Pub Date : 2013-03-09DOI: 10.1109/ICISCON.2013.6524195
B. Patil, S. Kinger, V. Pathak
Fault diagnosis is a central aspect of network fault management. Since faults are unavoidable in communication systems, their quick detection and isolation is essential for the robustness, reliability, and accessibility of a system. Probing technique for fault localization involves placement of probe stations (Probe stations are specially instrumented nodes from where probes can be sent to monitor the network) which affects the diagnosis capability of the probes sent by the probe stations. Probe station locations affect probing efficiency, monitoring capability, and deployment cost. At the same time, probe station selection affects the selection of probe set for fault localization. We are presenting a novel approach for minimal probe station selection with an objective to reduce probe set size that will be used for fault localization. The probe station selected through this approach results into reduced deployment cost as well as it helps in producing smaller probe set for fault localization reducing overall operation cost. We provide experimental evaluation of the proposed algorithms through simulation results.
{"title":"Probe station placement algorithm for probe set reduction in network fault localization","authors":"B. Patil, S. Kinger, V. Pathak","doi":"10.1109/ICISCON.2013.6524195","DOIUrl":"https://doi.org/10.1109/ICISCON.2013.6524195","url":null,"abstract":"Fault diagnosis is a central aspect of network fault management. Since faults are unavoidable in communication systems, their quick detection and isolation is essential for the robustness, reliability, and accessibility of a system. Probing technique for fault localization involves placement of probe stations (Probe stations are specially instrumented nodes from where probes can be sent to monitor the network) which affects the diagnosis capability of the probes sent by the probe stations. Probe station locations affect probing efficiency, monitoring capability, and deployment cost. At the same time, probe station selection affects the selection of probe set for fault localization. We are presenting a novel approach for minimal probe station selection with an objective to reduce probe set size that will be used for fault localization. The probe station selected through this approach results into reduced deployment cost as well as it helps in producing smaller probe set for fault localization reducing overall operation cost. We provide experimental evaluation of the proposed algorithms through simulation results.","PeriodicalId":216110,"journal":{"name":"2013 International Conference on Information Systems and Computer Networks","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127295863","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 : 2013-03-09DOI: 10.1109/ICISCON.2013.6524162
D. Ather, R. Singh, V. Katiyar
Theory of computation is always been an issue for the students to understand. This paper present a algorithm which will simplify the method to design Deterministic finite automata that accept strings over input symbol a, b having exactly x number of a & y number of b. Objective of the research is to make the method of teaching learning easier, simpler and understandable for students. In this paper we develop an algorithm to design finite automata that accept strings over input symbol a, b having exactly x number of a & y number of b.
{"title":"An algorithm to design finite automata that accept strings over input symbol a and b having exactly x number of a & y number of b","authors":"D. Ather, R. Singh, V. Katiyar","doi":"10.1109/ICISCON.2013.6524162","DOIUrl":"https://doi.org/10.1109/ICISCON.2013.6524162","url":null,"abstract":"Theory of computation is always been an issue for the students to understand. This paper present a algorithm which will simplify the method to design Deterministic finite automata that accept strings over input symbol a, b having exactly x number of a & y number of b. Objective of the research is to make the method of teaching learning easier, simpler and understandable for students. In this paper we develop an algorithm to design finite automata that accept strings over input symbol a, b having exactly x number of a & y number of b.","PeriodicalId":216110,"journal":{"name":"2013 International Conference on Information Systems and Computer Networks","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129462459","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 : 2013-03-09DOI: 10.1109/ICISCON.2013.6524196
Ankit Gupta, Shruti Kohli, SN Jha
Grid computing is one of the most important domain of distributed network. Scheduling in grid is a challenging task to the researchers around the globe. Many different kind of algorithms has been proposed in the literature but because Grid scheduling is a NP-complete problem, more work is undergoing to make the process more optimized and which can provide more effective and efficient solution to the grid load balancing. This paper tries to show some different aspect of one of the most popular grid scheduling algorithm EDF-BF under a special kind of load balancing scheme based on a QoS constraint-CPU speed of the Clusters. Three different parameters were used to test the effectiveness of the approach and the output shows that this novel approach although unconventional, is very effective and a grid scheduler can user this QoS driven approach for this algorithm.
{"title":"Performance of EDF-BF algorithm under QoS constraint in grid heterogeneous environment","authors":"Ankit Gupta, Shruti Kohli, SN Jha","doi":"10.1109/ICISCON.2013.6524196","DOIUrl":"https://doi.org/10.1109/ICISCON.2013.6524196","url":null,"abstract":"Grid computing is one of the most important domain of distributed network. Scheduling in grid is a challenging task to the researchers around the globe. Many different kind of algorithms has been proposed in the literature but because Grid scheduling is a NP-complete problem, more work is undergoing to make the process more optimized and which can provide more effective and efficient solution to the grid load balancing. This paper tries to show some different aspect of one of the most popular grid scheduling algorithm EDF-BF under a special kind of load balancing scheme based on a QoS constraint-CPU speed of the Clusters. Three different parameters were used to test the effectiveness of the approach and the output shows that this novel approach although unconventional, is very effective and a grid scheduler can user this QoS driven approach for this algorithm.","PeriodicalId":216110,"journal":{"name":"2013 International Conference on Information Systems and Computer Networks","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115689941","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 : 2013-03-09DOI: 10.1109/ICISCON.2013.6524182
R. Popli, N. Chauhan
In the last few years Agile methodologies appeared as a reaction to traditional software development methodologies. The Scrum is the widely used method of Agile. Most of the software development organizations are using Scrum these days but these are facing problems related to estimation of cost and effort. It has been observed that the current estimation method in Scrum mostly rely on historical data from past projects and expert opinion but in absence of historical data and experts these methods are not efficient. So there is need of an algorithmic method, which can calculate cost and effort of the software project. In this direction S. Bhalero, Maya Ingel [2] has considered some project-related factors that calculate the cost as well as effort of the project for a general Agile environment. However, several other project as well as people related factors may affect the Scrum environment. In this work an Algorithmic estimation method is being proposed considering various factors thereby estimating the more accurate release date, cost, effort and duration for the project specifically for Scrum. The effectiveness and feasibility of the proposed algorithm has been shown by considering three cases in which different levels of factors are taken and compared.
{"title":"A sprint-point based estimation technique in Scrum","authors":"R. Popli, N. Chauhan","doi":"10.1109/ICISCON.2013.6524182","DOIUrl":"https://doi.org/10.1109/ICISCON.2013.6524182","url":null,"abstract":"In the last few years Agile methodologies appeared as a reaction to traditional software development methodologies. The Scrum is the widely used method of Agile. Most of the software development organizations are using Scrum these days but these are facing problems related to estimation of cost and effort. It has been observed that the current estimation method in Scrum mostly rely on historical data from past projects and expert opinion but in absence of historical data and experts these methods are not efficient. So there is need of an algorithmic method, which can calculate cost and effort of the software project. In this direction S. Bhalero, Maya Ingel [2] has considered some project-related factors that calculate the cost as well as effort of the project for a general Agile environment. However, several other project as well as people related factors may affect the Scrum environment. In this work an Algorithmic estimation method is being proposed considering various factors thereby estimating the more accurate release date, cost, effort and duration for the project specifically for Scrum. The effectiveness and feasibility of the proposed algorithm has been shown by considering three cases in which different levels of factors are taken and compared.","PeriodicalId":216110,"journal":{"name":"2013 International Conference on Information Systems and Computer Networks","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127314097","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 : 2013-03-09DOI: 10.1109/ICISCON.2013.6524203
S. Bansal, P. Pandey
Rapid progression of Internet technology and related services has enhanced the simplicity of access to digital information through web, leading to the problem of associated copyright to be confined. The problem of rightful ownership has direct to giving the digital watermarking as an evident solution. The paper has been proposed to emphasize the security issues in new robust reference logo watermarking scheme in Fractional Fourier Transform domain. Recently Bhatnagar and Raman have provided a robust reference logo watermarking algorithm for digital images based on singular value decomposition. Through this paper we have enlighten the issue of false positive problem in reference watermarking algorithm. We have extracted a false watermark by using our proposed algorithm from the reference watermarking scheme in Fractional Fourier Transform domain. Mathematical analysis and experimental results has been used to support our conclusion.
{"title":"On the security of robust reference logo watermarking scheme in Fractional Fourier Transform domain","authors":"S. Bansal, P. Pandey","doi":"10.1109/ICISCON.2013.6524203","DOIUrl":"https://doi.org/10.1109/ICISCON.2013.6524203","url":null,"abstract":"Rapid progression of Internet technology and related services has enhanced the simplicity of access to digital information through web, leading to the problem of associated copyright to be confined. The problem of rightful ownership has direct to giving the digital watermarking as an evident solution. The paper has been proposed to emphasize the security issues in new robust reference logo watermarking scheme in Fractional Fourier Transform domain. Recently Bhatnagar and Raman have provided a robust reference logo watermarking algorithm for digital images based on singular value decomposition. Through this paper we have enlighten the issue of false positive problem in reference watermarking algorithm. We have extracted a false watermark by using our proposed algorithm from the reference watermarking scheme in Fractional Fourier Transform domain. Mathematical analysis and experimental results has been used to support our conclusion.","PeriodicalId":216110,"journal":{"name":"2013 International Conference on Information Systems and Computer Networks","volume":"253 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134151860","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 : 2013-03-09DOI: 10.1109/ICISCON.2013.6524184
Ashutosh Kumar Singh, R. Singh
Software Quality is the very popular and a very important topic for researchers within the software engineering communities, most probably everyone has an opinion about the meaning of quality. However, many disagreements and conflicts are very often leaded between peoples whose involve in software development, when they implement to it in the real world. This has been highly notable in the case of customer's complaints about faults in the software products. It is well known that many organizations or individuals are relishing many challenges to preserve software product quality, whenever they develop any types of software product. Appearance of defects is the very much contributor to reduce the product quality and prominently increases in development costs and completion time due to amendment and rework time. The success and demand of a software system is not only pivot on cost and proceedings, but also on software quality. In between many software quality features, to identify the vestigial defects in the product has become the actual industry standard. This paper is a study about software quality, software defect and how both are relate to each other and also discuss defect prediction is batter approach in compare defect correction to assure software product quality. We also discuss some data mining methodologies in brief; they are used to build defect prediction models to ensure the level of defect density of target program modules of software product.
{"title":"Assuring Software Quality using data mining methodology: A literature study","authors":"Ashutosh Kumar Singh, R. Singh","doi":"10.1109/ICISCON.2013.6524184","DOIUrl":"https://doi.org/10.1109/ICISCON.2013.6524184","url":null,"abstract":"Software Quality is the very popular and a very important topic for researchers within the software engineering communities, most probably everyone has an opinion about the meaning of quality. However, many disagreements and conflicts are very often leaded between peoples whose involve in software development, when they implement to it in the real world. This has been highly notable in the case of customer's complaints about faults in the software products. It is well known that many organizations or individuals are relishing many challenges to preserve software product quality, whenever they develop any types of software product. Appearance of defects is the very much contributor to reduce the product quality and prominently increases in development costs and completion time due to amendment and rework time. The success and demand of a software system is not only pivot on cost and proceedings, but also on software quality. In between many software quality features, to identify the vestigial defects in the product has become the actual industry standard. This paper is a study about software quality, software defect and how both are relate to each other and also discuss defect prediction is batter approach in compare defect correction to assure software product quality. We also discuss some data mining methodologies in brief; they are used to build defect prediction models to ensure the level of defect density of target program modules of software product.","PeriodicalId":216110,"journal":{"name":"2013 International Conference on Information Systems and Computer Networks","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116512455","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 : 2013-03-09DOI: 10.1109/ICISCON.2013.6524205
P. Sethi, N. Chauhan, D. Juneja
Data fusion deals with collaborative in-network processing and gathers relatively accurate information about the events in the environment. Conventional data fusion algorithms when assisted with mobile agent technology shifts computationally intensive tasks to these intelligent units thereby increasing the lifetime of the network. There exist mobile agent based event driven protocols for accumulating and forwarding the information to the sink(base station) eg: Tree-based Itinerary Design [4]. Usually, such protocols either deploy value-based fusion or decision-based fusion but very few are using both at the same time. Moreover, use of multi-agent systems(MAS) in such protocols is still in its infancy. The focus of this work is thus to propose a multi-agent hybrid protocol exploiting the benefits of both value and decision fusion by performing aggregation at the source level in a clustered WSN.
{"title":"A multi-agent hybrid protocol for data fusion and data aggregation in non-deterministic wireless sensor networks","authors":"P. Sethi, N. Chauhan, D. Juneja","doi":"10.1109/ICISCON.2013.6524205","DOIUrl":"https://doi.org/10.1109/ICISCON.2013.6524205","url":null,"abstract":"Data fusion deals with collaborative in-network processing and gathers relatively accurate information about the events in the environment. Conventional data fusion algorithms when assisted with mobile agent technology shifts computationally intensive tasks to these intelligent units thereby increasing the lifetime of the network. There exist mobile agent based event driven protocols for accumulating and forwarding the information to the sink(base station) eg: Tree-based Itinerary Design [4]. Usually, such protocols either deploy value-based fusion or decision-based fusion but very few are using both at the same time. Moreover, use of multi-agent systems(MAS) in such protocols is still in its infancy. The focus of this work is thus to propose a multi-agent hybrid protocol exploiting the benefits of both value and decision fusion by performing aggregation at the source level in a clustered WSN.","PeriodicalId":216110,"journal":{"name":"2013 International Conference on Information Systems and Computer Networks","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133663582","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 : 2013-03-09DOI: 10.1109/ICISCON.2013.6524179
R. Soni, D. Puja
This paper compares the performance of Gradient descent with momentum & adaptive backpropagation (TRAINGDX) and BFGS quasi-Newton backpropagation (TRAINBFG) of Backpropagation Algorithm in multilayer feed forward Neural Network for Handwritten English Characters of Vowels. This analysis is done with five samples of Handwritten English Characters of Vowels collected from five different people and stored as an image. After partition these scanned image into 4 portions, the densities of these images are determined by using MATLAB function. An input pattern will use these 4 densities of each character as an input for the two different Neural Network architectures. In our proposed work the Multilayer feed forward neural networks will train with two learning algorithms; those are the variant of Backpropagation learning algorithm namely Quasi-Newton backpropagation learning algorithm and Gradient descent with momentum and adaptive backpropagation learning algorithm for training set of the Handwritten English Characters of Vowels. The performance analysis of both Neural Network architectures is done for convergence and nonconvergence. Different observations have been considered for trends of error in the case of nonconvergence. From the observation of the result, it can be shown that in the performance of these above two learning algorithms with the training set of handwritten characters of Vowels, there is limitation of gradient descent learning algorithm for convergence due to the problem of local minima which is inherit problem of backpropagation learning algorithm.
{"title":"Performance evaluation of multilayer feed forward neural network for handwritten English Vowels Characters","authors":"R. Soni, D. Puja","doi":"10.1109/ICISCON.2013.6524179","DOIUrl":"https://doi.org/10.1109/ICISCON.2013.6524179","url":null,"abstract":"This paper compares the performance of Gradient descent with momentum & adaptive backpropagation (TRAINGDX) and BFGS quasi-Newton backpropagation (TRAINBFG) of Backpropagation Algorithm in multilayer feed forward Neural Network for Handwritten English Characters of Vowels. This analysis is done with five samples of Handwritten English Characters of Vowels collected from five different people and stored as an image. After partition these scanned image into 4 portions, the densities of these images are determined by using MATLAB function. An input pattern will use these 4 densities of each character as an input for the two different Neural Network architectures. In our proposed work the Multilayer feed forward neural networks will train with two learning algorithms; those are the variant of Backpropagation learning algorithm namely Quasi-Newton backpropagation learning algorithm and Gradient descent with momentum and adaptive backpropagation learning algorithm for training set of the Handwritten English Characters of Vowels. The performance analysis of both Neural Network architectures is done for convergence and nonconvergence. Different observations have been considered for trends of error in the case of nonconvergence. From the observation of the result, it can be shown that in the performance of these above two learning algorithms with the training set of handwritten characters of Vowels, there is limitation of gradient descent learning algorithm for convergence due to the problem of local minima which is inherit problem of backpropagation learning algorithm.","PeriodicalId":216110,"journal":{"name":"2013 International Conference on Information Systems and Computer Networks","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132039305","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 : 2013-03-09DOI: 10.1109/ICISCON.2013.6524206
P. Puri, M. Singh
This paper presents a comprehensive survey on delay-tolerant networks, an architecture originally designed for the Interplanetary Internet, this delay-tolerant networks is a communication system used to provide Internet-like services in interplanetary distances to support of deep space exploration. This paper describes the basic of Delay-Tolerant Networks (DTN) and its different areas. It also explores the routing techniques used in Delay-Tolerant Networks (DTN). It also comprises the comparison of different routing protocols in Delay-Tolerant Networks (DTN). At last, based on shortcoming of existing protocol, this paper presents the problem definition for new work.
{"title":"A survey paper on routing in delay-tolerant networks","authors":"P. Puri, M. Singh","doi":"10.1109/ICISCON.2013.6524206","DOIUrl":"https://doi.org/10.1109/ICISCON.2013.6524206","url":null,"abstract":"This paper presents a comprehensive survey on delay-tolerant networks, an architecture originally designed for the Interplanetary Internet, this delay-tolerant networks is a communication system used to provide Internet-like services in interplanetary distances to support of deep space exploration. This paper describes the basic of Delay-Tolerant Networks (DTN) and its different areas. It also explores the routing techniques used in Delay-Tolerant Networks (DTN). It also comprises the comparison of different routing protocols in Delay-Tolerant Networks (DTN). At last, based on shortcoming of existing protocol, this paper presents the problem definition for new work.","PeriodicalId":216110,"journal":{"name":"2013 International Conference on Information Systems and Computer Networks","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116674981","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 : 2013-03-09DOI: 10.1109/ICISCON.2013.6524198
N. Akhtar, S. N. Khan
Many of the engineering applications employ linear algebra to furnish the analysis. Image Processing deals with Eigen values/vectors, Machine Design requires principal component analysis of stress, Statistics and Data compression requires minimization of dimensionality in data. Singular Value Decomposition serves as the answer to all these varied needs. This method alone serves many computational & analytical purposes. Although the computation of SVD of a matrix is bulky, the process involves a sequence of vector operations. This makes it a good candidate for parallelization of over Graphic Processors. This paper proposes parallelization of SVD modules in LAPACK over GPGPU using OpenCL. OpenCL is crucial for making the implementation platform independent. Narayanan[1] too considers parallelization of SVD over CUDA using CUBLAS. This work proposes a scheme which is platform independent, and focuses on routines beyond BLAS.
{"title":"Optimization of SVD over Graphic Processor","authors":"N. Akhtar, S. N. Khan","doi":"10.1109/ICISCON.2013.6524198","DOIUrl":"https://doi.org/10.1109/ICISCON.2013.6524198","url":null,"abstract":"Many of the engineering applications employ linear algebra to furnish the analysis. Image Processing deals with Eigen values/vectors, Machine Design requires principal component analysis of stress, Statistics and Data compression requires minimization of dimensionality in data. Singular Value Decomposition serves as the answer to all these varied needs. This method alone serves many computational & analytical purposes. Although the computation of SVD of a matrix is bulky, the process involves a sequence of vector operations. This makes it a good candidate for parallelization of over Graphic Processors. This paper proposes parallelization of SVD modules in LAPACK over GPGPU using OpenCL. OpenCL is crucial for making the implementation platform independent. Narayanan[1] too considers parallelization of SVD over CUDA using CUBLAS. This work proposes a scheme which is platform independent, and focuses on routines beyond BLAS.","PeriodicalId":216110,"journal":{"name":"2013 International Conference on Information Systems and Computer Networks","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125438363","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：