Pub Date : 1900-01-01DOI: 10.1109/ISCO.2016.7726923
G. Murthy, B. Anuradha, S. Krishna, B. Reddy, R. Sithara
Identification of objects of interest is most sought problem in computer vision related applications. This is in particular needed, when large volumes of data are available and a decision is to be made regarding relevance of an object to a specific region. In medical related applications, analysis of structural variations is much required for disease identification and progression. Manually delineating the affected portions is time consuming and prone to error. In the current paper, a novel algorithm is proposed to extract most significant tissue of human brain, Hippocampus. The algorithm uses labeling algorithm which is simple of its kind and does not need any prior knowledge. The segmented results are further compared with ground truth image using most prominent similarity indices, Dice Similarity Coefficient (DSC) and Jaccard coefficient.
{"title":"Slice specific atlas independent hippocampus segmentation using simple labeling","authors":"G. Murthy, B. Anuradha, S. Krishna, B. Reddy, R. Sithara","doi":"10.1109/ISCO.2016.7726923","DOIUrl":"https://doi.org/10.1109/ISCO.2016.7726923","url":null,"abstract":"Identification of objects of interest is most sought problem in computer vision related applications. This is in particular needed, when large volumes of data are available and a decision is to be made regarding relevance of an object to a specific region. In medical related applications, analysis of structural variations is much required for disease identification and progression. Manually delineating the affected portions is time consuming and prone to error. In the current paper, a novel algorithm is proposed to extract most significant tissue of human brain, Hippocampus. The algorithm uses labeling algorithm which is simple of its kind and does not need any prior knowledge. The segmented results are further compared with ground truth image using most prominent similarity indices, Dice Similarity Coefficient (DSC) and Jaccard coefficient.","PeriodicalId":320699,"journal":{"name":"2016 10th International Conference on Intelligent Systems and Control (ISCO)","volume":"1 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":"132150015","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 : 1900-01-01DOI: 10.1109/ISCO.2016.7727007
Dushyant S. Potdar, T. Pattewar
Data mining is nothing but the process of automatically searching large stores of data to discover patterns and trends that go beyond simple analysis. So it is observed that while doing clustering there may be a chance of occurring dissimilar data object in a cluster. This paper introduces such technology that makes the patterns more accurate, and it helps to search more accurate analysis of data. This System greedily picks the next frequent item set in the next cluster. For this the multiple viewpoints are used to measure the similarity between two different data objects is introduced. We can define similarity between two objects explicitly or implicitly. Cosine similarity measures will resolve this problem. As multiple viewpoints will focuses on similarity measures at multiple levels. These criteria will be used to group the documents based on similarity. The similarity measured between current cluster documents and also other cluster group documents.
{"title":"A novel similarity measure technique for clustering using multiple viewpoint based method","authors":"Dushyant S. Potdar, T. Pattewar","doi":"10.1109/ISCO.2016.7727007","DOIUrl":"https://doi.org/10.1109/ISCO.2016.7727007","url":null,"abstract":"Data mining is nothing but the process of automatically searching large stores of data to discover patterns and trends that go beyond simple analysis. So it is observed that while doing clustering there may be a chance of occurring dissimilar data object in a cluster. This paper introduces such technology that makes the patterns more accurate, and it helps to search more accurate analysis of data. This System greedily picks the next frequent item set in the next cluster. For this the multiple viewpoints are used to measure the similarity between two different data objects is introduced. We can define similarity between two objects explicitly or implicitly. Cosine similarity measures will resolve this problem. As multiple viewpoints will focuses on similarity measures at multiple levels. These criteria will be used to group the documents based on similarity. The similarity measured between current cluster documents and also other cluster group documents.","PeriodicalId":320699,"journal":{"name":"2016 10th International Conference on Intelligent Systems and Control (ISCO)","volume":"1 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":"130231373","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 : 1900-01-01DOI: 10.1109/ISCO.2016.7727139
V. R. Saraswathy, N. Kasthuri, I. P. Ramyadevi
Intrusion detection system (IDS) is essential in order to overcome the security threats in the network community. IDS examines a large number of features in the data set to detect the intrusion. The process of feature selection is required to reduce the time consumption and storage memory. The data set may contain noisy, uncertain and redundant information. Rough Set Theory (RST) is one of the mathematical tool to reduce the features in the dataset. The quick reduct and relative reduct algorithms are hybridized with the Particle Swarm Optimization (PSO)to improve the effectiveness of the feature reduction. Multi-granularity is applied for network dataset and the reduct is obtained. It is observed that the reduct obtained through the multi-granularity approach produces better result in terms of time than the reduct obtained by the direct application of rough set algorithm.
{"title":"Multi-granularity approach for enhancing the performance of network intrusion detection with supervised learning","authors":"V. R. Saraswathy, N. Kasthuri, I. P. Ramyadevi","doi":"10.1109/ISCO.2016.7727139","DOIUrl":"https://doi.org/10.1109/ISCO.2016.7727139","url":null,"abstract":"Intrusion detection system (IDS) is essential in order to overcome the security threats in the network community. IDS examines a large number of features in the data set to detect the intrusion. The process of feature selection is required to reduce the time consumption and storage memory. The data set may contain noisy, uncertain and redundant information. Rough Set Theory (RST) is one of the mathematical tool to reduce the features in the dataset. The quick reduct and relative reduct algorithms are hybridized with the Particle Swarm Optimization (PSO)to improve the effectiveness of the feature reduction. Multi-granularity is applied for network dataset and the reduct is obtained. It is observed that the reduct obtained through the multi-granularity approach produces better result in terms of time than the reduct obtained by the direct application of rough set algorithm.","PeriodicalId":320699,"journal":{"name":"2016 10th International Conference on Intelligent Systems and Control (ISCO)","volume":"47 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":"127945419","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 : 1900-01-01DOI: 10.1109/ISCO.2016.7727063
P. Hemachandu, V. C. Veera Reddy
Now-a-days, the renewable energy sources are used extensively with the accumulated desired energy & several concerns of the environmental issues around the world. The efficient & excellent energy management is attained from proposed co-generation units; it may exert the fuel cell/photovoltaic systems. These are the primary energy sources to assist the micro-grid system using power conditioning units by adaptive neuro-fuzzy inference controller. This controller predicts the switching angles & optimum modulation index essentials for an improved output voltage & prevents the sudden variations of the asymmetrical 15-level modern multilevel inverter with fever switches. Here, this model has several inputs such as grid voltage, difference voltage, controlled target voltage. By means of these parameters, this proposed controller makes the rules & can be tuned imperatively for getting enhanced quality voltage at grid, greater transient stability. In this process, the proposed methodology provides a pure sinusoidal current is in-phase with the grid voltage, then interfacing to the grid by adaptive neuro-fuzzy classifier. A Simulink model is designed to validate the performance evaluation of this proposed work using Matlab/Simulink platform and results are conferred.
{"title":"A critical evaluation of modern multi-level inverter for grid integrated co-generation scheme using ANFIS controller","authors":"P. Hemachandu, V. C. Veera Reddy","doi":"10.1109/ISCO.2016.7727063","DOIUrl":"https://doi.org/10.1109/ISCO.2016.7727063","url":null,"abstract":"Now-a-days, the renewable energy sources are used extensively with the accumulated desired energy & several concerns of the environmental issues around the world. The efficient & excellent energy management is attained from proposed co-generation units; it may exert the fuel cell/photovoltaic systems. These are the primary energy sources to assist the micro-grid system using power conditioning units by adaptive neuro-fuzzy inference controller. This controller predicts the switching angles & optimum modulation index essentials for an improved output voltage & prevents the sudden variations of the asymmetrical 15-level modern multilevel inverter with fever switches. Here, this model has several inputs such as grid voltage, difference voltage, controlled target voltage. By means of these parameters, this proposed controller makes the rules & can be tuned imperatively for getting enhanced quality voltage at grid, greater transient stability. In this process, the proposed methodology provides a pure sinusoidal current is in-phase with the grid voltage, then interfacing to the grid by adaptive neuro-fuzzy classifier. A Simulink model is designed to validate the performance evaluation of this proposed work using Matlab/Simulink platform and results are conferred.","PeriodicalId":320699,"journal":{"name":"2016 10th International Conference on Intelligent Systems and Control (ISCO)","volume":"24 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":"125446254","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 : 1900-01-01DOI: 10.1109/ISCO.2016.7726978
G. Sandhiya, R. Jothikumar
In Wireless Sensor Networks (WSN) energy consumption takes place during transmission. To reduce energy consumption and to increase network lifetime an enhanced K mean with dijikstra algorithm was proposed. This method eliminates the redundancy using spatial similarity method and find the shortest path between nodes. Simulation results show that our technique has largely reduced the data redundancy in the whole network and also extended the network lifetime.
{"title":"Enhanced K-means with dijikstra algorithm for energy consumption in wireless sensor network","authors":"G. Sandhiya, R. Jothikumar","doi":"10.1109/ISCO.2016.7726978","DOIUrl":"https://doi.org/10.1109/ISCO.2016.7726978","url":null,"abstract":"In Wireless Sensor Networks (WSN) energy consumption takes place during transmission. To reduce energy consumption and to increase network lifetime an enhanced K mean with dijikstra algorithm was proposed. This method eliminates the redundancy using spatial similarity method and find the shortest path between nodes. Simulation results show that our technique has largely reduced the data redundancy in the whole network and also extended the network lifetime.","PeriodicalId":320699,"journal":{"name":"2016 10th International Conference on Intelligent Systems and Control (ISCO)","volume":"87 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":"123251486","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 : 1900-01-01DOI: 10.1109/ISCO.2016.7727052
K. Geethapriya, I. Kala, S. Karthik
Nowadays, wireless sensor networks (WSNs) seen as an emerging technology due to its multi serviceable, low cost and low power sensor nodes, that are deployed randomly and densely over a network to collect a useful information from there. Since the nodes are deployed densely, makes it hard to recharge or replace their batteries. Basically, the node senses the data and transmit it to a base station. The node, which is nearer to the base station may deplete their energy quickly than other nodes due to more traffic relaying on it. Furthermore the nodes may sense and transmit the redundant information to other nodes, which leads to energy wastage. Due to these types of issues, it is difficult to design a data aggregation scheme with optimal energy consumption across the sensing area to enhance the network lifetime. In this paper, a detailed study has been made about the available data aggregation techniques in the form of taxonomy.
{"title":"A study on data aggregation scheme over wireless sensor network","authors":"K. Geethapriya, I. Kala, S. Karthik","doi":"10.1109/ISCO.2016.7727052","DOIUrl":"https://doi.org/10.1109/ISCO.2016.7727052","url":null,"abstract":"Nowadays, wireless sensor networks (WSNs) seen as an emerging technology due to its multi serviceable, low cost and low power sensor nodes, that are deployed randomly and densely over a network to collect a useful information from there. Since the nodes are deployed densely, makes it hard to recharge or replace their batteries. Basically, the node senses the data and transmit it to a base station. The node, which is nearer to the base station may deplete their energy quickly than other nodes due to more traffic relaying on it. Furthermore the nodes may sense and transmit the redundant information to other nodes, which leads to energy wastage. Due to these types of issues, it is difficult to design a data aggregation scheme with optimal energy consumption across the sensing area to enhance the network lifetime. In this paper, a detailed study has been made about the available data aggregation techniques in the form of taxonomy.","PeriodicalId":320699,"journal":{"name":"2016 10th International Conference on Intelligent Systems and Control (ISCO)","volume":"9 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":"126247213","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 : 1900-01-01DOI: 10.1109/ISCO.2016.7727018
S. Sakib, Mohammad Sayem Bin Abdullah
In this paper, an upgraded version of vehicle tracking system is developed for inland vessels. In addition to the features available in traditional VTS (Vehicle Tracking System) for automobiles, it has the capability of remote monitoring of the vessel's motion and orientation. Furthermore, this device can detect capsize events and other accidents by motion tracking and instantly notify the authority and/or the owner with current coordinates of the vessel, which is obtained using the Global Positioning System (GPS). This can certainly boost up the rescue process and minimize losses. We have used GSM network for the communication between the device installed in the ship and the ground control. So, this can be implemented only in the inland vessels. But using iridium satellite communication instead of GSM will enable the device to be used in any sea-going ships. At last, a model of an integrated inland waterway control system (IIWCS) based on this device is discussed.
{"title":"GPS-GSM based inland vessel tracking system for automatic emergency detection and position notification","authors":"S. Sakib, Mohammad Sayem Bin Abdullah","doi":"10.1109/ISCO.2016.7727018","DOIUrl":"https://doi.org/10.1109/ISCO.2016.7727018","url":null,"abstract":"In this paper, an upgraded version of vehicle tracking system is developed for inland vessels. In addition to the features available in traditional VTS (Vehicle Tracking System) for automobiles, it has the capability of remote monitoring of the vessel's motion and orientation. Furthermore, this device can detect capsize events and other accidents by motion tracking and instantly notify the authority and/or the owner with current coordinates of the vessel, which is obtained using the Global Positioning System (GPS). This can certainly boost up the rescue process and minimize losses. We have used GSM network for the communication between the device installed in the ship and the ground control. So, this can be implemented only in the inland vessels. But using iridium satellite communication instead of GSM will enable the device to be used in any sea-going ships. At last, a model of an integrated inland waterway control system (IIWCS) based on this device is discussed.","PeriodicalId":320699,"journal":{"name":"2016 10th International Conference on Intelligent Systems and Control (ISCO)","volume":"1 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":"126528735","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 : 1900-01-01DOI: 10.1109/ISCO.2016.7727039
K. Devi, R. Muthuselvi
Health care is the hardest real time constrained domain. Queuing system, Delay in treatment, Difficult to treat rural people, Disability to do remote treatment are the major issues in current health care system. Internet of Things (IoT) allows caring of people from remote locations with the help of integration of wireless sensor network with internet. Different sensors are used to measure different health parameters. Processing of smart health care data in an efficient manner is necessary. Slight time variation causes severe effect such as loss of life. In IoT, delay occur in processing large volume of sensor data in real time. Energy spent by the sensors also affected by processing delay. Because sensors spent energy in idle state. To reduce delay in processing smart health care data, Multi core technology is included with IoT. SixLoWPAN is the technique used to connect low configured devices with internet. In this paper, Task Level Parallelism (TLP) is applied to process different health parameters in parallel. TLP utilizes the available resources in optimal way. It makes our system as more efficient. The proposed system improves performance upto 65.5%. Efficient system also reduces power consumption of the devices. This will increase the life time of the sensor network.
{"title":"Parallel processing of IoT health care applications","authors":"K. Devi, R. Muthuselvi","doi":"10.1109/ISCO.2016.7727039","DOIUrl":"https://doi.org/10.1109/ISCO.2016.7727039","url":null,"abstract":"Health care is the hardest real time constrained domain. Queuing system, Delay in treatment, Difficult to treat rural people, Disability to do remote treatment are the major issues in current health care system. Internet of Things (IoT) allows caring of people from remote locations with the help of integration of wireless sensor network with internet. Different sensors are used to measure different health parameters. Processing of smart health care data in an efficient manner is necessary. Slight time variation causes severe effect such as loss of life. In IoT, delay occur in processing large volume of sensor data in real time. Energy spent by the sensors also affected by processing delay. Because sensors spent energy in idle state. To reduce delay in processing smart health care data, Multi core technology is included with IoT. SixLoWPAN is the technique used to connect low configured devices with internet. In this paper, Task Level Parallelism (TLP) is applied to process different health parameters in parallel. TLP utilizes the available resources in optimal way. It makes our system as more efficient. The proposed system improves performance upto 65.5%. Efficient system also reduces power consumption of the devices. This will increase the life time of the sensor network.","PeriodicalId":320699,"journal":{"name":"2016 10th International Conference on Intelligent Systems and Control (ISCO)","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":"122267701","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 : 1900-01-01DOI: 10.1109/ISCO.2016.7726963
M. S. Sundary, V. Logisvary
Communication becomes most important in today's life. The world is dreaded to think beyond any communication gadgets. Data communication basically involves transfers of data from one place to another or from one point of time to another. Error may be introduced by the channel which makes data unreliable for user. Hence we need different error detection and error correction schemes. Our need is to achieve High speed and low complexity. The proposed work is to detect and correct a multiple error using low complexity novel cross parity code at lower overhead over GF(2m). It is able to correct m<;= Dw<;= 3m/2-1 multiple error combination out of all the possible 2m-1 error. Our proposed work is to test on 128 bit parallel and 163 bit (FIPT/NIST) standard word level GF multiplier and improve the efficiency of the circuit when compare to the existing work. Then we implement the design using VHDL, then simulated and synthesized using Modelsim SE 6 simulator and Xilinx ISE 6.3i respectively.
沟通在今天的生活中变得最重要。这个世界害怕超越任何通讯工具。数据通信基本上包括将数据从一个地方传输到另一个地方或从一个时间点传输到另一个时间点。信道可能引入错误，使用户的数据不可靠。因此，我们需要不同的错误检测和纠错方案。我们需要的是实现高速度和低复杂性。提出的工作是使用低复杂度的新型交叉奇偶校验码在GF(2m)上以较低的开销检测和纠正多重错误。能够在所有可能的2m-1误差中，对m<;= Dw<;= 3m/2-1多重误差组合进行校正。我们提出的工作是在128位并行和163位(FIPT/NIST)标准字电平GF乘法器上进行测试，与现有工作相比，提高电路的效率。然后使用VHDL实现设计，然后分别使用Modelsim SE 6模拟器和Xilinx ISE 6.3i进行仿真和合成。
{"title":"Multiple error detection and correction over GF(2m) using novel cross parity code","authors":"M. S. Sundary, V. Logisvary","doi":"10.1109/ISCO.2016.7726963","DOIUrl":"https://doi.org/10.1109/ISCO.2016.7726963","url":null,"abstract":"Communication becomes most important in today's life. The world is dreaded to think beyond any communication gadgets. Data communication basically involves transfers of data from one place to another or from one point of time to another. Error may be introduced by the channel which makes data unreliable for user. Hence we need different error detection and error correction schemes. Our need is to achieve High speed and low complexity. The proposed work is to detect and correct a multiple error using low complexity novel cross parity code at lower overhead over GF(2m). It is able to correct m<;= Dw<;= 3m/2-1 multiple error combination out of all the possible 2m-1 error. Our proposed work is to test on 128 bit parallel and 163 bit (FIPT/NIST) standard word level GF multiplier and improve the efficiency of the circuit when compare to the existing work. Then we implement the design using VHDL, then simulated and synthesized using Modelsim SE 6 simulator and Xilinx ISE 6.3i respectively.","PeriodicalId":320699,"journal":{"name":"2016 10th International Conference on Intelligent Systems and Control (ISCO)","volume":"33 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":"115271033","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 : 1900-01-01DOI: 10.1109/ISCO.2016.7727081
Sruthi V. Nair, G. Lakhekar, V. Panchade
This paper addresses design of optimal fuzzy sliding mode control technique for minimization of reaching time along with robust stabilization of nonlinear singularly perturbed systems (NSPS). In singular perturbation method, the original system is decomposed into two reduced order subsystems such as slow and fast models, in which nonlinear uncertain terms are involved with two-times scale representation. The proposed control technique has single input singe output (SISO) Sugeno type fuzzy inference engine applied to slow subsystem so as to achieve minimum settling time for slow state variables but this scheme does not consider for fast dynamic model. Each subsystem has a separate control target expressed in terms of slow and fast control command. The composite control action based on slow and fast control signal is applied for asymptotic stabilization of two-times scale model which minimizes the effect of chattering by considering boundary layer width for full order system. Further, we investigated parameter estimation of fuzzy sliding mode control such as sliding surface coefficient, hitting gain and boundary layer width with simplified control framework based on minimum number of rule base, utilized in the control design. Finally closed loop stability can be proved by direct method and Composite Lyapunov function for the two-time scale model.
{"title":"Fuzzy sliding mode control approach for two time scale system: Stability issues","authors":"Sruthi V. Nair, G. Lakhekar, V. Panchade","doi":"10.1109/ISCO.2016.7727081","DOIUrl":"https://doi.org/10.1109/ISCO.2016.7727081","url":null,"abstract":"This paper addresses design of optimal fuzzy sliding mode control technique for minimization of reaching time along with robust stabilization of nonlinear singularly perturbed systems (NSPS). In singular perturbation method, the original system is decomposed into two reduced order subsystems such as slow and fast models, in which nonlinear uncertain terms are involved with two-times scale representation. The proposed control technique has single input singe output (SISO) Sugeno type fuzzy inference engine applied to slow subsystem so as to achieve minimum settling time for slow state variables but this scheme does not consider for fast dynamic model. Each subsystem has a separate control target expressed in terms of slow and fast control command. The composite control action based on slow and fast control signal is applied for asymptotic stabilization of two-times scale model which minimizes the effect of chattering by considering boundary layer width for full order system. Further, we investigated parameter estimation of fuzzy sliding mode control such as sliding surface coefficient, hitting gain and boundary layer width with simplified control framework based on minimum number of rule base, utilized in the control design. Finally closed loop stability can be proved by direct method and Composite Lyapunov function for the two-time scale model.","PeriodicalId":320699,"journal":{"name":"2016 10th International Conference on Intelligent Systems and Control (ISCO)","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":"115609808","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：