Pub Date : 2012-12-31DOI: 10.1109/ICCICT.2012.6398173
Ahlam Ansari, K. Devadkar
Back Propagation Network (BPN) is one of the widely used neural network. Despite of worldwide adoption it suffers from performance degradation if the number of training data set and attributes increase. In this paper, we propose a novel method to improve the performance of BPN using Grid Computing. Using grid a set of disparate resources connected through a middleware can be used for increasing the performance of BPN.
{"title":"Grid Computing based Back Propagation Network","authors":"Ahlam Ansari, K. Devadkar","doi":"10.1109/ICCICT.2012.6398173","DOIUrl":"https://doi.org/10.1109/ICCICT.2012.6398173","url":null,"abstract":"Back Propagation Network (BPN) is one of the widely used neural network. Despite of worldwide adoption it suffers from performance degradation if the number of training data set and attributes increase. In this paper, we propose a novel method to improve the performance of BPN using Grid Computing. Using grid a set of disparate resources connected through a middleware can be used for increasing the performance of BPN.","PeriodicalId":319467,"journal":{"name":"2012 International Conference on Communication, Information & Computing Technology (ICCICT)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116947316","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 : 2012-12-31DOI: 10.1109/ICCICT.2012.6398099
S. Tannu, A. Sharma
Realization of high-quality random number generator (RNG) is essential for secure communication. In this paper, a RNG, which utilizes single-electron phenomena, is proposed. A room-temperature operating titanium oxide single-electron transistor(SET) is considered. Electron pocket is used as a high-quality, ultra-small RNG. In the proposed RNG, a stochastic single-electron capture/emission process is utilized to generate the 16 bit random numbers. Because of its small-size and low-power, it has potential to change the future of encryption.
{"title":"Low power random number generator using single electron transistor","authors":"S. Tannu, A. Sharma","doi":"10.1109/ICCICT.2012.6398099","DOIUrl":"https://doi.org/10.1109/ICCICT.2012.6398099","url":null,"abstract":"Realization of high-quality random number generator (RNG) is essential for secure communication. In this paper, a RNG, which utilizes single-electron phenomena, is proposed. A room-temperature operating titanium oxide single-electron transistor(SET) is considered. Electron pocket is used as a high-quality, ultra-small RNG. In the proposed RNG, a stochastic single-electron capture/emission process is utilized to generate the 16 bit random numbers. Because of its small-size and low-power, it has potential to change the future of encryption.","PeriodicalId":319467,"journal":{"name":"2012 International Conference on Communication, Information & Computing Technology (ICCICT)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125561898","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 : 2012-12-31DOI: 10.1109/ICCICT.2012.6398189
M. Arif, R. Anand
In this paper, a comparison is made among the performance of transform domain techniques with respect to various performance parameters of speech signal. The speech signal is taken from the International Phonetic Alphabet data base in the category of a Narrative of the French language and then the computation of compression ratio is carried out by setting appropriate threshold values in all the transform domain techniques. After that, the other speech signal parameters such as mean square error, signal o noise ratio, peak signal to noise ratio and normalized root mean square error are computed at the decoder end. The results shown indicate that the performance of the discrete sine transform is better than the discrete cosine transform and fast Fourier transform in terms of compression ratio and other computed speech signal parameters.
{"title":"Comparative evaluation of transform domain speech compression techniques","authors":"M. Arif, R. Anand","doi":"10.1109/ICCICT.2012.6398189","DOIUrl":"https://doi.org/10.1109/ICCICT.2012.6398189","url":null,"abstract":"In this paper, a comparison is made among the performance of transform domain techniques with respect to various performance parameters of speech signal. The speech signal is taken from the International Phonetic Alphabet data base in the category of a Narrative of the French language and then the computation of compression ratio is carried out by setting appropriate threshold values in all the transform domain techniques. After that, the other speech signal parameters such as mean square error, signal o noise ratio, peak signal to noise ratio and normalized root mean square error are computed at the decoder end. The results shown indicate that the performance of the discrete sine transform is better than the discrete cosine transform and fast Fourier transform in terms of compression ratio and other computed speech signal parameters.","PeriodicalId":319467,"journal":{"name":"2012 International Conference on Communication, Information & Computing Technology (ICCICT)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122456138","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 : 2012-12-31DOI: 10.1109/ICCICT.2012.6398223
P. Shete, P. Venkat, D. Sarode, M. Laghate, S. K. Bose, R. Mundada
In this paper, we propose and implement an object oriented framework for the GPU based image processing. Compute Unified Device Architecture i.e. the CUDA is a novel and promising GPU programming framework from the NVIDIA. The CUDA has been used to speedup many computationally intensive graphics as well as non graphics applications, but it requires more than just kernel programming. A pyramidal image blending algorithm is essential for a seamless panoramic mosaic. We introduce an object oriented framework for the CUDA based pyramidal image blending using software engineering principles and design patterns. We illustrate a set of design patterns, which assist in reusing an existing functionality. We show that use of design patterns facilitate extending existing functionality by adding new classes, rather than modifying an existing classes or functionality. We also talk about extending our framework for computation using the GPU texture memory. We talk about the framework's performance in terms of programming efforts and a speedup factor achieved.
{"title":"Object oriented framework for CUDA based image processing","authors":"P. Shete, P. Venkat, D. Sarode, M. Laghate, S. K. Bose, R. Mundada","doi":"10.1109/ICCICT.2012.6398223","DOIUrl":"https://doi.org/10.1109/ICCICT.2012.6398223","url":null,"abstract":"In this paper, we propose and implement an object oriented framework for the GPU based image processing. Compute Unified Device Architecture i.e. the CUDA is a novel and promising GPU programming framework from the NVIDIA. The CUDA has been used to speedup many computationally intensive graphics as well as non graphics applications, but it requires more than just kernel programming. A pyramidal image blending algorithm is essential for a seamless panoramic mosaic. We introduce an object oriented framework for the CUDA based pyramidal image blending using software engineering principles and design patterns. We illustrate a set of design patterns, which assist in reusing an existing functionality. We show that use of design patterns facilitate extending existing functionality by adding new classes, rather than modifying an existing classes or functionality. We also talk about extending our framework for computation using the GPU texture memory. We talk about the framework's performance in terms of programming efforts and a speedup factor achieved.","PeriodicalId":319467,"journal":{"name":"2012 International Conference on Communication, Information & Computing Technology (ICCICT)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127484332","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 : 2012-12-31DOI: 10.1109/ICCICT.2012.6398229
K. Thakare, R. Manthalkar, A. Rajurkar, D. Deshapande
Similarity matching algorithm plays an important role in Video retrieval system. Most of the video retrieval systems are designed using traditional similarity matching algorithms that are based on distance measures. As the Accuracy of retrieval system depends on the method used for detecting shots, kind of features we use for retrieval, it is also mandatory to think about the algorithms that we use for similarity matching of video clips. Here we propose a new technique latent semantic indexing technique which is based on Singular value decomposition. A key feature of LSI is its ability to establish associations between similar kind of information, It easily provides the accurate index terms that matches with the query clip index. We compare the results obtained with results of traditional Euclidean Distance method. Results are satisfactory.
{"title":"Video retrieval using singilar value decomposition and latent semantic indexing","authors":"K. Thakare, R. Manthalkar, A. Rajurkar, D. Deshapande","doi":"10.1109/ICCICT.2012.6398229","DOIUrl":"https://doi.org/10.1109/ICCICT.2012.6398229","url":null,"abstract":"Similarity matching algorithm plays an important role in Video retrieval system. Most of the video retrieval systems are designed using traditional similarity matching algorithms that are based on distance measures. As the Accuracy of retrieval system depends on the method used for detecting shots, kind of features we use for retrieval, it is also mandatory to think about the algorithms that we use for similarity matching of video clips. Here we propose a new technique latent semantic indexing technique which is based on Singular value decomposition. A key feature of LSI is its ability to establish associations between similar kind of information, It easily provides the accurate index terms that matches with the query clip index. We compare the results obtained with results of traditional Euclidean Distance method. Results are satisfactory.","PeriodicalId":319467,"journal":{"name":"2012 International Conference on Communication, Information & Computing Technology (ICCICT)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132103082","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 : 2012-12-31DOI: 10.1109/ICCICT.2012.6398100
H. B. Kekre, V. Kulkarni
In this paper a novel approach to text dependent speaker identification based on feature vector reduction technique of the row mean is proposed. Five different Orthogonal Transform Techniques: Discrete Fourier Transform (DFT), Discrete Cosine Transform (DCT), Discrete Sine Transform (DST), Discrete Hartley Transform (DHT) and Walsh Hadamard Transform (WHT) are applied on the framed speech signal. Feature extraction in the testing and matching phases has been done by using feature vector reduction technique applied on the row mean vector of the magnitude of the transformed speech signal. Two similarity measures Euclidean distance and Manhattan distance are used for feature matching. The results indicate that the accuracy using both the similarity measures remains steady up to certain reduction in feature vector permitting to reduce feature vector size. This algorithm is tested using two databases: a locally created database and CSLU Database. It is observed that, DFT allows maximum percentage of feature vector reduction. It out performs other Transforms with a big margin.
{"title":"Speaker identification using feature vector reduction of row mean of different transforms","authors":"H. B. Kekre, V. Kulkarni","doi":"10.1109/ICCICT.2012.6398100","DOIUrl":"https://doi.org/10.1109/ICCICT.2012.6398100","url":null,"abstract":"In this paper a novel approach to text dependent speaker identification based on feature vector reduction technique of the row mean is proposed. Five different Orthogonal Transform Techniques: Discrete Fourier Transform (DFT), Discrete Cosine Transform (DCT), Discrete Sine Transform (DST), Discrete Hartley Transform (DHT) and Walsh Hadamard Transform (WHT) are applied on the framed speech signal. Feature extraction in the testing and matching phases has been done by using feature vector reduction technique applied on the row mean vector of the magnitude of the transformed speech signal. Two similarity measures Euclidean distance and Manhattan distance are used for feature matching. The results indicate that the accuracy using both the similarity measures remains steady up to certain reduction in feature vector permitting to reduce feature vector size. This algorithm is tested using two databases: a locally created database and CSLU Database. It is observed that, DFT allows maximum percentage of feature vector reduction. It out performs other Transforms with a big margin.","PeriodicalId":319467,"journal":{"name":"2012 International Conference on Communication, Information & Computing Technology (ICCICT)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131373018","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 : 2012-12-31DOI: 10.1109/ICCICT.2012.6398231
H. B. Kekre, T. Sarode, R. Karani
In this paper, an unusual form of image registration is proposed which focuses upon using various transforms for fast and accurate image registration. Image registration is the process of transforming different sets of data into one coordinate system. The data set can be a set of photographs, data from various sensors, from different times, or from different viewpoints. The applications of image registration are in the field of computer vision, medical imaging, military automatic target recognition, and in analyzing images and data from satellites. The proposed technique works upon satellite images. It tries to find out area of interest by comparing the unregistered image with source image and finding the part that has highest similarity matching. The paper mainly works on the concept of seeking water or land in a stored image. The proposed technique uses different transforms like Discrete Cosine Transform, Discrete Wavelet Transform, HAAR Transform and Walsh transform to achieve accurate image registration. The paper also focuses upon using normalized cross correlation as an area based technique of image registration for the purpose of comparison. The proposed algorithm is worked over various sizes of satellite images such as 256×256, 1024×1024 etc. The root mean square error is used as similarity measure. The experiment results show that the proposed algorithm can successfully register the template and can also process local distortion in high-resolution satellite images.
{"title":"A deviant transform based approach for color image registration","authors":"H. B. Kekre, T. Sarode, R. Karani","doi":"10.1109/ICCICT.2012.6398231","DOIUrl":"https://doi.org/10.1109/ICCICT.2012.6398231","url":null,"abstract":"In this paper, an unusual form of image registration is proposed which focuses upon using various transforms for fast and accurate image registration. Image registration is the process of transforming different sets of data into one coordinate system. The data set can be a set of photographs, data from various sensors, from different times, or from different viewpoints. The applications of image registration are in the field of computer vision, medical imaging, military automatic target recognition, and in analyzing images and data from satellites. The proposed technique works upon satellite images. It tries to find out area of interest by comparing the unregistered image with source image and finding the part that has highest similarity matching. The paper mainly works on the concept of seeking water or land in a stored image. The proposed technique uses different transforms like Discrete Cosine Transform, Discrete Wavelet Transform, HAAR Transform and Walsh transform to achieve accurate image registration. The paper also focuses upon using normalized cross correlation as an area based technique of image registration for the purpose of comparison. The proposed algorithm is worked over various sizes of satellite images such as 256×256, 1024×1024 etc. The root mean square error is used as similarity measure. The experiment results show that the proposed algorithm can successfully register the template and can also process local distortion in high-resolution satellite images.","PeriodicalId":319467,"journal":{"name":"2012 International Conference on Communication, Information & Computing Technology (ICCICT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122197976","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 : 2012-12-31DOI: 10.1109/ICCICT.2012.6398183
S. V. Khangar, D. P. Bharne, L. Malik
The paper deals with the effective compression of the handwritten text images in Devnagri script. As data compression is one of interesting area in image processing. Compression methods for printed text images are available. But in the context of Indian language there is absence of the compression techniques for handwritten text document images. Here a method for compression of handwritten gray level document images is proposed. Experiments have been done for Marathi and Hindi Devnagri script. The strategy is based on the connected components analysis and shifting of connected components of an image. The results are shown for gray level images at various dpi and outperform towards achieving good compression ratio.
{"title":"Compression strategy for handwritten gray level document images","authors":"S. V. Khangar, D. P. Bharne, L. Malik","doi":"10.1109/ICCICT.2012.6398183","DOIUrl":"https://doi.org/10.1109/ICCICT.2012.6398183","url":null,"abstract":"The paper deals with the effective compression of the handwritten text images in Devnagri script. As data compression is one of interesting area in image processing. Compression methods for printed text images are available. But in the context of Indian language there is absence of the compression techniques for handwritten text document images. Here a method for compression of handwritten gray level document images is proposed. Experiments have been done for Marathi and Hindi Devnagri script. The strategy is based on the connected components analysis and shifting of connected components of an image. The results are shown for gray level images at various dpi and outperform towards achieving good compression ratio.","PeriodicalId":319467,"journal":{"name":"2012 International Conference on Communication, Information & Computing Technology (ICCICT)","volume":" 486","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113946731","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 : 2012-12-31DOI: 10.1109/ICCICT.2012.6398216
S. Mahajan, V. Jadhav
A major task of query processor is to produce query results, as efficiently as possible. For efficient query result, query has to follow proper execution plan which minimizes the cost of query execution. The sequence in which source tables are accessed during query execution is very important. Query optimizer which is the core component of query processor gives the best execution plan from many possible plans for the same query. The paper is the extended version of previous work [12]. Paper describes four phases of query optimization along with their execution plan. It gives the analysis of access methods and different types of joins used in execution plan of the query.
{"title":"An analysis of execution plans in query optimization","authors":"S. Mahajan, V. Jadhav","doi":"10.1109/ICCICT.2012.6398216","DOIUrl":"https://doi.org/10.1109/ICCICT.2012.6398216","url":null,"abstract":"A major task of query processor is to produce query results, as efficiently as possible. For efficient query result, query has to follow proper execution plan which minimizes the cost of query execution. The sequence in which source tables are accessed during query execution is very important. Query optimizer which is the core component of query processor gives the best execution plan from many possible plans for the same query. The paper is the extended version of previous work [12]. Paper describes four phases of query optimization along with their execution plan. It gives the analysis of access methods and different types of joins used in execution plan of the query.","PeriodicalId":319467,"journal":{"name":"2012 International Conference on Communication, Information & Computing Technology (ICCICT)","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124125232","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 : 2012-12-31DOI: 10.1109/ICCICT.2012.6398186
M. Qayyum, P. Subhash, M. Husamuddin
Mobile Ad Hoc Networks (MANETs) are exposed to several extra threats as compared to legacy wireless networks due to their nature. The security management in MANETs, where node level security monitoring plays an integral role in maintaining security and the problem of measuring the overall security level of MANETs. This paper presented the major components of the security level of MANETs. Security issues of Data Query Processing and Location Monitoring. The security level estimation architecture, security level classification and in applications is also presented.
{"title":"Security issues of data query processing and location monitoring in MANETS","authors":"M. Qayyum, P. Subhash, M. Husamuddin","doi":"10.1109/ICCICT.2012.6398186","DOIUrl":"https://doi.org/10.1109/ICCICT.2012.6398186","url":null,"abstract":"Mobile Ad Hoc Networks (MANETs) are exposed to several extra threats as compared to legacy wireless networks due to their nature. The security management in MANETs, where node level security monitoring plays an integral role in maintaining security and the problem of measuring the overall security level of MANETs. This paper presented the major components of the security level of MANETs. Security issues of Data Query Processing and Location Monitoring. The security level estimation architecture, security level classification and in applications is also presented.","PeriodicalId":319467,"journal":{"name":"2012 International Conference on Communication, Information & Computing Technology (ICCICT)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116702462","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：