Pub Date : 2017-02-01DOI: 10.1109/ICACI.2017.7974484
Mudassir Jann, S. Anavatti, Sumana Biswas
This paper aims at investigating the dynamic path planning of a multi-agent autonomous swarm to execute a task of traversing a certain terrain with specified start and goal state. The area under consideration also includes a specified number of secondary goals/checkpoints to be explored/visited by at-least one vehicle of the swarm while avoiding the static and dynamic obstacles. The decision about the traversal to the checkpoints is made by the swarm itself, thus providing a decentralized control. D∗lite is employed for dynamic path planning. Numerical simulation results are presented to validate the path planning algorithm with different number of agents and obstacles.
{"title":"Path planning for multi-vehicle autonomous swarms in dynamic environment","authors":"Mudassir Jann, S. Anavatti, Sumana Biswas","doi":"10.1109/ICACI.2017.7974484","DOIUrl":"https://doi.org/10.1109/ICACI.2017.7974484","url":null,"abstract":"This paper aims at investigating the dynamic path planning of a multi-agent autonomous swarm to execute a task of traversing a certain terrain with specified start and goal state. The area under consideration also includes a specified number of secondary goals/checkpoints to be explored/visited by at-least one vehicle of the swarm while avoiding the static and dynamic obstacles. The decision about the traversal to the checkpoints is made by the swarm itself, thus providing a decentralized control. D∗lite is employed for dynamic path planning. Numerical simulation results are presented to validate the path planning algorithm with different number of agents and obstacles.","PeriodicalId":260701,"journal":{"name":"2017 Ninth International Conference on Advanced Computational Intelligence (ICACI)","volume":"268 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116555451","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 : 2017-02-01DOI: 10.1109/ICACI.2017.7974494
Yinzhe Wu, J. Zhong, Ling Liu
In this paper, we study the global mean square exponential synchronization of stochastic neural networks with time-varying delays (MSDNN). Two types of control scheme are served to synchronize a sort of MSDNN. A variety of synchronization qualifications depended on system structure are established by the means of Lyapunov function and itô formula. Some statistical examples are supplied to authenticate the results.
{"title":"Global mean square exponential synchronization of stochastic neural networks with time-varying delays","authors":"Yinzhe Wu, J. Zhong, Ling Liu","doi":"10.1109/ICACI.2017.7974494","DOIUrl":"https://doi.org/10.1109/ICACI.2017.7974494","url":null,"abstract":"In this paper, we study the global mean square exponential synchronization of stochastic neural networks with time-varying delays (MSDNN). Two types of control scheme are served to synchronize a sort of MSDNN. A variety of synchronization qualifications depended on system structure are established by the means of Lyapunov function and itô formula. Some statistical examples are supplied to authenticate the results.","PeriodicalId":260701,"journal":{"name":"2017 Ninth International Conference on Advanced Computational Intelligence (ICACI)","volume":"7 21","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113946474","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 : 2017-02-01DOI: 10.1109/ICACI.2017.7974517
Chaojie Li, Chen Liu, Xinghuo Yu, Xing He, Huiwei Wang
The dynamical economic dispatch problem is studied and reformulated by a distributed interior point method via a logarithmic barrier. By the facilitation of the graph Laplacian, a fully distributed primal-dual dynamical multiagent system is developed in a smart grid scenario to seek the saddle point of dynamical economic dispatch which coincides with the optimal solution. Specifically, to avoid high singularity of the θ-logarithmic barrier at boundary, an adaptive parameter switching strategy is introduced into this dynamical multiagent system. The convergence rate of the distributed algorithm is obtained. The good performance of this new dynamical system is verified by the IEEE 6-bus test system based simulation.
{"title":"Distributed consensus based optimization in dynamical economic dispatch","authors":"Chaojie Li, Chen Liu, Xinghuo Yu, Xing He, Huiwei Wang","doi":"10.1109/ICACI.2017.7974517","DOIUrl":"https://doi.org/10.1109/ICACI.2017.7974517","url":null,"abstract":"The dynamical economic dispatch problem is studied and reformulated by a distributed interior point method via a logarithmic barrier. By the facilitation of the graph Laplacian, a fully distributed primal-dual dynamical multiagent system is developed in a smart grid scenario to seek the saddle point of dynamical economic dispatch which coincides with the optimal solution. Specifically, to avoid high singularity of the θ-logarithmic barrier at boundary, an adaptive parameter switching strategy is introduced into this dynamical multiagent system. The convergence rate of the distributed algorithm is obtained. The good performance of this new dynamical system is verified by the IEEE 6-bus test system based simulation.","PeriodicalId":260701,"journal":{"name":"2017 Ninth International Conference on Advanced Computational Intelligence (ICACI)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122533841","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 : 2017-02-01DOI: 10.1109/ICACI.2017.7974518
Cheng-Yi Wang, Shyi-Ming Chen
This paper proposes a multiple attribute decision making (MADM) method using IVIFSs, the linear programming methodology, and the TOPSIS method, where the linear programming methodology is used to obtain optimal weights of attributes. It is very useful for handling MADM problems.
{"title":"A new multiple attribute decision making method based on interval-valued intuitionistic fuzzy sets, linear programming methodology, and the TOPSIS method","authors":"Cheng-Yi Wang, Shyi-Ming Chen","doi":"10.1109/ICACI.2017.7974518","DOIUrl":"https://doi.org/10.1109/ICACI.2017.7974518","url":null,"abstract":"This paper proposes a multiple attribute decision making (MADM) method using IVIFSs, the linear programming methodology, and the TOPSIS method, where the linear programming methodology is used to obtain optimal weights of attributes. It is very useful for handling MADM problems.","PeriodicalId":260701,"journal":{"name":"2017 Ninth International Conference on Advanced Computational Intelligence (ICACI)","volume":"199 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122651301","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}
On account of the substation is a basis and important element of the power system, its maintenance plays a pivotal role in the stable operation of power grid. As the maintainer of the substation, the on-site staffs work long-term in strong electromagnetic field environment. Therefore, it is necessary to wear the working clothes strictly. In order to strengthen the working clothes wearing circumstance supervision, its better to carry out the real-time supervision on the on-site staffs. In this paper, a video-based working clothes wearing circumstance detection method was put forward. Firstly, we extract characteristics by HOG(Histogram of Oriented Gradient) method and the color spatial distribution compactness presented in this paper. Secondly, the SVM(Support Vector Machine) classifier is trained to realize the substation maintainer detection. Finally, we model the electricity working clothes in the HSV(Hue, Saturation, Value) color space and combine the performance characteristics to get the final results. The experimental results demonstrate that this method has a high accuracy in the substation surveillance video.
变电站是电力系统的基础和重要组成部分，其维护对电网的稳定运行起着举足轻重的作用。现场工作人员作为变电站的维护人员，长期在强电磁场环境中工作。因此，严格穿着工作服是必要的。为了加强工作服穿着情况的监管，最好对现场工作人员进行实时监管。提出了一种基于视频的工作服穿着情况检测方法。首先，利用HOG(Histogram of Oriented Gradient)方法和本文提出的色彩空间分布紧密度提取特征;其次，训练支持向量机分类器，实现变电站维修人员检测;最后，在HSV(Hue, Saturation, Value)色彩空间中对电工作服进行建模，并结合性能特征得到最终结果。实验结果表明，该方法在变电站监控视频中具有较高的准确率。
{"title":"Working clothes detection of substation workers based on the image processing","authors":"Jie Li, Tianzheng Wang, Yongxiang Li, Yun Tian, Shuai Wang, Muliu Zhang, Yongjie Zhai, Shiying Sun, Xiaoguang Zhao","doi":"10.1109/ICACI.2017.7974505","DOIUrl":"https://doi.org/10.1109/ICACI.2017.7974505","url":null,"abstract":"On account of the substation is a basis and important element of the power system, its maintenance plays a pivotal role in the stable operation of power grid. As the maintainer of the substation, the on-site staffs work long-term in strong electromagnetic field environment. Therefore, it is necessary to wear the working clothes strictly. In order to strengthen the working clothes wearing circumstance supervision, its better to carry out the real-time supervision on the on-site staffs. In this paper, a video-based working clothes wearing circumstance detection method was put forward. Firstly, we extract characteristics by HOG(Histogram of Oriented Gradient) method and the color spatial distribution compactness presented in this paper. Secondly, the SVM(Support Vector Machine) classifier is trained to realize the substation maintainer detection. Finally, we model the electricity working clothes in the HSV(Hue, Saturation, Value) color space and combine the performance characteristics to get the final results. The experimental results demonstrate that this method has a high accuracy in the substation surveillance video.","PeriodicalId":260701,"journal":{"name":"2017 Ninth International Conference on Advanced Computational Intelligence (ICACI)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125654232","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 : 2017-02-01DOI: 10.1109/ICACI.2017.7974512
Ahmad Jobran Al-Mahasneh, S. G. Anavatu, M. Garratt
This research focuses on studying the effect of using evolutionary algorithms in improving neural network capabilities in identification of non-linear multi-input and multi-output dynamic systems such as a quadcopter. In addition, comparison of the different neural network based approaches is carried out in order to reveal the variations among the different methods. The results show that using evolutionary algorithms in training a neural network enhanced the system identification accuracy. Furthermore, the results show that differential evolution neural networks have promising potential to be used in multi-input multi-output system identification.
{"title":"Nonlinear multi-input multi-output system identification using neuro-evolutionary methods for a quadcopter","authors":"Ahmad Jobran Al-Mahasneh, S. G. Anavatu, M. Garratt","doi":"10.1109/ICACI.2017.7974512","DOIUrl":"https://doi.org/10.1109/ICACI.2017.7974512","url":null,"abstract":"This research focuses on studying the effect of using evolutionary algorithms in improving neural network capabilities in identification of non-linear multi-input and multi-output dynamic systems such as a quadcopter. In addition, comparison of the different neural network based approaches is carried out in order to reveal the variations among the different methods. The results show that using evolutionary algorithms in training a neural network enhanced the system identification accuracy. Furthermore, the results show that differential evolution neural networks have promising potential to be used in multi-input multi-output system identification.","PeriodicalId":260701,"journal":{"name":"2017 Ninth International Conference on Advanced Computational Intelligence (ICACI)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124987754","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 : 2017-02-01DOI: 10.1109/ICACI.2017.7974503
Junpeng Ma, Lidan Wang, Jiening Wu, Shukai Duan
A novel three-dimensional multi-scroll nonlinear model is successfully designed in the short article. Several specific chaotic features of the new model, such as the initial value sensitivity, fractal dimension, Lyapunov exponent, complexity of this novel model are introduced. Moreover, the nonlinear electronic circuit of this system is realized by PSPICE. Finally, the synchronization scheme via chaotic control theory is also designed. And the outcomes of this experiment are in conformance with the corresponding numeric calculation, which verifies the practicability of the new chaotic model.
{"title":"A multi-scroll chaotic system with novel attractors: Dynamics, circuit implementation and synchronization","authors":"Junpeng Ma, Lidan Wang, Jiening Wu, Shukai Duan","doi":"10.1109/ICACI.2017.7974503","DOIUrl":"https://doi.org/10.1109/ICACI.2017.7974503","url":null,"abstract":"A novel three-dimensional multi-scroll nonlinear model is successfully designed in the short article. Several specific chaotic features of the new model, such as the initial value sensitivity, fractal dimension, Lyapunov exponent, complexity of this novel model are introduced. Moreover, the nonlinear electronic circuit of this system is realized by PSPICE. Finally, the synchronization scheme via chaotic control theory is also designed. And the outcomes of this experiment are in conformance with the corresponding numeric calculation, which verifies the practicability of the new chaotic model.","PeriodicalId":260701,"journal":{"name":"2017 Ninth International Conference on Advanced Computational Intelligence (ICACI)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121638879","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 : 2017-02-01DOI: 10.1109/ICACI.2017.7974501
Marwa Sharawi, E. Emary
This work introduces a cluster head selection optimization model in wireless sensor networks (WSN). It applies the grey wolf optimization. The optimization of WSN cluster heads greatly influences the network life time. Grey wolf optimization(GWO) is a recently proposed optimizer that has a variety of successful applications. Therefore, adapted and applied in here to solve the CH selection problem. Suitable fitness function were employed to ensure coverage of the WSN and is fed to the GWO to find its optimum. Results of the introduced model is compared with the LEACH routing protocol. Four different deployments of the WSN are examined. Lifetime, residual energy and network throughput performance indicators are examined in our experiments as assessment indicators. The introduced system outperforms the LEACH in almost all topologies using the different indicators.
{"title":"Impact of grey wolf optimization on WSN cluster formation and lifetime expansion","authors":"Marwa Sharawi, E. Emary","doi":"10.1109/ICACI.2017.7974501","DOIUrl":"https://doi.org/10.1109/ICACI.2017.7974501","url":null,"abstract":"This work introduces a cluster head selection optimization model in wireless sensor networks (WSN). It applies the grey wolf optimization. The optimization of WSN cluster heads greatly influences the network life time. Grey wolf optimization(GWO) is a recently proposed optimizer that has a variety of successful applications. Therefore, adapted and applied in here to solve the CH selection problem. Suitable fitness function were employed to ensure coverage of the WSN and is fed to the GWO to find its optimum. Results of the introduced model is compared with the LEACH routing protocol. Four different deployments of the WSN are examined. Lifetime, residual energy and network throughput performance indicators are examined in our experiments as assessment indicators. The introduced system outperforms the LEACH in almost all topologies using the different indicators.","PeriodicalId":260701,"journal":{"name":"2017 Ninth International Conference on Advanced Computational Intelligence (ICACI)","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116041130","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 : 2017-02-01DOI: 10.1109/ICACI.2017.7974520
Mohamed Zied Chaari, M. Lahiani, H. Ghariani
The purpose of this paper is to present a new solution to produce DC energy from electromagnetic radiation generated by compact fluorescent lamps and stored in the super capacitor bank. The proposed device is based on a magnetic coupling between flat wound induction coil and pollution generator represented in the compact florescent lamp. Most of the energy will be stored in the super capacitor and then in battery through DC/DC Up convertor. It is shown that more than 0.91W can be generated from a 20W compact fluorescent lamp. So the proposed electronic device can absorb pollution at home, protect our children from radiation, and recycle EM radiation for charging battery. Besides, we can use it for many other applications.
{"title":"Energy harvesting from electromagnetic radiation emissions by compact flouresent lamp","authors":"Mohamed Zied Chaari, M. Lahiani, H. Ghariani","doi":"10.1109/ICACI.2017.7974520","DOIUrl":"https://doi.org/10.1109/ICACI.2017.7974520","url":null,"abstract":"The purpose of this paper is to present a new solution to produce DC energy from electromagnetic radiation generated by compact fluorescent lamps and stored in the super capacitor bank. The proposed device is based on a magnetic coupling between flat wound induction coil and pollution generator represented in the compact florescent lamp. Most of the energy will be stored in the super capacitor and then in battery through DC/DC Up convertor. It is shown that more than 0.91W can be generated from a 20W compact fluorescent lamp. So the proposed electronic device can absorb pollution at home, protect our children from radiation, and recycle EM radiation for charging battery. Besides, we can use it for many other applications.","PeriodicalId":260701,"journal":{"name":"2017 Ninth International Conference on Advanced Computational Intelligence (ICACI)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117240941","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 : 2017-02-01DOI: 10.1109/ICACI.2017.7974500
G. Tambouratzis
This article investigates the evolution of the velocity vector as the AdPSO (Adaptive PSO) algorithm optimizes a set of parameters through a number of epochs. Experimental results have shown that when using a swarm to find the optimal solution to a specific natural language processing (NLP) application gradually the velocity vector is decreased towards a very small value that causes the particles to switch from exploration (i.e., the attempt to determine radically new solutions) towards exploitation (search of solutions that are close to those already identified). Based on this observation, a study is carried out to determine whether the velocity vector may be handled in a more efficient manner. An algorithm for reinitializing the velocity of swarm particles is proposed, which improves the exploration of the swarm, by reenergizing particles that have very low velocities. Also, the effect of bounding the initial velocity of particles is studied, to determine whether improved optimization performance can be achieved. The effectiveness of the velocity reinitialisation mechanism is further examined by application to a selection of benchmark test functions. These experimental results are supplemented by relevant statistical tests that indicate a significant improvement in many cases.
{"title":"Modifying the velocity in adaptive PSO to improve optimisation performance","authors":"G. Tambouratzis","doi":"10.1109/ICACI.2017.7974500","DOIUrl":"https://doi.org/10.1109/ICACI.2017.7974500","url":null,"abstract":"This article investigates the evolution of the velocity vector as the AdPSO (Adaptive PSO) algorithm optimizes a set of parameters through a number of epochs. Experimental results have shown that when using a swarm to find the optimal solution to a specific natural language processing (NLP) application gradually the velocity vector is decreased towards a very small value that causes the particles to switch from exploration (i.e., the attempt to determine radically new solutions) towards exploitation (search of solutions that are close to those already identified). Based on this observation, a study is carried out to determine whether the velocity vector may be handled in a more efficient manner. An algorithm for reinitializing the velocity of swarm particles is proposed, which improves the exploration of the swarm, by reenergizing particles that have very low velocities. Also, the effect of bounding the initial velocity of particles is studied, to determine whether improved optimization performance can be achieved. The effectiveness of the velocity reinitialisation mechanism is further examined by application to a selection of benchmark test functions. These experimental results are supplemented by relevant statistical tests that indicate a significant improvement in many cases.","PeriodicalId":260701,"journal":{"name":"2017 Ninth International Conference on Advanced Computational Intelligence (ICACI)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117116896","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：