Saumya Bansal
Research Subjects
Saumya Bansal has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Niyati Baliyan
Department of Computer Engineering, National Institute of Technology Kuruksehtra, Thanesar, India
4 shared publications - Prerna Aggarwal
Department of Information Technology, Indira Gandhi Delhi Technical University for Women, Delhi, India
2 shared publications Niyati Baliyan
Indira Gandhi Delhi Technical University for Women
1 shared publication
Latest Publications
- Retraction
- 3 August 2026
- Published by Springer Nature in International Journal of Information Technology
- p. 1
Retraction Note: Improved biometric authentication using surf based variational Bayesian extreme learning machine
- 3 August 2026
- Published by Springer Nature in International Journal of Information Technology
- p. 1
RetractionRetraction Note: Improved biometric authentication using surf based variational Bayesian extreme learning machine
- Retracted
- 18 April 2024
- Published by Springer Nature in International Journal of Information Technology
- Vol. 16 (5) , 2925-2935
Improved biometric authentication using surf based variational Bayesian extreme learning machine
- 18 April 2024
- Published by Springer Nature in International Journal of Information Technology
- Vol. 16 (5) , 2925-2935
RetractedImproved biometric authentication using surf based variational Bayesian extreme learning machine
- 4 September 2022
- Published by Springer Nature in Journal of Ambient Intelligence and Humanized Computing
- Vol. 14 (12) , 16025-16036
Remembering past and predicting future: a hybrid recurrent neural network based recommender system
Traditional recommender systems (RS) assume users’ taste to be static (taste remains same over time) and reactive (a change in taste cannot be predicted and is observed only after it occurs). Further, traditional RS restricts the recommendation process to candidate items generation. This work aims to explore two phases of RS, i.e., Candidate Generation as well as Candidate Ranking. We propose a RS from a multi-objective (short-term prediction, long-term prediction, diversity, and popularity bias) perspective which was previously overlooked. The sequential and non-sequential behavior of users is exploited to predict future behavioral trajectories with the consideration of short-term and long-term prediction using recurrent neural networks and nearest neighbors approach. Further, a novel candidate ranking method is introduced to prevent users from being entangled in recommended items. On multiple datasets, largest being MovieLens (ML) 1M, our model shows excellent results achieving a hit rate and short-term prediction success of 58% and 71% respectively on ML 1M. Further, it implicitly handles two important parameters, i.e., diversity and item popularity with a success rate of 59.22% and 34.28% respectively.
- 4 September 2022
- Published by Springer Nature in Journal of Ambient Intelligence and Humanized Computing
- Vol. 14 (12) , 16025-16036
Remembering past and predicting future: a hybrid recurrent neural network based recommender system
Traditional recommender systems (RS) assume users’ taste to be static (taste remains same over time) and reactive (a change in taste cannot be predicted and is observed only after it occurs). Further, traditional RS restricts the recommendation process to candidate items generation. This work aims to explore two phases of RS, i.e., Candidate Generation as well as Candidate Ranking. We propose a RS from a multi-objective (short-term prediction, long-term prediction, diversity, and popularity bias) perspective which was previously overlooked. The sequential and non-sequential behavior of users is exploited to predict future behavioral trajectories with the consideration of short-term and long-term prediction using recurrent neural networks and nearest neighbors approach. Further, a novel candidate ranking method is introduced to prevent users from being entangled in recommended items. On multiple datasets, largest being MovieLens (ML) 1M, our model shows excellent results achieving a hit rate and short-term prediction success of 58% and 71% respectively on ML 1M. Further, it implicitly handles two important parameters, i.e., diversity and item popularity with a success rate of 59.22% and 34.28% respectively.
- 14 October 2021
- Published by Springer Nature
- p. 91-102
A Multi-criteria Evaluation of Evolutionary Algorithms Against Segment Based Shilling Attacks
- 14 October 2021
- Published by Springer Nature
- p. 91-102
A Multi-criteria Evaluation of Evolutionary Algorithms Against Segment Based Shilling Attacks
- 2 June 2021
- Published by Springer Nature in Journal of Ambient Intelligence and Humanized Computing
- Vol. 14 (2) , 697-710
ShillDetector: a binary grey wolf optimization technique for detection of shilling profiles
- 2 June 2021
- Published by Springer Nature in Journal of Ambient Intelligence and Humanized Computing
- Vol. 14 (2) , 697-710
ShillDetector: a binary grey wolf optimization technique for detection of shilling profiles