Pub Date : 2020-09-01DOI: 10.1109/CSIEC49655.2020.9237299
Azadeh Haratiannezhadi, S. Setayeshi, J. Hatami
Human attention is a limited resource that makes it valuable. Moreover, it is the first step in human brain cognition. Multiple factors affect their performance. The cognitive model of attention helps to understand the complexity of its role and involved factors. This study aimed at developing a novel machine-learning system of human care by different psychological tasks and collected information, which able to predict attention scores. A web-based system is developed for multiple cognitive tasks to gather information. The proposed model evaluates the human attention performance level by the Attentional Network Test (ANT). Data were collected from 62 participants. Decision tree, AdaBoost, and Gradient boosting models were developed, and the hyperparameters model was tuned. The model selection is based on finding performance. The performance was analyzed using Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE). AdaBoost regression shows the best performance with MAE: 0.69 and RMSE: 3.9198 in comparison with other models. The AdaBoost model ensures the rapid and accurate estimation performance of attention.
{"title":"Boosting Model of Attention Network Task","authors":"Azadeh Haratiannezhadi, S. Setayeshi, J. Hatami","doi":"10.1109/CSIEC49655.2020.9237299","DOIUrl":"https://doi.org/10.1109/CSIEC49655.2020.9237299","url":null,"abstract":"Human attention is a limited resource that makes it valuable. Moreover, it is the first step in human brain cognition. Multiple factors affect their performance. The cognitive model of attention helps to understand the complexity of its role and involved factors. This study aimed at developing a novel machine-learning system of human care by different psychological tasks and collected information, which able to predict attention scores. A web-based system is developed for multiple cognitive tasks to gather information. The proposed model evaluates the human attention performance level by the Attentional Network Test (ANT). Data were collected from 62 participants. Decision tree, AdaBoost, and Gradient boosting models were developed, and the hyperparameters model was tuned. The model selection is based on finding performance. The performance was analyzed using Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE). AdaBoost regression shows the best performance with MAE: 0.69 and RMSE: 3.9198 in comparison with other models. The AdaBoost model ensures the rapid and accurate estimation performance of attention.","PeriodicalId":373376,"journal":{"name":"2020 4th Conference on Swarm Intelligence and Evolutionary Computation (CSIEC)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125408419","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 : 2020-09-01DOI: 10.1109/CSIEC49655.2020.9237316
M. Soleimanpour-moghadam, H. Nezamabadi-pour
In this paper, a Discrete Genetic Algorithm (DGA) is proposed for solving the task allocation problem in a multi-robot scenario. In the proposed DGA, a discrete population generation is proposed to adjust the genetic algorithm for solving the task allocation problem of a multi-robot system which aims to maintain the balance of exploration and exploitation. In the proposed scenario, the defined problem consists of assigning the robots to the known targets in two-dimensional search space. The scalability of the proposed DGA algorithm is tested in terms of the number of robots. The comparison confirms the superiority of the proposed method compared to the existing methods.
{"title":"Discrete Genetic Algorithm for Solving Task Allocation of Multi-robot Systems","authors":"M. Soleimanpour-moghadam, H. Nezamabadi-pour","doi":"10.1109/CSIEC49655.2020.9237316","DOIUrl":"https://doi.org/10.1109/CSIEC49655.2020.9237316","url":null,"abstract":"In this paper, a Discrete Genetic Algorithm (DGA) is proposed for solving the task allocation problem in a multi-robot scenario. In the proposed DGA, a discrete population generation is proposed to adjust the genetic algorithm for solving the task allocation problem of a multi-robot system which aims to maintain the balance of exploration and exploitation. In the proposed scenario, the defined problem consists of assigning the robots to the known targets in two-dimensional search space. The scalability of the proposed DGA algorithm is tested in terms of the number of robots. The comparison confirms the superiority of the proposed method compared to the existing methods.","PeriodicalId":373376,"journal":{"name":"2020 4th Conference on Swarm Intelligence and Evolutionary Computation (CSIEC)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115851056","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 : 2020-09-01DOI: 10.1109/CSIEC49655.2020.9237318
Seyed Mohamad Ali Tousi, Abbas Mostafanasab, M. Teshnehlab
In this work, a new particle swarm optimization (PSO)-based optimization algorithm, and the idea of a running match is introduced and employed in a non-linear system PID controller design. This algorithm aims to modify the formula of velocity calculating of the general PSO method to increase the diversity of the searching process. In this process of designing an optimal PID controller for a non-linear system, the three gains of the PID controller form a particle, which is a parameter vector and will be updated iteratively. Many of those particles then form a population. To reach the PID gains which are optimum, using modified velocity updating formula and position updating formula, the position of all particles of the population will be moved into the optimization direction. In the meanwhile, an objective function may be minimized as the performance of the controller get improved. To corroborate the controller functioning of this method, a non-linear system known as inverted pendulum will be controlled by the designed PID controller. The results confirm that the new method can show excellent performance in the non-linear PID controller design task.
{"title":"Design of Self Tuning PID Controller Based on Competitional PSO","authors":"Seyed Mohamad Ali Tousi, Abbas Mostafanasab, M. Teshnehlab","doi":"10.1109/CSIEC49655.2020.9237318","DOIUrl":"https://doi.org/10.1109/CSIEC49655.2020.9237318","url":null,"abstract":"In this work, a new particle swarm optimization (PSO)-based optimization algorithm, and the idea of a running match is introduced and employed in a non-linear system PID controller design. This algorithm aims to modify the formula of velocity calculating of the general PSO method to increase the diversity of the searching process. In this process of designing an optimal PID controller for a non-linear system, the three gains of the PID controller form a particle, which is a parameter vector and will be updated iteratively. Many of those particles then form a population. To reach the PID gains which are optimum, using modified velocity updating formula and position updating formula, the position of all particles of the population will be moved into the optimization direction. In the meanwhile, an objective function may be minimized as the performance of the controller get improved. To corroborate the controller functioning of this method, a non-linear system known as inverted pendulum will be controlled by the designed PID controller. The results confirm that the new method can show excellent performance in the non-linear PID controller design task.","PeriodicalId":373376,"journal":{"name":"2020 4th Conference on Swarm Intelligence and Evolutionary Computation (CSIEC)","volume":"184 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114433082","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 : 2020-09-01DOI: 10.1109/csiec49655.2020.9237301
{"title":"International Fuzzy Systems Association","authors":"","doi":"10.1109/csiec49655.2020.9237301","DOIUrl":"https://doi.org/10.1109/csiec49655.2020.9237301","url":null,"abstract":"","PeriodicalId":373376,"journal":{"name":"2020 4th Conference on Swarm Intelligence and Evolutionary Computation (CSIEC)","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123234568","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 : 2020-09-01DOI: 10.1109/CSIEC49655.2020.9237308
Mohammad Akafan, B. Minaei-Bidgoli, A. Bagheri
The social network embodies real-life social graphs. Detecting communities or clusters from these graphs is an ill-posed difficult task. The communities are identified using the adjacent nodes that have shared edges and similar features. One of the principal concerns after community detection is to identify the active nodes in a network who attend several communities. So, finding communities that are overlapped in a social network is an important topic in social network analysis. This paper introduces a multiagent algorithm particle swarm optimization. The proposed algorithm detects overlapping as well as non-overlapping communities. Following the detection of overlapping communities, this algorithm can identify those nodes leading to overlapping and ultimately it can determine the affiliation ratio of each node to the given community. The algorithm uses a special type of coding to identify the number of communities without any prior knowledge. In my method, the modularity measure is used as a fitness function to enhance particle swarm. Several tests show that the proposed algorithm which is called Fuzzy Overlapping Community Detection based on Multi-Agent Particle Swarm Optimization (FOCDMAPSO), is superior compared with four other competitive algorithms. This algorithm is implemented over six well-known datasets in the literature. Our algorithm is accomplished in detecting nodes in overlapping communities with high accurateness. Furthermore, the proposed algorithm can detect the affiliation percentage of each node that leads to overlapping communities which is a novel feature in the area of the social network.
{"title":"A Multi-agent PSO Algorithm to Determine the Membership percentage of Each Node in Overlapping Community in Social Networks","authors":"Mohammad Akafan, B. Minaei-Bidgoli, A. Bagheri","doi":"10.1109/CSIEC49655.2020.9237308","DOIUrl":"https://doi.org/10.1109/CSIEC49655.2020.9237308","url":null,"abstract":"The social network embodies real-life social graphs. Detecting communities or clusters from these graphs is an ill-posed difficult task. The communities are identified using the adjacent nodes that have shared edges and similar features. One of the principal concerns after community detection is to identify the active nodes in a network who attend several communities. So, finding communities that are overlapped in a social network is an important topic in social network analysis. This paper introduces a multiagent algorithm particle swarm optimization. The proposed algorithm detects overlapping as well as non-overlapping communities. Following the detection of overlapping communities, this algorithm can identify those nodes leading to overlapping and ultimately it can determine the affiliation ratio of each node to the given community. The algorithm uses a special type of coding to identify the number of communities without any prior knowledge. In my method, the modularity measure is used as a fitness function to enhance particle swarm. Several tests show that the proposed algorithm which is called Fuzzy Overlapping Community Detection based on Multi-Agent Particle Swarm Optimization (FOCDMAPSO), is superior compared with four other competitive algorithms. This algorithm is implemented over six well-known datasets in the literature. Our algorithm is accomplished in detecting nodes in overlapping communities with high accurateness. Furthermore, the proposed algorithm can detect the affiliation percentage of each node that leads to overlapping communities which is a novel feature in the area of the social network.","PeriodicalId":373376,"journal":{"name":"2020 4th Conference on Swarm Intelligence and Evolutionary Computation (CSIEC)","volume":"41 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120866863","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 : 2020-09-01DOI: 10.1109/CSIEC49655.2020.9237319
M. Shahrouzi, A. Salehi
Structural sizing problems are treated as rewarding optimization tasks characterized by non-differentiable constraints and objective functions. In this category, a number of new large-scale space trusses are offered here as structural benchmarks to declare effectiveness and efficiency of zero-order optimization methods. Furthermore, an optimization method is offered for such a task utilizing opposition-based learning that switches between certain vectors directed to the best individual. The proposed algorithm is developed with simple yet efficient operators as a specific-parameter-Iess method. Although it does not bring about high tuning effort for control parameters, numerical simulations exhibit competitive performance of the proposed method in structural sizing problems compared with recent meta-heuristic algorithms.
{"title":"Design of Large-Scale Structures by an enhanced Metaheuristic utilizing Opposition-based Learning","authors":"M. Shahrouzi, A. Salehi","doi":"10.1109/CSIEC49655.2020.9237319","DOIUrl":"https://doi.org/10.1109/CSIEC49655.2020.9237319","url":null,"abstract":"Structural sizing problems are treated as rewarding optimization tasks characterized by non-differentiable constraints and objective functions. In this category, a number of new large-scale space trusses are offered here as structural benchmarks to declare effectiveness and efficiency of zero-order optimization methods. Furthermore, an optimization method is offered for such a task utilizing opposition-based learning that switches between certain vectors directed to the best individual. The proposed algorithm is developed with simple yet efficient operators as a specific-parameter-Iess method. Although it does not bring about high tuning effort for control parameters, numerical simulations exhibit competitive performance of the proposed method in structural sizing problems compared with recent meta-heuristic algorithms.","PeriodicalId":373376,"journal":{"name":"2020 4th Conference on Swarm Intelligence and Evolutionary Computation (CSIEC)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124605278","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 : 2020-09-01DOI: 10.1109/CSIEC49655.2020.9237309
Maryam Tehrani Zadeh, F. Rad, M. Yousefi, H. Hessami, Matin Rahmatian
Permutation is one of the widely used methods in Multi-Criteria Decision Making (MCDM) for prioritizing alternatives. Making the best decision will become more challenging by growing the number of criteria. High computational cost is the main disadvantage of this method. In this paper, an innovative algorithm is applied for obtaining an optimized solution for the permutation method. In this research, a combined algorithm of particle swarm optimization (PSO) and simulated annealing (SA) is proposed and implemented for reducing the high calculation costs. This combined algorithm possesses the higher convergence properties of PSO in finding the best answer as well as holds the SA feature of avoiding from facing local minimum. This algorithm investigated two sets of numeric data. The results verify its highest efficiency in detecting an optimized sequence of prior alternatives choices at a shorter time. This work proved that the suggested methodology could be employed with high confidence for common permutation problems in case of the presence of many alternatives.
{"title":"Modification of Permutation Method in Multi-Criteria Decision Making Using PSO-SA","authors":"Maryam Tehrani Zadeh, F. Rad, M. Yousefi, H. Hessami, Matin Rahmatian","doi":"10.1109/CSIEC49655.2020.9237309","DOIUrl":"https://doi.org/10.1109/CSIEC49655.2020.9237309","url":null,"abstract":"Permutation is one of the widely used methods in Multi-Criteria Decision Making (MCDM) for prioritizing alternatives. Making the best decision will become more challenging by growing the number of criteria. High computational cost is the main disadvantage of this method. In this paper, an innovative algorithm is applied for obtaining an optimized solution for the permutation method. In this research, a combined algorithm of particle swarm optimization (PSO) and simulated annealing (SA) is proposed and implemented for reducing the high calculation costs. This combined algorithm possesses the higher convergence properties of PSO in finding the best answer as well as holds the SA feature of avoiding from facing local minimum. This algorithm investigated two sets of numeric data. The results verify its highest efficiency in detecting an optimized sequence of prior alternatives choices at a shorter time. This work proved that the suggested methodology could be employed with high confidence for common permutation problems in case of the presence of many alternatives.","PeriodicalId":373376,"journal":{"name":"2020 4th Conference on Swarm Intelligence and Evolutionary Computation (CSIEC)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114494678","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 : 2020-09-01DOI: 10.1109/CSIEC49655.2020.9237311
M. Soleimanpour-moghadam, Mohammad Askarizade, S. Talebi
Multi-relay networking is known to have remarkable ability to increase network capacity and transmission quality. However, the rate maximization of amplify─and─forward multi-antenna in cooperative networks poses a nonlinear and nonconvex optimization challenge with nonlinear constraints that requires a highly complex solution. Based on mathematical principles, we unveil a novel method that reduces the complexity of the multi-antenna multi-relay rate maximization problem to an equivalent linear scalar expression. Having simplified the problem, we then apply the Branch and Bound algorithm as a known global optimization method to solve the expression.
{"title":"Simplified Power Allocation method for AF-Based Multi-Antennas Multiple Relays Networks","authors":"M. Soleimanpour-moghadam, Mohammad Askarizade, S. Talebi","doi":"10.1109/CSIEC49655.2020.9237311","DOIUrl":"https://doi.org/10.1109/CSIEC49655.2020.9237311","url":null,"abstract":"Multi-relay networking is known to have remarkable ability to increase network capacity and transmission quality. However, the rate maximization of amplify─and─forward multi-antenna in cooperative networks poses a nonlinear and nonconvex optimization challenge with nonlinear constraints that requires a highly complex solution. Based on mathematical principles, we unveil a novel method that reduces the complexity of the multi-antenna multi-relay rate maximization problem to an equivalent linear scalar expression. Having simplified the problem, we then apply the Branch and Bound algorithm as a known global optimization method to solve the expression.","PeriodicalId":373376,"journal":{"name":"2020 4th Conference on Swarm Intelligence and Evolutionary Computation (CSIEC)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114837379","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 : 2020-09-01DOI: 10.1109/CSIEC49655.2020.9237305
Nasibeh Rady Raz, M. Akbarzadeh-T., S. Setayeshi
Medical Delivery which is the propagation of indispensable nutrition i.e. oxygen in the body is used specifically in the field of Emergency Medicine (EM). In the EM, drug and nutrition delivery as early as possible to the target organ is the key factor. In this paper, the swarm of biosensors is injected into the body in the two groups of carriers and external trackable nodes. The carrier nodes deliver and spread the material to the target, while the trackable nodes are considered as the anchor points with the known coordination and bonding ability to the certain organs. Here, to localize the carrier node, we perform two estimation algorithms. As soon as the carriers are located in the area of anchor points, their local nutrition propagation is started to the organ in the emergency state. The PF approach usage in the proposed method leads to a better result in organ survival and precise node localization.
{"title":"Biosensors Localization for Swarm Medical Delivery","authors":"Nasibeh Rady Raz, M. Akbarzadeh-T., S. Setayeshi","doi":"10.1109/CSIEC49655.2020.9237305","DOIUrl":"https://doi.org/10.1109/CSIEC49655.2020.9237305","url":null,"abstract":"Medical Delivery which is the propagation of indispensable nutrition i.e. oxygen in the body is used specifically in the field of Emergency Medicine (EM). In the EM, drug and nutrition delivery as early as possible to the target organ is the key factor. In this paper, the swarm of biosensors is injected into the body in the two groups of carriers and external trackable nodes. The carrier nodes deliver and spread the material to the target, while the trackable nodes are considered as the anchor points with the known coordination and bonding ability to the certain organs. Here, to localize the carrier node, we perform two estimation algorithms. As soon as the carriers are located in the area of anchor points, their local nutrition propagation is started to the organ in the emergency state. The PF approach usage in the proposed method leads to a better result in organ survival and precise node localization.","PeriodicalId":373376,"journal":{"name":"2020 4th Conference on Swarm Intelligence and Evolutionary Computation (CSIEC)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120987751","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：