Mohammed Rokibul Alam Kotwal, Foyzul Hassan, Md. Shafiul Alam, Shakib Ibn Daud, Faisal Ahmed, M. N. Huda
Speaker-specific characteristics play an important role on the performance of Bangla (widely used as Bengali) automatic speech recognition (ASR). It is difficult to recognize speech affected by gender factors, especially when an ASR system contains only a single acoustic model. If there exists any suppression process that represses the decrease of differences in acoustic-likelihood among categories resulted from gender factors, a robust ASR system can be realized. In this paper, we have proposed a technique of gender effects suppression that composed of two hidden Markov model (HMM)-based classifiers and that focused on a gender factor. In an experiment on Bangla speech database prepared by us, the proposed system has provided a significant improvement of word correct rate, word accuracy and sentence correct rate in comparison with the method that incorporates only a single HMM-based classifier for both male and female speakers.
{"title":"Gender Effects Suppression in Bangla ASR by Designing Multiple HMM-Based Classifiers","authors":"Mohammed Rokibul Alam Kotwal, Foyzul Hassan, Md. Shafiul Alam, Shakib Ibn Daud, Faisal Ahmed, M. N. Huda","doi":"10.1109/CICN.2011.82","DOIUrl":"https://doi.org/10.1109/CICN.2011.82","url":null,"abstract":"Speaker-specific characteristics play an important role on the performance of Bangla (widely used as Bengali) automatic speech recognition (ASR). It is difficult to recognize speech affected by gender factors, especially when an ASR system contains only a single acoustic model. If there exists any suppression process that represses the decrease of differences in acoustic-likelihood among categories resulted from gender factors, a robust ASR system can be realized. In this paper, we have proposed a technique of gender effects suppression that composed of two hidden Markov model (HMM)-based classifiers and that focused on a gender factor. In an experiment on Bangla speech database prepared by us, the proposed system has provided a significant improvement of word correct rate, word accuracy and sentence correct rate in comparison with the method that incorporates only a single HMM-based classifier for both male and female speakers.","PeriodicalId":292190,"journal":{"name":"2011 International Conference on Computational Intelligence and Communication Networks","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129196003","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 present the transformer design optimization problem. The objective of transformer design optimization problem requires to minimizing the total mass (or cost) of the core and wire material by satisfying constraints imposed by international standards and transformer user specification. The constraints include appropriate limits on efficiency, voltage regulation, temperature rise, no-load current and winding fill factor. The design optimizations seek a constrained minimum mass (or cost) solution by optimally setting the transformer geometry parameters and require magnetic properties. This paper shows the above design problems can be formulated in fuzzy logic (FL). The importance of the FL format stems for two main features. First it provides efficient and reliable solution for the design optimization problem with several variables. Second, it guaranteed that the obtained solution is global optimum. This paper includes a demonstration of the application of the FL technique for transformer design.
{"title":"Application Research Based on Fuzzy Logic to Predict Minimum Loss for Transformer Design Optimization","authors":"Malik Hasmat, Anil Kr, Amit Kr, Yadav, R. Jarial","doi":"10.1109/CICN.2011.41","DOIUrl":"https://doi.org/10.1109/CICN.2011.41","url":null,"abstract":"This paper present the transformer design optimization problem. The objective of transformer design optimization problem requires to minimizing the total mass (or cost) of the core and wire material by satisfying constraints imposed by international standards and transformer user specification. The constraints include appropriate limits on efficiency, voltage regulation, temperature rise, no-load current and winding fill factor. The design optimizations seek a constrained minimum mass (or cost) solution by optimally setting the transformer geometry parameters and require magnetic properties. This paper shows the above design problems can be formulated in fuzzy logic (FL). The importance of the FL format stems for two main features. First it provides efficient and reliable solution for the design optimization problem with several variables. Second, it guaranteed that the obtained solution is global optimum. This paper includes a demonstration of the application of the FL technique for transformer design.","PeriodicalId":292190,"journal":{"name":"2011 International Conference on Computational Intelligence and Communication Networks","volume":"688 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128825934","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}
Although various wireless access network technologies with different characteristics and performance level have been developed, no single network that can satisfy the anytime, anywhere, and any service wireless access needs of mobile users. A truly seamless mobile environment can only be realized by considering vertical and horizontal handoffs together. One of the major design issues in heterogeneous wireless networks is the support of vertical handoff. Vertical handoff occurs when a user with a multi-interface terminal changes association from one type of wireless access technology to another while maintaining an active session. It is believed that vertical handoff decision will be based on multiple criteria. In this paper review of Vertical Handoff Mechanisms (VHM), decision models and IEEE standard 802.21 (also called Media Independent Handover) have been discussed for seamless vertical handover.
{"title":"Media Independent Handover (IEEE 802.21): Framework for Next Generation Vertical Handover Protocols","authors":"Vikas Sharma, Ankith Agarwal, M. Qadeer","doi":"10.1109/CICN.2011.106","DOIUrl":"https://doi.org/10.1109/CICN.2011.106","url":null,"abstract":"Although various wireless access network technologies with different characteristics and performance level have been developed, no single network that can satisfy the anytime, anywhere, and any service wireless access needs of mobile users. A truly seamless mobile environment can only be realized by considering vertical and horizontal handoffs together. One of the major design issues in heterogeneous wireless networks is the support of vertical handoff. Vertical handoff occurs when a user with a multi-interface terminal changes association from one type of wireless access technology to another while maintaining an active session. It is believed that vertical handoff decision will be based on multiple criteria. In this paper review of Vertical Handoff Mechanisms (VHM), decision models and IEEE standard 802.21 (also called Media Independent Handover) have been discussed for seamless vertical handover.","PeriodicalId":292190,"journal":{"name":"2011 International Conference on Computational Intelligence and Communication Networks","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123377885","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}
Moving vehicle detection in digital image sequences is one of the key technologies of Intelligent Transportation Systems (ITS). Traffic Surveillance System is being more and important with the enlarging of urban scale and increasing number of vehicles. This Paper presents an intelligent vehicle counting method based on blob analysis in traffic surveillance. The algorithm is composed of moving object segmentation, blob analysis, and tracking. By analyzing the blob of vehicles, the meaningful features are extracted. In addition, the speed of each vehicle and the vehicle flow through a predefined area can be calculated by analyzing blobs of vehicles. The experimental results show that the proposed system can provide useful information for traffic surveillance. We analyze the procedure of video-based traffic congestion system and divide it into graying, binarization, denoising and moving target detection. The system first reads video and converts them into grayscale images. We also put forward a Boundary block detection algorithm with noise reduction to identify the moving objects.
{"title":"An Implementation of Moving Object Detection, Tracking and Counting Objects for Traffic Surveillance System","authors":"Yoginee B. Brahme, P. S. Kulkarni","doi":"10.1109/CICN.2011.28","DOIUrl":"https://doi.org/10.1109/CICN.2011.28","url":null,"abstract":"Moving vehicle detection in digital image sequences is one of the key technologies of Intelligent Transportation Systems (ITS). Traffic Surveillance System is being more and important with the enlarging of urban scale and increasing number of vehicles. This Paper presents an intelligent vehicle counting method based on blob analysis in traffic surveillance. The algorithm is composed of moving object segmentation, blob analysis, and tracking. By analyzing the blob of vehicles, the meaningful features are extracted. In addition, the speed of each vehicle and the vehicle flow through a predefined area can be calculated by analyzing blobs of vehicles. The experimental results show that the proposed system can provide useful information for traffic surveillance. We analyze the procedure of video-based traffic congestion system and divide it into graying, binarization, denoising and moving target detection. The system first reads video and converts them into grayscale images. We also put forward a Boundary block detection algorithm with noise reduction to identify the moving objects.","PeriodicalId":292190,"journal":{"name":"2011 International Conference on Computational Intelligence and Communication Networks","volume":"194 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121064865","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 deals with the comparison of various optimization techniques used for detection of spatially multiplexed transmitted symbols in multiple input multiple output orthogonal frequency division multiplexing (MIMO OFDM) system. It may be helpful in evaluating the performance of the detection techniques viz zero forcing (ZF), minimum mean square error (MMSE) and maximum likelihood (ML) on the basis of the bit error rate (BER) for a given signal to noise ratio (SNR). A 2x2 MIMO system is used for the performance evaluation in simulation. The receiver decodes the binary phase shift keying (BPSK) signal through low density parity check (LDPC) decoder. A simulation result shows that ML is having a better performance over ZF and MMSE.
{"title":"Comparative Analysis of Various Optimization Techniques with Coded MIMO-OFDM Transmission","authors":"S. Singh, Sumit Raghuvanshi","doi":"10.1109/CICN.2011.54","DOIUrl":"https://doi.org/10.1109/CICN.2011.54","url":null,"abstract":"This paper deals with the comparison of various optimization techniques used for detection of spatially multiplexed transmitted symbols in multiple input multiple output orthogonal frequency division multiplexing (MIMO OFDM) system. It may be helpful in evaluating the performance of the detection techniques viz zero forcing (ZF), minimum mean square error (MMSE) and maximum likelihood (ML) on the basis of the bit error rate (BER) for a given signal to noise ratio (SNR). A 2x2 MIMO system is used for the performance evaluation in simulation. The receiver decodes the binary phase shift keying (BPSK) signal through low density parity check (LDPC) decoder. A simulation result shows that ML is having a better performance over ZF and MMSE.","PeriodicalId":292190,"journal":{"name":"2011 International Conference on Computational Intelligence and Communication Networks","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116270301","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}
Wireless Sensor Networks need energy efficient protocol for carrying out various operations. Cooperation among nodes may save significant energy by avoiding retransmission from distant nodes. In this work, a new scheme has been suggested for LEACH based WSN by introducing cooperation among various cluster heads. Significant improvement in BER has been observed for comparable overall lifetime of ordinary WSN. Cooperative communication with punctured convolutional channel coding is used in operation phase where as point to point transmission technique is used in clustering phase. Rayleigh fading channel and additional energy consumption due to retransmissions by relay nodes has been accounted in simulation. Bit error rate (BER) and overall life time of WSN is found to be dependent on the number of cooperative nodes, sensor nodes density in WSN, etc factors.
{"title":"A New Scheme for Cooperative Communication in LEACH Based Wireless Sensor Network","authors":"N. Purohit, H. Agrawal, A. Jain","doi":"10.1109/CICN.2011.10","DOIUrl":"https://doi.org/10.1109/CICN.2011.10","url":null,"abstract":"Wireless Sensor Networks need energy efficient protocol for carrying out various operations. Cooperation among nodes may save significant energy by avoiding retransmission from distant nodes. In this work, a new scheme has been suggested for LEACH based WSN by introducing cooperation among various cluster heads. Significant improvement in BER has been observed for comparable overall lifetime of ordinary WSN. Cooperative communication with punctured convolutional channel coding is used in operation phase where as point to point transmission technique is used in clustering phase. Rayleigh fading channel and additional energy consumption due to retransmissions by relay nodes has been accounted in simulation. Bit error rate (BER) and overall life time of WSN is found to be dependent on the number of cooperative nodes, sensor nodes density in WSN, etc factors.","PeriodicalId":292190,"journal":{"name":"2011 International Conference on Computational Intelligence and Communication Networks","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127007792","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}
A vehicular ad-hoc network (VANET), is an instance of intelligent transportation system that provides vehicle-to-vehicle communication aided by road side infrastructure for in-vehicle entertainment and safer road environment. VANET is characterized by highly mobile vehicles, predetermined topology and the requirement of reliable time bound message delivery over error prone shared wireless medium. The security solutions are constrained by these characteristics. In this paper we are discussing the various type of attack on VANET along with intersection attack on anonymity and the security issue that need to kept in mind while developing any protocol to make VANET secure. Simulation and results indicate that intersection attack is breach the privacy even though cryptographic and noncryptographic security mechanism is enabled over the VANET.
{"title":"Attacks on Anonymity in VANET","authors":"B. Chaurasia, S. Verma, G. Tomar","doi":"10.1109/CICN.2011.43","DOIUrl":"https://doi.org/10.1109/CICN.2011.43","url":null,"abstract":"A vehicular ad-hoc network (VANET), is an instance of intelligent transportation system that provides vehicle-to-vehicle communication aided by road side infrastructure for in-vehicle entertainment and safer road environment. VANET is characterized by highly mobile vehicles, predetermined topology and the requirement of reliable time bound message delivery over error prone shared wireless medium. The security solutions are constrained by these characteristics. In this paper we are discussing the various type of attack on VANET along with intersection attack on anonymity and the security issue that need to kept in mind while developing any protocol to make VANET secure. Simulation and results indicate that intersection attack is breach the privacy even though cryptographic and noncryptographic security mechanism is enabled over the VANET.","PeriodicalId":292190,"journal":{"name":"2011 International Conference on Computational Intelligence and Communication Networks","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133914926","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 performance comparison of three leading face recognition techniques. In the first method, the face recognition is done using principle component analysis (PCA). In the second method we combine K-nearest neighbor (KNN) classification method with PCA. The face recognition using histogram is also carried out. The above methods are compared on the basis of accuracy and time taken in an ORL database and YALE database.
{"title":"Comparative Study of Different Face Recognition Techniques","authors":"Sandeep Kukreja, Rekha Gupta","doi":"10.1109/CICN.2011.55","DOIUrl":"https://doi.org/10.1109/CICN.2011.55","url":null,"abstract":"This paper presents performance comparison of three leading face recognition techniques. In the first method, the face recognition is done using principle component analysis (PCA). In the second method we combine K-nearest neighbor (KNN) classification method with PCA. The face recognition using histogram is also carried out. The above methods are compared on the basis of accuracy and time taken in an ORL database and YALE database.","PeriodicalId":292190,"journal":{"name":"2011 International Conference on Computational Intelligence and Communication Networks","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124774311","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-line condition monitoring and diagnostic system for power transformers, an important component of electric utility, is valuable for preventing damages. The paper focuses on the area of monitoring using wireless condition monitoring systems can be cost effectively implemented in extensive applications that were historically handled by running routes with data collectors. The result would be a lower cost program with more frequent data collection, increased safety, and lower spare parts inventories. Facilities would be able to run leaner because they will have more confidence in their ability to avoid downtime. If we consider the communication range(middle range of 100m or less), data rate (about 100kbps) and power consumption(tens of mA), candidates of wireless communication technologies adequate for power monitoring system narrow down to Bluetooth and Zigbee.
{"title":"Condition Monitoring and Diagnostics of Power Transformers Using WSNs","authors":"Nagpal Tapsi, Singh Yaduvir","doi":"10.1109/CICN.2011.56","DOIUrl":"https://doi.org/10.1109/CICN.2011.56","url":null,"abstract":"On-line condition monitoring and diagnostic system for power transformers, an important component of electric utility, is valuable for preventing damages. The paper focuses on the area of monitoring using wireless condition monitoring systems can be cost effectively implemented in extensive applications that were historically handled by running routes with data collectors. The result would be a lower cost program with more frequent data collection, increased safety, and lower spare parts inventories. Facilities would be able to run leaner because they will have more confidence in their ability to avoid downtime. If we consider the communication range(middle range of 100m or less), data rate (about 100kbps) and power consumption(tens of mA), candidates of wireless communication technologies adequate for power monitoring system narrow down to Bluetooth and Zigbee.","PeriodicalId":292190,"journal":{"name":"2011 International Conference on Computational Intelligence and Communication Networks","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133681975","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 the image retrieval technology, the aim is to retrieve an image based on DCT color coefficients. There were many algorithms based on single feature, presented in past. Those algorithms have lack of speed and require more computational capability. In this algorithm by using DCT, most similar images are retrieved. The idea of DCT was to decouples the color component of image using YCbCr color model and transform these color components into DCT coefficients moreover reduce the number of bits simply dividing of each DCT coefficients with constant quantization matrix and round them into nearest number to calculate features of that image for performing similarity measure.
{"title":"Image Retrieval Algorithm Based on Quantized DCT Coefficients","authors":"Arvind Sharma, Nishchol Mishra, P. Sharma","doi":"10.1109/CICN.2011.90","DOIUrl":"https://doi.org/10.1109/CICN.2011.90","url":null,"abstract":"In the image retrieval technology, the aim is to retrieve an image based on DCT color coefficients. There were many algorithms based on single feature, presented in past. Those algorithms have lack of speed and require more computational capability. In this algorithm by using DCT, most similar images are retrieved. The idea of DCT was to decouples the color component of image using YCbCr color model and transform these color components into DCT coefficients moreover reduce the number of bits simply dividing of each DCT coefficients with constant quantization matrix and round them into nearest number to calculate features of that image for performing similarity measure.","PeriodicalId":292190,"journal":{"name":"2011 International Conference on Computational Intelligence and Communication Networks","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131780406","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：