Eswaran Poovammal
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Eswaran Poovammal has a total of 58 co-authors. Here are the top co-authors by number of shared publications:
- Kadiyala Ramana
Department of Artificial Intelligence and Data Science, Chaitanya Bharathi Institute of Technology, Hyderabad, India
4 shared publications - B. Cynthia Sherin
SRM Institute of Science and Technology
3 shared publications - Feisal Alaswad
Department of Computing Technologies, SRM Institute of Science and Technology, Kattankulathur, Tamil Nadu, India
3 shared publications Mayank Kumar Nagda
3 shared publications- Saurabh Singh
AI and Big Data, Endicott College, Woosong University, Daejeon 34606, Republic of Korea
3 shared publications - Arfat Ahmad Khan
Khon Kaen University
2 shared publications
Latest Publications
- Open Access
- 6 July 2026
- Published by Springer Nature in Discover Computing
- Vol. 29 (1) , 424
Hybrid intelligence effort for software effort estimation in LLM assisted development
Software effort estimation remains a cornerstone of project planning and control, yet existing estimation models are grounded in the assumption that software development effort is dominated by human reasoning and manual construction. The rapid integration of large language models (LLMs) into development workflows fundamentally challenges this assumption by automating substantial portions of code synthesis while shifting human effort toward supervision, validation, and integration. As a result, traditional effort estimation proxies such as Story Points and size-based metrics may no longer reliably characterize development effort. This paper presents an empirical study examining how effort manifests in LLM-assisted software development. Rather than using LLMs as predictive estimation tools, we investigate how their adoption reshapes the underlying cost structure of development work. We introduce the notion of Hybrid Intelligence Effort (HIE), conceptualizing effort as the combined burden of model-performed reasoning and human oversight activities. Using a controlled experiment involving 22 developers, 110 real-world tasks, and three LLMs, we compare the explanatory power of traditional estimation metrics against interaction- and oversight-based Hybrid Intelligence dimensions. Our results show that while Story Points retain partial explanatory validity, they fail to capture dominant sources of effort in LLM-assisted workflows. In controlled experiments, HIE dimensions increase explained variance in observed effort from approximately 72–80%, while substantially reducing systematic estimation error. Human validation and corrective intervention emerge as the primary drivers of effort, outweighing artifact-level characteristics. These findings suggest that effort estimation models must move beyond human-centric and size-based assumptions to remain effective in AI-augmented software engineering.
- 6 July 2026
- Published by Springer Nature in Discover Computing
- Vol. 29 (1) , 424
Open AccessHybrid intelligence effort for software effort estimation in LLM assisted development
Software effort estimation remains a cornerstone of project planning and control, yet existing estimation models are grounded in the assumption that software development effort is dominated by human reasoning and manual construction. The rapid integration of large language models (LLMs) into development workflows fundamentally challenges this assumption by automating substantial portions of code synthesis while shifting human effort toward supervision, validation, and integration. As a result, traditional effort estimation proxies such as Story Points and size-based metrics may no longer reliably characterize development effort. This paper presents an empirical study examining how effort manifests in LLM-assisted software development. Rather than using LLMs as predictive estimation tools, we investigate how their adoption reshapes the underlying cost structure of development work. We introduce the notion of Hybrid Intelligence Effort (HIE), conceptualizing effort as the combined burden of model-performed reasoning and human oversight activities. Using a controlled experiment involving 22 developers, 110 real-world tasks, and three LLMs, we compare the explanatory power of traditional estimation metrics against interaction- and oversight-based Hybrid Intelligence dimensions. Our results show that while Story Points retain partial explanatory validity, they fail to capture dominant sources of effort in LLM-assisted workflows. In controlled experiments, HIE dimensions increase explained variance in observed effort from approximately 72–80%, while substantially reducing systematic estimation error. Human validation and corrective intervention emerge as the primary drivers of effort, outweighing artifact-level characteristics. These findings suggest that effort estimation models must move beyond human-centric and size-based assumptions to remain effective in AI-augmented software engineering.
- Open Access
- 25 June 2026
- Published by Elsevier in Machine Learning with Applications
- Vol. 25
AST-guided transformers for sustainable and reliable UML modeling
- 25 June 2026
- Published by Elsevier in Machine Learning with Applications
- Vol. 25
Open AccessAST-guided transformers for sustainable and reliable UML modeling
- Open Access
- 5 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 36051-36075
From COCOMO to GPT: A Comprehensive Evaluation of LLM-Based Software Effort Estimation
Accurate software effort estimation remains a critical yet challenging task in software engineering. While recent advances in Large Language Models (LLMs) have demonstrated impressive capabilities across a wide range of software engineering activities, their effectiveness for effort estimation has not been systematically evaluated. This paper presents a comprehensive empirical benchmark comparing zero-shot LLM-based estimation with classical Machine Learning (ML) models and transformer-based regression approaches across two complementary settings: textual story-point estimation and structured project-level effort estimation. We evaluate multiple model families on two large-scale story-point datasets (Agile and NEO) and five widely adopted project-level datasets (Desharnais, COCOMO81, NASA93, Maxwell, and Kitchenham). Predictive accuracy is assessed across all datasets. The story-point benchmark further analyzes cross-project generalization, linguistic robustness, computational cost, and human–AI interaction effects, whereas the project-level benchmark evaluates robustness under noise injection, missing-value stress testing, and feature ablation. Experimental results show that off-the-shelf LLMs operating in zero-shot settings consistently underperform task-specific ML and transformer-based regression models in terms of absolute accuracy and cost efficiency. Classical ML models remain the most reliable estimators for structured datasets, while fine-tuned transformer regressors achieve the best performance on textual story-point estimation. Despite their lower numerical accuracy, LLMs demonstrate relatively low sensitivity to linguistic variation and may influence human judgment through persuasive explanations, as suggested by the exploratory human–LLM interaction study. These findings suggest that zero-shot LLMs may be suited as qualitative decision-support tools rather than as autonomous effort estimators. Overall, this work highlights the importance of architectural alignment, cost-aware evaluation, and human-centered considerations when deploying AI models for software effort estimation.
- 5 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 36051-36075
Open AccessFrom COCOMO to GPT: A Comprehensive Evaluation of LLM-Based Software Effort Estimation
Accurate software effort estimation remains a critical yet challenging task in software engineering. While recent advances in Large Language Models (LLMs) have demonstrated impressive capabilities across a wide range of software engineering activities, their effectiveness for effort estimation has not been systematically evaluated. This paper presents a comprehensive empirical benchmark comparing zero-shot LLM-based estimation with classical Machine Learning (ML) models and transformer-based regression approaches across two complementary settings: textual story-point estimation and structured project-level effort estimation. We evaluate multiple model families on two large-scale story-point datasets (Agile and NEO) and five widely adopted project-level datasets (Desharnais, COCOMO81, NASA93, Maxwell, and Kitchenham). Predictive accuracy is assessed across all datasets. The story-point benchmark further analyzes cross-project generalization, linguistic robustness, computational cost, and human–AI interaction effects, whereas the project-level benchmark evaluates robustness under noise injection, missing-value stress testing, and feature ablation. Experimental results show that off-the-shelf LLMs operating in zero-shot settings consistently underperform task-specific ML and transformer-based regression models in terms of absolute accuracy and cost efficiency. Classical ML models remain the most reliable estimators for structured datasets, while fine-tuned transformer regressors achieve the best performance on textual story-point estimation. Despite their lower numerical accuracy, LLMs demonstrate relatively low sensitivity to linguistic variation and may influence human judgment through persuasive explanations, as suggested by the exploratory human–LLM interaction study. These findings suggest that zero-shot LLMs may be suited as qualitative decision-support tools rather than as autonomous effort estimators. Overall, this work highlights the importance of architectural alignment, cost-aware evaluation, and human-centered considerations when deploying AI models for software effort estimation.
- 14 January 2026
- Published by Springer Nature in International Journal of Information Technology
- p. 1-9
A robust and ensemble greenhouse model for enhancing yield of tomato crops
- 14 January 2026
- Published by Springer Nature in International Journal of Information Technology
- p. 1-9
A robust and ensemble greenhouse model for enhancing yield of tomato crops
- 6 October 2025
- Published by Springer Nature in Journal of Electrical Engineering & Technology
- Vol. 21 (2) , 1919-1927
Sustainable Real-Time Urban Mobility with Attention-Based YOLOv5s and Refined Deep SORT Algorithm
- 6 October 2025
- Published by Springer Nature in Journal of Electrical Engineering & Technology
- Vol. 21 (2) , 1919-1927
Sustainable Real-Time Urban Mobility with Attention-Based YOLOv5s and Refined Deep SORT Algorithm
- 3 October 2025
- Published by Springer Nature in International Journal of Information Technology
- Vol. 17 (9) , 5743-5750
CIFWL-XGB-RA: a cost-sensitive framework with regularized attention mechanism to forecast angina pectoris (AP)
- 3 October 2025
- Published by Springer Nature in International Journal of Information Technology
- Vol. 17 (9) , 5743-5750
CIFWL-XGB-RA: a cost-sensitive framework with regularized attention mechanism to forecast angina pectoris (AP)
- Open Access
- 8 August 2025
- Published by Taylor & Francis in Automatika
- Vol. 66 (4) , 658-678
Optimizing vehicle re-identification: extended neighbourhood distance re-ranking for images captured from multi-camera surveillance systems
- 8 August 2025
- Published by Taylor & Francis in Automatika
- Vol. 66 (4) , 658-678
Open AccessOptimizing vehicle re-identification: extended neighbourhood distance re-ranking for images captured from multi-camera surveillance systems
- Open Access
- 1 January 2025
- Published by Engineering and Technology Publishing in Journal of Advances in Information Technology
- Vol. 16 (1)
An Efficacious Detecting Tomato Leaf Disease Using RCOA-Based RNN Method
JAIT is a scientific open access journal which focuses on empirical research results and critical analysis of technology development, use, management and impacts in information technology.
- 1 January 2025
- Published by Engineering and Technology Publishing in Journal of Advances in Information Technology
- Vol. 16 (1)
Open AccessAn Efficacious Detecting Tomato Leaf Disease Using RCOA-Based RNN Method
JAIT is a scientific open access journal which focuses on empirical research results and critical analysis of technology development, use, management and impacts in information technology.
- 16 November 2024
- Published by Springer Nature
- p. 86-101
Software Requirements to UML Class Diagrams Using Machine Learning and Rule-Based Approach
- 16 November 2024
- Published by Springer Nature
- p. 86-101
Software Requirements to UML Class Diagrams Using Machine Learning and Rule-Based Approach