Papers by Akanksha Dhamija
International Journal of Computing and Digital Systems, Sep 30, 2022
Recommender systems have become a key technology to help the users in interacting with the increa... more Recommender systems have become a key technology to help the users in interacting with the increasingly larger data and information available online. The rapid advancements in Deep Learning techniques have been very useful in recommendation systems as it enhances the overall performance and accuracy of the recommendation systems. This paper attempts to work on a hybrid recommendation model by considering a weighted average of top N recommendations from both content based and collaborative based filtering methods and hence eliminating their individual shortcomings. A LightFM module has been also used to evaluate the loss functions on this hybrid model and to capture the latent features about attributes of users and items. Thereafter, a class of two-layer undirected graphical models, called Restricted Boltzmann Machine (RBM) and Auto-encoder is successfully applied to the Movielens data set to provide the accurate recommendations. This study shows that the proposed approach outperform the traditional recommender systems in terms of accuracy.
A Framework for Virtual Reality in Healthcare
CRC Press eBooks, Apr 26, 2023
International Journal of Computing and Digital Systems
Recommender systems have become a key technology to help the users in interacting with the increa... more Recommender systems have become a key technology to help the users in interacting with the increasingly larger data and information available online. The rapid advancements in Deep Learning techniques have been very useful in recommendation systems as it enhances the overall performance and accuracy of the recommendation systems. This paper attempts to work on a hybrid recommendation model by considering a weighted average of top N recommendations from both content based and collaborative based filtering methods and hence eliminating their individual shortcomings. A LightFM module has been also used to evaluate the loss functions on this hybrid model and to capture the latent features about attributes of users and items. Thereafter, a class of two-layer undirected graphical models, called Restricted Boltzmann Machine (RBM) and Auto-encoder is successfully applied to the Movielens data set to provide the accurate recommendations. This study shows that the proposed approach outperform the traditional recommender systems in terms of accuracy.
Natural Selection Simulator using Machine Learning
2022 Fifth International Conference on Computational Intelligence and Communication Technologies (CCICT)
Time Series Prediction for Stock Market Analysis
Advances in Systems Analysis, Software Engineering, and High Performance Computing
The stock market is an ideal way to invest money and earn potential returns. But, even with advan... more The stock market is an ideal way to invest money and earn potential returns. But, even with advanced technology and computational power, this chapter still cannot predict the patterns of rise and fall in the stock market, and still, it is considered a risky business. To ease the process of investment and to provide better consciousness, this chapter proposes the prediction of stock market deviation using the ARIMA (auto-regressive integrated moving average) algorithm and long short-term memory (LSTM) algorithm. This chapter is using an algorithm which is trying to predict the future pattern for any stock based on the real-time analysis and data provided from Yahoo Finance data. The software provides pictorial and graphical representations. The objective is to provide short-term and long-term prediction competence to prepare for future potential investments.
Advances in Vision Computing: An International Journal, 2016
Social Networking Sites, in the present scenario, are an amalgam of knowledge and spam. As their ... more Social Networking Sites, in the present scenario, are an amalgam of knowledge and spam. As their popularity surges among the users day by day so does it among the spammers looking at easy targets for their campaigns. The threat due to spams causing atrocious harm to the bandwidth, overloading the servers, spreading malicious pages online et cetera has increased manifold making it necessary for researchers to foray into this field of spam detection and reduce their effect on the various social networking sites. In this paper, we propose a framework for spam detection in the two largest social networking sites namely, Twitter and Facebook. We'll be utilizing the data publically available on these two giants of social networking era. Initially, we'll be citing the various approaches that have already been explored in this field. After that we'll briefly explain the two methods that we used to collect the datasets from these websites.
Uploads
Papers by Akanksha Dhamija