Rajeev Kumar
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Rajeev Kumar has a total of 31 co-authors. Here are the top co-authors by number of shared publications:
- Naveen Chauhan
Department of Computer Science and Engineering, National Institute of Technology, Hamirpur, India
8 shared publications - Deepa Rani
Department of Computer Science and Engineering, National Institute of Technology, Hamirpur, India
4 shared publications - Narottam Chand
Department of Computer Science and Engineering, National Institute of Technology, Hamirpur, India
2 shared publications - Samridhi Singh
National Institute of Technology
2 shared publications - Tanuj Wala
NIT Hamirpur
2 shared publications Adil Umar Khan
Qualcomm India Private Limited
1 shared publication
Latest Publications
- 3 October 2026
- Published by Springer Nature in SN Computer Science
- Vol. 7 (7) , 782
A Systematic Review of Layered-Architecture, Taxonomy and Challenges for IoT-Based Healthcare System
- 3 October 2026
- Published by Springer Nature in SN Computer Science
- Vol. 7 (7) , 782
A Systematic Review of Layered-Architecture, Taxonomy and Challenges for IoT-Based Healthcare System
- 2 August 2026
- Published by Springer Nature
- p. 355-365
Unraveling Plasticity Loss in Deep Neural Networks Under Non-Stationary Objectives
- 2 August 2026
- Published by Springer Nature
- p. 355-365
Unraveling Plasticity Loss in Deep Neural Networks Under Non-Stationary Objectives
- 14 July 2026
- Published by IOP Publishing in Biomedical Physics & Engineering Express
- Vol. 12 (4) , 045022
NurtureNest: an IoT–wearable predictive analytics framework for real-time maternal risk assessment
Pregnancy-related complications are increasing globally, necessitating timely and accurate risk prediction for effective clinical intervention. This paper presents NurtureNest, an internet of things-enabled machine learning framework for automated pregnancy risk assessment. The system integrates wearable sensor data from smartwatches with user-provided clinical parameters via a mobile application, enabling continuous remote monitoring. Historical clinical data are used to train multiple machine learning models for multi-class classification of pregnancy risk into low-, medium-, and high-risk categories. Ensemble learning techniques are independently trained and evaluated alongside conventional machine learning classifiers to assess their effectiveness in pregnancy risk prediction. Experimental results show that LightGBM achieves the highest performance with 92.86% test accuracy and 95.04% cross-validation accuracy. Model performance is validated using ROC analysis and feature importance evaluation. The proposed framework enables early risk detection and supports timely clinical decision-making, improving maternal healthcare outcomes.
- 14 July 2026
- Published by IOP Publishing in Biomedical Physics & Engineering Express
- Vol. 12 (4) , 045022
NurtureNest: an IoT–wearable predictive analytics framework for real-time maternal risk assessment
Pregnancy-related complications are increasing globally, necessitating timely and accurate risk prediction for effective clinical intervention. This paper presents NurtureNest, an internet of things-enabled machine learning framework for automated pregnancy risk assessment. The system integrates wearable sensor data from smartwatches with user-provided clinical parameters via a mobile application, enabling continuous remote monitoring. Historical clinical data are used to train multiple machine learning models for multi-class classification of pregnancy risk into low-, medium-, and high-risk categories. Ensemble learning techniques are independently trained and evaluated alongside conventional machine learning classifiers to assess their effectiveness in pregnancy risk prediction. Experimental results show that LightGBM achieves the highest performance with 92.86% test accuracy and 95.04% cross-validation accuracy. Model performance is validated using ROC analysis and feature importance evaluation. The proposed framework enables early risk detection and supports timely clinical decision-making, improving maternal healthcare outcomes.
- 31 January 2026
- Published by Springer Nature
- p. 405-416
Enhancing Malware Detection Accuracy Exploring Advanced Machine Learning Strategies
- 31 January 2026
- Published by Springer Nature
- p. 405-416
Enhancing Malware Detection Accuracy Exploring Advanced Machine Learning Strategies
- 13 November 2025
- Published by Springer Nature
- p. 503-516
Applying Genetic Algorithms in Machine Learning to Predict Risk in Pregnancy
- 13 November 2025
- Published by Springer Nature
- p. 503-516
Applying Genetic Algorithms in Machine Learning to Predict Risk in Pregnancy
- 1 September 2025
- Published by Springer Nature
- p. 355-365
Deep Learning-Based Early Prediction Models for Ovarian Cancer
- 1 September 2025
- Published by Springer Nature
- p. 355-365
Deep Learning-Based Early Prediction Models for Ovarian Cancer
- 7 October 2024
- Published by Springer Nature in Network Modeling Analysis in Health Informatics and Bioinformatics
- Vol. 13 (1) , 1-37
Survey of AI-driven techniques for ovarian cancer detection: state-of-the-art methods and open challenges
- 7 October 2024
- Published by Springer Nature in Network Modeling Analysis in Health Informatics and Bioinformatics
- Vol. 13 (1) , 1-37
Survey of AI-driven techniques for ovarian cancer detection: state-of-the-art methods and open challenges
- 9 August 2024
- Published by Springer Nature in SN Computer Science
- Vol. 5 (6) , 1-17
Study Influencing Factors of Maternal Health and the Role of Internet of Things (IoT) to Improve Maternal Care
- 9 August 2024
- Published by Springer Nature in SN Computer Science
- Vol. 5 (6) , 1-17
Study Influencing Factors of Maternal Health and the Role of Internet of Things (IoT) to Improve Maternal Care
- Open Access
- 30 July 2023
- Published by Blue Eyes Intelligence Engineering and Sciences Engineering and Sciences Publication (BEIESP) in International Journal of Recent Technology and Engineering (IJRTE)
- Vol. 12 (2) , 102-108
Link Prediction in Social Networks using Vertex Entropy
Many link prediction methods have been put out and tested on several actual networks. The weights of linkages are rarely considered in these studies. Taking both the network's structure and link weight into account is required for link prediction. Previous researchers mostly overlooked the topological structure data in favour of the naturally occurring link weight. With the use of the concept of entropy, a new link prediction algorithm has been put forth in this paper.When used in real-time social networks, this algorithm outperforms the industry standard techniques. This paper concentrated on both topological structural information which focuses on calculating the vertex entropy of each very vertex and link weight in the proposed method. Both weighted and unweighted networks can benefit from the proposed method. Unipartite and bipartite networks can also use the suggested methods. Further, results demonstrate that the proposed method performs better than competing or traditional strategies, particularly when targeted social networks are sufficiently dense.
- 30 July 2023
- Published by Blue Eyes Intelligence Engineering and Sciences Engineering and Sciences Publication (BEIESP) in International Journal of Recent Technology and Engineering (IJRTE)
- Vol. 12 (2) , 102-108
Open AccessLink Prediction in Social Networks using Vertex Entropy
Many link prediction methods have been put out and tested on several actual networks. The weights of linkages are rarely considered in these studies. Taking both the network's structure and link weight into account is required for link prediction. Previous researchers mostly overlooked the topological structure data in favour of the naturally occurring link weight. With the use of the concept of entropy, a new link prediction algorithm has been put forth in this paper.When used in real-time social networks, this algorithm outperforms the industry standard techniques. This paper concentrated on both topological structural information which focuses on calculating the vertex entropy of each very vertex and link weight in the proposed method. Both weighted and unweighted networks can benefit from the proposed method. Unipartite and bipartite networks can also use the suggested methods. Further, results demonstrate that the proposed method performs better than competing or traditional strategies, particularly when targeted social networks are sufficiently dense.