Pub Date : 2011-06-15DOI: 10.1109/INISTA.2011.5946145
N. Talbi, K. Belarbi
One of the most important considerations in designing any fuzzy controller is the generation of the fuzzy rules as well as the membership functions for each fuzzy set. Metaheuristic algorithms have been widely used for optimal design of fuzzy controllers. In this paper, we propose new auto-tuning fuzzy PD controllers using Tabu Search (TS) for generating knowledge bases for fuzzy logic systems. The algorithm dynamically adjusts the membership functions and fuzzy rules according to different environments. it was tested on the control of angle of inverted pendulum and compared with GA.
{"title":"A self organized fuzzy PD controller using Tabu Search","authors":"N. Talbi, K. Belarbi","doi":"10.1109/INISTA.2011.5946145","DOIUrl":"https://doi.org/10.1109/INISTA.2011.5946145","url":null,"abstract":"One of the most important considerations in designing any fuzzy controller is the generation of the fuzzy rules as well as the membership functions for each fuzzy set. Metaheuristic algorithms have been widely used for optimal design of fuzzy controllers. In this paper, we propose new auto-tuning fuzzy PD controllers using Tabu Search (TS) for generating knowledge bases for fuzzy logic systems. The algorithm dynamically adjusts the membership functions and fuzzy rules according to different environments. it was tested on the control of angle of inverted pendulum and compared with GA.","PeriodicalId":301397,"journal":{"name":"2011 International Symposium on Innovations in Intelligent Systems and Applications","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116653381","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 : 2011-06-15DOI: 10.1109/INISTA.2011.5946075
M. Ettefagh, F. Abbasidoust, H. Milanchian, M. Y. Asr
The present article describes the application of Genetic Algorithm for force and moment balancing of a crank-slider mechanism. This technique permits competing design objectives to be considered through the investigation of trade-offs between those objectives. The objective functions of the design parameters are determined and their values are minimized by adjusting the independent variables of the designer and the limitation of design. The technique permits both partial force and moment balancing to be accomplished simultaneously while the desired constraints are satisfied. In this case, we minimize the forces with regard to the constraints of the moments using Genetic algorithm (GA). One of the proper types of GA is Binary Genetic Algorithm (BGA) that uses the chromosomes as binary codes. Therefore, in presented paper, BGA is selected to have good trade-off between the answers accuracy and convergence speed.
{"title":"Complex crank-slider mechanism dynamic balancing by Binary Genetic Algorithm(BGA)","authors":"M. Ettefagh, F. Abbasidoust, H. Milanchian, M. Y. Asr","doi":"10.1109/INISTA.2011.5946075","DOIUrl":"https://doi.org/10.1109/INISTA.2011.5946075","url":null,"abstract":"The present article describes the application of Genetic Algorithm for force and moment balancing of a crank-slider mechanism. This technique permits competing design objectives to be considered through the investigation of trade-offs between those objectives. The objective functions of the design parameters are determined and their values are minimized by adjusting the independent variables of the designer and the limitation of design. The technique permits both partial force and moment balancing to be accomplished simultaneously while the desired constraints are satisfied. In this case, we minimize the forces with regard to the constraints of the moments using Genetic algorithm (GA). One of the proper types of GA is Binary Genetic Algorithm (BGA) that uses the chromosomes as binary codes. Therefore, in presented paper, BGA is selected to have good trade-off between the answers accuracy and convergence speed.","PeriodicalId":301397,"journal":{"name":"2011 International Symposium on Innovations in Intelligent Systems and Applications","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123891811","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 : 2011-06-15DOI: 10.1109/INISTA.2011.5946054
J. Mohammed
Adaptive infinite impulse response (IIR) filters are particularly beneficial in modeling real systems because they require lower computational complexity and can achieve performance more efficiently as compared to the finite impulse response (FIR) filters. In this paper, an adaptive IIR-RLS filter employing subband decomposition is investigated. The proposed subband IIR-RLS filter is based on oversampled uniform DFT banks. To investigate the performance and the stability of the proposed subband IIR-RLS filter in a practical implementation, real data for far-end speech signal and its echo were used in car environment. The computer simulations are included in order to verify the performance of the algorithm. The proposed subband IIR-RLS filter produces results that are significantly favorable than fullband versions of FIR-RLS and IIR-RLS filters and traditional subband FIR-NLMS filter. Moreover, this approach greatly reduces the computational complexity while the stability of the low-order IIR filters in the proposed subband IIR-RLS filter could be monitored easily. Therefore, the proposed subband system identification technique is very attractive for the practical use with real time implementation.
{"title":"Low complexity and fast system identification using adaptive IIR filter employing subband decomposition","authors":"J. Mohammed","doi":"10.1109/INISTA.2011.5946054","DOIUrl":"https://doi.org/10.1109/INISTA.2011.5946054","url":null,"abstract":"Adaptive infinite impulse response (IIR) filters are particularly beneficial in modeling real systems because they require lower computational complexity and can achieve performance more efficiently as compared to the finite impulse response (FIR) filters. In this paper, an adaptive IIR-RLS filter employing subband decomposition is investigated. The proposed subband IIR-RLS filter is based on oversampled uniform DFT banks. To investigate the performance and the stability of the proposed subband IIR-RLS filter in a practical implementation, real data for far-end speech signal and its echo were used in car environment. The computer simulations are included in order to verify the performance of the algorithm. The proposed subband IIR-RLS filter produces results that are significantly favorable than fullband versions of FIR-RLS and IIR-RLS filters and traditional subband FIR-NLMS filter. Moreover, this approach greatly reduces the computational complexity while the stability of the low-order IIR filters in the proposed subband IIR-RLS filter could be monitored easily. Therefore, the proposed subband system identification technique is very attractive for the practical use with real time implementation.","PeriodicalId":301397,"journal":{"name":"2011 International Symposium on Innovations in Intelligent Systems and Applications","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123948814","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 : 2011-06-15DOI: 10.1109/INISTA.2011.5946079
Nevrez Imamoglu, Aydín Eresen, A. Ozbayoglu
Feature extraction techniques play a vital part in pattern recognition applications. In order to achieve the best performance in a particular classification problem, the most appropriate feature extractor for the problem is pursued. In this paper, a Pseudo-Zernike Moments based model is used as the feature extractor due to its reliability in illumination and rotation invariant multi-class object classification. A Hierarchical Rule-Based Neural Networks (HRB-NN) approach is proposed to classify multi-class data using hierarchical classification based on similarity measures between different classes. HRB-NN performance is compared to Nearest Neighbor and Bayesian classifiers. For implementation, a database of 960 images (640 training, 320 testing) for 8 different objects is used. The proposed method was able to classify the given data without any failure by giving the best performance outperforming the other chosen classifiers.
{"title":"Hierarchical rule-based neural network for multi-object classification using invariant features","authors":"Nevrez Imamoglu, Aydín Eresen, A. Ozbayoglu","doi":"10.1109/INISTA.2011.5946079","DOIUrl":"https://doi.org/10.1109/INISTA.2011.5946079","url":null,"abstract":"Feature extraction techniques play a vital part in pattern recognition applications. In order to achieve the best performance in a particular classification problem, the most appropriate feature extractor for the problem is pursued. In this paper, a Pseudo-Zernike Moments based model is used as the feature extractor due to its reliability in illumination and rotation invariant multi-class object classification. A Hierarchical Rule-Based Neural Networks (HRB-NN) approach is proposed to classify multi-class data using hierarchical classification based on similarity measures between different classes. HRB-NN performance is compared to Nearest Neighbor and Bayesian classifiers. For implementation, a database of 960 images (640 training, 320 testing) for 8 different objects is used. The proposed method was able to classify the given data without any failure by giving the best performance outperforming the other chosen classifiers.","PeriodicalId":301397,"journal":{"name":"2011 International Symposium on Innovations in Intelligent Systems and Applications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130823886","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 : 2011-06-15DOI: 10.1109/INISTA.2011.5946127
S. Liaqat, S. A. Khan, M. B. Ihsan, S. Z. Asghar, A. Ejaz, A. Bhatti
This paper presents a novel feature vector to be used with a robust automatic target recognition (ATR) classifier designed for a ground surveillance radar. A three element feature vector has been used where features are based on radar audio signal of 100 milliseconds duration. The short feature length allows fast real-time implementation of the classifier. Classification is done using a k-nearest neighbor (k-NN) classifier. There are two input classes to the classifier; automobile and pedestrian. Training has been done on real radar data. Classifier performance has been tested using test data from two different data sets. It has been demonstrated that in both cases, the overall classifier performance is above 80%.
{"title":"Automatic recognition of ground radar targets based on target RCS and short time spectrum variance","authors":"S. Liaqat, S. A. Khan, M. B. Ihsan, S. Z. Asghar, A. Ejaz, A. Bhatti","doi":"10.1109/INISTA.2011.5946127","DOIUrl":"https://doi.org/10.1109/INISTA.2011.5946127","url":null,"abstract":"This paper presents a novel feature vector to be used with a robust automatic target recognition (ATR) classifier designed for a ground surveillance radar. A three element feature vector has been used where features are based on radar audio signal of 100 milliseconds duration. The short feature length allows fast real-time implementation of the classifier. Classification is done using a k-nearest neighbor (k-NN) classifier. There are two input classes to the classifier; automobile and pedestrian. Training has been done on real radar data. Classifier performance has been tested using test data from two different data sets. It has been demonstrated that in both cases, the overall classifier performance is above 80%.","PeriodicalId":301397,"journal":{"name":"2011 International Symposium on Innovations in Intelligent Systems and Applications","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130058568","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 : 2011-06-15DOI: 10.1109/INISTA.2011.5946104
H. Ozyavru, N. Ozkurt, S. Men
In this study, a fuzzy clustering method has been proposed in order to segment brain tissues affected by the multiple sclerosis (MS). In traditional fuzzy clustering, the neighboring relations between pixels have not been taken account of. Additionally, the performance of the clustering reduces drastically because of the pixels having close gray levels due to noise. Therefore, in this study, a novel robust fuzzy clustering algorithm which uses spatial information has been proposed for segmentation of MS plagues. In addition to spatial information, standard deviation dependent filtering is incorporated to the algorithm to achieve better noise immunity. Also, fuzzy clustering is adjusted to be more selective on vertical elliptic objects instead of circular objects since most of the plagues are in this shape.
{"title":"Segmentation of multiple sclerosis plagues by robust fuzzy clustering with spatial information","authors":"H. Ozyavru, N. Ozkurt, S. Men","doi":"10.1109/INISTA.2011.5946104","DOIUrl":"https://doi.org/10.1109/INISTA.2011.5946104","url":null,"abstract":"In this study, a fuzzy clustering method has been proposed in order to segment brain tissues affected by the multiple sclerosis (MS). In traditional fuzzy clustering, the neighboring relations between pixels have not been taken account of. Additionally, the performance of the clustering reduces drastically because of the pixels having close gray levels due to noise. Therefore, in this study, a novel robust fuzzy clustering algorithm which uses spatial information has been proposed for segmentation of MS plagues. In addition to spatial information, standard deviation dependent filtering is incorporated to the algorithm to achieve better noise immunity. Also, fuzzy clustering is adjusted to be more selective on vertical elliptic objects instead of circular objects since most of the plagues are in this shape.","PeriodicalId":301397,"journal":{"name":"2011 International Symposium on Innovations in Intelligent Systems and Applications","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127732804","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 : 2011-06-15DOI: 10.1109/INISTA.2011.5946055
S. Ergin, S. Tezel, M. B. Gulmezoglu
In this paper, faults in induction motors were diagnosed by using the Common Vector Approach (CVA). CVA is a well-known subspace-based pattern recognition method that is widely used in speech recognition, speaker recognition, and image recognition problems. In order to analyze the performance of CVA, a database including the current signals of six identical induction motors were used. One of these induction motors was healthy motor whereas the remaining five induction motors were exposed to different synthetic faults. The multi-step One-Dimensional Discrete Wavelet Transform (1D-DWT) is applied on the current signals in order to construct feature vectors of each faulty class in the database. While performing CVA, the leave-20-out strategy was followed in order to test all feature vectors in the database. Highly satisfactory classification results were obtained.
{"title":"DWT-based fault diagnosis in induction motors by using CVA","authors":"S. Ergin, S. Tezel, M. B. Gulmezoglu","doi":"10.1109/INISTA.2011.5946055","DOIUrl":"https://doi.org/10.1109/INISTA.2011.5946055","url":null,"abstract":"In this paper, faults in induction motors were diagnosed by using the Common Vector Approach (CVA). CVA is a well-known subspace-based pattern recognition method that is widely used in speech recognition, speaker recognition, and image recognition problems. In order to analyze the performance of CVA, a database including the current signals of six identical induction motors were used. One of these induction motors was healthy motor whereas the remaining five induction motors were exposed to different synthetic faults. The multi-step One-Dimensional Discrete Wavelet Transform (1D-DWT) is applied on the current signals in order to construct feature vectors of each faulty class in the database. While performing CVA, the leave-20-out strategy was followed in order to test all feature vectors in the database. Highly satisfactory classification results were obtained.","PeriodicalId":301397,"journal":{"name":"2011 International Symposium on Innovations in Intelligent Systems and Applications","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126489299","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 : 2011-06-15DOI: 10.1109/INISTA.2011.5946095
I. Uzun, R. Edizkan
In this work, we investigated performance improvement of the distributed Turkish continuous speech recognition system (TCSRS) with some well-known packet loss concealment (PLC) techniques. The PLC techniques, Lagrange, Spline and maximum a-posteriori (MAP) are applied to the sparse and burst packet losses in the system. The experimental results showed that the interpolation methods give acceptable performance during sparse packet losses. But for burst losses, the performance of MAP estimation method is better than that of interpolation methods.
{"title":"Performance improvement in distributed Turkish continuous speech recognition system using packet loss concealment techniques","authors":"I. Uzun, R. Edizkan","doi":"10.1109/INISTA.2011.5946095","DOIUrl":"https://doi.org/10.1109/INISTA.2011.5946095","url":null,"abstract":"In this work, we investigated performance improvement of the distributed Turkish continuous speech recognition system (TCSRS) with some well-known packet loss concealment (PLC) techniques. The PLC techniques, Lagrange, Spline and maximum a-posteriori (MAP) are applied to the sparse and burst packet losses in the system. The experimental results showed that the interpolation methods give acceptable performance during sparse packet losses. But for burst losses, the performance of MAP estimation method is better than that of interpolation methods.","PeriodicalId":301397,"journal":{"name":"2011 International Symposium on Innovations in Intelligent Systems and Applications","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133061254","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 : 2011-06-15DOI: 10.1109/INISTA.2011.5946135
Sinem On, A. Yazıcı
In this study, a reference governor approach is proposed for path tracking of nonholonomic mobile robot considering prescribed constraints. The proposed approach is designed to minimize the tracking error with a desired speed while satisfying all other constraints such as bounds on linear and angular velocities, acceleration. This approach determines the control inputs of a path tracking algorithm based on current-state, reference trajectory and prescribed constraints. This is achieved by designing a reference governor module addition to the classical path tracking approaches.
{"title":"A reference governor approach for path tracking of nonholonomic mobile robot","authors":"Sinem On, A. Yazıcı","doi":"10.1109/INISTA.2011.5946135","DOIUrl":"https://doi.org/10.1109/INISTA.2011.5946135","url":null,"abstract":"In this study, a reference governor approach is proposed for path tracking of nonholonomic mobile robot considering prescribed constraints. The proposed approach is designed to minimize the tracking error with a desired speed while satisfying all other constraints such as bounds on linear and angular velocities, acceleration. This approach determines the control inputs of a path tracking algorithm based on current-state, reference trajectory and prescribed constraints. This is achieved by designing a reference governor module addition to the classical path tracking approaches.","PeriodicalId":301397,"journal":{"name":"2011 International Symposium on Innovations in Intelligent Systems and Applications","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122704730","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 : 2011-06-15DOI: 10.1109/INISTA.2011.5946139
S. Serin, N. Morova, S. Terzi, Ş. Sargın
In this study, an experimental study has been conducted to determine compressive strength of asphalt concrete. The scope of study by preparing 45 Marshall samples Marshall stability experiment was conducted and compressive strength of asphalt concrete was determined. Compressive strength of asphalt concrete as depending on bituminous amount prediction models were developed by using obtained experiment results. Compressive strength of asphalt concrete values as depending on bituminous amount have been estimated on prediction models developed with regression analyses and Artificial Neural Network (ANN) Methods. Results obtained from models were compared with experiment results. Prediction performances of developed models were evaluated as compared. As a result it was determined that possible to estimate the compressive strength of asphalt concrete as depending on bituminous amount with developed ANN model and that ANN model was more successful than regression model for estimating the compressive strength of asphalt concrete.
{"title":"Determining amount of bituminous effects on asphalt concrete strength with artificial intelligence and statistical analysis methods","authors":"S. Serin, N. Morova, S. Terzi, Ş. Sargın","doi":"10.1109/INISTA.2011.5946139","DOIUrl":"https://doi.org/10.1109/INISTA.2011.5946139","url":null,"abstract":"In this study, an experimental study has been conducted to determine compressive strength of asphalt concrete. The scope of study by preparing 45 Marshall samples Marshall stability experiment was conducted and compressive strength of asphalt concrete was determined. Compressive strength of asphalt concrete as depending on bituminous amount prediction models were developed by using obtained experiment results. Compressive strength of asphalt concrete values as depending on bituminous amount have been estimated on prediction models developed with regression analyses and Artificial Neural Network (ANN) Methods. Results obtained from models were compared with experiment results. Prediction performances of developed models were evaluated as compared. As a result it was determined that possible to estimate the compressive strength of asphalt concrete as depending on bituminous amount with developed ANN model and that ANN model was more successful than regression model for estimating the compressive strength of asphalt concrete.","PeriodicalId":301397,"journal":{"name":"2011 International Symposium on Innovations in Intelligent Systems and Applications","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122875840","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：