Marathi is one of the ancient Indian languages majorly spoken in the state of Maharashtra. Marathi is one of the Devanagari script and the literals and numerals are almost similar to Hindi. Recognition of handwritten Marathi numerals is quite challenging task because people have the practice of writing these numerals in variant ways. In this work we have presented a method to recognize the handwritten Marathi numerals using multilayer feed-forward neural network. The scanned document image is pre-processed to eliminate the noise and care is taken to link the broken characters. Each numeral is segmented from the document and it is resized to 7 × 5 pixels using cubic interpolation. While resizing a technique is used to provide better representation for every pixel in segmented numeral. This resized numeral is converted into a vector with 35 values before inputting it to the neural network. We have used 100 sets containing 1000 numerals for this experimentation, of which 50 sets are used for training the network and 50 sets for the testing purpose. The overall recognition rate of the proposed method is 97%.
{"title":"Recognition of Marathi Handwritten Numerals Using Multi-Layer Feed-Forward Neural Network","authors":"R. Hegadi, Parshuram M. Kamble","doi":"10.1109/WCCCT.2014.9","DOIUrl":"https://doi.org/10.1109/WCCCT.2014.9","url":null,"abstract":"Marathi is one of the ancient Indian languages majorly spoken in the state of Maharashtra. Marathi is one of the Devanagari script and the literals and numerals are almost similar to Hindi. Recognition of handwritten Marathi numerals is quite challenging task because people have the practice of writing these numerals in variant ways. In this work we have presented a method to recognize the handwritten Marathi numerals using multilayer feed-forward neural network. The scanned document image is pre-processed to eliminate the noise and care is taken to link the broken characters. Each numeral is segmented from the document and it is resized to 7 × 5 pixels using cubic interpolation. While resizing a technique is used to provide better representation for every pixel in segmented numeral. This resized numeral is converted into a vector with 35 values before inputting it to the neural network. We have used 100 sets containing 1000 numerals for this experimentation, of which 50 sets are used for training the network and 50 sets for the testing purpose. The overall recognition rate of the proposed method is 97%.","PeriodicalId":421793,"journal":{"name":"2014 World Congress on Computing and Communication Technologies","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133369195","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}
Cloud computing is a more flexible, cost effective and proven delivery platform for providing business or consumer services over the Internet. Cloud computing supports distributed service oriented architecture, multi-user and multi-domain administrative infrastructure. So, it is more prone to security threats and vulnerabilities. At present, a major concern in cloud adoption is towards its security and privacy. Security and privacy issues are of great concern to cloud service providers who are actually hosting the services. In most cases, the provider must guarantee that their infrastructure is secure and clients' data and applications are safe, by implementing security policies and mechanisms. The security issues are organized into several general categories: trust, identity management, software isolation, data protection, availability reliability, ownership, data backup, data portability and conversion, multi platform support and intellectual property. In this paper, it is discuss about some of the techniques that were implemented to protect data and propose architecture to protect data in cloud. This architecture was developed to store data in cloud in encrypted data format using cryptography technique which is based on block cipher.
{"title":"An Architecture for Data Security in Cloud Computing","authors":"M. Sugumaran, B. Murugan, D. Kamalraj","doi":"10.1109/WCCCT.2014.53","DOIUrl":"https://doi.org/10.1109/WCCCT.2014.53","url":null,"abstract":"Cloud computing is a more flexible, cost effective and proven delivery platform for providing business or consumer services over the Internet. Cloud computing supports distributed service oriented architecture, multi-user and multi-domain administrative infrastructure. So, it is more prone to security threats and vulnerabilities. At present, a major concern in cloud adoption is towards its security and privacy. Security and privacy issues are of great concern to cloud service providers who are actually hosting the services. In most cases, the provider must guarantee that their infrastructure is secure and clients' data and applications are safe, by implementing security policies and mechanisms. The security issues are organized into several general categories: trust, identity management, software isolation, data protection, availability reliability, ownership, data backup, data portability and conversion, multi platform support and intellectual property. In this paper, it is discuss about some of the techniques that were implemented to protect data and propose architecture to protect data in cloud. This architecture was developed to store data in cloud in encrypted data format using cryptography technique which is based on block cipher.","PeriodicalId":421793,"journal":{"name":"2014 World Congress on Computing and Communication Technologies","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127466598","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In current web applications, more businesses are gradually publishing their business as services over the web. This growing number of web services available within an organization and on the Web raises a new and challenging search problem: locating desired web services. Searching for web services with conventional web search engines is insufficient in this context. Automatically clustering Web Service Description Language (WSDL) files on the web into functionally similar homogeneous service groups can be seen as a bootstrapping step for creating a service search engine and, at the same time, reducing the search space for service discovery. In order to overcome some the limitations of pattern-matching approach, the proposed work uses two semantic approaches to cluster similar services. An experimental study based on an information retrieval technique known as latent semantic analysis is applied to the collection of WSDL files and the another semantic approach is based on WordNet which is a lexical database to cluster similar services, as a predecessor step to retrieve the relevant Web services for a user request by search engines. The baseline approach and the two approaches based on semantic is applied on a collection of WSDL documents consisting of to test the quality of clusters formed. As a result, WordNet based approach for clustering shows better cluster quality.
{"title":"Performance Evaluation of Semantic Approaches for Automatic Clustering of Similar Web Services","authors":"G. Vadivelou, E. Ilavarasan","doi":"10.1109/WCCCT.2014.41","DOIUrl":"https://doi.org/10.1109/WCCCT.2014.41","url":null,"abstract":"In current web applications, more businesses are gradually publishing their business as services over the web. This growing number of web services available within an organization and on the Web raises a new and challenging search problem: locating desired web services. Searching for web services with conventional web search engines is insufficient in this context. Automatically clustering Web Service Description Language (WSDL) files on the web into functionally similar homogeneous service groups can be seen as a bootstrapping step for creating a service search engine and, at the same time, reducing the search space for service discovery. In order to overcome some the limitations of pattern-matching approach, the proposed work uses two semantic approaches to cluster similar services. An experimental study based on an information retrieval technique known as latent semantic analysis is applied to the collection of WSDL files and the another semantic approach is based on WordNet which is a lexical database to cluster similar services, as a predecessor step to retrieve the relevant Web services for a user request by search engines. The baseline approach and the two approaches based on semantic is applied on a collection of WSDL documents consisting of to test the quality of clusters formed. As a result, WordNet based approach for clustering shows better cluster quality.","PeriodicalId":421793,"journal":{"name":"2014 World Congress on Computing and Communication Technologies","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129151131","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}
Augmented reality is an emerging technology of Virtual Reality, which has a great development and application prospects. Augmented Reality involves knowledge about sensors, image recognition, computer vision, human-computer interaction, virtual reality, and many other areas. The key technologies include displaying, registration and tracking, interactive etc. There exist a number of augmented reality applications. Most of them are able to collect the data from different servers related to the environment and traffic etc. But the softwares which address the students' issues are very less or in the discussion stages. Hence in this paper, we planned to focus on one of the major issue of automating Library application with the augmented reality software and we propose architecture for accessing the library books meta-data.
{"title":"SaaS Framework for Library Augmented Reality Application","authors":"A. Alex, S. Jegatha, J. Jayanthi, S. Rabara","doi":"10.1109/WCCCT.2014.58","DOIUrl":"https://doi.org/10.1109/WCCCT.2014.58","url":null,"abstract":"Augmented reality is an emerging technology of Virtual Reality, which has a great development and application prospects. Augmented Reality involves knowledge about sensors, image recognition, computer vision, human-computer interaction, virtual reality, and many other areas. The key technologies include displaying, registration and tracking, interactive etc. There exist a number of augmented reality applications. Most of them are able to collect the data from different servers related to the environment and traffic etc. But the softwares which address the students' issues are very less or in the discussion stages. Hence in this paper, we planned to focus on one of the major issue of automating Library application with the augmented reality software and we propose architecture for accessing the library books meta-data.","PeriodicalId":421793,"journal":{"name":"2014 World Congress on Computing and Communication Technologies","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127739281","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}
DNA sequences contain hereditary information of all living organisms. The exploration of genomic research compulsorily involves such large sequences in high volumes and it requires voluminous storage. An initiative to reduce such storage is achieved through DNA data compression. The compression time is another influencing factor for compression algorithms and whose consumption must be reduced. This paper aims the same by proposing Parallelized Pattern Recognition based DNA Sequence Compression (PPRDNAC) algorithm that compresses the DNA sequences by identifying the appropriate patterns simultaneously with appreciable computation time.
{"title":"Parallelized Pattern Recognition Based DNA Sequence Compressor","authors":"S. P. Arokiaraj, L. Robert","doi":"10.1109/WCCCT.2014.33","DOIUrl":"https://doi.org/10.1109/WCCCT.2014.33","url":null,"abstract":"DNA sequences contain hereditary information of all living organisms. The exploration of genomic research compulsorily involves such large sequences in high volumes and it requires voluminous storage. An initiative to reduce such storage is achieved through DNA data compression. The compression time is another influencing factor for compression algorithms and whose consumption must be reduced. This paper aims the same by proposing Parallelized Pattern Recognition based DNA Sequence Compression (PPRDNAC) algorithm that compresses the DNA sequences by identifying the appropriate patterns simultaneously with appreciable computation time.","PeriodicalId":421793,"journal":{"name":"2014 World Congress on Computing and Communication Technologies","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115815423","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}
Data hiding is the skill of hiding messages in such a way that only the sender and the receiver of the message know that the message has been hidden. In the contexts of secured information transmission and reception, efficient techniques for data encryption and decryption are very much essential. Though many algorithms have been developed for hiding the data, DNA sequences based data encryption seems to be a promising strategy for fulfilling the current information security needs. In this paper, an algorithm using DNA sequences for data hiding is proposed and discussed for secure data transmission and reception.
{"title":"Message Encryption Using DNA Sequences","authors":"K. Menaka","doi":"10.1109/WCCCT.2014.35","DOIUrl":"https://doi.org/10.1109/WCCCT.2014.35","url":null,"abstract":"Data hiding is the skill of hiding messages in such a way that only the sender and the receiver of the message know that the message has been hidden. In the contexts of secured information transmission and reception, efficient techniques for data encryption and decryption are very much essential. Though many algorithms have been developed for hiding the data, DNA sequences based data encryption seems to be a promising strategy for fulfilling the current information security needs. In this paper, an algorithm using DNA sequences for data hiding is proposed and discussed for secure data transmission and reception.","PeriodicalId":421793,"journal":{"name":"2014 World Congress on Computing and Communication Technologies","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116930535","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}
The young upcoming industry is the cloud storage with lots of potential in terms of growth of storage capacity and the potential of faster retrieval. The architecture of the cloud is designed so as to not only offer unlimited storage capacity, but also has to eliminate the old data backups - created as a part of the constant replication of data. In this paper, the key component is storage-as-a-service solution, that is, the cloud storage is analyzed and comprehended for the storage and retrieval speeds on various free cloud storage sites. The experiments were piloted for files varying in sizes and various time spans. Time spans are deliberated based on network traffic. This paper overall tries to give a snapshot of the data working on different free clouds available. The analysis done gives an identification of the free cloud storage capacity, its performance, betterments and evaluation.
{"title":"Cloud Storage and Retrieval - A User Perspective","authors":"V. Abhishek, S. Megha","doi":"10.1109/WCCCT.2014.20","DOIUrl":"https://doi.org/10.1109/WCCCT.2014.20","url":null,"abstract":"The young upcoming industry is the cloud storage with lots of potential in terms of growth of storage capacity and the potential of faster retrieval. The architecture of the cloud is designed so as to not only offer unlimited storage capacity, but also has to eliminate the old data backups - created as a part of the constant replication of data. In this paper, the key component is storage-as-a-service solution, that is, the cloud storage is analyzed and comprehended for the storage and retrieval speeds on various free cloud storage sites. The experiments were piloted for files varying in sizes and various time spans. Time spans are deliberated based on network traffic. This paper overall tries to give a snapshot of the data working on different free clouds available. The analysis done gives an identification of the free cloud storage capacity, its performance, betterments and evaluation.","PeriodicalId":421793,"journal":{"name":"2014 World Congress on Computing and Communication Technologies","volume":"229 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115738452","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}
I. Carol, George Gabriel Richard Roy, A. J. P. Prassanna
The integration of information and communication technologies in education according to the global trend is occupying a great interest in the world through E-Learning techniques. And the institutions of higher education are dipping their toes into the cloud computing waters, just as organizations in the broader market are doing. A new model for accessing the E-materials in the educational community cloud is proposed in this paper. The educational materials can be stored and accessed from the cloud servers rather than every institution maintaining their own computing facilities. The learners need an environment to access the application anywhere, anytime and with any device at a minimum cost. This paper strengthens the traditional learning technique by proposing a new model for Effective E-learning in the cloud.
{"title":"A Cloud Model for Effective E-Learning","authors":"I. Carol, George Gabriel Richard Roy, A. J. P. Prassanna","doi":"10.1109/WCCCT.2014.51","DOIUrl":"https://doi.org/10.1109/WCCCT.2014.51","url":null,"abstract":"The integration of information and communication technologies in education according to the global trend is occupying a great interest in the world through E-Learning techniques. And the institutions of higher education are dipping their toes into the cloud computing waters, just as organizations in the broader market are doing. A new model for accessing the E-materials in the educational community cloud is proposed in this paper. The educational materials can be stored and accessed from the cloud servers rather than every institution maintaining their own computing facilities. The learners need an environment to access the application anywhere, anytime and with any device at a minimum cost. This paper strengthens the traditional learning technique by proposing a new model for Effective E-learning in the cloud.","PeriodicalId":421793,"journal":{"name":"2014 World Congress on Computing and Communication Technologies","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115123836","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}
The efficiency of cryptographic algorithm is not only based on the time taken for encryption and decryption, but also the number of levels used to get the cipher text from a plain text. The public key cryptosystem RSA is one of the widely used algorithms. However, several attacks are introduced to break this algorithm due to certain limitations. Also, it may not be guaranteed that the cipher text is fully secured. One of such limitations in the past cryptosystem is using ASCII characters for numerical representation of the text. To overcome the above said limitation, an innovative algorithm namely Magic Rectangle Generation Algorithm (MRGA) is being proposed in this work. It is helpful to enhance the security due to its complexity in encryption process. The singly even magic rectangle is formed based on the seed number, start number, row sum and column sum. The value of row sum and column sum is very difficult to be traced. The proposed work introduces one more level of security in public key algorithms such as RSA, ElGAMAL etc. Finally, MRGA helps to overcome the weakness of public key cryptosystem. Cipher text developed by this method can be entirely different when compared to the plain text and will be suitable for the secured transmission over the internet.
{"title":"Enhancing Security Level for Public Key Cryptosystem Using MRGA","authors":"D. Amalarethinam","doi":"10.1109/WCCCT.2014.32","DOIUrl":"https://doi.org/10.1109/WCCCT.2014.32","url":null,"abstract":"The efficiency of cryptographic algorithm is not only based on the time taken for encryption and decryption, but also the number of levels used to get the cipher text from a plain text. The public key cryptosystem RSA is one of the widely used algorithms. However, several attacks are introduced to break this algorithm due to certain limitations. Also, it may not be guaranteed that the cipher text is fully secured. One of such limitations in the past cryptosystem is using ASCII characters for numerical representation of the text. To overcome the above said limitation, an innovative algorithm namely Magic Rectangle Generation Algorithm (MRGA) is being proposed in this work. It is helpful to enhance the security due to its complexity in encryption process. The singly even magic rectangle is formed based on the seed number, start number, row sum and column sum. The value of row sum and column sum is very difficult to be traced. The proposed work introduces one more level of security in public key algorithms such as RSA, ElGAMAL etc. Finally, MRGA helps to overcome the weakness of public key cryptosystem. Cipher text developed by this method can be entirely different when compared to the plain text and will be suitable for the secured transmission over the internet.","PeriodicalId":421793,"journal":{"name":"2014 World Congress on Computing and Communication Technologies","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129457467","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}
Collaborative Filtering (CF) is one of the most effective technologies in making rating prediction for recommender systems. Traditional user-based CF methods take user-item matrices as input and compute the prediction value based on user similarity. The computation of similarity between each user pair requires exact matching on item set by finding a minimum number of same items rated by both users. However in real-world scenario, the input matrix is very sparse, therefore the amount of required information is far from enough to compute reliable similarity. To deal with this so-called data sparsity problem, we introduce a novel user similarity measure based on user favorite items (UFI) and apply it into Slope One scheme for rating prediction. The experimental results suggest that UFI user similarity measure is effective in user-based approaches and UFI-based Slope One algorithm can provide better quality of prediction than best available similarity-based CF algorithms.
{"title":"Applying User-Favorite-Item-Based Similarity into Slope One Scheme for Collaborative Filtering","authors":"Ziqing Zhang, Xinhuai Tang, D. Chen","doi":"10.1109/WCCCT.2014.43","DOIUrl":"https://doi.org/10.1109/WCCCT.2014.43","url":null,"abstract":"Collaborative Filtering (CF) is one of the most effective technologies in making rating prediction for recommender systems. Traditional user-based CF methods take user-item matrices as input and compute the prediction value based on user similarity. The computation of similarity between each user pair requires exact matching on item set by finding a minimum number of same items rated by both users. However in real-world scenario, the input matrix is very sparse, therefore the amount of required information is far from enough to compute reliable similarity. To deal with this so-called data sparsity problem, we introduce a novel user similarity measure based on user favorite items (UFI) and apply it into Slope One scheme for rating prediction. The experimental results suggest that UFI user similarity measure is effective in user-based approaches and UFI-based Slope One algorithm can provide better quality of prediction than best available similarity-based CF algorithms.","PeriodicalId":421793,"journal":{"name":"2014 World Congress on Computing and Communication Technologies","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116727854","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：