, must include a marker by which the system will distinguish a predetermined emotional response of a person. Pupillometry and tracking can be successfully used in such systems. Biometric systems aimed at searching for certain signs of a psychophysical state with the help of pupils must be able to interpret them correctly. The decryption process is very difficult because the size of the pupil depends on many factors. Thus, one of the most important tasks, the solution of which is a determining factor in whether the developed biometric system will work, is to explain each plot of the pupil. In addition, the task of accurately contouring and building a spotlight track comes to the fore. Our research aims to improve the accuracy of attention tracking without using infrared lighting.
{"title":"Method for Increasing The Accuracy of Tracking The Center of Attention of The Gaze","authors":"P. BoronenkoM., L. IsaevaO., I. ZelenskyV.","doi":"10.1145/3459104.3459172","DOIUrl":"https://doi.org/10.1145/3459104.3459172","url":null,"abstract":"Defending against threats in today's world requires the latest technology. One of the promising methods for solving problems is biometric. The algorithm of operation of optoelectronic biometric security systems, the task of which is to assess the emotional response of a person to a specific test object, must include a marker by which the system will distinguish a predetermined emotional response of a person. Pupillometry and tracking can be successfully used in such systems. Biometric systems aimed at searching for certain signs of a psychophysical state with the help of pupils must be able to interpret them correctly. The decryption process is very difficult because the size of the pupil depends on many factors. Thus, one of the most important tasks, the solution of which is a determining factor in whether the developed biometric system will work, is to explain each plot of the pupil. In addition, the task of accurately contouring and building a spotlight track comes to the fore. Our research aims to improve the accuracy of attention tracking without using infrared lighting.","PeriodicalId":322229,"journal":{"name":"International Symposium on Electrical, Electronics and Information Engineering","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128993180","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Angel Felipe Magnossão de Paula, Roberto Fray da Silva, B. Nishimoto, C. Cugnasca, Anna Helena Reali Costa
Multiple-choice question answering for the open domain is a task that consists of answering challenging questions from multiple domains, without direct pieces of evidence in the text corpora. The main application of multiple-choice question answering is self-tutoring. We propose the Multiple-Choice Reinforcement Learner (MCRL) model, which uses a policy gradient algorithm in a partially observable Markov decision process to reformulate question-answer pairs in order to find new pieces of evidence to support each answer choice. Its inputs are the question and the answer choices. MCRL learns to generate queries that improve the evidence found for each answer choice, using iteration cycles. After a predefined number of iteration cycles, MCRL provides the best answer choice and the text passages that support it. We use accuracy and mean reward per episode to conduct an in-depth hyperparameter analysis of the number of iteration cycles, reward function design, and weight of the pieces of evidence found in each iteration cycle on the final answer choice. The MCRL model with the best performance reached an accuracy of 0.346, a value higher than naive, random, and the traditional end-to-end deep learning QA models. We conclude with recommendations for future developments of the model, which can be adapted for different languages using text corpora and word embedding models for each language.
{"title":"Answer Selection Using Reinforcement Learning for Complex Question Answering on the Open Domain","authors":"Angel Felipe Magnossão de Paula, Roberto Fray da Silva, B. Nishimoto, C. Cugnasca, Anna Helena Reali Costa","doi":"10.1145/3459104.3459149","DOIUrl":"https://doi.org/10.1145/3459104.3459149","url":null,"abstract":"Multiple-choice question answering for the open domain is a task that consists of answering challenging questions from multiple domains, without direct pieces of evidence in the text corpora. The main application of multiple-choice question answering is self-tutoring. We propose the Multiple-Choice Reinforcement Learner (MCRL) model, which uses a policy gradient algorithm in a partially observable Markov decision process to reformulate question-answer pairs in order to find new pieces of evidence to support each answer choice. Its inputs are the question and the answer choices. MCRL learns to generate queries that improve the evidence found for each answer choice, using iteration cycles. After a predefined number of iteration cycles, MCRL provides the best answer choice and the text passages that support it. We use accuracy and mean reward per episode to conduct an in-depth hyperparameter analysis of the number of iteration cycles, reward function design, and weight of the pieces of evidence found in each iteration cycle on the final answer choice. The MCRL model with the best performance reached an accuracy of 0.346, a value higher than naive, random, and the traditional end-to-end deep learning QA models. We conclude with recommendations for future developments of the model, which can be adapted for different languages using text corpora and word embedding models for each language.","PeriodicalId":322229,"journal":{"name":"International Symposium on Electrical, Electronics and Information Engineering","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115098927","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：