Minu Balakrishnan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Minu Balakrishnan has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Anandakumar Haldorai
Sri Eshwar College of Engineering
26 shared publications - Babitha Lincy
Department of Computer and Communication Engineering, Sri Eshwar College of Engineering, Coimbatore, Tamil Nadu, India
26 shared publications - Suriya Murugan
Sri Eshwar College of Engineering
25 shared publications B. Aruna
Department of MBA, Ramachandra College of Engineering, Eluru - 534007, India
2 shared publications- Sarika Koluguri
Department of MBA, KG Reddy College of Engineering and Technology, Moinabad, Rangareddy, Telangana, India
2 shared publications - Aakanksha Shivani
Expedia Group
1 shared publication
Latest Publications
- 2 August 2026
- Published by Springer Nature
- p. 433-446
IoT-Cloud Based Offloading Framework in 6G Networks
- 2 August 2026
- Published by Springer Nature
- p. 433-446
IoT-Cloud Based Offloading Framework in 6G Networks
- 3 July 2026
- Published by Elsevier in Clinical Nutrition ESPEN
- Vol. 75, 103455
Comment on “An Artificial Intelligence Malnutrition Screening Tool Based on Electronic Medical Records”
- 3 July 2026
- Published by Elsevier in Clinical Nutrition ESPEN
- Vol. 75, 103455
Comment on “An Artificial Intelligence Malnutrition Screening Tool Based on Electronic Medical Records”
- 18 June 2026
- Published by Elsevier in Journal of Pediatric Urology
- Vol. 22 (5) , 106102
Letter to the Editor re: “ChatGPT-4o′s performance on pediatric vesicoureteral reflux”
- 18 June 2026
- Published by Elsevier in Journal of Pediatric Urology
- Vol. 22 (5) , 106102
Letter to the Editor re: “ChatGPT-4o′s performance on pediatric vesicoureteral reflux”
- Open Access
- 6 January 2026
- Published by Elaris Publications Private Limited in Elaris Computing Nexus
Automated Code Review and Technical Debt Detection in Agile Development Using Natural Language Processing on Commit Histories
A significant issue in the recent development is the growing concern with the quality of code and low levels of technical debt in the agile software development environments that can lead to an absence of adequate manual reviews of the code. Recent automated review systems primarily rely on the application of static code analysis and they fail to give credit to contextual and semantic information found in commit histories. This paper demonstrates a severe lack in the exploitation of the information stored in natural language and which developers add to their commits to detect the early indications of technical debt trends. To overcome this drawback, a new framework that presents the utilization of Natural Language Processing (NLP) tools to handle commit messages and other metadata to generate an automatic code review and debt analysis is proposed. The methodology is a combination of transformer-based language model, semantic similarity analysis and classification alongside the application of keywords to detect debt-inducing changes. The experimental background is rooted in the examination of publicly available Git repositories comprising annotated examples of technical debt and evaluates performance with the measures of accuracy, recall, and F1-score. The F1-score of the specified method improves the conventional tools of the statical analysis by 18.6% and the precision and the recall values are more than 0.89 and 0.87, respectively. The main component of this work is the availability of environment-sensitive, NLP-based framework, which enhances automated review of the code and the proactive management of technical debt of the agile development cycles.
- 6 January 2026
- Published by Elaris Publications Private Limited in Elaris Computing Nexus
Open AccessAutomated Code Review and Technical Debt Detection in Agile Development Using Natural Language Processing on Commit Histories
A significant issue in the recent development is the growing concern with the quality of code and low levels of technical debt in the agile software development environments that can lead to an absence of adequate manual reviews of the code. Recent automated review systems primarily rely on the application of static code analysis and they fail to give credit to contextual and semantic information found in commit histories. This paper demonstrates a severe lack in the exploitation of the information stored in natural language and which developers add to their commits to detect the early indications of technical debt trends. To overcome this drawback, a new framework that presents the utilization of Natural Language Processing (NLP) tools to handle commit messages and other metadata to generate an automatic code review and debt analysis is proposed. The methodology is a combination of transformer-based language model, semantic similarity analysis and classification alongside the application of keywords to detect debt-inducing changes. The experimental background is rooted in the examination of publicly available Git repositories comprising annotated examples of technical debt and evaluates performance with the measures of accuracy, recall, and F1-score. The F1-score of the specified method improves the conventional tools of the statical analysis by 18.6% and the precision and the recall values are more than 0.89 and 0.87, respectively. The main component of this work is the availability of environment-sensitive, NLP-based framework, which enhances automated review of the code and the proactive management of technical debt of the agile development cycles.
- Open Access
- 12 October 2025
- Published by Elaris Publications Private Limited in Elaris Computing Nexus
- p. 170-180
Comparative Analysis of Surface Electrical Potential Distribution Across Semiconductor Wafers Using Advanced 3D Simulation Models
Correct mapping of electrical potential using semiconductor wafer is critical to the operation, productivity, and homogeneity of gadgets particularly in the present-day trend in electronics and nearing the nanoscale. Traditional numerical and analysis methods, including Finite Differentiation, Finite Element, Drift Differences, and Poisson Boltzmann algorithms, may be challenging to resolve the fine details around the edges of wafer or high gradients, in contrast to data-driven algorithms, e.g. Neural Network Regression, which are fast without physical insight. To overcome all these shortcomings, this paper suggests a Hybrid Quantum Numerical Model (HQNM), which applies classical numerical computation together with terms of quantum correction to make it more accurate and physical. A set of six surface potential simulations of this model was compared to five known methods with the same boundary and material conditions. Findings indicate that HQNM has the best root mean square error, smoothness factor and correct edge performance at moderate cost of computation. The results demonstrate that the model is a promising approach to high-fidelity wafer-level potential mapping, a balanced solution to offer numerically stable, accurate, and computationally-efficient solutions.
- 12 October 2025
- Published by Elaris Publications Private Limited in Elaris Computing Nexus
- p. 170-180
Open AccessComparative Analysis of Surface Electrical Potential Distribution Across Semiconductor Wafers Using Advanced 3D Simulation Models
Correct mapping of electrical potential using semiconductor wafer is critical to the operation, productivity, and homogeneity of gadgets particularly in the present-day trend in electronics and nearing the nanoscale. Traditional numerical and analysis methods, including Finite Differentiation, Finite Element, Drift Differences, and Poisson Boltzmann algorithms, may be challenging to resolve the fine details around the edges of wafer or high gradients, in contrast to data-driven algorithms, e.g. Neural Network Regression, which are fast without physical insight. To overcome all these shortcomings, this paper suggests a Hybrid Quantum Numerical Model (HQNM), which applies classical numerical computation together with terms of quantum correction to make it more accurate and physical. A set of six surface potential simulations of this model was compared to five known methods with the same boundary and material conditions. Findings indicate that HQNM has the best root mean square error, smoothness factor and correct edge performance at moderate cost of computation. The results demonstrate that the model is a promising approach to high-fidelity wafer-level potential mapping, a balanced solution to offer numerically stable, accurate, and computationally-efficient solutions.
- Open Access
- 6 September 2025
- Published by Ansis Publications in Journal of Computer and Communication Networks
- p. 187-196
Weighted Tree Similarity Based Optimization for Agent Matching in Multi Agent Markets
The article analyzes the nature of multi-agent markets and suggests a new framework based on hierarchical matching and decision architecture. Furthermore, the framework adopts weighted tree similarity algorithms to obtain a more detailed perspective of the agents’ interaction and preferences. The article describes the theoretical background of fuzzy similarity measures based on trees and introduces a new weighted tree similarity algorithm that enables assessment of the agent preferences and characteristics by employing fuzzy representations and hierarchy. Therefore, it fosters better and specific matching decisions that can be made. In addition, the article examines whether and how the Stackelberg equilibrium, a form of game theory, can help to enhance the efficiency of the interactions and decisions of the agents. The main conclusions in this article include the creation of the new weighted tree similarity algorithm for multi-agent markets, the creation of the hierarchical matching and decision system, and the verification that the proposed system significantly improves the efficiency of interactions between agents in the market. The effectiveness of these conclusions is supported by case and empirical evidence, which further emphasizes the applicability and the possibility of the projected framework in real-world market scenarios. This is beneficial in providing significant information concerning the improvement of the market forces and decision making.
- 6 September 2025
- Published by Ansis Publications in Journal of Computer and Communication Networks
- p. 187-196
Open AccessWeighted Tree Similarity Based Optimization for Agent Matching in Multi Agent Markets
The article analyzes the nature of multi-agent markets and suggests a new framework based on hierarchical matching and decision architecture. Furthermore, the framework adopts weighted tree similarity algorithms to obtain a more detailed perspective of the agents’ interaction and preferences. The article describes the theoretical background of fuzzy similarity measures based on trees and introduces a new weighted tree similarity algorithm that enables assessment of the agent preferences and characteristics by employing fuzzy representations and hierarchy. Therefore, it fosters better and specific matching decisions that can be made. In addition, the article examines whether and how the Stackelberg equilibrium, a form of game theory, can help to enhance the efficiency of the interactions and decisions of the agents. The main conclusions in this article include the creation of the new weighted tree similarity algorithm for multi-agent markets, the creation of the hierarchical matching and decision system, and the verification that the proposed system significantly improves the efficiency of interactions between agents in the market. The effectiveness of these conclusions is supported by case and empirical evidence, which further emphasizes the applicability and the possibility of the projected framework in real-world market scenarios. This is beneficial in providing significant information concerning the improvement of the market forces and decision making.
- 13 April 2024
- Published by Springer Nature
- p. 407-427
Nature Inspired Optimizers and Their Importance for AI: An Inclusive Analysis
- 13 April 2024
- Published by Springer Nature
- p. 407-427
Nature Inspired Optimizers and Their Importance for AI: An Inclusive Analysis
- 13 April 2024
- Published by Springer Nature
- p. 293-315
Bi-Model Emotional AI for Audio-Visual Human Emotion Detection Using Hybrid Deep Learning Model
- 13 April 2024
- Published by Springer Nature
- p. 293-315
Bi-Model Emotional AI for Audio-Visual Human Emotion Detection Using Hybrid Deep Learning Model