Kyun-Sang Park, Young-Jun Cho, Yunhee Kim, Jong-Tae Lim
In this paper, the robust stability of uncertain nonlinear singularly perturbed discrete systems is considered via the Lyapunov function method. We decompose the uncertain nonlinear singularly perturbed discrete system into the slow subsystem and the fast subsystem based on the manifold from the slow dynamics. Then, the stability conditions of the slow subsystem and the fast subsystem are obtained, respectively. The stability conditions of the slow subsystem and the fast subsystem guarantee the robust stability of the uncertain nonlinear singularly perturbed discrete system through the composite Lyapunov function. Finally, we show an illustrative example in order to show the validity of our result. Keywords-Singular perturbation; Discrete-time system; Lyapunov method; Robust stability;
{"title":"Stability Analysis of Uncertain Nonlinear Singularly Perturbed Discrete Systems","authors":"Kyun-Sang Park, Young-Jun Cho, Yunhee Kim, Jong-Tae Lim","doi":"10.1109/CIMSIM.2011.35","DOIUrl":"https://doi.org/10.1109/CIMSIM.2011.35","url":null,"abstract":"In this paper, the robust stability of uncertain nonlinear singularly perturbed discrete systems is considered via the Lyapunov function method. We decompose the uncertain nonlinear singularly perturbed discrete system into the slow subsystem and the fast subsystem based on the manifold from the slow dynamics. Then, the stability conditions of the slow subsystem and the fast subsystem are obtained, respectively. The stability conditions of the slow subsystem and the fast subsystem guarantee the robust stability of the uncertain nonlinear singularly perturbed discrete system through the composite Lyapunov function. Finally, we show an illustrative example in order to show the validity of our result. Keywords-Singular perturbation; Discrete-time system; Lyapunov method; Robust stability;","PeriodicalId":125671,"journal":{"name":"2011 Third International Conference on Computational Intelligence, Modelling & Simulation","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127295669","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper presents theoretical investigations into the dynamic characterisation of a two dimensional gantry crane system incorporating payload. A dynamic model of the system is developed using Euler-Langrange formulation. Simulation exercises are performed in Matlab with two different control strategies, PD and PD-Fuzzy controllers. To study the effects of payload weight on the response of the gantry crane system, the sway angle movement of the rope and its respective power spectral density are evaluated with different payload weight being placed at the end of the rope. Simulation results are presented in time and frequency domains. The robustness of the classical and fuzzy controllers in minimizing the sway angle is examined in terms of time response specifications and the results are then discussed in details.
{"title":"Investigation of Classical and Fuzzy Controller Robustness for Gantry Crane System Incorporating Payload","authors":"M. Zawawi, J. Bidin, M. Tumari, M. S. Saealal","doi":"10.1109/CIMSIM.2011.33","DOIUrl":"https://doi.org/10.1109/CIMSIM.2011.33","url":null,"abstract":"This paper presents theoretical investigations into the dynamic characterisation of a two dimensional gantry crane system incorporating payload. A dynamic model of the system is developed using Euler-Langrange formulation. Simulation exercises are performed in Matlab with two different control strategies, PD and PD-Fuzzy controllers. To study the effects of payload weight on the response of the gantry crane system, the sway angle movement of the rope and its respective power spectral density are evaluated with different payload weight being placed at the end of the rope. Simulation results are presented in time and frequency domains. The robustness of the classical and fuzzy controllers in minimizing the sway angle is examined in terms of time response specifications and the results are then discussed in details.","PeriodicalId":125671,"journal":{"name":"2011 Third International Conference on Computational Intelligence, Modelling & Simulation","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126091384","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}
In this work, we propose new method beside the classic method, to control the motorized wheelchair using EOG signals. The new method allows the user to look around freely while the wheelchair navigates automatically to the desired goal point. Only EOG signals are used to control the wheelchair, eye gazing and blinking. The user can still choose to control the wheelchair using the classic manual method in case the environment and obstacles structure does not help with the auto navigation method. In the new auto navigation method the micro controller can know the goal point direction and distance by calculating the gaze angle that the user is gazing at. Gaze angle and blinks are measured and used as inputs for the controlling method. Tangent Bug algorithm is used to navigate the wheelchair in Auto controlling method.
{"title":"Guiding Wheelchair Motion Based on EOG Signals Using Tangent Bug Algorithm","authors":"A. Al-Haddad, R. Sudirman, C. Omar","doi":"10.1109/CIMSIM.2011.17","DOIUrl":"https://doi.org/10.1109/CIMSIM.2011.17","url":null,"abstract":"In this work, we propose new method beside the classic method, to control the motorized wheelchair using EOG signals. The new method allows the user to look around freely while the wheelchair navigates automatically to the desired goal point. Only EOG signals are used to control the wheelchair, eye gazing and blinking. The user can still choose to control the wheelchair using the classic manual method in case the environment and obstacles structure does not help with the auto navigation method. In the new auto navigation method the micro controller can know the goal point direction and distance by calculating the gaze angle that the user is gazing at. Gaze angle and blinks are measured and used as inputs for the controlling method. Tangent Bug algorithm is used to navigate the wheelchair in Auto controlling method.","PeriodicalId":125671,"journal":{"name":"2011 Third International Conference on Computational Intelligence, Modelling & Simulation","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127018882","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}
O. E. Oguike, S. Echezona, M. Agu, D. Ebem, H. Longe, O. Abass
In a heterogeneous parallel computer system, the computational power of each of the processors differs from one another. Furthermore, with distributed memory, the capacity of the memory, which is distributed to each of the processors, differs from one another. Using queuing system to describe a distributed memory heterogeneous parallel computer system, each of the heterogeneous processors will have its own heterogeneous queue. The variation of a performance metric of heterogeneous parallel computer system with distributed memory needs to be modeled because it will help designers of parallel computer system to determine the extent of variation of a performance metric. It will also help users to know when to realize minimum variation of a performance metric. This paper models the variation of a performance metric of distributed memory heterogeneous parallel computer system using recursive models.
{"title":"Modeling Variation of Performance Metric of Distributed Memory Heterogeneous Parallel Computer System Using Recursive Models","authors":"O. E. Oguike, S. Echezona, M. Agu, D. Ebem, H. Longe, O. Abass","doi":"10.1109/CIMSIM.2011.74","DOIUrl":"https://doi.org/10.1109/CIMSIM.2011.74","url":null,"abstract":"In a heterogeneous parallel computer system, the computational power of each of the processors differs from one another. Furthermore, with distributed memory, the capacity of the memory, which is distributed to each of the processors, differs from one another. Using queuing system to describe a distributed memory heterogeneous parallel computer system, each of the heterogeneous processors will have its own heterogeneous queue. The variation of a performance metric of heterogeneous parallel computer system with distributed memory needs to be modeled because it will help designers of parallel computer system to determine the extent of variation of a performance metric. It will also help users to know when to realize minimum variation of a performance metric. This paper models the variation of a performance metric of distributed memory heterogeneous parallel computer system using recursive models.","PeriodicalId":125671,"journal":{"name":"2011 Third International Conference on Computational Intelligence, Modelling & Simulation","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126512065","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}
Rate adaptation algorithms play an important role in improving the performance of WLANs. However, just few numbers of efforts have been made on this area. These algorithms try to provide more throughputs by increasing or decreasing rates upon channel condition and obtained goodput. However, it is a little different in 802.11n. Unfortunately, just a few efforts have been made on this issue. This paper presents a learning automata based algorithm, called learning_RA, to determine the best rate in 802.11n networks. As it is shown in the results, our proposed algorithm provides better results and it has a simple implementation too. We provided a comparison of three different states in the same scenario, that is, without rate adaption, using zigzag and learning_RA algorithms. Obtained results imply that the proposed algorithm outperforms zigzag, which is a well-known rate adaption algorithm. Keywords-component; rate adaption; learning automta; 802.11n
速率自适应算法对提高无线局域网的性能起着重要作用。然而，在这方面所作的努力很少。这些算法试图根据信道条件通过增减速率来提供更多的吞吐量，并获得良好的吞吐量。但是，在802.11n中略有不同。不幸的是，在这个问题上只做了很少的努力。本文提出了一种基于学习自动机的算法，称为learning_RA，用于确定802.11n网络中的最佳速率。结果表明，我们提出的算法具有较好的结果和简单的实现。我们提供了在相同场景下的三种不同状态的比较，即没有速率自适应，使用zigzag和learning_RA算法。结果表明，该算法优于zigzag算法，zigzag是一种著名的速率自适应算法。Keywords-component;率适应;学习automta;802.11 n
{"title":"A Learning Based Rate Adaption Algorithm in 802.11n Networks","authors":"Pouria Babakhani, M. Sabaei","doi":"10.1109/CIMSIM.2011.60","DOIUrl":"https://doi.org/10.1109/CIMSIM.2011.60","url":null,"abstract":"Rate adaptation algorithms play an important role in improving the performance of WLANs. However, just few numbers of efforts have been made on this area. These algorithms try to provide more throughputs by increasing or decreasing rates upon channel condition and obtained goodput. However, it is a little different in 802.11n. Unfortunately, just a few efforts have been made on this issue. This paper presents a learning automata based algorithm, called learning_RA, to determine the best rate in 802.11n networks. As it is shown in the results, our proposed algorithm provides better results and it has a simple implementation too. We provided a comparison of three different states in the same scenario, that is, without rate adaption, using zigzag and learning_RA algorithms. Obtained results imply that the proposed algorithm outperforms zigzag, which is a well-known rate adaption algorithm. Keywords-component; rate adaption; learning automta; 802.11n","PeriodicalId":125671,"journal":{"name":"2011 Third International Conference on Computational Intelligence, Modelling & Simulation","volume":"2013 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131029759","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}
Seamless handover has become an important challenging issue among research groups over the past 5 years. Researchers and scientists have been making efforts to provide robust and integrated connectivity while the mobile node (MN) moves between networks. Running certain procedures such as movement detection (MD), neighbor discovery (ND), duplicate address detection (DAD) and sending binding updates (Bus) are needed in order to achieve complete handover procedure which results in handover latency and eventually packet loss. Recently, scientists have found that by utilizing information provided by the Global Positioning System (GPS) device, it is possible to reduce the amount of handover latency by decreasing the amount of time consumed by MD, ND and DAD procedures. In this paper we are going to investigate the proposed GPS models and their effects on the handover procedure in the MIPv6 protocol.
{"title":"A Novel Approach for Efficient Resource Consumption in GPS-Based Mobile IPv6 Wireless LAN","authors":"A. Moravejosharieh, R. Salleh, Hero Modares","doi":"10.1109/CIMSIM.2011.61","DOIUrl":"https://doi.org/10.1109/CIMSIM.2011.61","url":null,"abstract":"Seamless handover has become an important challenging issue among research groups over the past 5 years. Researchers and scientists have been making efforts to provide robust and integrated connectivity while the mobile node (MN) moves between networks. Running certain procedures such as movement detection (MD), neighbor discovery (ND), duplicate address detection (DAD) and sending binding updates (Bus) are needed in order to achieve complete handover procedure which results in handover latency and eventually packet loss. Recently, scientists have found that by utilizing information provided by the Global Positioning System (GPS) device, it is possible to reduce the amount of handover latency by decreasing the amount of time consumed by MD, ND and DAD procedures. In this paper we are going to investigate the proposed GPS models and their effects on the handover procedure in the MIPv6 protocol.","PeriodicalId":125671,"journal":{"name":"2011 Third International Conference on Computational Intelligence, Modelling & Simulation","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133492515","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper presents an analytical and simulation solution for MEMS (Microelectromechanical Systems) capacitive pressure sensor operating in harsh environment. The proposed sensor consists of a circular SiC (Silicon Carbide) diaphragm suspended over sealed cavity on a Si (Silicon) substrate. SiC is selected in this work due to its excellent electrical stability, mechanical robustness and chemical inertness properties, which is very adequate for harsh environment. The design is based on the use of COMSOL multiphysics structural analysis to design and obtain analytical solution for a circular diaphragm deflection. The proposed sensor demonstrated diaphragm of 100 μm diameter with the gap depth 0.64 μm and the sensor exhibit a linear response with pressure load up to 3.5 MPa with maximum deflection up to 0.52 μm. Keywords-COMSOL; harsh environment; high dielectric materials; silicon carbide
{"title":"SiC Capacitive Pressure Sensor Node for Harsh Industrial Environment","authors":"A. Anis, M. M. Abutaleb, H. Ragai, M. Eladawy","doi":"10.1109/CIMSIM.2011.82","DOIUrl":"https://doi.org/10.1109/CIMSIM.2011.82","url":null,"abstract":"This paper presents an analytical and simulation solution for MEMS (Microelectromechanical Systems) capacitive pressure sensor operating in harsh environment. The proposed sensor consists of a circular SiC (Silicon Carbide) diaphragm suspended over sealed cavity on a Si (Silicon) substrate. SiC is selected in this work due to its excellent electrical stability, mechanical robustness and chemical inertness properties, which is very adequate for harsh environment. The design is based on the use of COMSOL multiphysics structural analysis to design and obtain analytical solution for a circular diaphragm deflection. The proposed sensor demonstrated diaphragm of 100 μm diameter with the gap depth 0.64 μm and the sensor exhibit a linear response with pressure load up to 3.5 MPa with maximum deflection up to 0.52 μm. Keywords-COMSOL; harsh environment; high dielectric materials; silicon carbide","PeriodicalId":125671,"journal":{"name":"2011 Third International Conference on Computational Intelligence, Modelling & Simulation","volume":"408 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133206576","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}
Networks are being used in various areas and the demand of users nowadays has motivated the emergence of the Mobile Ad Hoc Network (MANET). MANET is a dynamic network without fixed infrastructure due to their wireless nature and can be deployed as multi-hop packet networks. It is a wireless network and has dynamic topology due to its node mobility. There are two types of MANET, homogeneous and heterogeneous MANET. An architecture has been designed in previous work to model these two types of MANET. Three scenarios have been defined from this architecture: scenario I (communication entirely within MANET, homogeneous MANET), scenario II (communication between MANET and wireless LAN, heterogeneous MANET) and scenario III (communication between MANET with wireless LAN and wired LAN, heterogeneous MANET). MANET has its own routing protocols which can compromised with frequent route exchange, dynamic topology, bandwidth constraint and multi-hop routing. Ad hoc On Demand Distance Vector (AODV) is one of the routing protocols in MANET. The aim of this research is to assess the effects of different packet size with the implementation of AODV routing protocols in homogeneous and heterogeneous MANET through the simulation method. The three scenarios above have been developed in the OMNeT++ network simulator. The results achieved from the test have been evaluated using the metrics assigned, throughput and packet delivery ratio (PDR). The tests show that the increase of throughput and PDR performance was parallel with the increase of packet size. From the test also, we can conclude that the performance due to the packet size effect in homogeneous MANET is better than in heterogeneous MANET.
网络被应用于各个领域，当今用户的需求推动了移动自组网(MANET)的出现。由于其无线特性，MANET是一种没有固定基础设施的动态网络，可以作为多跳分组网络部署。它是一个无线网络，由于其节点的移动性而具有动态拓扑结构。MANET有两种类型，同质MANET和异构MANET。在之前的工作中已经设计了一个架构来模拟这两种类型的MANET。该架构定义了三个场景:场景I(完全在MANET内通信，同构MANET)，场景II (MANET和无线局域网之间的通信，异构MANET)和场景III (MANET与无线局域网和有线局域网之间的通信，异构MANET)。MANET有自己的路由协议，但会受到频繁路由交换、动态拓扑、带宽限制和多跳路由的影响。AODV (Ad hoc On Demand Distance Vector)是MANET中的一种路由协议。本研究的目的是通过仿真方法评估不同数据包大小对同构和异构MANET中AODV路由协议实现的影响。上述三个场景都是在omnet++网络模拟器中开发的。使用分配的指标、吞吐量和分组传输比率(PDR)对测试获得的结果进行了评估。测试结果表明，吞吐量和PDR性能的提高与数据包大小的增加是并行的。从测试中我们也可以得出结论，均匀MANET中由于数据包大小效应的性能优于异构MANET。
{"title":"Effects of Packet Size on AODV Routing Protocol Implementation in Homogeneous and Heterogeneous MANET","authors":"Zahian Ismail, R. Hassan","doi":"10.1109/CIMSIM.2011.70","DOIUrl":"https://doi.org/10.1109/CIMSIM.2011.70","url":null,"abstract":"Networks are being used in various areas and the demand of users nowadays has motivated the emergence of the Mobile Ad Hoc Network (MANET). MANET is a dynamic network without fixed infrastructure due to their wireless nature and can be deployed as multi-hop packet networks. It is a wireless network and has dynamic topology due to its node mobility. There are two types of MANET, homogeneous and heterogeneous MANET. An architecture has been designed in previous work to model these two types of MANET. Three scenarios have been defined from this architecture: scenario I (communication entirely within MANET, homogeneous MANET), scenario II (communication between MANET and wireless LAN, heterogeneous MANET) and scenario III (communication between MANET with wireless LAN and wired LAN, heterogeneous MANET). MANET has its own routing protocols which can compromised with frequent route exchange, dynamic topology, bandwidth constraint and multi-hop routing. Ad hoc On Demand Distance Vector (AODV) is one of the routing protocols in MANET. The aim of this research is to assess the effects of different packet size with the implementation of AODV routing protocols in homogeneous and heterogeneous MANET through the simulation method. The three scenarios above have been developed in the OMNeT++ network simulator. The results achieved from the test have been evaluated using the metrics assigned, throughput and packet delivery ratio (PDR). The tests show that the increase of throughput and PDR performance was parallel with the increase of packet size. From the test also, we can conclude that the performance due to the packet size effect in homogeneous MANET is better than in heterogeneous MANET.","PeriodicalId":125671,"journal":{"name":"2011 Third International Conference on Computational Intelligence, Modelling & Simulation","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114552688","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}
Fadzilah Siraj, M. Yusoff, Megat Firdaus Haris, Muhammad Ashraq Salahuddin, Shahrin Rizlan Mohd Yusof, Md. Rajib Hasan
The granting of loan by a financial institution is one of the important decision that require insubstantial care.Currently, SME Banks in Malaysia are using conventional approach to process loan applications.Due to this conventional approach, analyzing information related to entrepreneurs manually is very time consuming.Based on SMEs expert criteria in Malaysia that has been collected from collected from corporate sector and financial institutions such as SME Corp. Malaysia and SME Bank, the design and development of the prototype for an intelligent decision support system has been implemented.Therefore, this study extends the manual concept of SME loan application processing to a digital, automated and intelligent processing to a digital, automated and intelligent processing that learns and supports the user in decision making.It explores the use of hybrid technology such as Neural Networks and Case Based Reasoning.The system known as I-SME is able to classify SME market segment into three distinctive groups, there are MICRO, MEDIUM and SMALL with accuracy of 98.97 percent.In addition i-SME recommends to the management whether an application should be accepted or rejected.The evaluation based on Perceived Usefulness and Perceived Ease of Use reveals that i-SME is useful and easy to use.Furthermore, it is possible to transform the patterns generated from i-SME into actionable plans that are likely to assist SME Bank to be more effective and competitive.
{"title":"i-SME: Loan Decision Support System Using Neuro-CBR Approach","authors":"Fadzilah Siraj, M. Yusoff, Megat Firdaus Haris, Muhammad Ashraq Salahuddin, Shahrin Rizlan Mohd Yusof, Md. Rajib Hasan","doi":"10.1109/CIMSIM.2011.25","DOIUrl":"https://doi.org/10.1109/CIMSIM.2011.25","url":null,"abstract":"The granting of loan by a financial institution is one of the important decision that require insubstantial care.Currently, SME Banks in Malaysia are using conventional approach to process loan applications.Due to this conventional approach, analyzing information related to entrepreneurs manually is very time consuming.Based on SMEs expert criteria in Malaysia that has been collected from collected from corporate sector and financial institutions such as SME Corp. Malaysia and SME Bank, the design and development of the prototype for an intelligent decision support system has been implemented.Therefore, this study extends the manual concept of SME loan application processing to a digital, automated and intelligent processing to a digital, automated and intelligent processing that learns and supports the user in decision making.It explores the use of hybrid technology such as Neural Networks and Case Based Reasoning.The system known as I-SME is able to classify SME market segment into three distinctive groups, there are MICRO, MEDIUM and SMALL with accuracy of 98.97 percent.In addition i-SME recommends to the management whether an application should be accepted or rejected.The evaluation based on Perceived Usefulness and Perceived Ease of Use reveals that i-SME is useful and easy to use.Furthermore, it is possible to transform the patterns generated from i-SME into actionable plans that are likely to assist SME Bank to be more effective and competitive.","PeriodicalId":125671,"journal":{"name":"2011 Third International Conference on Computational Intelligence, Modelling & Simulation","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124614562","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper presents a method for optimizing PIlike Fuzzy Logic Controller (FLC) using Imperialist Competitive Algorithm (ICA) and Genetic Algorithm (GA) in order to control the speed of DC motor. So as to achieve a better control performance, the ICA and GA optimize the parameters of FLC, which are Membership Functions (MFs) and gain factors. The number of rule in the designed PI-like FLC is low and consequently requires less computation. This makes the FLC more suitable for real-time implementation, particularly at high-speed operating conditions. Simulation results show that optimizing the PI-like FLC through ICA is the best performance compared to PI-like FLC and GAoptimized PI-like FLC. KeywordsDC Motor; PI-like Fuzzy Logic Controller (FLC); Imperialist Competitive Algorithm (ICA)
{"title":"Speed Control of DC Motor Using Imperialist Competitive Algorithm Based on PI-Like FLC","authors":"Sh. L. Ghalehpardaz, M. Shafiee","doi":"10.1109/CIMSIM.2011.15","DOIUrl":"https://doi.org/10.1109/CIMSIM.2011.15","url":null,"abstract":"This paper presents a method for optimizing PIlike Fuzzy Logic Controller (FLC) using Imperialist Competitive Algorithm (ICA) and Genetic Algorithm (GA) in order to control the speed of DC motor. So as to achieve a better control performance, the ICA and GA optimize the parameters of FLC, which are Membership Functions (MFs) and gain factors. The number of rule in the designed PI-like FLC is low and consequently requires less computation. This makes the FLC more suitable for real-time implementation, particularly at high-speed operating conditions. Simulation results show that optimizing the PI-like FLC through ICA is the best performance compared to PI-like FLC and GAoptimized PI-like FLC. KeywordsDC Motor; PI-like Fuzzy Logic Controller (FLC); Imperialist Competitive Algorithm (ICA)","PeriodicalId":125671,"journal":{"name":"2011 Third International Conference on Computational Intelligence, Modelling & Simulation","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124763741","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：