Jayna Shah | Sardar Vallabhbhai Patel Institute of Technology (original) (raw)

Papers by Jayna Shah

2022 6th International Conference on Electronics, Communication and Aerospace Technology

2019 3rd International Conference on Computing Methodologies and Communication (ICCMC)

Text classification is a process of allocating one or more class label to a text document. If the... more Text classification is a process of allocating one or more class label to a text document. If the text classification problem has too many categories, and there are certain categories with less number of training documents, text classification task becomes difficult. Recall will be less for categories with less number of training documents. To handle text classification problem with too many categories and to take into consideration parent-child/sibling relationships between categories in user profile and document profile for content-based filtering, hierarchical classification is better approach. The main issue with hierarchical classification is error propagation. The error that occurs at early level in hierarchy will carry forward to all the levels below it. So, misclassification at early level in hierarchy needs to be reduced. Term ambiguity may be one of the reasons for classification error. Naïve Bayes classification method is mostly used in text classification problem as it takes less time for training and testing. Naïve Bayes model considers that terms are not dependent on each other for a given class. For data where terms are dependent on each other, performance of naïve Bayes is degraded. In this paper, word-level n-gram based Multinomial Naïve Bayes classification method is combined with hierarchical classification to reduce misclassification that occur at early level in hierarchy & improve content-based filtering. Proposed algorithm also suggests a way to reduce execution time requirements for calculating probabilities of terms for n-gram naïve bayes model.

International journal of scientific research in computer science, engineering and information technology, Feb 28, 2018

International journal of innovative research and development, 2014

Wireless sensors networks (WSNs) consist of a large number of tiny, spatially distributed, and au... more Wireless sensors networks (WSNs) consist of a large number of tiny, spatially distributed, and autonomous devices, called sensor nodes. The nodes are densely deployed. The ad hoc nature of WSNs, their deployment in hostile areas, and their physical interaction with environment, make them vulnerable to several types of security attacks. One of the most important attacks in WSNs is the wormhole attack in which a malicious node receives packets from one location and tunnels them to another location in the network. Wormhole attack can be achieved with the help of several techniques such as packet encapsulation, high transmission power and high quality communication links etc. In this paper, we have surveyed various existing techniques to detect wormhole attack in wireless sensor networks.

International Journal of Advance Engineering and Research Development, 2015

Recently, it has become more and more difficult for the existing web based systems to locate or r... more Recently, it has become more and more difficult for the existing web based systems to locate or retrieve any kind of relevant information, due to the rapid growth of the World Wide Web in terms of the information space and the amount of the users in that space. However, in today's world, many systems and approaches make it possible for the users to be guided by the recommendations that they provide about new items such as articles, news, books, music, and movies. However, a lot of traditional recommender systems result in failure when the data to be used throughout the recommendation process is sparse. This Paper focuses on the development and evaluation of a web based movie recommendation system.

International Journal For Scientific Research and Development, 2015

Sequential pattern mining plays an important role in many applications, such as bioinformatics an... more Sequential pattern mining plays an important role in many applications, such as bioinformatics and consumer behaviour analysis. However, the classic frequency-based framework often leads to many patterns being identified, most of which are not informative enough for business decision-making. So a recent effort has been to incorporate utility into the sequential pattern selection framework, so that high utility (frequent or infrequent) sequential patterns are mined which address typical business concerns such as dollar value associated with each pattern. So this paper presents detailed different approaches adopted for Sequential pattern mining algorithms as well as high utility sequential pattern mining techniques.

International Journal of Computer Applications, 2015

Frequent Pattern mining is modified by Sequential Pattern Mining to consider time regularity whic... more Frequent Pattern mining is modified by Sequential Pattern Mining to consider time regularity which is further enhanced to high utility sequential pattern mining (HUS) by incorporating utility into sequential pattern mining for business value and impact. In the process of mining HUS, when new sequences are added into the existing database the whole procedure of mining HUS starts from the scratch, in spite of mining HUS only from incremental sequences. This results in excess of time as well as efforts. So in this paper an incremental algorithm is proposed to mine HUS from the Incremental Database. Experimental results show that the proposed algorithm executes faster than existing PHUS algorithm resulting in saving of time as well as efforts.

International Journal of Computer Applications, 2012

Data clustering is a highly valuable field of computational statistics and data mining. Data clus... more Data clustering is a highly valuable field of computational statistics and data mining. Data clustering can be considered as the most important unsupervised learning technique as it deals with finding a structure in a collection of unlabeled data. A Clustering is division of data into similar objects. A major difficulty in the design of data clustering algorithms is that, in majority of applications, new data are dynamically appended into an existing database and it is not feasible to perform data clustering from scratch every time new data instances get added up in the database. The development of clustering algorithms which handle the incremental updating of data points is known as an Incremental clustering. In this paper authors have reviewed Partition based clustering methods mainly, K-means & DBSCAN and provided a detailed comparison of Traditional clustering and Incremental clustering method for both.

IOSR Journal of Computer Engineering, 2014

Cloud computing is emerging trend in Information Technology community. Cloud resources are delive... more Cloud computing is emerging trend in Information Technology community. Cloud resources are delivered to cloud users based on the requirements. Because of the services provided by cloud, it is becoming more popular among internet users. Hence, the number of cloud users is increasing day by day. Because of this, load on the cloud server needs to be managed for optimum resource utilization. This research proposes new load balancing algorithm which considers parameter like weight of each task, execution time of each task, current load and future load on the server. Current load balancing algorithms don't consider these parameters together for load balancing. Proposed scheme selects the best node based on these parameters to achieve optimum use of resources.

IOSR Journal of Computer Engineering, 2014

A mobile ad hoc network (MANET) is a self-configuring network that is formed automatically by a c... more A mobile ad hoc network (MANET) is a self-configuring network that is formed automatically by a collection of mobile nodes. There is no centralized management. Both legitimate and malicious nodes can access the network, so there are many possible attacks in MANET. In a black hole attack, a malicious node attracts traffic towards it and drops all packets without forwarding to the destination. The security of the AODV protocol is compromised by a particular type of attack called black hole attack.

International Journal of Computer Applications, 2015

A factory has a production plan to produce products which are created from number of components a... more A factory has a production plan to produce products which are created from number of components and thus create profit. During financial crisis, the factory cannot afford to purchase all the necessary items as usual. Mining of erasable itemsets finds the itemsets which can be eliminated and do not greatly affect the factory's profit. The managers uses erasable itemset (EI) mining to locate EIs. If the manager wants to determine which new products are beneficial for the factory, we have to apply EI mining on the original database with new products from the scratch. So, here the incremental approach to mine erasable itemsets is proposed which scans only new products and update the EIs which were found previously from original database.

Frequent Pattern mining is modified by Sequential Pattern Mining to consider time regularity whic... more Frequent Pattern mining is modified by Sequential Pattern Mining to consider time regularity which is further enhanced to high utility sequential pattern mining (HUS) by incorporating utility into sequential pattern mining for business value and impact. In the process of mining HUS, when new sequences are added into the existing database the whole procedure of mining HUS starts from the scratch, in spite of mining HUS only from incremental sequences. This results in excess of time as well as efforts. So in this paper an incremental algorithm is proposed to mine HUS from the Incremental Database. Experimental results show that the proposed algorithm executes faster than existing PHUS algorithm resulting in saving of time as well as efforts.

2022 6th International Conference on Electronics, Communication and Aerospace Technology

2019 3rd International Conference on Computing Methodologies and Communication (ICCMC)

Text classification is a process of allocating one or more class label to a text document. If the... more Text classification is a process of allocating one or more class label to a text document. If the text classification problem has too many categories, and there are certain categories with less number of training documents, text classification task becomes difficult. Recall will be less for categories with less number of training documents. To handle text classification problem with too many categories and to take into consideration parent-child/sibling relationships between categories in user profile and document profile for content-based filtering, hierarchical classification is better approach. The main issue with hierarchical classification is error propagation. The error that occurs at early level in hierarchy will carry forward to all the levels below it. So, misclassification at early level in hierarchy needs to be reduced. Term ambiguity may be one of the reasons for classification error. Naïve Bayes classification method is mostly used in text classification problem as it takes less time for training and testing. Naïve Bayes model considers that terms are not dependent on each other for a given class. For data where terms are dependent on each other, performance of naïve Bayes is degraded. In this paper, word-level n-gram based Multinomial Naïve Bayes classification method is combined with hierarchical classification to reduce misclassification that occur at early level in hierarchy & improve content-based filtering. Proposed algorithm also suggests a way to reduce execution time requirements for calculating probabilities of terms for n-gram naïve bayes model.

International journal of scientific research in computer science, engineering and information technology, Feb 28, 2018

International journal of innovative research and development, 2014

Wireless sensors networks (WSNs) consist of a large number of tiny, spatially distributed, and au... more Wireless sensors networks (WSNs) consist of a large number of tiny, spatially distributed, and autonomous devices, called sensor nodes. The nodes are densely deployed. The ad hoc nature of WSNs, their deployment in hostile areas, and their physical interaction with environment, make them vulnerable to several types of security attacks. One of the most important attacks in WSNs is the wormhole attack in which a malicious node receives packets from one location and tunnels them to another location in the network. Wormhole attack can be achieved with the help of several techniques such as packet encapsulation, high transmission power and high quality communication links etc. In this paper, we have surveyed various existing techniques to detect wormhole attack in wireless sensor networks.

International Journal of Advance Engineering and Research Development, 2015

Recently, it has become more and more difficult for the existing web based systems to locate or r... more Recently, it has become more and more difficult for the existing web based systems to locate or retrieve any kind of relevant information, due to the rapid growth of the World Wide Web in terms of the information space and the amount of the users in that space. However, in today's world, many systems and approaches make it possible for the users to be guided by the recommendations that they provide about new items such as articles, news, books, music, and movies. However, a lot of traditional recommender systems result in failure when the data to be used throughout the recommendation process is sparse. This Paper focuses on the development and evaluation of a web based movie recommendation system.

International Journal For Scientific Research and Development, 2015

Sequential pattern mining plays an important role in many applications, such as bioinformatics an... more Sequential pattern mining plays an important role in many applications, such as bioinformatics and consumer behaviour analysis. However, the classic frequency-based framework often leads to many patterns being identified, most of which are not informative enough for business decision-making. So a recent effort has been to incorporate utility into the sequential pattern selection framework, so that high utility (frequent or infrequent) sequential patterns are mined which address typical business concerns such as dollar value associated with each pattern. So this paper presents detailed different approaches adopted for Sequential pattern mining algorithms as well as high utility sequential pattern mining techniques.

International Journal of Computer Applications, 2015

Frequent Pattern mining is modified by Sequential Pattern Mining to consider time regularity whic... more Frequent Pattern mining is modified by Sequential Pattern Mining to consider time regularity which is further enhanced to high utility sequential pattern mining (HUS) by incorporating utility into sequential pattern mining for business value and impact. In the process of mining HUS, when new sequences are added into the existing database the whole procedure of mining HUS starts from the scratch, in spite of mining HUS only from incremental sequences. This results in excess of time as well as efforts. So in this paper an incremental algorithm is proposed to mine HUS from the Incremental Database. Experimental results show that the proposed algorithm executes faster than existing PHUS algorithm resulting in saving of time as well as efforts.

International Journal of Computer Applications, 2012

Data clustering is a highly valuable field of computational statistics and data mining. Data clus... more Data clustering is a highly valuable field of computational statistics and data mining. Data clustering can be considered as the most important unsupervised learning technique as it deals with finding a structure in a collection of unlabeled data. A Clustering is division of data into similar objects. A major difficulty in the design of data clustering algorithms is that, in majority of applications, new data are dynamically appended into an existing database and it is not feasible to perform data clustering from scratch every time new data instances get added up in the database. The development of clustering algorithms which handle the incremental updating of data points is known as an Incremental clustering. In this paper authors have reviewed Partition based clustering methods mainly, K-means & DBSCAN and provided a detailed comparison of Traditional clustering and Incremental clustering method for both.

IOSR Journal of Computer Engineering, 2014

Cloud computing is emerging trend in Information Technology community. Cloud resources are delive... more Cloud computing is emerging trend in Information Technology community. Cloud resources are delivered to cloud users based on the requirements. Because of the services provided by cloud, it is becoming more popular among internet users. Hence, the number of cloud users is increasing day by day. Because of this, load on the cloud server needs to be managed for optimum resource utilization. This research proposes new load balancing algorithm which considers parameter like weight of each task, execution time of each task, current load and future load on the server. Current load balancing algorithms don't consider these parameters together for load balancing. Proposed scheme selects the best node based on these parameters to achieve optimum use of resources.

IOSR Journal of Computer Engineering, 2014

A mobile ad hoc network (MANET) is a self-configuring network that is formed automatically by a c... more A mobile ad hoc network (MANET) is a self-configuring network that is formed automatically by a collection of mobile nodes. There is no centralized management. Both legitimate and malicious nodes can access the network, so there are many possible attacks in MANET. In a black hole attack, a malicious node attracts traffic towards it and drops all packets without forwarding to the destination. The security of the AODV protocol is compromised by a particular type of attack called black hole attack.

International Journal of Computer Applications, 2015

A factory has a production plan to produce products which are created from number of components a... more A factory has a production plan to produce products which are created from number of components and thus create profit. During financial crisis, the factory cannot afford to purchase all the necessary items as usual. Mining of erasable itemsets finds the itemsets which can be eliminated and do not greatly affect the factory's profit. The managers uses erasable itemset (EI) mining to locate EIs. If the manager wants to determine which new products are beneficial for the factory, we have to apply EI mining on the original database with new products from the scratch. So, here the incremental approach to mine erasable itemsets is proposed which scans only new products and update the EIs which were found previously from original database.

Frequent Pattern mining is modified by Sequential Pattern Mining to consider time regularity whic... more Frequent Pattern mining is modified by Sequential Pattern Mining to consider time regularity which is further enhanced to high utility sequential pattern mining (HUS) by incorporating utility into sequential pattern mining for business value and impact. In the process of mining HUS, when new sequences are added into the existing database the whole procedure of mining HUS starts from the scratch, in spite of mining HUS only from incremental sequences. This results in excess of time as well as efforts. So in this paper an incremental algorithm is proposed to mine HUS from the Incremental Database. Experimental results show that the proposed algorithm executes faster than existing PHUS algorithm resulting in saving of time as well as efforts.