Pub Date : 2020-06-29DOI: 10.1109/CoDIT49905.2020.9263901
Chaima Dachraoui, A. Mouelhi, C. Drissi, S. Labidi
The diagnosis, evaluation, and treatment of multiple sclerosis are based essentially on a visual analysis of brain MR-Images. The main objective of this paper is to propose a new predictive approach of the multiple sclerosis lesions evolution’s in order to computerise the daily routine and sometimes difficult diagnostic process and moreover the follow-up. Hence, we chose to introduce the chaos theory. This theory can be used to provide a better understanding of complex systems whose comportment is unpredictable in the long term due to their high sensitivity to initial conditions. A quantitative study is presented in this paper to validate our results using the BrainWeb simulator, MICCAI2008 and MICCAI2016. This funded research was tested on 10 clinical cases (5 pathological patients and 5 healthy cases). Patients with multiple sclerosis are divided into 2 men and 3 women with an age group ranging from 30 to 72 years. The proposed method presents promising results showing the robustness of our segmentation as well as insights into multiple sclerosis which can act as a guideline for the medical neurology researchers. It presents a novel method to analyze the MR-images using the chaotic theory.
{"title":"Predictive Approach of Multiple Sclerosis MR-Lesions Evolution based on Chaotic Attributes","authors":"Chaima Dachraoui, A. Mouelhi, C. Drissi, S. Labidi","doi":"10.1109/CoDIT49905.2020.9263901","DOIUrl":"https://doi.org/10.1109/CoDIT49905.2020.9263901","url":null,"abstract":"The diagnosis, evaluation, and treatment of multiple sclerosis are based essentially on a visual analysis of brain MR-Images. The main objective of this paper is to propose a new predictive approach of the multiple sclerosis lesions evolution’s in order to computerise the daily routine and sometimes difficult diagnostic process and moreover the follow-up. Hence, we chose to introduce the chaos theory. This theory can be used to provide a better understanding of complex systems whose comportment is unpredictable in the long term due to their high sensitivity to initial conditions. A quantitative study is presented in this paper to validate our results using the BrainWeb simulator, MICCAI2008 and MICCAI2016. This funded research was tested on 10 clinical cases (5 pathological patients and 5 healthy cases). Patients with multiple sclerosis are divided into 2 men and 3 women with an age group ranging from 30 to 72 years. The proposed method presents promising results showing the robustness of our segmentation as well as insights into multiple sclerosis which can act as a guideline for the medical neurology researchers. It presents a novel method to analyze the MR-images using the chaotic theory.","PeriodicalId":355781,"journal":{"name":"2020 7th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121111074","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}
Pub Date : 2020-06-29DOI: 10.1109/CoDIT49905.2020.9263952
N. Meslem, A. Hably, T. Raïssi
In this contribution, interval extensions for both full-order and reduced-order unknown input observers are proposed for uncertain discrete time linear systems. The introduced interval estimators do not rely on the positive systems property of the estimation errors. They are mainly based on numerical schemes conceived to characterize in a rigorous way the reached set of some classes of uncertain dynamical systems. Thus, only the classical existence conditions of unknown input observers are needed to design their interval extensions. Interval analysis is used as a convenient tool to implement the proposed state estimation algorithms. However, other bounded geometrical sets could be also applied. Numerical examples are studied to highlight the effectiveness of the introduced interval estimators in the presence of both system’s uncertainties and unknown inputs.
{"title":"Partial and Full Order Interval Unknown Input State Estimators","authors":"N. Meslem, A. Hably, T. Raïssi","doi":"10.1109/CoDIT49905.2020.9263952","DOIUrl":"https://doi.org/10.1109/CoDIT49905.2020.9263952","url":null,"abstract":"In this contribution, interval extensions for both full-order and reduced-order unknown input observers are proposed for uncertain discrete time linear systems. The introduced interval estimators do not rely on the positive systems property of the estimation errors. They are mainly based on numerical schemes conceived to characterize in a rigorous way the reached set of some classes of uncertain dynamical systems. Thus, only the classical existence conditions of unknown input observers are needed to design their interval extensions. Interval analysis is used as a convenient tool to implement the proposed state estimation algorithms. However, other bounded geometrical sets could be also applied. Numerical examples are studied to highlight the effectiveness of the introduced interval estimators in the presence of both system’s uncertainties and unknown inputs.","PeriodicalId":355781,"journal":{"name":"2020 7th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124775840","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}
Pub Date : 2020-06-29DOI: 10.1109/CoDIT49905.2020.9263820
J. A. Morente-Molinera, I. J. Cabrerizo, S. Alonso, I. Pérez, E. Herrera-Viedma
The appearance of novel Web technologies and the high amount of information available on the Internet make it difficult for a traditional group decision making method to work correctly. In this kind of environment, the debates become more complicated. For instance, new information arises at any time and some of the discussed information becomes old. Therefore, this situation requires the developing of novel group decision making methods that allow experts to carry out group decision making processes in dynamic contexts. Although there already exists methods that takes into account a variable set of alternatives, there is few research when this variation is present on the criteria values also. In this paper, a novel group decision making method that takes into account scenarios where the amount of criteria and alternatives vary over time is presented. Experts can also select the subset of alternatives and criteria that they want to provide information for. This way, they do not have to provide information for those situations they do not have knowledge about. Moreover, multi-granular fuzzy linguistic modelling methods are used for the experts to select the preference representation that they prefer.
{"title":"Managing changes in alternatives and criteria during a dynamic multi-criteria group decision making process","authors":"J. A. Morente-Molinera, I. J. Cabrerizo, S. Alonso, I. Pérez, E. Herrera-Viedma","doi":"10.1109/CoDIT49905.2020.9263820","DOIUrl":"https://doi.org/10.1109/CoDIT49905.2020.9263820","url":null,"abstract":"The appearance of novel Web technologies and the high amount of information available on the Internet make it difficult for a traditional group decision making method to work correctly. In this kind of environment, the debates become more complicated. For instance, new information arises at any time and some of the discussed information becomes old. Therefore, this situation requires the developing of novel group decision making methods that allow experts to carry out group decision making processes in dynamic contexts. Although there already exists methods that takes into account a variable set of alternatives, there is few research when this variation is present on the criteria values also. In this paper, a novel group decision making method that takes into account scenarios where the amount of criteria and alternatives vary over time is presented. Experts can also select the subset of alternatives and criteria that they want to provide information for. This way, they do not have to provide information for those situations they do not have knowledge about. Moreover, multi-granular fuzzy linguistic modelling methods are used for the experts to select the preference representation that they prefer.","PeriodicalId":355781,"journal":{"name":"2020 7th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124896653","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}
Pub Date : 2020-06-29DOI: 10.1109/CoDIT49905.2020.9263987
M. Hifi, Amir Mohamed-Youssouf, T. Saadi, Labib Yousef
The knapsack problem arises in real world applications, like transportation, manufacturing systems, finance, and supply chain management. In this paper, we investigate the use of a cooperative particle swarm optimization for solving the quadratic multiple knapsack problem. The standard swarm optimization is reenforced by using a local search procedure, where the swapping operator is introduced that combines items belonging to different bins (knapsacks) according to their critical items. The performance of the method is evaluated on benchmark instances of the literature, where its results are compared to the best available bounds available in the literature.
{"title":"A Cooperative Swarm Optimization-Based Algorithm for the Quadratic Multiple Knapsack Problem","authors":"M. Hifi, Amir Mohamed-Youssouf, T. Saadi, Labib Yousef","doi":"10.1109/CoDIT49905.2020.9263987","DOIUrl":"https://doi.org/10.1109/CoDIT49905.2020.9263987","url":null,"abstract":"The knapsack problem arises in real world applications, like transportation, manufacturing systems, finance, and supply chain management. In this paper, we investigate the use of a cooperative particle swarm optimization for solving the quadratic multiple knapsack problem. The standard swarm optimization is reenforced by using a local search procedure, where the swapping operator is introduced that combines items belonging to different bins (knapsacks) according to their critical items. The performance of the method is evaluated on benchmark instances of the literature, where its results are compared to the best available bounds available in the literature.","PeriodicalId":355781,"journal":{"name":"2020 7th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125314702","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}
Pub Date : 2020-06-29DOI: 10.1109/CoDIT49905.2020.9263883
Pierre Moreau, David Durand, J. Bosche, Michel Lefranc
People’s movements say a lot about their activities. Whether it concerns sports, music (playing an instrument), at work, in re-education, each domain has its own specific moves. However, some of it, such as sports competition, need high-precision movements. Tools are available to measure movements in all sectors. First, sensors are placed on different strategic points on the person’s body that allow us to retrieve temporal data from the body of the user. In this work, no camera is used for motion recognition in order to let the user free to go in different spaces. A considerable number of algorithms help for movement recognition such as deep learning, convolutional neural networks or dynamic modelling, but in most cases, cameras are used. So, our approach consists of two phases. First, model the users thanks to whole-body sensors and save characteristic movements. Second, we still use sensors, to model the test person to find characteristic movements depending on the activity.
{"title":"A motion recognition algorithm using polytopic modeling","authors":"Pierre Moreau, David Durand, J. Bosche, Michel Lefranc","doi":"10.1109/CoDIT49905.2020.9263883","DOIUrl":"https://doi.org/10.1109/CoDIT49905.2020.9263883","url":null,"abstract":"People’s movements say a lot about their activities. Whether it concerns sports, music (playing an instrument), at work, in re-education, each domain has its own specific moves. However, some of it, such as sports competition, need high-precision movements. Tools are available to measure movements in all sectors. First, sensors are placed on different strategic points on the person’s body that allow us to retrieve temporal data from the body of the user. In this work, no camera is used for motion recognition in order to let the user free to go in different spaces. A considerable number of algorithms help for movement recognition such as deep learning, convolutional neural networks or dynamic modelling, but in most cases, cameras are used. So, our approach consists of two phases. First, model the users thanks to whole-body sensors and save characteristic movements. Second, we still use sensors, to model the test person to find characteristic movements depending on the activity.","PeriodicalId":355781,"journal":{"name":"2020 7th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126728249","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}
Pub Date : 2020-06-29DOI: 10.1109/CoDIT49905.2020.9263837
Sebastian-Andrei Avatamanitei, A. Căilean, Adrian Done, M. Dimian, V. Popa
Current research studies envision that the safety and the efficiency of road transportation can be significantly improved with the help of wireless communication technologies that enable inter-vehicle and traffic infrastructure to vehicle data exchange. Nevertheless, some studies also demonstrate that existing wireless technologies can have reliability issues that postpone their market deployment in automotive applications. In this context, this paper provides an analysis concerning the effect of snowfall on the performances of outdoor visible light communications (VLC). Thus, this work provides the results for the experimental evaluation of a 50 meters VLC traffic light to VLC receiver link in snowfall conditions. The experimental results show that moderate snow has a limited effect on VLC performances, whereas intensive snowfall and blizzard episodes significantly affect the Bit Error Ratio. So, the experimental results demonstrate that a physical BER as low as 10-7 can be achieved, whereas snowfall and blizzard can increase the error ratio up to 10-3 values.
{"title":"Experimental Evaluation of Traffic Light to Vehicle Visible Light Communications in Snowfall Conditions","authors":"Sebastian-Andrei Avatamanitei, A. Căilean, Adrian Done, M. Dimian, V. Popa","doi":"10.1109/CoDIT49905.2020.9263837","DOIUrl":"https://doi.org/10.1109/CoDIT49905.2020.9263837","url":null,"abstract":"Current research studies envision that the safety and the efficiency of road transportation can be significantly improved with the help of wireless communication technologies that enable inter-vehicle and traffic infrastructure to vehicle data exchange. Nevertheless, some studies also demonstrate that existing wireless technologies can have reliability issues that postpone their market deployment in automotive applications. In this context, this paper provides an analysis concerning the effect of snowfall on the performances of outdoor visible light communications (VLC). Thus, this work provides the results for the experimental evaluation of a 50 meters VLC traffic light to VLC receiver link in snowfall conditions. The experimental results show that moderate snow has a limited effect on VLC performances, whereas intensive snowfall and blizzard episodes significantly affect the Bit Error Ratio. So, the experimental results demonstrate that a physical BER as low as 10-7 can be achieved, whereas snowfall and blizzard can increase the error ratio up to 10-3 values.","PeriodicalId":355781,"journal":{"name":"2020 7th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115353670","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}
Pub Date : 2020-06-29DOI: 10.1109/CoDIT49905.2020.9263979
Kian Gheitasi, Walter Lucia
In the last decade, several cyber-attacks against Cyber-Physical Systems (CPSs) have been investigated, and different active and passive control solutions have been proposed to assure the absence of undetectable attacks. In this paper, first, we show that most of the studied attacks, if performed for a finite-time duration, can be straightforwardly detected in the post-attack phase. Then, given a proper justification for the existence of finite-time attacks, we show that a finite-time stealthy covert attack can be performed if the attacker takes ad-hoc actions before terminating. We propose a practical implementation of a finite-time covert attack, obtained by combining a finite impulse response receding-horizon filter and reachability arguments. Finally, a simulation example, involving a quadruple-tanks water system, is shown to better clarify the capabilities of the designed attack.
{"title":"A Finite-Time Stealthy Covert Attack Against Cyber-Physical Systems","authors":"Kian Gheitasi, Walter Lucia","doi":"10.1109/CoDIT49905.2020.9263979","DOIUrl":"https://doi.org/10.1109/CoDIT49905.2020.9263979","url":null,"abstract":"In the last decade, several cyber-attacks against Cyber-Physical Systems (CPSs) have been investigated, and different active and passive control solutions have been proposed to assure the absence of undetectable attacks. In this paper, first, we show that most of the studied attacks, if performed for a finite-time duration, can be straightforwardly detected in the post-attack phase. Then, given a proper justification for the existence of finite-time attacks, we show that a finite-time stealthy covert attack can be performed if the attacker takes ad-hoc actions before terminating. We propose a practical implementation of a finite-time covert attack, obtained by combining a finite impulse response receding-horizon filter and reachability arguments. Finally, a simulation example, involving a quadruple-tanks water system, is shown to better clarify the capabilities of the designed attack.","PeriodicalId":355781,"journal":{"name":"2020 7th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"208 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122691816","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}
Pub Date : 2020-06-29DOI: 10.1109/CoDIT49905.2020.9263880
Ralph Karam, M. Salomon, R. Couturier
Since the 1920’s, air traffic is becoming more prevalent by the year which results in a steady increase of the number of aircrafts roaming the airspace. This requires the expansion of the air surveillance systems in order to be able to manage each one of these aircrafts. Such an accommodation is planned to be implemented using different technologies and notably the Automatic Dependent Surveillance Broadcast (ADS-B) system. The ADS-B protocol is based on the idea that aircrafts as well as air traffic controllers communicate with each other using messages. However, for practicality reasons, those messages are not encrypted thus malicious messages can be injected. Hence, these attacks need to be detected to ensure the safety of the protocol. In this paper, we evaluate deep learning architectures for the purpose of detecting anomalous/malicious ADS-B messages, especially LSTM architectures which appear to be the most promising ones.
{"title":"A Comparative Study of Deep Learning Architectures for Detection of Anomalous ADS-B Messages*","authors":"Ralph Karam, M. Salomon, R. Couturier","doi":"10.1109/CoDIT49905.2020.9263880","DOIUrl":"https://doi.org/10.1109/CoDIT49905.2020.9263880","url":null,"abstract":"Since the 1920’s, air traffic is becoming more prevalent by the year which results in a steady increase of the number of aircrafts roaming the airspace. This requires the expansion of the air surveillance systems in order to be able to manage each one of these aircrafts. Such an accommodation is planned to be implemented using different technologies and notably the Automatic Dependent Surveillance Broadcast (ADS-B) system. The ADS-B protocol is based on the idea that aircrafts as well as air traffic controllers communicate with each other using messages. However, for practicality reasons, those messages are not encrypted thus malicious messages can be injected. Hence, these attacks need to be detected to ensure the safety of the protocol. In this paper, we evaluate deep learning architectures for the purpose of detecting anomalous/malicious ADS-B messages, especially LSTM architectures which appear to be the most promising ones.","PeriodicalId":355781,"journal":{"name":"2020 7th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122607175","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}
Pub Date : 2020-06-29DOI: 10.1109/CoDIT49905.2020.9263923
A. Peregudin, I. Furtat
This paper is dedicated to the problem of compensation of bounded external disturbances in the presence of bounded measurement noises. The synthesis of a linear feedback controller minimizing the size of invariant ellipsoids of a closed-loop system is considered. Based on the method of Lyapunov functions, S-procedure and the alternating optimization method, an iterative algorithm for finding optimal controller parameters is proposed. The efficiency of the obtained algorithm is demonstrated.
{"title":"Optimal Compensation of Bounded External Disturbances and Measurement Noises for Linear Systems*","authors":"A. Peregudin, I. Furtat","doi":"10.1109/CoDIT49905.2020.9263923","DOIUrl":"https://doi.org/10.1109/CoDIT49905.2020.9263923","url":null,"abstract":"This paper is dedicated to the problem of compensation of bounded external disturbances in the presence of bounded measurement noises. The synthesis of a linear feedback controller minimizing the size of invariant ellipsoids of a closed-loop system is considered. Based on the method of Lyapunov functions, S-procedure and the alternating optimization method, an iterative algorithm for finding optimal controller parameters is proposed. The efficiency of the obtained algorithm is demonstrated.","PeriodicalId":355781,"journal":{"name":"2020 7th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121889641","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}
Pub Date : 2020-06-29DOI: 10.1109/CoDIT49905.2020.9263879
K. Shalini, D. Vrushabh, K. Sonam
Optimal control theory deals with finding the policy that minimizes the discounted infinite horizon quadratic cost function. For finding the optimal control policy, the solution of the Hamilton-Jacobi-Bellman (HJB) equation must be found i.e. the value function which satisfies the Bellman equation. However, the HJB is a partial differential equation that is difficult to solve for a nonlinear system. The paper employs the approximate dynamic programming method to solve the HJB equation for the deterministic nonlinear discrete-time systems in continuous state and action space. The approximate solution of the HJB is found by the policy iteration algorithm which has the framework of actor-critic architecture. The control policy and value function are approximated using function approximators such as neural network represented in the form of linearly independent basis function. The gradient descent optimization algorithm is employed to tune the weights of the actor and critic network. The control algorithm is implemented for cart pole inverted pendulum system, the effectiveness of this approach is provided in simulations.
{"title":"On-policy Approximate Dynamic Programming for Optimal Control of non-linear systems","authors":"K. Shalini, D. Vrushabh, K. Sonam","doi":"10.1109/CoDIT49905.2020.9263879","DOIUrl":"https://doi.org/10.1109/CoDIT49905.2020.9263879","url":null,"abstract":"Optimal control theory deals with finding the policy that minimizes the discounted infinite horizon quadratic cost function. For finding the optimal control policy, the solution of the Hamilton-Jacobi-Bellman (HJB) equation must be found i.e. the value function which satisfies the Bellman equation. However, the HJB is a partial differential equation that is difficult to solve for a nonlinear system. The paper employs the approximate dynamic programming method to solve the HJB equation for the deterministic nonlinear discrete-time systems in continuous state and action space. The approximate solution of the HJB is found by the policy iteration algorithm which has the framework of actor-critic architecture. The control policy and value function are approximated using function approximators such as neural network represented in the form of linearly independent basis function. The gradient descent optimization algorithm is employed to tune the weights of the actor and critic network. The control algorithm is implemented for cart pole inverted pendulum system, the effectiveness of this approach is provided in simulations.","PeriodicalId":355781,"journal":{"name":"2020 7th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117266429","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：