sneha soni - Academia.edu (original) (raw)

Papers by sneha soni

Research paper thumbnail of Enhance Clustering Approach using PSO-A* for E-Commerce

International Journal of Computer Applications, 2019

In the current trends most of the people uses online searching and purchasing the items. So web d... more In the current trends most of the people uses online searching and purchasing the items. So web data size is drastically increases and after some time not possible to put all data in memory. So there is a need to manage data access speed and also increase the speed of searching. In the existing system most of clustering algorithm uses only basic criteria for machine learning and data mining algorithms. Initially it is not able to select the good center point so it will do to increase the number of iteration. Second problem is to access of full database and third problem is needed to increase searching speed. The proposed approach uses PSO-A* algorithm for clustering and searching that is used for select the good center point initial for clustering. After that only clustered data is access not full database that make partial database access to manage memory management and speed. Finally third approach is uses for increase searching speed. Now the proposed approach is to perform well and improve the ecommerce website performance.

Research paper thumbnail of Link Prediction in Social Network using Artificial Neural Network

International Journal of Computer Applications

The prediction process from prior information of the event helps to know the evolution of social ... more The prediction process from prior information of the event helps to know the evolution of social network and assists the companies in effective decisions making during a typical recommendation system. Social network connection prediction is an efficient technique for the analysis of the evolution of social organizations and formation of the social network relations. Link prediction is a crucial research direction within the field of complex networks and data processing. In this work, we proposed a technique which is based on node similarity measure and Artificial Neural Network concept. We consider the features or information which are available in data set then assign the score to all pairs of nodes and apply Artificial Neural Network concept to the system. The proposed technique will improve the accuracy of Link Prediction.

Research paper thumbnail of Applications of ANNs in Stock Market Prediction : A Survey

This paper surveys recent literature in the domain of machine learning techniques and artificial ... more This paper surveys recent literature in the domain of machine learning techniques and artificial intelligence used to predict stock market movements. Artificial Neural Networks (ANNs) are identified to be the dominant machine learning technique in stock market prediction area. Keywords— Artificial Neural Networks (ANNs); Stock Market; Prediction

Research paper thumbnail of Implementation of Multivariate Data Set by Cart Algorithm

Data mining deals with various applications such as the discovery of hidden knowledge, unexpected... more Data mining deals with various applications such as the discovery of hidden knowledge, unexpected patterns and new rules from large Databases that guide to make decisions about enterprise to products and services competitive. Basically, data mining is concerned with the analysis ...

Research paper thumbnail of Brief Analysis of Methods for Cloud Computing Key Management

Journal of Information Engineering and Applications, 2013

Research paper thumbnail of Prevalence of depression and associated risk factors among the elderly in Middle Anatolia, Turkey

Background Depression is a common mental health problem in medical students worldwide. The associ... more Background Depression is a common mental health problem in medical students worldwide. The association between depression and motivation in Vietnamese medical students is not welldocumented. Objectives To estimate the prevalence of self-reported depression and to identify associated risk factors among medical students at Hanoi Medical University (HMU). Method A cross-sectional study was conducted on medical students with clinical experience at HMU from November 2015 to January 2016. We used the multistage cluster random sampling technique to select and invite students to complete a questionnaire including demographic characteristics, Patient Health Questionnaire 9 (PHQ-9), Academic Motivation Scale (AMS), and International Physical Activity Questionnaire Short Form (IPAQ). Results Among 494 participants (78.8% response rate), the prevalence of self-reported depression was 15.2% (95%CI:12.0%-19.0%), and suicidal ideation was 7.7% (95%CI:6.2%-9.5%). Self-reported depression was significantly associated with perceived financial burden, physical inactivity, being senior student, perceived negative influence of night shifts, and nonself-determined motivation profile. Suicidal ideation was significantly associated with perceived financial burden and non-self-determined motivation profile. In the multivariable regression models, significant risk factors for self-reported depression were non-self-determined motivation (PR = 2.62, 95%CI:1.68-4.07), perceived financial burden (PR = 1.95,

Research paper thumbnail of Enhance Clustering Approach using PSO-A* for E-Commerce

International Journal of Computer Applications, 2019

In the current trends most of the people uses online searching and purchasing the items. So web d... more In the current trends most of the people uses online searching and purchasing the items. So web data size is drastically increases and after some time not possible to put all data in memory. So there is a need to manage data access speed and also increase the speed of searching. In the existing system most of clustering algorithm uses only basic criteria for machine learning and data mining algorithms. Initially it is not able to select the good center point so it will do to increase the number of iteration. Second problem is to access of full database and third problem is needed to increase searching speed. The proposed approach uses PSO-A* algorithm for clustering and searching that is used for select the good center point initial for clustering. After that only clustered data is access not full database that make partial database access to manage memory management and speed. Finally third approach is uses for increase searching speed. Now the proposed approach is to perform well and improve the ecommerce website performance.

Research paper thumbnail of Link Prediction in Social Network using Artificial Neural Network

International Journal of Computer Applications

The prediction process from prior information of the event helps to know the evolution of social ... more The prediction process from prior information of the event helps to know the evolution of social network and assists the companies in effective decisions making during a typical recommendation system. Social network connection prediction is an efficient technique for the analysis of the evolution of social organizations and formation of the social network relations. Link prediction is a crucial research direction within the field of complex networks and data processing. In this work, we proposed a technique which is based on node similarity measure and Artificial Neural Network concept. We consider the features or information which are available in data set then assign the score to all pairs of nodes and apply Artificial Neural Network concept to the system. The proposed technique will improve the accuracy of Link Prediction.

Research paper thumbnail of Applications of ANNs in Stock Market Prediction : A Survey

This paper surveys recent literature in the domain of machine learning techniques and artificial ... more This paper surveys recent literature in the domain of machine learning techniques and artificial intelligence used to predict stock market movements. Artificial Neural Networks (ANNs) are identified to be the dominant machine learning technique in stock market prediction area. Keywords— Artificial Neural Networks (ANNs); Stock Market; Prediction

Research paper thumbnail of Implementation of Multivariate Data Set by Cart Algorithm

Data mining deals with various applications such as the discovery of hidden knowledge, unexpected... more Data mining deals with various applications such as the discovery of hidden knowledge, unexpected patterns and new rules from large Databases that guide to make decisions about enterprise to products and services competitive. Basically, data mining is concerned with the analysis ...

Research paper thumbnail of Brief Analysis of Methods for Cloud Computing Key Management

Journal of Information Engineering and Applications, 2013

Research paper thumbnail of Prevalence of depression and associated risk factors among the elderly in Middle Anatolia, Turkey

Background Depression is a common mental health problem in medical students worldwide. The associ... more Background Depression is a common mental health problem in medical students worldwide. The association between depression and motivation in Vietnamese medical students is not welldocumented. Objectives To estimate the prevalence of self-reported depression and to identify associated risk factors among medical students at Hanoi Medical University (HMU). Method A cross-sectional study was conducted on medical students with clinical experience at HMU from November 2015 to January 2016. We used the multistage cluster random sampling technique to select and invite students to complete a questionnaire including demographic characteristics, Patient Health Questionnaire 9 (PHQ-9), Academic Motivation Scale (AMS), and International Physical Activity Questionnaire Short Form (IPAQ). Results Among 494 participants (78.8% response rate), the prevalence of self-reported depression was 15.2% (95%CI:12.0%-19.0%), and suicidal ideation was 7.7% (95%CI:6.2%-9.5%). Self-reported depression was significantly associated with perceived financial burden, physical inactivity, being senior student, perceived negative influence of night shifts, and nonself-determined motivation profile. Suicidal ideation was significantly associated with perceived financial burden and non-self-determined motivation profile. In the multivariable regression models, significant risk factors for self-reported depression were non-self-determined motivation (PR = 2.62, 95%CI:1.68-4.07), perceived financial burden (PR = 1.95,