Metti Vinodh Kumar
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Metti Vinodh Kumar has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Ayesha Siddiqua
Nitte Meenakshi Institute of Technology
1 shared publication - B. P. Upendra Roy
Channabasaveshwara Institute of Technology
1 shared publication G.P. Ramesh
Department of Electronics and Communication Engineering, St. Peter’s Institute of Higher Education and Research (SPIHER) , Avadi , Chennai , India
1 shared publicationLeeladhar Gudala
Independent Researcher
1 shared publicationManjula B M
Department of Electronics and Communication Engineering, Nitte Meenakshi Institute of Technology, Nitte (Deemed to be University), Bengaluru, India
1 shared publicationS. Latha Bhuvaneswari
Dhanalakshmi Srinivasan College of Engineering and Technology
1 shared publication
Latest Publications
- 1 February 2026
- Published by Springer Nature
- p. 155-166
Transformer-Based Deep Neural Network for Accurate Signal Detection and Interference Cancellation
- 1 February 2026
- Published by Springer Nature
- p. 155-166
Transformer-Based Deep Neural Network for Accurate Signal Detection and Interference Cancellation
- Open Access
- 8 October 2025
- Published by EDP Sciences in ITM Web of Conferences
- Vol. 79, 01039
Reinforcement Learning with Knowledge Graphs for Personalized News Recommendation
In recent years, the rapid growth of online media and personalized news recommendations have become essential for reducing information overload and improving user engagement. However, traditional models significantly rely on semantic similarity and suffered to capture dynamic user preferences. Moreover, the extensive dissemination of misinformation poses serious limitations, necessitating recommendation systems that are both adaptive and knowledge aware. To overcome these limitations, a Reinforcement Learning with Knowledge Graphs (RL-KG) framework for personalized news recommendations. Initially, data was gathered from the MIND dataset, which consist of millions of users’ news interactions enriched with titles, abstracts, and entity annotations. During preprocessing, text normalization and entity linking are employed for semantic clarity and structured knowledge representation. Furthermore, feature extraction integrates Bidirectional Encoder Representations from Transformer (BERT) embeddings for contextual semantics with Knowledge Graph embeddings for entity-level reasoning. Moreover, the Reinforcement Learning (RL) model was utilized for sequential decision-making procedures in which user histories form states, candidate news represents actions, and rewards provide engagement. Finally, the recommendation module integrates hybrid features and RL policies to deliver personalized, diverse news suggestions. The experimental results demonstrate that RL-KG achieves higher accuracy (96.77%), precision (95.55%), recall (96.45%), and F1-score (93.76%) than the existing model Recommendation for Mitigation (Rec4Mit).
- 8 October 2025
- Published by EDP Sciences in ITM Web of Conferences
- Vol. 79, 01039
Open AccessReinforcement Learning with Knowledge Graphs for Personalized News Recommendation
In recent years, the rapid growth of online media and personalized news recommendations have become essential for reducing information overload and improving user engagement. However, traditional models significantly rely on semantic similarity and suffered to capture dynamic user preferences. Moreover, the extensive dissemination of misinformation poses serious limitations, necessitating recommendation systems that are both adaptive and knowledge aware. To overcome these limitations, a Reinforcement Learning with Knowledge Graphs (RL-KG) framework for personalized news recommendations. Initially, data was gathered from the MIND dataset, which consist of millions of users’ news interactions enriched with titles, abstracts, and entity annotations. During preprocessing, text normalization and entity linking are employed for semantic clarity and structured knowledge representation. Furthermore, feature extraction integrates Bidirectional Encoder Representations from Transformer (BERT) embeddings for contextual semantics with Knowledge Graph embeddings for entity-level reasoning. Moreover, the Reinforcement Learning (RL) model was utilized for sequential decision-making procedures in which user histories form states, candidate news represents actions, and rewards provide engagement. Finally, the recommendation module integrates hybrid features and RL policies to deliver personalized, diverse news suggestions. The experimental results demonstrate that RL-KG achieves higher accuracy (96.77%), precision (95.55%), recall (96.45%), and F1-score (93.76%) than the existing model Recommendation for Mitigation (Rec4Mit).
- Open Access
- 1 December 2024
- Published by Walter de Gruyter GmbH in Journal of Smart Internet of Things
- Vol. 2024 (2) , 133-147
Smart IoT based health care environment for an effective information sharing using Resource Constraint LLM Models
The integration of Internet of Things (IoT) technologies with Healthcare system(HS) has revolutionized patient monitoring, diagnosis, and treatment. Effective information sharing in such systems is hindered by resource constraints, including limited computational capacity, energy consumption, and the need for real-time data processing. Existing systems often struggle to deploy large-scale language models (LLMs) in resource-constrained environments, limiting their ability to analyse and communicate critical healthcare information effectively. To resolve these issues, this study recommends a Smart IoT-based Health Care environment utilizing a lightweight BERT (Bidirectional Encoder Representations from Transformers) model for efficient and scalable information sharing. By optimizing BERT for resource-limited IoT devices, the proposed system ensures real-time processing of patient data while maintaining accuracy and efficiency. The system was examined by utilizing the MIMIC-III clinical dataset, focusing on real-time health monitoring and communication between connected devices. Results demonstrated improved computational efficiency, reduced latency, and enhanced accuracy in extracting and sharing critical healthcare information. This innovative approach bridges the gap between IoT and healthcare by providing a resource-efficient solution for intelligent information sharing.
- 1 December 2024
- Published by Walter de Gruyter GmbH in Journal of Smart Internet of Things
- Vol. 2024 (2) , 133-147
Open AccessSmart IoT based health care environment for an effective information sharing using Resource Constraint LLM Models
The integration of Internet of Things (IoT) technologies with Healthcare system(HS) has revolutionized patient monitoring, diagnosis, and treatment. Effective information sharing in such systems is hindered by resource constraints, including limited computational capacity, energy consumption, and the need for real-time data processing. Existing systems often struggle to deploy large-scale language models (LLMs) in resource-constrained environments, limiting their ability to analyse and communicate critical healthcare information effectively. To resolve these issues, this study recommends a Smart IoT-based Health Care environment utilizing a lightweight BERT (Bidirectional Encoder Representations from Transformers) model for efficient and scalable information sharing. By optimizing BERT for resource-limited IoT devices, the proposed system ensures real-time processing of patient data while maintaining accuracy and efficiency. The system was examined by utilizing the MIMIC-III clinical dataset, focusing on real-time health monitoring and communication between connected devices. Results demonstrated improved computational efficiency, reduced latency, and enhanced accuracy in extracting and sharing critical healthcare information. This innovative approach bridges the gap between IoT and healthcare by providing a resource-efficient solution for intelligent information sharing.