Pub Date : 2013-04-15DOI: 10.1109/ICPRIME.2013.6496457
G. T. Shrivakshan
This paper deals in classifying shark fishes using the Edges characterize boundaries. It is a problem of fundamental importance in detecting the type of shark fish in the deep sea. The edge detection is in the head of computer vision system for recognition of objects and estimate it is critical to have a good perceptive of edge detection techniques. In this paper the comparative analysis of various Image Edge Detection techniques are considered. The proposed work was tested in MATLAB tool. It has been shown that the Gabor's filter performs better than Sobel filter.
{"title":"An analysis of SOBEL and GABOR image filters for identifying fish","authors":"G. T. Shrivakshan","doi":"10.1109/ICPRIME.2013.6496457","DOIUrl":"https://doi.org/10.1109/ICPRIME.2013.6496457","url":null,"abstract":"This paper deals in classifying shark fishes using the Edges characterize boundaries. It is a problem of fundamental importance in detecting the type of shark fish in the deep sea. The edge detection is in the head of computer vision system for recognition of objects and estimate it is critical to have a good perceptive of edge detection techniques. In this paper the comparative analysis of various Image Edge Detection techniques are considered. The proposed work was tested in MATLAB tool. It has been shown that the Gabor's filter performs better than Sobel filter.","PeriodicalId":123210,"journal":{"name":"2013 International Conference on Pattern Recognition, Informatics and Mobile Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130910995","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 : 2013-04-15DOI: 10.1109/ICPRIME.2013.6496717
M. G. Ananthara, T. Arunkumar, R. Hemavathy
Agricultural researchers over the world insist on the need for an efficient mechanism to predict and improve the crop growth. The need for an integrated crop growth control with accurate predictive yield management methodology is highly felt among farming community. The complexity of predicting the crop yield is highly due to multi dimensional variable metrics and unavailability of predictive modeling approach, which leads to loss in crop yield. This research paper suggests a crop yield prediction model (CRY) which works on an adaptive cluster approach over dynamically updated historical crop data set to predict the crop yield and improve the decision making in precision agriculture. CRY uses bee hive modeling approach to analyze and classify the crop based on crop growth pattern, yield. CRY classified dataset had been tested using Clementine over existing crop domain knowledge. The results and performance shows comparison of CRY over with other cluster approaches.
{"title":"CRY — An improved crop yield prediction model using bee hive clustering approach for agricultural data sets","authors":"M. G. Ananthara, T. Arunkumar, R. Hemavathy","doi":"10.1109/ICPRIME.2013.6496717","DOIUrl":"https://doi.org/10.1109/ICPRIME.2013.6496717","url":null,"abstract":"Agricultural researchers over the world insist on the need for an efficient mechanism to predict and improve the crop growth. The need for an integrated crop growth control with accurate predictive yield management methodology is highly felt among farming community. The complexity of predicting the crop yield is highly due to multi dimensional variable metrics and unavailability of predictive modeling approach, which leads to loss in crop yield. This research paper suggests a crop yield prediction model (CRY) which works on an adaptive cluster approach over dynamically updated historical crop data set to predict the crop yield and improve the decision making in precision agriculture. CRY uses bee hive modeling approach to analyze and classify the crop based on crop growth pattern, yield. CRY classified dataset had been tested using Clementine over existing crop domain knowledge. The results and performance shows comparison of CRY over with other cluster approaches.","PeriodicalId":123210,"journal":{"name":"2013 International Conference on Pattern Recognition, Informatics and Mobile Engineering","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126541737","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 : 2013-04-15DOI: 10.1109/ICPRIME.2013.6496476
Amol D. Gaikwad, Ctech Deptt
Web service is a popular standard to publish services for users. However, diversified users need to access web service according to their particular preferences. Mobile search is quite different from standard PC-based web search in a number of ways: (a) the user interfaces and I/O are limited by screen real state, (b) key pads are tiny and inconvenient for use, (c) limited bandwidth and (d) costly connection fees. This review paper focuses on the personalization strategies which explicitly and implicitly infer user search context at individual user level. The paper also focuses on an architecture which collects user information (at mobile device and carrier network) and derives user intention in given situations.
{"title":"Personal approach for mobile search: A review","authors":"Amol D. Gaikwad, Ctech Deptt","doi":"10.1109/ICPRIME.2013.6496476","DOIUrl":"https://doi.org/10.1109/ICPRIME.2013.6496476","url":null,"abstract":"Web service is a popular standard to publish services for users. However, diversified users need to access web service according to their particular preferences. Mobile search is quite different from standard PC-based web search in a number of ways: (a) the user interfaces and I/O are limited by screen real state, (b) key pads are tiny and inconvenient for use, (c) limited bandwidth and (d) costly connection fees. This review paper focuses on the personalization strategies which explicitly and implicitly infer user search context at individual user level. The paper also focuses on an architecture which collects user information (at mobile device and carrier network) and derives user intention in given situations.","PeriodicalId":123210,"journal":{"name":"2013 International Conference on Pattern Recognition, Informatics and Mobile Engineering","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114197744","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 : 2013-04-15DOI: 10.1109/ICPRIME.2013.6496465
D. N. Rao, M. Srinath, P. Hiranmani Bala
E-Learning has become a major field of interest in recent year, and multiple approaches and solutions have been developed. Testing in E-Iearning software is the most important way of assuring the quality of the application. The E-Learning software contains miscommunication or no communication, software complexity, programming errors, time pressures and changing requirements, there are too many unrealistic software which results in bugs. In order to remove or defuse the bugs that cause a lot of project failures at the final stage of the delivery., this paper focuses on adducing a Reliable code coverage technique in software testing, which will ensure a bug free delivery of the software development. Software testing aims at detecting error-prone areas. This helps in the detection and correction of errors. It can be applied at the unit of integration and system levels of the software testing process, and it is usually done at the unit level. This method of test design uncovered many errors or problems. Experimental results show that, the increase in software performance rating and software quality assurance increases the testing level in performance.
{"title":"Reliable code coverage technique in software testing","authors":"D. N. Rao, M. Srinath, P. Hiranmani Bala","doi":"10.1109/ICPRIME.2013.6496465","DOIUrl":"https://doi.org/10.1109/ICPRIME.2013.6496465","url":null,"abstract":"E-Learning has become a major field of interest in recent year, and multiple approaches and solutions have been developed. Testing in E-Iearning software is the most important way of assuring the quality of the application. The E-Learning software contains miscommunication or no communication, software complexity, programming errors, time pressures and changing requirements, there are too many unrealistic software which results in bugs. In order to remove or defuse the bugs that cause a lot of project failures at the final stage of the delivery., this paper focuses on adducing a Reliable code coverage technique in software testing, which will ensure a bug free delivery of the software development. Software testing aims at detecting error-prone areas. This helps in the detection and correction of errors. It can be applied at the unit of integration and system levels of the software testing process, and it is usually done at the unit level. This method of test design uncovered many errors or problems. Experimental results show that, the increase in software performance rating and software quality assurance increases the testing level in performance.","PeriodicalId":123210,"journal":{"name":"2013 International Conference on Pattern Recognition, Informatics and Mobile Engineering","volume":"64 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120899257","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 : 2013-04-15DOI: 10.1109/ICPRIME.2013.6496519
P. Ashok, G. M. Kadhar Nawaz, K. Thangavel, E. Elayaraja
A large molecule composed of one or more chains of amino acids in a specific order, the order is determined by the base sequence of nucleotides in the gene that codes for the protein. Proteins are required for the structure, function, and regulation of the body's cells, tissues, and organs and each protein has unique functions. Localization sites of proteins are identified by the mechanism and moved to its corresponding organelles. In this paper, we introduce the method clustering and its type's K-Means and K-Medoids. The clustering algorithms are improved by implementing the two initial centroid selection methods instead of selecting centroid randomly. K-Means algorithm can be improved by implementing the initial cluster centroids are selected by the two proposed algorithms instead of selecting centroids randomly, which is compared by using Davie Bouldin index measure, hence the proposed algorithm1 overcomes the drawbacks of selecting initial cluster centers then other methods. In the yeast dataset, the defective proteins (objects) are considered as outliers, which are identified by the clustering methods with ADOC (Average Distance between Object and Centroid) function. The outlier's detection method and performance analysis method are studied and compared, the experimental results shows that the K-Medoids method performs well when compare with the K-Means clustering.
{"title":"Outliers detection on protein localization sites by partitional clustering methods","authors":"P. Ashok, G. M. Kadhar Nawaz, K. Thangavel, E. Elayaraja","doi":"10.1109/ICPRIME.2013.6496519","DOIUrl":"https://doi.org/10.1109/ICPRIME.2013.6496519","url":null,"abstract":"A large molecule composed of one or more chains of amino acids in a specific order, the order is determined by the base sequence of nucleotides in the gene that codes for the protein. Proteins are required for the structure, function, and regulation of the body's cells, tissues, and organs and each protein has unique functions. Localization sites of proteins are identified by the mechanism and moved to its corresponding organelles. In this paper, we introduce the method clustering and its type's K-Means and K-Medoids. The clustering algorithms are improved by implementing the two initial centroid selection methods instead of selecting centroid randomly. K-Means algorithm can be improved by implementing the initial cluster centroids are selected by the two proposed algorithms instead of selecting centroids randomly, which is compared by using Davie Bouldin index measure, hence the proposed algorithm1 overcomes the drawbacks of selecting initial cluster centers then other methods. In the yeast dataset, the defective proteins (objects) are considered as outliers, which are identified by the clustering methods with ADOC (Average Distance between Object and Centroid) function. The outlier's detection method and performance analysis method are studied and compared, the experimental results shows that the K-Medoids method performs well when compare with the K-Means clustering.","PeriodicalId":123210,"journal":{"name":"2013 International Conference on Pattern Recognition, Informatics and Mobile Engineering","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125642507","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 : 2013-04-15DOI: 10.1109/ICPRIME.2013.6496506
R. M. Jeya Jothi, A. Amutha
A Graph G is Super Strongly Perfect Graph if every induced sub graph H of G possesses a minimal dominating set that meets all the maximal complete sub graphs of H. In this paper we have characterized the structure of super strongly perfect graphs in Prism and Rook's Networks. Along with this characterization, we have investigated the Super Strongly Perfect ness in Prism and Rook's Networks. Also we have given the relationship between diameter, domination and co-domination numbers of Prism Network.
{"title":"Super Strongly Perfect ness of Prism and Rook's Networks","authors":"R. M. Jeya Jothi, A. Amutha","doi":"10.1109/ICPRIME.2013.6496506","DOIUrl":"https://doi.org/10.1109/ICPRIME.2013.6496506","url":null,"abstract":"A Graph G is Super Strongly Perfect Graph if every induced sub graph H of G possesses a minimal dominating set that meets all the maximal complete sub graphs of H. In this paper we have characterized the structure of super strongly perfect graphs in Prism and Rook's Networks. Along with this characterization, we have investigated the Super Strongly Perfect ness in Prism and Rook's Networks. Also we have given the relationship between diameter, domination and co-domination numbers of Prism Network.","PeriodicalId":123210,"journal":{"name":"2013 International Conference on Pattern Recognition, Informatics and Mobile Engineering","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132611671","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 : 2013-04-15DOI: 10.1109/ICPRIME.2013.6496505
A. N. Kumar, C. Sureshkumar
In video surveillance systems, background subtraction is the first processing stage and it is used to determine the objects in a particular scene. It is a general term for a process which aims to separate foreground objects from a relatively stationary background. It should be processed in real time. It is obtained in human detection system by computing the variation, pixel-by-pixel, between the current frame and the image of the background, followed by an automatic threshold. This paper proposed a K means based background subtraction for real time video processing in video surveillance. We have analyzed and evaluate the performance of the proposed method, with standard K-means and other background subtractions algorithms. The experimental results showed that the proposed method provides better output.
{"title":"Background subtraction based on threshold detection using modified K-means algorithm","authors":"A. N. Kumar, C. Sureshkumar","doi":"10.1109/ICPRIME.2013.6496505","DOIUrl":"https://doi.org/10.1109/ICPRIME.2013.6496505","url":null,"abstract":"In video surveillance systems, background subtraction is the first processing stage and it is used to determine the objects in a particular scene. It is a general term for a process which aims to separate foreground objects from a relatively stationary background. It should be processed in real time. It is obtained in human detection system by computing the variation, pixel-by-pixel, between the current frame and the image of the background, followed by an automatic threshold. This paper proposed a K means based background subtraction for real time video processing in video surveillance. We have analyzed and evaluate the performance of the proposed method, with standard K-means and other background subtractions algorithms. The experimental results showed that the proposed method provides better output.","PeriodicalId":123210,"journal":{"name":"2013 International Conference on Pattern Recognition, Informatics and Mobile Engineering","volume":"111 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133245258","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 : 2013-04-15DOI: 10.1109/ICPRIME.2013.6496510
V. Sasirekha, M. Ilanzkumaran
The selection of the most appropriate network in heterogeneous Wireless environment is one of the critical issues to provide the best Quality of Service (QOS) to the users. The selection of an apt network among various alternatives is a kind of Multi Criteria Decision Making (MCDM) problem. This paper describes a novel Multi Criteria Decision Making (MCDM) method to evaluate and select the suitable network for homogeneous wireless network environment. The proposed MCDM technique involves Fuzzy Analytical Hierarchy Process (FAHP) is integrated with Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) and VlseKriterijumska Optimizacija I Kompromisno Resenje in Serbian (VIKOR) techniques. FAHP is used to determine the criteria weights, whereas TOPSIS and VIKOR used to find the performance ranking of the alternative networks. This study focuses on five network alternatives such as WLAN, GPRS, UMTS, WIMAX, and CDMA and ten evaluation criteria such as bandwidth, latency, jitter, BER, Retransmission, Packet loss, through put, preference, security, cost to select the appropriate network.
{"title":"Heterogeneous wireless network selection using FAHP integrated with TOPSIS and VIKOR","authors":"V. Sasirekha, M. Ilanzkumaran","doi":"10.1109/ICPRIME.2013.6496510","DOIUrl":"https://doi.org/10.1109/ICPRIME.2013.6496510","url":null,"abstract":"The selection of the most appropriate network in heterogeneous Wireless environment is one of the critical issues to provide the best Quality of Service (QOS) to the users. The selection of an apt network among various alternatives is a kind of Multi Criteria Decision Making (MCDM) problem. This paper describes a novel Multi Criteria Decision Making (MCDM) method to evaluate and select the suitable network for homogeneous wireless network environment. The proposed MCDM technique involves Fuzzy Analytical Hierarchy Process (FAHP) is integrated with Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) and VlseKriterijumska Optimizacija I Kompromisno Resenje in Serbian (VIKOR) techniques. FAHP is used to determine the criteria weights, whereas TOPSIS and VIKOR used to find the performance ranking of the alternative networks. This study focuses on five network alternatives such as WLAN, GPRS, UMTS, WIMAX, and CDMA and ten evaluation criteria such as bandwidth, latency, jitter, BER, Retransmission, Packet loss, through put, preference, security, cost to select the appropriate network.","PeriodicalId":123210,"journal":{"name":"2013 International Conference on Pattern Recognition, Informatics and Mobile Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133421155","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 : 2013-04-15DOI: 10.1109/ICPRIME.2013.6496468
R. Shaleni, S. R. Swaathiha, P. Karthikeyan
Wireless Sensor Network (WSN) design for intruder detection application requires the decision of deployment of nodes with respect to the lifetime of the network. Based on literature survey it is found that few works have been made on optimizing both decision variables for maximizing the network coverage and lifetime. But the above two objectives in the latter studies are considered individually without any application specific. In this work, it is defined as the multi-objective Deployment and Power Assignment Problem (DPAP) for intruder detection application is solved using Multi Objective Evolutionary Algorithm (MOEA) based on decomposition. The M-tour Selection (M-tourS), Adaptive crossover and Adaptive mutation are introduced to improve the MOEA/D algorithm. The DPAP decomposed into a set of sub problems that are classified based on the above proposed genetic operators into seven different combinations. The proposed operators adapt to the requirements and objective preferences of each combination dynamically during the evolution, resulting in significant improvements on the overall performance of MOEA/D. Simulation parameters are fixed by considering the above application specific. The results show that the proposed algorithm significantly better than the existing algorithms in different network instances.
{"title":"Deployment and power assignment problem in Wireless Sensor Networks for intruder detection application using MEA","authors":"R. Shaleni, S. R. Swaathiha, P. Karthikeyan","doi":"10.1109/ICPRIME.2013.6496468","DOIUrl":"https://doi.org/10.1109/ICPRIME.2013.6496468","url":null,"abstract":"Wireless Sensor Network (WSN) design for intruder detection application requires the decision of deployment of nodes with respect to the lifetime of the network. Based on literature survey it is found that few works have been made on optimizing both decision variables for maximizing the network coverage and lifetime. But the above two objectives in the latter studies are considered individually without any application specific. In this work, it is defined as the multi-objective Deployment and Power Assignment Problem (DPAP) for intruder detection application is solved using Multi Objective Evolutionary Algorithm (MOEA) based on decomposition. The M-tour Selection (M-tourS), Adaptive crossover and Adaptive mutation are introduced to improve the MOEA/D algorithm. The DPAP decomposed into a set of sub problems that are classified based on the above proposed genetic operators into seven different combinations. The proposed operators adapt to the requirements and objective preferences of each combination dynamically during the evolution, resulting in significant improvements on the overall performance of MOEA/D. Simulation parameters are fixed by considering the above application specific. The results show that the proposed algorithm significantly better than the existing algorithms in different network instances.","PeriodicalId":123210,"journal":{"name":"2013 International Conference on Pattern Recognition, Informatics and Mobile Engineering","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114688858","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 : 2013-04-15DOI: 10.1109/ICPRIME.2013.6496450
D. A. Kumar, T. Yu
Forecasting based on time series data for stock prices, currency exchange rate, price indices, etc., is one of the active research areas in many field viz., finance, mathematics, physics, machine learning, etc. Initially, the problem of financial time sequences analysis and prediction are solved by many statistical models. During the past few decades, a large number of neural network models have been proposed to solve the problem of financial data and to obtain accurate prediction result. The statistical model integrated with ANN (Hybrid model) has given better result than using single model. This work discusses some basic ideas of time series data, need of ANN, importance of stock indices, survey of the previous works and it investigates neural network models for time series in forecasting. The forecasting accuracy is analyzed and measured with reference to an Indian stock market index such as Bombay Stock Exchange (BSE) and NIFTY MIDCAP50 in this study and it is found that the right parameters number of epochs, learning rate and momentum is 2960, 0.28 and 0.5 respectively for forecasting network by conducting various experiment.
{"title":"Performance analysis of Indian stock market index using neural network time series model","authors":"D. A. Kumar, T. Yu","doi":"10.1109/ICPRIME.2013.6496450","DOIUrl":"https://doi.org/10.1109/ICPRIME.2013.6496450","url":null,"abstract":"Forecasting based on time series data for stock prices, currency exchange rate, price indices, etc., is one of the active research areas in many field viz., finance, mathematics, physics, machine learning, etc. Initially, the problem of financial time sequences analysis and prediction are solved by many statistical models. During the past few decades, a large number of neural network models have been proposed to solve the problem of financial data and to obtain accurate prediction result. The statistical model integrated with ANN (Hybrid model) has given better result than using single model. This work discusses some basic ideas of time series data, need of ANN, importance of stock indices, survey of the previous works and it investigates neural network models for time series in forecasting. The forecasting accuracy is analyzed and measured with reference to an Indian stock market index such as Bombay Stock Exchange (BSE) and NIFTY MIDCAP50 in this study and it is found that the right parameters number of epochs, learning rate and momentum is 2960, 0.28 and 0.5 respectively for forecasting network by conducting various experiment.","PeriodicalId":123210,"journal":{"name":"2013 International Conference on Pattern Recognition, Informatics and Mobile Engineering","volume":"116 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123204034","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：