In this paper we introduced the concept of edge double domination and total edge double dominatio... more In this paper we introduced the concept of edge double domination and total edge double domination in intuitionistic fuzzy graphs. We determine the edge double domination number and total edge double domination number t for several classes of intuitionistic fuzzy graphs and obtain bounds for them. We also obtain nordhausgaddum type results for the parameters.
Data mining is used to discovering useful patterns hidden in a database from large datasets, but ... more Data mining is used to discovering useful patterns hidden in a database from large datasets, but sometimes these datasets are split among various sites and none of the sites is allowed to expose its database to another site. Association Rule mining in distributed database is one of the important and well researched techniques of data mining. This technique discloses some interesting relationship between local as well as global item sets.Mining of association rules from distributed databasesare essential in different area such as market basket analysis.But sometimes there are problem to determine a useful pattern in distributed databases.Also the protection of information from illegal access has been a long term goal for businesses and government organizations.So that it requires enhanced privacy. In this paper, we have shown the Association rule mining algorithm over horizontal distributed databases. Using our approach is to generate strong association rules from different data sets...
Mining high utility itemsets from a transactional database refers to the discovery of itemsets wi... more Mining high utility itemsets from a transactional database refers to the discovery of itemsets with high utility like profits. Although a number of relevant algorithms have been proposed in recent years, they incur the problem of producing a large number of candidate itemsets for high utility itemsets. Such a large number of candidate itemsets degrades the mining performance in terms of execution time and space requirement. The situation may become worse when the database contains lots of long transactions or long high utility itemsets. In this paper, we propose an algorithm for mining high utility itemsets with a set of effective strategies for pruning candidate itemsets as per periodicity. The information of high utility itemsets is maintained in a tree-based data structure named utility pattern tree such that candidate itemsets can be generated efficiently with only two scans of database. Experimental results show that the proposed algorithm not only reduce the number of candidat...
Mining high utility itemsets from a transactional database refers to the discovery of itemsets wi... more Mining high utility itemsets from a transactional database refers to the discovery of itemsets with high utility like profits. Although a number of relevant algorithms have been proposed in recent years, they incur the problem of producing a large number of candidate itemsets for high utility itemsets. Such a large number of candidate itemsets degrades the mining performance in terms of execution time and space requirement. The situation may become worse when the database contains lots of long transactions or long high utility itemsets. In this paper, we propose an algorithm for mining high utility itemsets with a set of effective strategies for pruning candidate itemsets as per periodicity. The information of high utility itemsets is maintained in a tree-based data structure named utility pattern tree such that candidate itemsets can be generated efficiently with only two scans of database. Experimental results show that the proposed algorithm not only reduce the number of candidat...
Recommender systems are used on the web for recommending products to users. Most of the electroni... more Recommender systems are used on the web for recommending products to users. Most of the electronic commerce sites have such systems. Collaborative filtering is an important and popular technique for recommender system. In this paper, an expert system for movie recommendation is presented with new approach. This system is implemented using co clustering method. Category of the movie and ratings given by users are used to give recommendations. Users are interested in grouping items into categories and for each category; there can be corresponding user group who like items in that category. Finding interest of user in particular item group and grouping users of similar interest is distinguishable feature, which differentiate our approach from the previous works.
Recommendation system can help users to provide right items from large number of avalible items.r... more Recommendation system can help users to provide right items from large number of avalible items.recommender systems suggest items to users by using the techniques of Collaborative filtering based on historical data of items that users have rated. In this paper we present a novel collabroative filtering approach called NPC collabroative filtering for item i.e books recommendations with malicious feedback rating detection and prevention system. Goal of detection and prevention system is to detect the malicious feedback rating and avoid or adjust this malicious feedback rating.The experimental results shows that our approach achieves better accuracy than other competing approaches.
Volume 5, Issue 5, September – October 2016 Page 72 Abstract Email is an essential thing in today... more Volume 5, Issue 5, September – October 2016 Page 72 Abstract Email is an essential thing in today’s era, as emails are main source of communication. Emails are used on personal and corporate levels. Emails are used by number of people to interact between each other. Many email users receives legitimate emails and also unwanted emails. It becomes necessary to classify legitimate emails (HAM) from unwanted emails (SPAM). There are many Machine learning techniques now a day’s used to automatically filter the spam e-mail. This paper proposes and reviews the classification technique. The purpose of proposed algorithm is to automatically classify mails into spam and legitimate message. The algorithm used for classification is support vector machine. The mails are classified on the basis of email text. The proposed algorithm is effective and reasonable method for email classification.
Model based testing approach for both test case generation and test case optimization for objecto... more Model based testing approach for both test case generation and test case optimization for objectoriented software using UML diagrams. The proposed approach addresses the issue of redundancy, size of test cases and optimization challenges. Automation of test case design process can result in significant reductions in time and effort, and at the same time it can help in improving reliability of the software through increased test coverage. The proposed approach uses genetic algorithm from which best test cases can be optimized. Moreover our method for test case generation inspires the developers to improve the design quality.
Recommender systems suggest items to users by utilizing the techniques of Collaborative filtering... more Recommender systems suggest items to users by utilizing the techniques of Collaborative filtering based on historical records of items that users have purchased. Recommender systems make use of data mining techniques to determine the similarity among a huge collection of data items, by analysing historical user data and then extracting hidden useful information or patterns. Goal of Collaborative filtering is finding the relationships among the individuals and the existing data items in order to further determine the similarity and provide recommendations. This paper, proposes the Context based Collaborative Filtering Recommender System, which can be used for any commercial onlinemarketing. Experimental evaluation of results and comparing them with traditional collaborative filtering approach, concludes that context based collaborative approach provide dramatically better performance than traditional-based algorithms, while at the same time providing better recommendation as per customer point of view.
Medical Imaging is a need for physians. Physians are relaying on the reports that are generated b... more Medical Imaging is a need for physians. Physians are relaying on the reports that are generated by radiologist. Lots of time and efforts are needed to be given by radiologist to prepare a report. Radiologist must read and observe the MRI image to detect and locate the lesion in MRI brain images.The research is helpful to reduce the effort of radiologist to detect the abnormalities in the MRI Image and classify them. It also help to increase the accuracy in detection of abnormalities. The main objective is to find the lesion present in MRI Image and to classify them. The brain tumor diagnostic procedure consists of three phases. The first phases involve image pre-processing. The feature extraction is the second phase and the classification using the k-nearest neighbor algorithm is the last phase.
The paper emphasizes on forecasting stock prices among the same sector known as intra sector and ... more The paper emphasizes on forecasting stock prices among the same sector known as intra sector and also among different sector known as inter sector and provides best rules using Intra and Inter Sector Association Rule Mining (IISARM) algorithm. Association rules are well suited for predicting stock market behavior. Our approach is to develop and test the algorithm that predicts the impact of company stock prices in intra and inter sector. Our approach is also to measure the impact in percentage. The object of this algorithm was to find hidden rules within sector having strong and relative association between them.
Any staff in the organization is imp ortant element in the systems development pro cess and its i... more Any staff in the organization is imp ortant element in the systems development pro cess and its improve ment. Their b ehavior definitely affects the systems pro ject if their b ehavioral measurement has not b een considered according to the some rule. Every pro ject as divided into planning, analysis, design and implementation, same can b e oriented Or analogous to the mans demeanor. The primitive properties, characteristics, effect and building blocks of characteristic s, output as bad behavior and go o d b ehavior of man can b e part of ab ove division . Thinking in the positive attitude yields to the optimum threshold of the decisions in the project. Ultimately it can b e useful for the system to increase the energy of system. Mental satisfaction of the staff in the system can give the projects output in decided time as it may b e affected by the financial position and physical capacity of that staff.
Inexpensive wireless communication, computation and sensing is now need of the Wireless Sensor Ne... more Inexpensive wireless communication, computation and sensing is now need of the Wireless Sensor Network (WSN). Wireless sensor networks (WSNs) comprises large number of wireless sensor nodes which can sense and process data in the environment in a periodic manner. In WSN, as the sensor node depends on its internal battery power, energy efficiency and lifetime of sensors have become a key issue on the performance of wireless network. To make effective utilization of energy resources of a sensor node, communication protocols can be designed precisely. Clustering the sensor nodes is one of the effective techniques to achieve this goal. Low-Energy Adaptive Clustering Hierarchy (LEACH) -A cluster based routing algorithm was proposed as a solution for low power consumption. One of problems in the LEACH protocol is "Extra Transmissions". The goal of our research is to optimize the energy consumption of wireless sensor network by introducing a novel and adaptive technique on the tr...
International Journal of Rough Sets and Data Analysis
The paper emphasizes on stock price trend prediction based on the online textual news. Cognitive ... more The paper emphasizes on stock price trend prediction based on the online textual news. Cognitive process uses existing knowledge and generates new knowledge. Contextual features (CF) from news sites are extracted & recommendations based on the interpretations are generated. A Naïve bays classification algorithm is used to classify the news sentiments. A News Sentiment Index (NSI) is calculated and effect of the news on particular stock is calculated to predict the trend. Along with news sentiment index, technical quality of the same stock is calculated by various statistical technical indicators which are called as Stock Technical Index (STI). The weighted index of NSI and STI is used to predict the trend of stock price. In the previous recommendation systems, the context of the recommendation is not considered. However, it is shown in this research that if the authors consider the news context while recommendation, the performance of the recommendation system will drastically impro...
In this paper we introduced the concept of edge double domination and total edge double dominatio... more In this paper we introduced the concept of edge double domination and total edge double domination in intuitionistic fuzzy graphs. We determine the edge double domination number and total edge double domination number t for several classes of intuitionistic fuzzy graphs and obtain bounds for them. We also obtain nordhausgaddum type results for the parameters.
Data mining is used to discovering useful patterns hidden in a database from large datasets, but ... more Data mining is used to discovering useful patterns hidden in a database from large datasets, but sometimes these datasets are split among various sites and none of the sites is allowed to expose its database to another site. Association Rule mining in distributed database is one of the important and well researched techniques of data mining. This technique discloses some interesting relationship between local as well as global item sets.Mining of association rules from distributed databasesare essential in different area such as market basket analysis.But sometimes there are problem to determine a useful pattern in distributed databases.Also the protection of information from illegal access has been a long term goal for businesses and government organizations.So that it requires enhanced privacy. In this paper, we have shown the Association rule mining algorithm over horizontal distributed databases. Using our approach is to generate strong association rules from different data sets...
Mining high utility itemsets from a transactional database refers to the discovery of itemsets wi... more Mining high utility itemsets from a transactional database refers to the discovery of itemsets with high utility like profits. Although a number of relevant algorithms have been proposed in recent years, they incur the problem of producing a large number of candidate itemsets for high utility itemsets. Such a large number of candidate itemsets degrades the mining performance in terms of execution time and space requirement. The situation may become worse when the database contains lots of long transactions or long high utility itemsets. In this paper, we propose an algorithm for mining high utility itemsets with a set of effective strategies for pruning candidate itemsets as per periodicity. The information of high utility itemsets is maintained in a tree-based data structure named utility pattern tree such that candidate itemsets can be generated efficiently with only two scans of database. Experimental results show that the proposed algorithm not only reduce the number of candidat...
Mining high utility itemsets from a transactional database refers to the discovery of itemsets wi... more Mining high utility itemsets from a transactional database refers to the discovery of itemsets with high utility like profits. Although a number of relevant algorithms have been proposed in recent years, they incur the problem of producing a large number of candidate itemsets for high utility itemsets. Such a large number of candidate itemsets degrades the mining performance in terms of execution time and space requirement. The situation may become worse when the database contains lots of long transactions or long high utility itemsets. In this paper, we propose an algorithm for mining high utility itemsets with a set of effective strategies for pruning candidate itemsets as per periodicity. The information of high utility itemsets is maintained in a tree-based data structure named utility pattern tree such that candidate itemsets can be generated efficiently with only two scans of database. Experimental results show that the proposed algorithm not only reduce the number of candidat...
Recommender systems are used on the web for recommending products to users. Most of the electroni... more Recommender systems are used on the web for recommending products to users. Most of the electronic commerce sites have such systems. Collaborative filtering is an important and popular technique for recommender system. In this paper, an expert system for movie recommendation is presented with new approach. This system is implemented using co clustering method. Category of the movie and ratings given by users are used to give recommendations. Users are interested in grouping items into categories and for each category; there can be corresponding user group who like items in that category. Finding interest of user in particular item group and grouping users of similar interest is distinguishable feature, which differentiate our approach from the previous works.
Recommendation system can help users to provide right items from large number of avalible items.r... more Recommendation system can help users to provide right items from large number of avalible items.recommender systems suggest items to users by using the techniques of Collaborative filtering based on historical data of items that users have rated. In this paper we present a novel collabroative filtering approach called NPC collabroative filtering for item i.e books recommendations with malicious feedback rating detection and prevention system. Goal of detection and prevention system is to detect the malicious feedback rating and avoid or adjust this malicious feedback rating.The experimental results shows that our approach achieves better accuracy than other competing approaches.
Volume 5, Issue 5, September – October 2016 Page 72 Abstract Email is an essential thing in today... more Volume 5, Issue 5, September – October 2016 Page 72 Abstract Email is an essential thing in today’s era, as emails are main source of communication. Emails are used on personal and corporate levels. Emails are used by number of people to interact between each other. Many email users receives legitimate emails and also unwanted emails. It becomes necessary to classify legitimate emails (HAM) from unwanted emails (SPAM). There are many Machine learning techniques now a day’s used to automatically filter the spam e-mail. This paper proposes and reviews the classification technique. The purpose of proposed algorithm is to automatically classify mails into spam and legitimate message. The algorithm used for classification is support vector machine. The mails are classified on the basis of email text. The proposed algorithm is effective and reasonable method for email classification.
Model based testing approach for both test case generation and test case optimization for objecto... more Model based testing approach for both test case generation and test case optimization for objectoriented software using UML diagrams. The proposed approach addresses the issue of redundancy, size of test cases and optimization challenges. Automation of test case design process can result in significant reductions in time and effort, and at the same time it can help in improving reliability of the software through increased test coverage. The proposed approach uses genetic algorithm from which best test cases can be optimized. Moreover our method for test case generation inspires the developers to improve the design quality.
Recommender systems suggest items to users by utilizing the techniques of Collaborative filtering... more Recommender systems suggest items to users by utilizing the techniques of Collaborative filtering based on historical records of items that users have purchased. Recommender systems make use of data mining techniques to determine the similarity among a huge collection of data items, by analysing historical user data and then extracting hidden useful information or patterns. Goal of Collaborative filtering is finding the relationships among the individuals and the existing data items in order to further determine the similarity and provide recommendations. This paper, proposes the Context based Collaborative Filtering Recommender System, which can be used for any commercial onlinemarketing. Experimental evaluation of results and comparing them with traditional collaborative filtering approach, concludes that context based collaborative approach provide dramatically better performance than traditional-based algorithms, while at the same time providing better recommendation as per customer point of view.
Medical Imaging is a need for physians. Physians are relaying on the reports that are generated b... more Medical Imaging is a need for physians. Physians are relaying on the reports that are generated by radiologist. Lots of time and efforts are needed to be given by radiologist to prepare a report. Radiologist must read and observe the MRI image to detect and locate the lesion in MRI brain images.The research is helpful to reduce the effort of radiologist to detect the abnormalities in the MRI Image and classify them. It also help to increase the accuracy in detection of abnormalities. The main objective is to find the lesion present in MRI Image and to classify them. The brain tumor diagnostic procedure consists of three phases. The first phases involve image pre-processing. The feature extraction is the second phase and the classification using the k-nearest neighbor algorithm is the last phase.
The paper emphasizes on forecasting stock prices among the same sector known as intra sector and ... more The paper emphasizes on forecasting stock prices among the same sector known as intra sector and also among different sector known as inter sector and provides best rules using Intra and Inter Sector Association Rule Mining (IISARM) algorithm. Association rules are well suited for predicting stock market behavior. Our approach is to develop and test the algorithm that predicts the impact of company stock prices in intra and inter sector. Our approach is also to measure the impact in percentage. The object of this algorithm was to find hidden rules within sector having strong and relative association between them.
Any staff in the organization is imp ortant element in the systems development pro cess and its i... more Any staff in the organization is imp ortant element in the systems development pro cess and its improve ment. Their b ehavior definitely affects the systems pro ject if their b ehavioral measurement has not b een considered according to the some rule. Every pro ject as divided into planning, analysis, design and implementation, same can b e oriented Or analogous to the mans demeanor. The primitive properties, characteristics, effect and building blocks of characteristic s, output as bad behavior and go o d b ehavior of man can b e part of ab ove division . Thinking in the positive attitude yields to the optimum threshold of the decisions in the project. Ultimately it can b e useful for the system to increase the energy of system. Mental satisfaction of the staff in the system can give the projects output in decided time as it may b e affected by the financial position and physical capacity of that staff.
Inexpensive wireless communication, computation and sensing is now need of the Wireless Sensor Ne... more Inexpensive wireless communication, computation and sensing is now need of the Wireless Sensor Network (WSN). Wireless sensor networks (WSNs) comprises large number of wireless sensor nodes which can sense and process data in the environment in a periodic manner. In WSN, as the sensor node depends on its internal battery power, energy efficiency and lifetime of sensors have become a key issue on the performance of wireless network. To make effective utilization of energy resources of a sensor node, communication protocols can be designed precisely. Clustering the sensor nodes is one of the effective techniques to achieve this goal. Low-Energy Adaptive Clustering Hierarchy (LEACH) -A cluster based routing algorithm was proposed as a solution for low power consumption. One of problems in the LEACH protocol is "Extra Transmissions". The goal of our research is to optimize the energy consumption of wireless sensor network by introducing a novel and adaptive technique on the tr...
International Journal of Rough Sets and Data Analysis
The paper emphasizes on stock price trend prediction based on the online textual news. Cognitive ... more The paper emphasizes on stock price trend prediction based on the online textual news. Cognitive process uses existing knowledge and generates new knowledge. Contextual features (CF) from news sites are extracted & recommendations based on the interpretations are generated. A Naïve bays classification algorithm is used to classify the news sentiments. A News Sentiment Index (NSI) is calculated and effect of the news on particular stock is calculated to predict the trend. Along with news sentiment index, technical quality of the same stock is calculated by various statistical technical indicators which are called as Stock Technical Index (STI). The weighted index of NSI and STI is used to predict the trend of stock price. In the previous recommendation systems, the context of the recommendation is not considered. However, it is shown in this research that if the authors consider the news context while recommendation, the performance of the recommendation system will drastically impro...
Uploads
Papers by vipul bag