Sehar Gul
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Sehar Gul has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Azri Azmi
Faculty of Artificial Intelligence, Universiti Teknologi Malaysia (UTM), Kuala Lumpur, Malaysia
3 shared publications - Sadaquat Ali Ruk
Faculty of Artificial Intelligence, Universiti Teknologi Malaysia (UTM), Kuala Lumpur, Malaysia
3 shared publications - Yasir Mahmood
Department of Software Engineering, College of Information Technology, United Arab Emirates University, Al Ain, United Arab Emirates
2 shared publications Nurulhuda Firdaus Mohd Azmi
Faculty of Artificial Intelligence, Universiti Teknologi Malaysia (UTM), Kuala Lumpur, Malaysia
1 shared publication- Nurulhuda Firdaus Mohd Azmi
Faculty of Artificial Intelligence, Universiti Teknologi Malaysia (UTM), Kuala Lumpur, Malaysia
1 shared publication - Salah Bouktif
Department of Computer Science and Software Engineering, College of Information Technology, United Arab Emirates University (UAEU), Al Ain, United Arab Emirates
1 shared publication
Latest Publications
- Open Access
- 15 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 79253-79283
HEEEM: A Hybrid Ensemble Effort Estimation Model for Agile and DevOps Development
Accurate effort estimation in Agile and DevOps software projects remains a persistent challenge, as traditional models fail to account for the iterative, continuous delivery nature of modern development environments. Existing single-technique estimation approaches, whether algorithmic, expert-based, or machine learning-based, each capture only a partial view of project complexity, leading to systematic underestimation in Agile DevOps contexts. This study proposes the Hybrid Ensemble Effort Estimation Model (HEEEM), which integrates Use Case Points (UCP) as an algorithmic anchor, the Delphi method as an expert-based judgment layer, and Extra Trees as a data-driven machine learning component. A two-stage framework is adopted: candidate machine learning models are first benchmarked across eight public datasets, spanning 945 projects, providing external validation of the data-driven component and confirming Extra Trees as the most consistent performer (MAE: 0.288, RMSE: 0.398, R2: 0.815), before being embedded into the hybrid ensemble. Empirical evaluation is conducted through case studies on five industrial Agile DevOps projects using standard performance metrics including Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Mean Magnitude of Relative Error (MMRE) and R2.The findings show that HEEEM significantly improved effort estimation accuracy, achieving an in-sample MAE of 21.60, RMSE of 25.32, MMRE of 0.0053, and an in-sample R2 of 0.9983, representing reductions of 69% in MAE, 71.9% in RMSE, and 72% in MMRE compared to individual baseline methods;under Leave-One-Out Cross-Validation, the corresponding out-of-sample metrics are MAE = 72.88, RMSE = 100.42, MMRE= 0.0192, and R2 = 0.9731, representing 45–52% reductions in MAE compared to the algorithmic and expert-based individual baselines. Statistical validation through the Friedman test confirmed these improvements are statistically significant (p = 0.0136). The proposed model offers actionable guidance for project managers and development teams regarding sprint planning, resource allocation, and risk management, and is particularly suited for continuous delivery environments where estimates require regular updating.
- 15 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 79253-79283
Open AccessHEEEM: A Hybrid Ensemble Effort Estimation Model for Agile and DevOps Development
Accurate effort estimation in Agile and DevOps software projects remains a persistent challenge, as traditional models fail to account for the iterative, continuous delivery nature of modern development environments. Existing single-technique estimation approaches, whether algorithmic, expert-based, or machine learning-based, each capture only a partial view of project complexity, leading to systematic underestimation in Agile DevOps contexts. This study proposes the Hybrid Ensemble Effort Estimation Model (HEEEM), which integrates Use Case Points (UCP) as an algorithmic anchor, the Delphi method as an expert-based judgment layer, and Extra Trees as a data-driven machine learning component. A two-stage framework is adopted: candidate machine learning models are first benchmarked across eight public datasets, spanning 945 projects, providing external validation of the data-driven component and confirming Extra Trees as the most consistent performer (MAE: 0.288, RMSE: 0.398, R2: 0.815), before being embedded into the hybrid ensemble. Empirical evaluation is conducted through case studies on five industrial Agile DevOps projects using standard performance metrics including Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Mean Magnitude of Relative Error (MMRE) and R2.The findings show that HEEEM significantly improved effort estimation accuracy, achieving an in-sample MAE of 21.60, RMSE of 25.32, MMRE of 0.0053, and an in-sample R2 of 0.9983, representing reductions of 69% in MAE, 71.9% in RMSE, and 72% in MMRE compared to individual baseline methods;under Leave-One-Out Cross-Validation, the corresponding out-of-sample metrics are MAE = 72.88, RMSE = 100.42, MMRE= 0.0192, and R2 = 0.9731, representing 45–52% reductions in MAE compared to the algorithmic and expert-based individual baselines. Statistical validation through the Friedman test confirmed these improvements are statistically significant (p = 0.0136). The proposed model offers actionable guidance for project managers and development teams regarding sprint planning, resource allocation, and risk management, and is particularly suited for continuous delivery environments where estimates require regular updating.
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 171504-171531
Performance Overfitting Trade-Offs: Analysis of Under-Sampling Techniques for Imbalanced Classification
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 171504-171531
Open AccessPerformance Overfitting Trade-Offs: Analysis of Under-Sampling Techniques for Imbalanced Classification
- Open Access
- 19 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 167925-167941
Effort Estimation in Agile and DevOps: A Systematic Literature Review of Stakeholder Dissatisfaction
Effort estimation is a critical aspect of software project management, directly influencing the budget, schedule, and resource allocation throughout the software development life cycle. Accurate estimation plays a central role in aligning team capabilities with stakeholder expectations, ensuring timely delivery and efficient use of resources. Despite the adoption of Agile and DevOps methodologies, which emphasize flexibility, rapid iterations and continuous integration, estimation inaccuracies remain a problematic area. These inaccuracies often result in project delays, cost overruns, and scope creep, ultimately leading to stakeholder dissatisfaction and a breakdown of trust in the development process. To investigate these challenges, a Systematic Literature Review (SLR) was conducted, surrounding 1,088 publications retrieved from six major digital libraries: Scopus (201), ScienceDirect (155), Springer (212), Google Scholar (145), IEEE (185), and ACM (190). This research examines the main drivers of estimation challenges in Agile and DevOps environments. Key findings indicate that human-centric issues (cognitive biases, lack of experience), technical issues (fluctuating requirements, lack of adequate history), and process inefficiencies (communication breakdown, poor planning) exert considerable influences on estimation accuracy. To address these challenges, the study categorizes and analyzes a range of estimation techniques, including machine learning models, expert-calibrated hybrid approaches, analogical estimation methods, and process calibration practices such as retrospectives. Findings reveal that a combination of data-driven tools and stakeholder-aligned strategies offers the most promise in narrowing the expectation experience gap. This research provides practitioners with practical recommendations and lays the ground for further study in developing estimation techniques to mitigate the expectation-experience gap.
- 19 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 167925-167941
Open AccessEffort Estimation in Agile and DevOps: A Systematic Literature Review of Stakeholder Dissatisfaction
Effort estimation is a critical aspect of software project management, directly influencing the budget, schedule, and resource allocation throughout the software development life cycle. Accurate estimation plays a central role in aligning team capabilities with stakeholder expectations, ensuring timely delivery and efficient use of resources. Despite the adoption of Agile and DevOps methodologies, which emphasize flexibility, rapid iterations and continuous integration, estimation inaccuracies remain a problematic area. These inaccuracies often result in project delays, cost overruns, and scope creep, ultimately leading to stakeholder dissatisfaction and a breakdown of trust in the development process. To investigate these challenges, a Systematic Literature Review (SLR) was conducted, surrounding 1,088 publications retrieved from six major digital libraries: Scopus (201), ScienceDirect (155), Springer (212), Google Scholar (145), IEEE (185), and ACM (190). This research examines the main drivers of estimation challenges in Agile and DevOps environments. Key findings indicate that human-centric issues (cognitive biases, lack of experience), technical issues (fluctuating requirements, lack of adequate history), and process inefficiencies (communication breakdown, poor planning) exert considerable influences on estimation accuracy. To address these challenges, the study categorizes and analyzes a range of estimation techniques, including machine learning models, expert-calibrated hybrid approaches, analogical estimation methods, and process calibration practices such as retrospectives. Findings reveal that a combination of data-driven tools and stakeholder-aligned strategies offers the most promise in narrowing the expectation experience gap. This research provides practitioners with practical recommendations and lays the ground for further study in developing estimation techniques to mitigate the expectation-experience gap.