Muhammad Zeeshan Babar

Dr. Muhammad Zeeshan Babar

Department of Computer Science, University of Leeds, Leeds, UK
orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 October 2025 in Scientific Reports
Verified
Journal Article
Open access
AZAmna Zahoor
Amna Zahoor
WAWaseem Abbasi
Waseem Abbasi
Muhammad Zeeshan BabarMuhammad Zeeshan Babar
Muhammad Zeeshan Babar
AAAbeer Aljohani
Abeer Aljohani
The rapid growth of cloud computing and the Internet of Things (IoT) has increased the exposure of IoT devices to cyber-attacks due to their resource limitations and lack of standardized security protocols. This paper presents a robust anomaly detection framework for IoT networks using two unsupervised machine learning models: Isolation Forest (IF) and One-Class Support Vector Machine (OCSVM). Leveraging the TON_IoT dataset, we conduct a comparative evaluation of IF, OCSVM, and a lightweight fusion approach called Combined Scoring Anomaly Detection (CSAD). Results show that OCSVM achieves superior precision, recall, and accuracy compared to both IF and CSAD. To ensure reliability, we apply Random Forest-based feature importance analysis, fivefold cross-validation and hyperparameter tuning. Model resilience is further examined under adversarial label-flip poisoning attacks and interpretability is enhanced through Local Interpretable Model-Agnostic Explanations (LIME). The findings demonstrate that lightweight unsupervised algorithms can provide effective, low-resource anomaly detection for modern IoT environments.

5 August 2025 in Ain Shams Engineering Journal
Verified
Journal Article
Open access
MAMuhammad Abdullah
Muhammad Abdullah
KAKhurram Saleem Alimgeer
Khurram Saleem Alimgeer
Ghulam HafeezGhulam Hafeez
Ghulam Hafeez
BABaheej Alghamdi
Baheej Alghamdi
AAAhmed Alsafran
Ahmed Alsafran
Muhammad Zeeshan BabarMuhammad Zeeshan Babar
Muhammad Zeeshan Babar

18 July 2025 in Discover Computing
Verified
Journal Article
Open access
PDF file
MGMuhammad Nadeem Gul
Muhammad Nadeem Gul
WAWaseem Abbasi
Waseem Abbasi
Muhammad Zeeshan BabarMuhammad Zeeshan Babar
Muhammad Zeeshan Babar
AAAbeer Aljohani
Abeer Aljohani
MAMuhammad Arif
Muhammad Arif
Accurately predicting student performance is essential for improving educational outcomes and guiding targeted interventions. This study applies eight advanced machine learning models-Decision Trees, Random Forest, Lasso, K-Nearest Neighbors, XGBoost, CatBoost, AdaBoost, and Gradient Boosting to analyze student performance based on demographic and academic features. Among these, CatBoost achieved the highest accuracy (87.46%) and less error rates, outperforming Gradient Boosting (87.28%) and Decision Trees (82.42%). Model evaluation was conducted using Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE), demonstrating the robustness of the proposed approach. The results highlight the effectiveness of data-driven methods in early identification of at-risk students, enabling educators to implement personalized learning strategies. This study underscores the transformative potential of machine learning in education, paving the way for more adaptive and student-centered learning environments.

1 February 2025 in Engineering, Technology & Applied Science Research
Verified
Journal Article
Open access
PDF file
MHMunawar Hussain
Munawar Hussain
HAHassan A Ahmed
Hassan A Ahmed
Muhammad Zeeshan BabarMuhammad Zeeshan Babar
Muhammad Zeeshan Babar
Arshad AliArshad Ali
Arshad Ali
H M ShahzadH M Shahzad
H M Shahzad
AAAbdulaziz Alshahrani
Abdulaziz Alshahrani
This study focuses on Diabetic Retinopathy (DR), a disease caused by diabetes that affects the retina of the eye and eventually leads to blindness. Diabetes development progresses to retinopathy and must be addressed at an early stage for effective treatment. Currently, DR is classified as Non-Proliferative DR (NPDR) and Proliferative DR (PDR). This study proposes an Enhanced DR (P-EDR) method based on CNN using a high-resolution dataset benchmark of retinal images. Initially, the data were preprocessed by normalization, augmentation, and resizing to improve image quality and feature extraction. Evaluation was based on accuracy, specificity, sensitivity, and AUC-ROC. The proposed CNN-based P-EDR outperformed advanced ML strategies such as Support Vector Machine (SVM), Random Forest (RF), Probabilistic Neural network (PNN), and Gradient Boosting Machine (GBM) that were executed and compared to diagnose and classify DR. The proposed P-EDR extracts features such as a hemorrhage of the NPDR retina image to identify the disease using image processing for classification. P-EDR provides significant features from images in detection and classification, making it a successful model for diagnosing DR with improved accuracy of 93%, sensitivity of 92%, specificity of 94%, and AUC-ROC of 0.97%. These results highlight the potential of a P-EDR-based machine learning model to support ophthalmologists with the early and precise detection of DR, eventually helping with appropriate treatment and prevention of vision loss.

7 July 2025 in IEEE Access
Verified
Journal Article
Open access
AAAhmed S. Alsafran
Ahmed S. Alsafran
SAFEER ULLAHSAFEER ULLAH
SAFEER ULLAH
Ameen UllahAmeen Ullah
Ameen Ullah
Ghulam HafeezGhulam Hafeez
Ghulam Hafeez
Muhammad Zeeshan BabarMuhammad Zeeshan Babar
Muhammad Zeeshan Babar
AAAbdullah A. Algethami
Abdullah A. Algethami
This paper presents a Robust Fractional-Order Sliding Mode Control (FOSMC) with Nonsingular Integral Terminal Dynamics, integrated with Densely Connected Convolutional Networks (DenseNet) for Lie Derivatives Estimation, to achieve Maximum Power Point Tracking (MPPT) in Wind Energy Conversion Systems (WECS) based on Permanent Magnet Synchronous Generators (PMSG). The proposed method effectively addresses the challenges of nonlinear dynamics, uncertain wind conditions, and chattering effects, which are common in traditional control approaches. The core innovation lies in fractional-order sliding mode control, which enhances convergence speed and robustness while ensuring finite-time stability. Unlike classical Sliding Mode Control (SMC), the proposed Nonsingular Terminal Sliding Mode (NTSM) formulation eliminates singularities and improves tracking accuracy. Additionally, to overcome inaccuracies in numerical differentiation, a Densely Connected Convolutional Neural Network (DenseNet) is employed to estimate higher-order Lie derivatives, providing real-time system state approximation and improving control precision. A rigorous Lyapunov stability theorem guarantees the finite-time convergence of the considered system. Extensive MATLAB/Simulink simulations validate the effectiveness of the proposed control law by comparing it with the existing classical controllers. The results demonstrate superior MPPT efficiency, faster transient response, reduced chattering, and enhanced robustness under varying wind conditions.

5 February 2026 in Scientific Reports
Verified
Journal Article
Open access
PDF file
AFAsif Feroz
Asif Feroz
WAWaseem Abbasi
Waseem Abbasi
Muhammad Zeeshan BabarMuhammad Zeeshan Babar
Muhammad Zeeshan Babar
AAAbeer Aljohani
Abeer Aljohani
Fake news has a significant effect on reader perceptions and is therefore a serious problem. It is difficult to differentiate between fake and real news as the number of News platforms on social media are growing daily. This work aims to create a complete fake news detection mechanism for Pakistani news by using many fact-checked APIs. A total of 14,178 real and fake news items from fifteen different regions and sections of reputable and authoritative Urdu newspapers and news broadcasting websites in Pakistan are included in the dataset. We evaluate the dataset via three deep learning models RoBERTa, XLM-RoBERTa and mBERT are embedded with concatenated BERT and GloVe. For the training of the selected models, we first use an extensive multilingual dataset. The results of the proposed models are as follows: evaluated via performance metrics such as the F1 score, accuracy, precision and recall. XLM-RoBERTa with concatenated GloVe embedding outperforms with an F1 score of 0.956, accuracy of 0.962, precision of 0.932 and recall of 0.940. A comparative analysis of the latest machine learning and deep learning models is also done. The latest Urdu benchmark dataset shows that the XLM-RoBERTa model with Concatenated BERT and GloVe embedding outperforms these models for Urdu fake news detection.