Bharathi Mohan Gurusamy
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Bharathi Mohan Gurusamy has a total of 51 co-authors. Here are the top co-authors by number of shared publications:
- Rangarajan Prasanna Kumar
Amrita Vishwa Vidyapeetham
15 shared publications - Elakkiya Rajasekhar
Department of Computer Science, Birla Institute of Technology & Science (BITS), Pilani, Dubai Campus, Dubai International Academic City, Dubai, United Arab Emirates
3 shared publications - Srinath Doss
Botho University
3 shared publications - A. Keerthinathan2 shared publications
Ali Altalbe
Faculty of Computing and Information Technology, King Abdulaziz University, Saudi Arabia
2 shared publications- G. Lavanya2 shared publications
Latest Publications
- Open Access
- 17 November 2026
- Published by Springer Nature in Scientific Reports
RAG-LegalAssist: a retrieval-augmented framework with adaptive hybrid legal chunking for high-precision legal retrieval
- 17 November 2026
- Published by Springer Nature in Scientific Reports
Open AccessRAG-LegalAssist: a retrieval-augmented framework with adaptive hybrid legal chunking for high-precision legal retrieval
- Open Access
- 17 May 2026
- Published by Elsevier in International Journal of Information Management Data Insights
- Vol. 6 (1)
Applications of machine learning in financial transactions: A method-centric review
- 17 May 2026
- Published by Elsevier in International Journal of Information Management Data Insights
- Vol. 6 (1)
Open AccessApplications of machine learning in financial transactions: A method-centric review
- Open Access
- 16 October 2025
- Published by BON VIEW PUBLISHING PTE in Journal of Computational and Cognitive Engineering
Real-Time Road Accident Detection and Severity Assessment Using IoU and Deep Learning Models
Road accidents are a significant global issue, claiming lives and cash in hand every year. The system introduces an adaptive model switching mechanism that selects the most suitable You Only Look Once (YOLO) model (v5, v8, or v11) based on system memory and weather visibility, ensuring optimal detection with minimal computational load—a feature rarely addressed in existing accident detection research. To alleviate this situation, this study envisages a near real-time accident detection and emergency response system, integrating computer vision and geospatial technologies. The developed system tracks vehicle movement and assesses collision by applying advanced object detection models such as YOLOv5, YOLOv8, and YOLOv11 with dynamic tracking and speed estimation. The system computes spatial overlap using the Intersection over Union (IoU) metric to localize vehicles accurately and recognize potential accidents while minimizing false-positive rates dramatically. Geographic data from OpenStreetMap is used in emergency routing with the help of the Haversine formula to find the shortest and fastest route to the nearest emergency services, allowing rapid notifications to hospitals and enforcement agencies. The developed framework includes a severity analysis module that assesses the degree of accident impact based on vehicular deformation, collision dynamics, and possible injuries to passengers, thus enabling emergency response prioritization based on the incident's urgency. An additional provision is made to incorporate an automatic license plate recognition system that enhances vehicle identification, thereby speeding up the initiation of insurance claims and post accident administrative processes. The framework has undergone rigorous field trials under varying environmental conditions and remains robust in its operation under such variations. Real-time alerts have an average latency of 2.1 s and cover a comprehensive report of the incident, including location, vehicle IDs, severity, and medical assistance required. The experimental evaluation proved the system's detection accuracy of 94.6% and precision of 92.8%, thus proving its reliability and effectiveness for implementation in real time. Received: 12 April 2025 | Revised: 21 August 2025 | Accepted: 8 September 2025 Conflicts of Interest The authors declare that they have no conflicts of interest to this work. Data Availability Statement The data that support the findings of this study are openly available in GitHub at https://github.com/772003pranav/Accident-Detection. Author Contribution Statement Bharathi Mohan Gurusamy: Conceptualization, Formal analysis, Resources, Supervision, Project administration. Pranav Reddy Sanikommu: Methodology, Software, Validation, Data curation, Writing – original draft, Writing – review & editing, Visualization. Gayathri Muthurasu: Investigation, Writing – review & editing, Visualization, Supervision, Project administration.
- 16 October 2025
- Published by BON VIEW PUBLISHING PTE in Journal of Computational and Cognitive Engineering
Open AccessReal-Time Road Accident Detection and Severity Assessment Using IoU and Deep Learning Models
Road accidents are a significant global issue, claiming lives and cash in hand every year. The system introduces an adaptive model switching mechanism that selects the most suitable You Only Look Once (YOLO) model (v5, v8, or v11) based on system memory and weather visibility, ensuring optimal detection with minimal computational load—a feature rarely addressed in existing accident detection research. To alleviate this situation, this study envisages a near real-time accident detection and emergency response system, integrating computer vision and geospatial technologies. The developed system tracks vehicle movement and assesses collision by applying advanced object detection models such as YOLOv5, YOLOv8, and YOLOv11 with dynamic tracking and speed estimation. The system computes spatial overlap using the Intersection over Union (IoU) metric to localize vehicles accurately and recognize potential accidents while minimizing false-positive rates dramatically. Geographic data from OpenStreetMap is used in emergency routing with the help of the Haversine formula to find the shortest and fastest route to the nearest emergency services, allowing rapid notifications to hospitals and enforcement agencies. The developed framework includes a severity analysis module that assesses the degree of accident impact based on vehicular deformation, collision dynamics, and possible injuries to passengers, thus enabling emergency response prioritization based on the incident's urgency. An additional provision is made to incorporate an automatic license plate recognition system that enhances vehicle identification, thereby speeding up the initiation of insurance claims and post accident administrative processes. The framework has undergone rigorous field trials under varying environmental conditions and remains robust in its operation under such variations. Real-time alerts have an average latency of 2.1 s and cover a comprehensive report of the incident, including location, vehicle IDs, severity, and medical assistance required. The experimental evaluation proved the system's detection accuracy of 94.6% and precision of 92.8%, thus proving its reliability and effectiveness for implementation in real time. Received: 12 April 2025 | Revised: 21 August 2025 | Accepted: 8 September 2025 Conflicts of Interest The authors declare that they have no conflicts of interest to this work. Data Availability Statement The data that support the findings of this study are openly available in GitHub at https://github.com/772003pranav/Accident-Detection. Author Contribution Statement Bharathi Mohan Gurusamy: Conceptualization, Formal analysis, Resources, Supervision, Project administration. Pranav Reddy Sanikommu: Methodology, Software, Validation, Data curation, Writing – original draft, Writing – review & editing, Visualization. Gayathri Muthurasu: Investigation, Writing – review & editing, Visualization, Supervision, Project administration.
- 1 October 2025
- Published by Springer Nature
- p. 250-260
Enhancing Detoxification of Text Summaries with Seq2seq Language Models Using Reinforcement Learning Based Fine-Tuning
- 1 October 2025
- Published by Springer Nature
- p. 250-260
Enhancing Detoxification of Text Summaries with Seq2seq Language Models Using Reinforcement Learning Based Fine-Tuning
- 1 October 2025
- Published by Springer Nature
- p. 321-334
Small Language Models: An Advancing Efficient Open-Source Alternatives to Large Language Models
- 1 October 2025
- Published by Springer Nature
- p. 321-334
Small Language Models: An Advancing Efficient Open-Source Alternatives to Large Language Models
- Open Access
- 3 September 2025
- Published by BON VIEW PUBLISHING PTE in Journal of Computational and Cognitive Engineering
- Vol. 5 (1) , 16-29
A Hybrid Framework Integrating QML, AI, and Quantum-Safe Cryptography for Cybersecurity
The rise of quantum computing poses threats to traditional cryptographic systems, thereby requiring security measures to safeguard against traditional and quantum-attacker cyber insecurity. This framework uses quantum machine learning (QML) algorithms along with quantum-safe encryption to boost security measures. The proposed system combines QML anomaly detection models variational quantum classifier (VQC) with quantum support vector classifier (QSVC) as well as quantum neural network and examines them based on the BB84 QKD protocol for information safety. This model was evaluated using three datasets of HIKARI Flow intrusion detection records, phishing activity logs, and malicious URLs. This includes all high-dimensional input by extensive application of feature engineering, which merges entropy scoring combined with keyword extraction and domain analysis to transmogrify it into suitable inputs for quantum processing. The QML models outperformed the traditional models with a maximum phishing detection accuracy of 97.75% by QSVC implementation. With the BB84 protocol, its eavesdropping detection was proved by quantum interference detection upon testing on IBM's Qiskit and Google's Cirq systems while the operations were secure and in attack scenarios. This system combines the latest features to address the limitations of the current AI security model and incorporates post-quantum cryptography to protect against quantum threats. In conclusion, QML and quantum cryptography work efficiently with operational cybersecurity platforms. Received: 31 December 2024 | Revised: 10 April 2025 | Accepted: 7 May 2025 Conflicts of Interest The authors declare that they have no conflicts of interest to this work. Data Availability Statement Data are available from the corresponding author upon reasonable request. Author Contribution Statement Ramasubramaniyan Gunasridharan: Methodology. Ali Altalbe: Methodology. Bharathi Mohan Gurusamy: Conceptualization, Writing - review & editing. Gundala Pallavi: Writing - original draft. Prasanna Kumar Rangarajan: Supervision.
- 3 September 2025
- Published by BON VIEW PUBLISHING PTE in Journal of Computational and Cognitive Engineering
- Vol. 5 (1) , 16-29
Open AccessA Hybrid Framework Integrating QML, AI, and Quantum-Safe Cryptography for Cybersecurity
The rise of quantum computing poses threats to traditional cryptographic systems, thereby requiring security measures to safeguard against traditional and quantum-attacker cyber insecurity. This framework uses quantum machine learning (QML) algorithms along with quantum-safe encryption to boost security measures. The proposed system combines QML anomaly detection models variational quantum classifier (VQC) with quantum support vector classifier (QSVC) as well as quantum neural network and examines them based on the BB84 QKD protocol for information safety. This model was evaluated using three datasets of HIKARI Flow intrusion detection records, phishing activity logs, and malicious URLs. This includes all high-dimensional input by extensive application of feature engineering, which merges entropy scoring combined with keyword extraction and domain analysis to transmogrify it into suitable inputs for quantum processing. The QML models outperformed the traditional models with a maximum phishing detection accuracy of 97.75% by QSVC implementation. With the BB84 protocol, its eavesdropping detection was proved by quantum interference detection upon testing on IBM's Qiskit and Google's Cirq systems while the operations were secure and in attack scenarios. This system combines the latest features to address the limitations of the current AI security model and incorporates post-quantum cryptography to protect against quantum threats. In conclusion, QML and quantum cryptography work efficiently with operational cybersecurity platforms. Received: 31 December 2024 | Revised: 10 April 2025 | Accepted: 7 May 2025 Conflicts of Interest The authors declare that they have no conflicts of interest to this work. Data Availability Statement Data are available from the corresponding author upon reasonable request. Author Contribution Statement Ramasubramaniyan Gunasridharan: Methodology. Ali Altalbe: Methodology. Bharathi Mohan Gurusamy: Conceptualization, Writing - review & editing. Gundala Pallavi: Writing - original draft. Prasanna Kumar Rangarajan: Supervision.
- Open Access
- 22 June 2025
- Published by Atlantis Press SARL
- p. 160-178
Comparative Study of Deep Learning Algorithms For Image Caption Generation
- 22 June 2025
- Published by Atlantis Press SARL
- p. 160-178
Open AccessComparative Study of Deep Learning Algorithms For Image Caption Generation
- 29 April 2025
- Published by Springer Nature in Language Resources and Evaluation
- Vol. 59 (3) , 2705-2736
Detoxifying language model outputs: combining multi-agent debates and reinforcement learning for improved summarization
- 29 April 2025
- Published by Springer Nature in Language Resources and Evaluation
- Vol. 59 (3) , 2705-2736
Detoxifying language model outputs: combining multi-agent debates and reinforcement learning for improved summarization
- 24 January 2025
- Published by Springer Nature in SN Computer Science
- Vol. 6 (2) , 1-13
Telugu Language Analysis with XLM-RoBERTa: Enhancing Parts of Speech Tagging for Effective Natural Language Processing
- 24 January 2025
- Published by Springer Nature in SN Computer Science
- Vol. 6 (2) , 1-13
Telugu Language Analysis with XLM-RoBERTa: Enhancing Parts of Speech Tagging for Effective Natural Language Processing
- 13 December 2024
- Published by Springer Nature
- p. 119-131
Advancing Abstractive Summarization: Evaluating GPT-2, BART, T5-Small, and Pegasus Models with Baseline in ROUGE and BLEU Metrics
- 13 December 2024
- Published by Springer Nature
- p. 119-131
Advancing Abstractive Summarization: Evaluating GPT-2, BART, T5-Small, and Pegasus Models with Baseline in ROUGE and BLEU Metrics