Pub Date : 2007-11-05DOI: 10.1109/ICSCN.2007.350694
D. Satyanarayana
One of the challenging tasks in the design of wireless ad hoc networks is the development of dynamic routing protocol that can efficiently transmit packets between two multihop communication nodes. Most of the geometric based greedy routing protocols suffer from the problem of local maximum. Inspite of this problem, it is not always efficient to use geometric graphs in the routing of adhoc networks. In this paper, we propose a new geometric routing algorithm called greedy local Delaunay triangulation (GLDT) protocol. GLDT uses greedy forwarding with its immediate neighborhood information. When a packet reaches the local maximum, the algorithm recovers it by using local Delaunay triangulation and forwards the packet using right hand rule. The algorithm not only solves the local maximum problem but also outperforms on end-to-end packet delay and delivery ratio compared to the previously proposed algorithms. The simulation results show the performance of GLDT protocol
{"title":"Greedy Local Delaunay Triangulation Routing for Wireless Ad Hoc Networks","authors":"D. Satyanarayana","doi":"10.1109/ICSCN.2007.350694","DOIUrl":"https://doi.org/10.1109/ICSCN.2007.350694","url":null,"abstract":"One of the challenging tasks in the design of wireless ad hoc networks is the development of dynamic routing protocol that can efficiently transmit packets between two multihop communication nodes. Most of the geometric based greedy routing protocols suffer from the problem of local maximum. Inspite of this problem, it is not always efficient to use geometric graphs in the routing of adhoc networks. In this paper, we propose a new geometric routing algorithm called greedy local Delaunay triangulation (GLDT) protocol. GLDT uses greedy forwarding with its immediate neighborhood information. When a packet reaches the local maximum, the algorithm recovers it by using local Delaunay triangulation and forwards the packet using right hand rule. The algorithm not only solves the local maximum problem but also outperforms on end-to-end packet delay and delivery ratio compared to the previously proposed algorithms. The simulation results show the performance of GLDT protocol","PeriodicalId":257948,"journal":{"name":"2007 International Conference on Signal Processing, Communications and Networking","volume":"168 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115377408","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 : 2007-11-05DOI: 10.1109/ICSCN.2007.350760
R. Srinivasan, V. Vaidehi, S. Arvind, A. Krishnakumar
Most of the prior works on formulating authentication schemes for multicast networks focus on less general models, where random, rather than adversarially selected, packets may be dropped and altered. Most of them don't tolerate new packet injections. In this paper an efficient secure reliable robust scheme is proposed and implementation results are presented. This scheme is based on a novel combination of error correcting codes with standard cryptographic primitives. A general network model is proposed where an adversary can perform various attacks on the transmitted streams. In this model, two parameters of the network, the survival rate and the flood rate, characterize the power of the adversary. This paper implement the authentication scheme in a generic manner so that the various network parameters, namely the survival rate, flood rate, decoder tolerance rate can be tuned to achieve better performance in terms of communication overhead and computation costs
{"title":"An Authentication Scheme for Multicast Networks","authors":"R. Srinivasan, V. Vaidehi, S. Arvind, A. Krishnakumar","doi":"10.1109/ICSCN.2007.350760","DOIUrl":"https://doi.org/10.1109/ICSCN.2007.350760","url":null,"abstract":"Most of the prior works on formulating authentication schemes for multicast networks focus on less general models, where random, rather than adversarially selected, packets may be dropped and altered. Most of them don't tolerate new packet injections. In this paper an efficient secure reliable robust scheme is proposed and implementation results are presented. This scheme is based on a novel combination of error correcting codes with standard cryptographic primitives. A general network model is proposed where an adversary can perform various attacks on the transmitted streams. In this model, two parameters of the network, the survival rate and the flood rate, characterize the power of the adversary. This paper implement the authentication scheme in a generic manner so that the various network parameters, namely the survival rate, flood rate, decoder tolerance rate can be tuned to achieve better performance in terms of communication overhead and computation costs","PeriodicalId":257948,"journal":{"name":"2007 International Conference on Signal Processing, Communications and Networking","volume":"247 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130725351","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 : 2007-11-05DOI: 10.1109/ICSCN.2007.350765
P. Kannan
Error concealment using information hiding has been an efficient tool to combat channel impairments that degrade the transmitted data quality by introducing channel errors/packet losses. The proposed model takes a stream of multimedia content and the binarised stream is subjected to bit level enhanced mapping procedure (PRASAN - Enhanced NFD approach) accompanied with a set of convergence models that ensure a high degree of convergence for a given error norm. The mapping is performed between the current frames with respect to the previous frame in case of video data. This approach often referred to as the correlation generation is followed by convergence mathematical function generation. This function is derived based on trying out the various convergence methodologies in a weighted round robin environment and choosing the best matching function by computing the mean square error. This error is termed map-fault and is kept a minimum. The test data taken are subjected to noisy channel environments and the power signal to noise ratios obtained experimentally support firmly the advantage of the proposed methodology in comparison to existing approaches
{"title":"Novel Convergence Model for Efficient Error Concealment using Information Hiding in Multimedia Streams","authors":"P. Kannan","doi":"10.1109/ICSCN.2007.350765","DOIUrl":"https://doi.org/10.1109/ICSCN.2007.350765","url":null,"abstract":"Error concealment using information hiding has been an efficient tool to combat channel impairments that degrade the transmitted data quality by introducing channel errors/packet losses. The proposed model takes a stream of multimedia content and the binarised stream is subjected to bit level enhanced mapping procedure (PRASAN - Enhanced NFD approach) accompanied with a set of convergence models that ensure a high degree of convergence for a given error norm. The mapping is performed between the current frames with respect to the previous frame in case of video data. This approach often referred to as the correlation generation is followed by convergence mathematical function generation. This function is derived based on trying out the various convergence methodologies in a weighted round robin environment and choosing the best matching function by computing the mean square error. This error is termed map-fault and is kept a minimum. The test data taken are subjected to noisy channel environments and the power signal to noise ratios obtained experimentally support firmly the advantage of the proposed methodology in comparison to existing approaches","PeriodicalId":257948,"journal":{"name":"2007 International Conference on Signal Processing, Communications and Networking","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124194700","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 : 2007-11-05DOI: 10.1109/ICSCN.2007.350780
W. Al-Khatib, A. Rajeswari, K. Gunavathi
The latest tremendous growth of the Internet has opened up a vast market for high-speed broadband data services to the home. Broadband network services have created great opportunities for new multimedia applications at both home and businesses. Data over cable service interface specification (DOCSIS) is the leading standard for data over cable networks. DOCSIS is developed to support IP flows with significantly higher data rate links for high quality data, audio, video and interactive services. It is important to provide traffic scheduling mechanisms to support quality of service (QoS) for such applications. DOCSIS defines six upstream services for supporting per-flow QoS. Among them it uses rt-PS service for real-time VBR traffic which has burst nature. The headend provides periodic opportunities for unicast request, namely polling, which yields higher delay and not suitable for real-time services. In this paper, a novel scheduling mechanism and bandwidth allocation algorithm has been proposed to support VBR multimedia traffic over DOCSIS. The proposed dynamic unsolicited grant service (DUGS) scheduling algorithm makes use of piggybacking request and changes the unsolicited grant size allocation dynamically. It is shown through simulation results that throughput, channel utilization and delay performance have been improved in case of DUGS, compared with current DOCSIS protocol. This algorithm can also keep fairness among connections
最近互联网的飞速发展为家庭高速宽带数据服务开辟了广阔的市场。宽带网络服务为家庭和企业的新型多媒体应用创造了巨大的机会。电缆数据服务接口规范(DOCSIS)是电缆数据网络的主要标准。开发DOCSIS是为了支持具有更高数据速率链路的IP流，以实现高质量的数据、音频、视频和交互式服务。提供流量调度机制以支持此类应用程序的服务质量(QoS)是非常重要的。DOCSIS定义了六个上游服务来支持逐流QoS。其中，对具有突发性质的实时VBR业务采用rt-PS业务。头端为单播请求提供周期性的机会，即轮询，产生较高的延迟，不适合实时服务。本文提出了一种新的调度机制和带宽分配算法来支持基于DOCSIS的VBR多媒体流量。提出的DUGS (dynamic unsolicited grant service)调度算法利用了负载请求，动态地改变了unsolicited grant大小的分配。仿真结果表明，与现有的DOCSIS协议相比，DUGS协议的吞吐量、信道利用率和延迟性能都得到了提高。该算法还可以保持连接之间的公平性
{"title":"Bandwidth Allocation Algorithm for DOCSIS Based HFC Broadband Networks","authors":"W. Al-Khatib, A. Rajeswari, K. Gunavathi","doi":"10.1109/ICSCN.2007.350780","DOIUrl":"https://doi.org/10.1109/ICSCN.2007.350780","url":null,"abstract":"The latest tremendous growth of the Internet has opened up a vast market for high-speed broadband data services to the home. Broadband network services have created great opportunities for new multimedia applications at both home and businesses. Data over cable service interface specification (DOCSIS) is the leading standard for data over cable networks. DOCSIS is developed to support IP flows with significantly higher data rate links for high quality data, audio, video and interactive services. It is important to provide traffic scheduling mechanisms to support quality of service (QoS) for such applications. DOCSIS defines six upstream services for supporting per-flow QoS. Among them it uses rt-PS service for real-time VBR traffic which has burst nature. The headend provides periodic opportunities for unicast request, namely polling, which yields higher delay and not suitable for real-time services. In this paper, a novel scheduling mechanism and bandwidth allocation algorithm has been proposed to support VBR multimedia traffic over DOCSIS. The proposed dynamic unsolicited grant service (DUGS) scheduling algorithm makes use of piggybacking request and changes the unsolicited grant size allocation dynamically. It is shown through simulation results that throughput, channel utilization and delay performance have been improved in case of DUGS, compared with current DOCSIS protocol. This algorithm can also keep fairness among connections","PeriodicalId":257948,"journal":{"name":"2007 International Conference on Signal Processing, Communications and Networking","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115078508","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 : 2007-11-05DOI: 10.1109/ICSCN.2007.350751
A. Vaish, M. Singh
Microstrip patch antennas are very popular due to their numerous advantages. This paper presents the design of a log periodic toothed planer trapezoid microstrip antenna. In this structure the dimensions of the successive sections were increased in geometric progression. A bandwidth of 18.18 percentage for voltage standing wave ratio less than two (VSWR<2) has been obtained from the proposed antenna. Investigations on the impedance and radiation characteristics have been carried out. The investigations show that the proposed antenna not only offers the enhanced impedance bandwidth, but also possesses the same characteristics over the desired frequency band
{"title":"Design and Analysis of Four Cells Log Periodic Trapezoid Microstrip Antenna","authors":"A. Vaish, M. Singh","doi":"10.1109/ICSCN.2007.350751","DOIUrl":"https://doi.org/10.1109/ICSCN.2007.350751","url":null,"abstract":"Microstrip patch antennas are very popular due to their numerous advantages. This paper presents the design of a log periodic toothed planer trapezoid microstrip antenna. In this structure the dimensions of the successive sections were increased in geometric progression. A bandwidth of 18.18 percentage for voltage standing wave ratio less than two (VSWR<2) has been obtained from the proposed antenna. Investigations on the impedance and radiation characteristics have been carried out. The investigations show that the proposed antenna not only offers the enhanced impedance bandwidth, but also possesses the same characteristics over the desired frequency band","PeriodicalId":257948,"journal":{"name":"2007 International Conference on Signal Processing, Communications and Networking","volume":"20 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123540475","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 : 2007-11-05DOI: 10.1109/ICSCN.2007.350744
L. Subramanian, H. Chandrababu, P. Moorthy, M. Kannan
This paper proposes a parallel architecture for motion estimation using the enhanced successive elimination (Enhanced SE) algorithm. The basic idea of this algorithm is to estimate the motion of an object by eliminating repeated access of search blocks, intense storage and computation, for all search blocks, thereby reducing power. Therefore, a parallel architecture employing this algorithm is more energy efficient as it is not as computation intensive as other block matching algorithms. Further, an architecture is used that prevents redundant memory accesses. The simulation and synthesis were carried out using Cadence tools, NcSim and RTL Compiler respectively, with 90 nm libraries. Low power, Multi VT and DFT flows have been executed. Logic equivalence has also been checked
{"title":"Analysis and Implementation of Parallel Low-Complexity Motion Estimation","authors":"L. Subramanian, H. Chandrababu, P. Moorthy, M. Kannan","doi":"10.1109/ICSCN.2007.350744","DOIUrl":"https://doi.org/10.1109/ICSCN.2007.350744","url":null,"abstract":"This paper proposes a parallel architecture for motion estimation using the enhanced successive elimination (Enhanced SE) algorithm. The basic idea of this algorithm is to estimate the motion of an object by eliminating repeated access of search blocks, intense storage and computation, for all search blocks, thereby reducing power. Therefore, a parallel architecture employing this algorithm is more energy efficient as it is not as computation intensive as other block matching algorithms. Further, an architecture is used that prevents redundant memory accesses. The simulation and synthesis were carried out using Cadence tools, NcSim and RTL Compiler respectively, with 90 nm libraries. Low power, Multi VT and DFT flows have been executed. Logic equivalence has also been checked","PeriodicalId":257948,"journal":{"name":"2007 International Conference on Signal Processing, Communications and Networking","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129805100","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 : 2007-11-05DOI: 10.1109/ICSCN.2007.350725
K. Santha, V. Vaidehi
The requirement of many data communication systems is to employ an adaptive equalizer to minimize the inter-symbol interference. Several adaptive Kalman equalizers have been reported in literature. In these works either the least mean square (LMS) or the recursive least squares (RLS) or the Kalman algorithm have been adopted for channel estimation. The Kalman estimation method can lead to significant improvement in the receiver bit error rate (BER) performance. The use of a Kalman filter for channel estimation leads to a state model of size 2ntimes2n, where n is the number of filter taps. These solutions are computationally intensive and follow a nonlinear relation in the observation equation. New methods have to be followed to solve the nonlinear model resulting in complex parallel structures. This paper proposes a new approach for the real time implementation of the adaptive Kalman equalizer by providing two Kalman filters that run concurrently to perform the estimation and detection. Thus the Kalman estimator operates in parallel with the Kalman filter based equalizer following a linear model and the size of the state matrix reduces to ntimesn. Parallel-pipelined architectures are proposed to perform the time update and measurement update equations of the Kalman equalizer and Kalman estimator. The functionality of the proposed architecture has been verified through VHDL simulation. The synthesis results are presented. It is shown that the convergence performance of the proposed approach is superior to that of the Kalman-RLS and Kalman-LMS adaptive equalizers
{"title":"Parallel-Pipelined Architecture for the Kalman Based Adaptive Equalizer","authors":"K. Santha, V. Vaidehi","doi":"10.1109/ICSCN.2007.350725","DOIUrl":"https://doi.org/10.1109/ICSCN.2007.350725","url":null,"abstract":"The requirement of many data communication systems is to employ an adaptive equalizer to minimize the inter-symbol interference. Several adaptive Kalman equalizers have been reported in literature. In these works either the least mean square (LMS) or the recursive least squares (RLS) or the Kalman algorithm have been adopted for channel estimation. The Kalman estimation method can lead to significant improvement in the receiver bit error rate (BER) performance. The use of a Kalman filter for channel estimation leads to a state model of size 2ntimes2n, where n is the number of filter taps. These solutions are computationally intensive and follow a nonlinear relation in the observation equation. New methods have to be followed to solve the nonlinear model resulting in complex parallel structures. This paper proposes a new approach for the real time implementation of the adaptive Kalman equalizer by providing two Kalman filters that run concurrently to perform the estimation and detection. Thus the Kalman estimator operates in parallel with the Kalman filter based equalizer following a linear model and the size of the state matrix reduces to ntimesn. Parallel-pipelined architectures are proposed to perform the time update and measurement update equations of the Kalman equalizer and Kalman estimator. The functionality of the proposed architecture has been verified through VHDL simulation. The synthesis results are presented. It is shown that the convergence performance of the proposed approach is superior to that of the Kalman-RLS and Kalman-LMS adaptive equalizers","PeriodicalId":257948,"journal":{"name":"2007 International Conference on Signal Processing, Communications and Networking","volume":"2007 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127300129","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 : 2007-11-05DOI: 10.1109/ICSCN.2007.350653
B. Sardar, Y. Maru, S. Reddy, N. Hegde, A. Sen, R. Arora
A cost-performance optimised design of GeoComm, geo-intelligent mobile communication and tracking system, is presented along with design validation and test results. The unique design features and the potential applications of this design are described
{"title":"Geocomm - A Cost Optimised Geo Intelligent Mobile Communicator and Tracker","authors":"B. Sardar, Y. Maru, S. Reddy, N. Hegde, A. Sen, R. Arora","doi":"10.1109/ICSCN.2007.350653","DOIUrl":"https://doi.org/10.1109/ICSCN.2007.350653","url":null,"abstract":"A cost-performance optimised design of GeoComm, geo-intelligent mobile communication and tracking system, is presented along with design validation and test results. The unique design features and the potential applications of this design are described","PeriodicalId":257948,"journal":{"name":"2007 International Conference on Signal Processing, Communications and Networking","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130881549","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 : 2007-11-05DOI: 10.1109/ICSCN.2007.350783
K. Vimala Devi, K. Mehata
Active networks provide a programmable user-network interface that supports dynamic modification of the network's behavior. Network nodes, in addition to forwarding packets, perform customized computation on the messages flowing through them. Individual packets carry executable code, or references to executable code. Active networks are changing considerably the scenery of computer networks and consequently, affect the way network management is conducted. Performance management is strongly related to quality of service (QoS) provisioning. In a heterogeneous networking environment, each node must understand the varying resource demands associated with specific network traffic. This paper describes and evaluates an approach to control the CPU utilization of malicious packets and to estimate the CPU demand for good packets in a heterogeneous active network environment. The network management systems can allocate the capacity better by anticipating varying demands and the network operators can better estimate the quality of service (QoS) that customers can expect
{"title":"Resource Control and Prediction Management for Quality of Service in Heterogeneous Active Networks","authors":"K. Vimala Devi, K. Mehata","doi":"10.1109/ICSCN.2007.350783","DOIUrl":"https://doi.org/10.1109/ICSCN.2007.350783","url":null,"abstract":"Active networks provide a programmable user-network interface that supports dynamic modification of the network's behavior. Network nodes, in addition to forwarding packets, perform customized computation on the messages flowing through them. Individual packets carry executable code, or references to executable code. Active networks are changing considerably the scenery of computer networks and consequently, affect the way network management is conducted. Performance management is strongly related to quality of service (QoS) provisioning. In a heterogeneous networking environment, each node must understand the varying resource demands associated with specific network traffic. This paper describes and evaluates an approach to control the CPU utilization of malicious packets and to estimate the CPU demand for good packets in a heterogeneous active network environment. The network management systems can allocate the capacity better by anticipating varying demands and the network operators can better estimate the quality of service (QoS) that customers can expect","PeriodicalId":257948,"journal":{"name":"2007 International Conference on Signal Processing, Communications and Networking","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131627705","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 : 2007-11-05DOI: 10.1109/ICSCN.2007.350778
V. Devendran, H. Thiagarajan, A. Wahi
Artificial neural networks, inspired by the information-processing strategies of the brain, are proving to be useful in a variety of the applications including object classification problems and many other areas of interest, can be updated continuously with new data to optimize its performance at any instant. The performance of the neural classifiers depends on many criteria i.e., structure of neural networks, initial weights, feature data, number of training samples used which are all still a challenging issues among the research community. This paper discusses a novel approach to improve the performance of neural classifier by changing the methodology of presenting the training samples to the neural classifier. The results are proving that network also depends on the methodology of giving the samples to the classifier. This work is carried out using real world dataset
{"title":"Novel Approach to Improve the Performance of Artificial Neural Networks","authors":"V. Devendran, H. Thiagarajan, A. Wahi","doi":"10.1109/ICSCN.2007.350778","DOIUrl":"https://doi.org/10.1109/ICSCN.2007.350778","url":null,"abstract":"Artificial neural networks, inspired by the information-processing strategies of the brain, are proving to be useful in a variety of the applications including object classification problems and many other areas of interest, can be updated continuously with new data to optimize its performance at any instant. The performance of the neural classifiers depends on many criteria i.e., structure of neural networks, initial weights, feature data, number of training samples used which are all still a challenging issues among the research community. This paper discusses a novel approach to improve the performance of neural classifier by changing the methodology of presenting the training samples to the neural classifier. The results are proving that network also depends on the methodology of giving the samples to the classifier. This work is carried out using real world dataset","PeriodicalId":257948,"journal":{"name":"2007 International Conference on Signal Processing, Communications and Networking","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133119176","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：