Asad Ali
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
Asad Ali has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Adam Khan
Department of Computer Science and IT, Sarhad University of Science and Information Technology, Peshawar, Pakistan
4 shared publications Carmine Gravino
2 shared publications- Carmine Gravino
University of Salerno
2 shared publications - Fasee Ullah
Department of Computing, Universiti Teknologi PETRONAS, Seri Iskandar, Malaysia
2 shared publications Jahangir Khan
Department of Computer Science and Information Technology, Sarhad University of Science Information Technology, Peshawar, Pakistan
2 shared publications- Muhammad Faheem
VTT Technical Research Centre of Finland, Espoo, Finland
2 shared publications
Latest Publications
- Open Access
- 27 June 2026
- Published by MDPI AG in Healthcare
- Vol. 14 (13) , 1881
Explainable Machine Learning for Predicting Dengue Recovery Duration: Insights from Multi-Center Clinical Data
Background: Dengue fever remains a major public health challenge in endemic regions, where recovery duration varies considerably across patients due to a combination of clinical, demographic, and contextual factors. Although machine learning (ML) approaches have increasingly been applied to dengue related prediction tasks, many existing models operate as black boxes, limiting their interpretability and practical usefulness in healthcare settings. This study presents an Explainable Artificial Intelligence (XAI) based machine learning framework for analyzing dengue recovery duration using a multi-center clinical dataset collected from healthcare institutions across Khyber Pakhtunkhwa, Pakistan. Methods: Clinical records from 100 laboratory-confirmed dengue patients treated across multiple healthcare institutions were analyzed. The dataset included demographic, socio-economic, and clinical variables. Four machine learning models: Linear Regression, Decision Tree, Random Forest, and Neural Network, were developed and evaluated using 10-fold cross-validation. Explainability techniques, including Partial Dependence Plots (PDP), Individual Conditional Expectation (ICE), and Local Interpretable Model-Agnostic Explanations (LIME), were employed to investigate global and patient specific factors influencing recovery duration. Results: Among the evaluated models, Random Forest demonstrated the best overall predictive performance, achieving the lowest Root Mean Square Error (RMSE; 11.29 days) and Mean Absolute Error (MAE; 9.09 days), corresponding to a 40.4% reduction in prediction error compared with Linear Regression. Decision Tree also showed substantial improvement, reducing RMSE by 37%, whereas the Neural Network achieved a more modest improvement of 8.6%. Although all models exhibited relatively low coefficient of determination (R2) values (maximum R2 = 0.026), the explainability analyses consistently identified age and platelet count as the most influential predictors of recovery duration. Older age and lower platelet counts were generally associated with longer recovery periods, while hospital type, education level, and blood group also contributed to prediction outcomes. ICE and LIME analyses further revealed considerable patient level heterogeneity, indicating that recovery trajectories are shaped by complex interactions among clinical, demographic, and contextual factors rather than a single dominant predictor.
- 27 June 2026
- Published by MDPI AG in Healthcare
- Vol. 14 (13) , 1881
Open AccessExplainable Machine Learning for Predicting Dengue Recovery Duration: Insights from Multi-Center Clinical Data
Background: Dengue fever remains a major public health challenge in endemic regions, where recovery duration varies considerably across patients due to a combination of clinical, demographic, and contextual factors. Although machine learning (ML) approaches have increasingly been applied to dengue related prediction tasks, many existing models operate as black boxes, limiting their interpretability and practical usefulness in healthcare settings. This study presents an Explainable Artificial Intelligence (XAI) based machine learning framework for analyzing dengue recovery duration using a multi-center clinical dataset collected from healthcare institutions across Khyber Pakhtunkhwa, Pakistan. Methods: Clinical records from 100 laboratory-confirmed dengue patients treated across multiple healthcare institutions were analyzed. The dataset included demographic, socio-economic, and clinical variables. Four machine learning models: Linear Regression, Decision Tree, Random Forest, and Neural Network, were developed and evaluated using 10-fold cross-validation. Explainability techniques, including Partial Dependence Plots (PDP), Individual Conditional Expectation (ICE), and Local Interpretable Model-Agnostic Explanations (LIME), were employed to investigate global and patient specific factors influencing recovery duration. Results: Among the evaluated models, Random Forest demonstrated the best overall predictive performance, achieving the lowest Root Mean Square Error (RMSE; 11.29 days) and Mean Absolute Error (MAE; 9.09 days), corresponding to a 40.4% reduction in prediction error compared with Linear Regression. Decision Tree also showed substantial improvement, reducing RMSE by 37%, whereas the Neural Network achieved a more modest improvement of 8.6%. Although all models exhibited relatively low coefficient of determination (R2) values (maximum R2 = 0.026), the explainability analyses consistently identified age and platelet count as the most influential predictors of recovery duration. Older age and lower platelet counts were generally associated with longer recovery periods, while hospital type, education level, and blood group also contributed to prediction outcomes. ICE and LIME analyses further revealed considerable patient level heterogeneity, indicating that recovery trajectories are shaped by complex interactions among clinical, demographic, and contextual factors rather than a single dominant predictor.
- Open Access
- 31 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 56947-56972
Explainable Artificial Intelligence in Software Engineering: Current Trends, Gaps, and Future Directions
Explainable Artificial Intelligence (XAI) has gained increasing attention for improving the transparency of artificial intelligence systems. However, there is a less clear understanding of its adoption and research patterns in the field of Software Engineering (SE).This systematic literature review focuses on the use of XAI within SE and the prospects of cross-domain learning. To achieve this, twenty-nine studies applying XAI in Software Engineering (SE), published between March 2020 and April 2024, were reviewed, and their findings were compared with XAI practices reported in healthcare and finance. The findings show that SE research mostly uses local explanation techniques: 86% of the studies employ instance-level methods, such as Local Interpretable Model-agnostic Explanations (LIME), whereas global explanation techniques that provide an overall view of the model are used less frequently. In terms of application domains, XAI studies in SE are mainly focused on software defect prediction, while other domains, such as software testing, and effort estimation remain comparatively underexplored. Regarding implementation tools, scikit-learn is the most frequently used machine learning (ML) library in XAI-based SE studies, and less often, TensorFlow, PyTorch, and R based-frameworks are used. The current study is more comprehensive in terms of scope compared to the previous review, as it addresses four research questions, examines the types of explanations, and clearly mentions the utilization of ML libraries. The findings indicate that future SE studies should incorporate global explanation techniques, diversify XAI methods, and extend the research to underrepresented SE tasks. In addition, clear reporting of tools and libraries is essential to enhance reproducibility. Overall, although XAI in SE is progressing, the domain remains at an early stage, and insights from other fields may help improve interpretability, reliability, and trust in SE systems.
- 31 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 56947-56972
Open AccessExplainable Artificial Intelligence in Software Engineering: Current Trends, Gaps, and Future Directions
Explainable Artificial Intelligence (XAI) has gained increasing attention for improving the transparency of artificial intelligence systems. However, there is a less clear understanding of its adoption and research patterns in the field of Software Engineering (SE).This systematic literature review focuses on the use of XAI within SE and the prospects of cross-domain learning. To achieve this, twenty-nine studies applying XAI in Software Engineering (SE), published between March 2020 and April 2024, were reviewed, and their findings were compared with XAI practices reported in healthcare and finance. The findings show that SE research mostly uses local explanation techniques: 86% of the studies employ instance-level methods, such as Local Interpretable Model-agnostic Explanations (LIME), whereas global explanation techniques that provide an overall view of the model are used less frequently. In terms of application domains, XAI studies in SE are mainly focused on software defect prediction, while other domains, such as software testing, and effort estimation remain comparatively underexplored. Regarding implementation tools, scikit-learn is the most frequently used machine learning (ML) library in XAI-based SE studies, and less often, TensorFlow, PyTorch, and R based-frameworks are used. The current study is more comprehensive in terms of scope compared to the previous review, as it addresses four research questions, examines the types of explanations, and clearly mentions the utilization of ML libraries. The findings indicate that future SE studies should incorporate global explanation techniques, diversify XAI methods, and extend the research to underrepresented SE tasks. In addition, clear reporting of tools and libraries is essential to enhance reproducibility. Overall, although XAI in SE is progressing, the domain remains at an early stage, and insights from other fields may help improve interpretability, reliability, and trust in SE systems.
- Open Access
- 8 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 75493-75524
Exploring Consistent Feature Selection for Software Fault Prediction: An XAI-Based Model-Agnostic Approach
Numerous Feature Selection (FS) techniques have been widely utilized in Software Engineering (SE) to enhance the predictive accuracy of Machine Learning (ML) models. However, how consistently these FS techniques extract features under various data changes (made to the training data) remains underexplored. While prior studies have assessed the stability of traditional FS techniques (e.g., Information Gain, Genetic Search, etc.), their findings remain limited. With the growing use of eXplainable Artificial Intelligence (XAI) in SE, it is important to assess the level of consistency of model-agnostic FS techniques to ensure their reliability within dynamic learning environments. This study evaluates the consistency of Permutation Feature Importance (PFI) and SHapley Additive exPlanations (SHAP), across five ML models, i.e., Linear Regression(LR). Multi-layer Perceptron (MLP), Random Forest (RF), Decision Trees (DT), Support Vector Machines(SVM), on six Software Fault Prediction datasets under various validation methods (such as 3-fold, Bootstrap etc.), data normalization, and dataset modifications. The findings reveal that model-agnostic FS shows higher consistency than traditional FS techniques across all changes. In the case of validation-based consistency and using the SHAP, SVM and DT achieve the highest average feature consistency (100%), while MLP achieves the lowest (74.27%). Similarly, using PFI, LR, DT, and SVM achieves 100% consistency, whereas MLP remains the lowest consistency at 44.03%. In the case of data change-based consistency, using SHAP, MLP achieves the highest consistency (76.20%), whereas SVM has the lowest (70.98%). Using PFI, RF achieves the highest average consistency (77.24%), and MLP is the least consistent (44.93%). Similarly, in an overall comparison, both XAI-based techniques outperform traditional techniques, confirming their reliability for SFP tasks.
- 8 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 75493-75524
Open AccessExploring Consistent Feature Selection for Software Fault Prediction: An XAI-Based Model-Agnostic Approach
Numerous Feature Selection (FS) techniques have been widely utilized in Software Engineering (SE) to enhance the predictive accuracy of Machine Learning (ML) models. However, how consistently these FS techniques extract features under various data changes (made to the training data) remains underexplored. While prior studies have assessed the stability of traditional FS techniques (e.g., Information Gain, Genetic Search, etc.), their findings remain limited. With the growing use of eXplainable Artificial Intelligence (XAI) in SE, it is important to assess the level of consistency of model-agnostic FS techniques to ensure their reliability within dynamic learning environments. This study evaluates the consistency of Permutation Feature Importance (PFI) and SHapley Additive exPlanations (SHAP), across five ML models, i.e., Linear Regression(LR). Multi-layer Perceptron (MLP), Random Forest (RF), Decision Trees (DT), Support Vector Machines(SVM), on six Software Fault Prediction datasets under various validation methods (such as 3-fold, Bootstrap etc.), data normalization, and dataset modifications. The findings reveal that model-agnostic FS shows higher consistency than traditional FS techniques across all changes. In the case of validation-based consistency and using the SHAP, SVM and DT achieve the highest average feature consistency (100%), while MLP achieves the lowest (74.27%). Similarly, using PFI, LR, DT, and SVM achieves 100% consistency, whereas MLP remains the lowest consistency at 44.03%. In the case of data change-based consistency, using SHAP, MLP achieves the highest consistency (76.20%), whereas SVM has the lowest (70.98%). Using PFI, RF achieves the highest average consistency (77.24%), and MLP is the least consistent (44.93%). Similarly, in an overall comparison, both XAI-based techniques outperform traditional techniques, confirming their reliability for SFP tasks.
- Top Cited PapersOpen Access
- 24 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 36421-36435
Using Permutation-Based Feature Importance for Improved Machine Learning Model Performance at Reduced Costs
In Software Quality Assurance (SQA), predicting defect-prone software modules is essential for ensuring software reliability and consistency. This task is commonly achieved through Machine Learning (ML) techniques, but improving model performance typically incurs significant computational costs. These high computational costs and uncertain payoffs make most Software engineering researchers reluctant to optimize ML models. This creates a need for novel techniques that can achieve near optimal performance of hyperparameter settings while maintaining the computational efficiency of default settings. To address this, we employed five ML models, Decision Tree, Ranger, Random Forest, Support Vector Machine, and k-nearest Neighbors and optimized their parameters using the random search technique. Our experiments covered six diverse Software Fault Prediction (SFP) datasets, encompassing a wide range of software features, application domains, and defect patterns, to evaluate the approach’s generalizability and effectiveness.. Moreover, the Permutation Feature Importance (PFI)-based model-agnostic method was employed to identify the top ten features critical for model accuracy and efficiency. These selected features were used to retrain the ML models without hyperparameter (default settings) to determine whether similar performance could be achieved at low computational cost. The results show an average accuracy improvement of 77.39% and a 92.02% reduction in computational cost. The most important case attained a 99.25% accuracy improvement and a 96.77% cost reduction. Such results clearly show that the PFI-based feature selection is capable of high performance at a fraction of computational cost, offering an efficient solution for software engineers to optimize ML models.
- 24 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 36421-36435
Top Cited PapersOpen AccessUsing Permutation-Based Feature Importance for Improved Machine Learning Model Performance at Reduced Costs
In Software Quality Assurance (SQA), predicting defect-prone software modules is essential for ensuring software reliability and consistency. This task is commonly achieved through Machine Learning (ML) techniques, but improving model performance typically incurs significant computational costs. These high computational costs and uncertain payoffs make most Software engineering researchers reluctant to optimize ML models. This creates a need for novel techniques that can achieve near optimal performance of hyperparameter settings while maintaining the computational efficiency of default settings. To address this, we employed five ML models, Decision Tree, Ranger, Random Forest, Support Vector Machine, and k-nearest Neighbors and optimized their parameters using the random search technique. Our experiments covered six diverse Software Fault Prediction (SFP) datasets, encompassing a wide range of software features, application domains, and defect patterns, to evaluate the approach’s generalizability and effectiveness.. Moreover, the Permutation Feature Importance (PFI)-based model-agnostic method was employed to identify the top ten features critical for model accuracy and efficiency. These selected features were used to retrain the ML models without hyperparameter (default settings) to determine whether similar performance could be achieved at low computational cost. The results show an average accuracy improvement of 77.39% and a 92.02% reduction in computational cost. The most important case attained a 99.25% accuracy improvement and a 96.77% cost reduction. Such results clearly show that the PFI-based feature selection is capable of high performance at a fraction of computational cost, offering an efficient solution for software engineers to optimize ML models.
- 1 January 2022
- Published by Elsevier in Science of Computer Programming
- Vol. 213
Evaluating the impact of feature selection consistency in software prediction
- 1 January 2022
- Published by Elsevier in Science of Computer Programming
- Vol. 213
Evaluating the impact of feature selection consistency in software prediction
- 13 June 2021
- Published by Wiley in Journal of Software: Evolution and Process
- Vol. 33 (8) , e2367
An empirical comparison of validation methods for software prediction models
Model validation methods (e.g., k‐fold cross‐validation) use historical data to predict how well an estimation technique (e.g., random forest) performs on the current (or future) data. Studies in the contexts of software development effort estimation (SDEE) and software fault prediction (SFP) have used and investigated different model validation methods. However, no conclusive indications to suggest which model validation method has a major impact on the prediction accuracy and stability of estimation techniques. Some studies have investigated model validation methods specific to data about either SDEE or SFP. To the best of our knowledge, there is no study in the literature, which has employed different validation methods both with SDEE and SFP data. The aim of this paper is to consider different methods (10) from the family of cross‐validation (CV) and bootstrap validation methods to identify which one contributes to obtaining a better prediction accuracy for both types of data. We also evaluate which model validation methods allow the estimation techniques to provide stable performances (i.e., with lower variance). To this aim, we present an empirical study involving six datasets from the domain of SDEE and six datasets from the SFP domain. The results reveal that repeated 10‐fold CV with SDEE and optimistic boot with SFP data are the model validation methods that provide a better prediction accuracy in a greater number of experiments than the other model validation methods. Furthermore, a model validation method can improve the prediction accuracy up to 60% with SDEE data and up to 36% when employing SFP data. The analysis also reveals that repeated fivefold CV produces more stable performances when the experiments are repeated on the same data.
- 13 June 2021
- Published by Wiley in Journal of Software: Evolution and Process
- Vol. 33 (8) , e2367
An empirical comparison of validation methods for software prediction models
Model validation methods (e.g., k‐fold cross‐validation) use historical data to predict how well an estimation technique (e.g., random forest) performs on the current (or future) data. Studies in the contexts of software development effort estimation (SDEE) and software fault prediction (SFP) have used and investigated different model validation methods. However, no conclusive indications to suggest which model validation method has a major impact on the prediction accuracy and stability of estimation techniques. Some studies have investigated model validation methods specific to data about either SDEE or SFP. To the best of our knowledge, there is no study in the literature, which has employed different validation methods both with SDEE and SFP data. The aim of this paper is to consider different methods (10) from the family of cross‐validation (CV) and bootstrap validation methods to identify which one contributes to obtaining a better prediction accuracy for both types of data. We also evaluate which model validation methods allow the estimation techniques to provide stable performances (i.e., with lower variance). To this aim, we present an empirical study involving six datasets from the domain of SDEE and six datasets from the SFP domain. The results reveal that repeated 10‐fold CV with SDEE and optimistic boot with SFP data are the model validation methods that provide a better prediction accuracy in a greater number of experiments than the other model validation methods. Furthermore, a model validation method can improve the prediction accuracy up to 60% with SDEE data and up to 36% when employing SFP data. The analysis also reveals that repeated fivefold CV produces more stable performances when the experiments are repeated on the same data.
- 25 July 2019
- Published by Wiley in Journal of Software: Evolution and Process
- Vol. 31 (10)
A systematic literature review of software effort prediction using machine learning methods
Machine learning (ML) techniques have been widely investigated for building prediction models, able to estimate software development effort as well as to improve the accuracy of other estimation techniques. The objective of this paper is to systematically review the recent studies which used and discussed the software effort estimation models built using ML techniques. The performed literature review is based on the empirical studies published in the time period of January 1991 to December 2017, by employing widely used guidelines. The review has selected a total of 75 primary studies after the careful filtering of inclusion/exclusion and quality assessment criteria. The performed analysis reveals that artificial neural network (ANN) as ML model, NASA as dataset, and mean magnitude of relative error (MMRE) as accuracy measure are widely used in the selected studies. ANN and support vector machine (SVM) are the two techniques which have outperformed other ML techniques in more studies. Regression techniques are the mostly used among the non‐ML techniques, which outperformed other ML techniques in about 19 studies. Moreover, SVM and regression techniques in combination are characterized by better predictions when compared with other ML and non‐ML techniques.
- 25 July 2019
- Published by Wiley in Journal of Software: Evolution and Process
- Vol. 31 (10)
A systematic literature review of software effort prediction using machine learning methods
Machine learning (ML) techniques have been widely investigated for building prediction models, able to estimate software development effort as well as to improve the accuracy of other estimation techniques. The objective of this paper is to systematically review the recent studies which used and discussed the software effort estimation models built using ML techniques. The performed literature review is based on the empirical studies published in the time period of January 1991 to December 2017, by employing widely used guidelines. The review has selected a total of 75 primary studies after the careful filtering of inclusion/exclusion and quality assessment criteria. The performed analysis reveals that artificial neural network (ANN) as ML model, NASA as dataset, and mean magnitude of relative error (MMRE) as accuracy measure are widely used in the selected studies. ANN and support vector machine (SVM) are the two techniques which have outperformed other ML techniques in more studies. Regression techniques are the mostly used among the non‐ML techniques, which outperformed other ML techniques in about 19 studies. Moreover, SVM and regression techniques in combination are characterized by better predictions when compared with other ML and non‐ML techniques.