ΕΛ EN
Home | People | Aslam, Sheraz
112
Scholarly Works
40%
OA Ratio
21%
Collaborative Ratio
Scholar

Aslam, Sheraz

Research Scientist

Department of Electrical Engineering, Computer Engineering and Informatics

8
H-index (Scopus)
5590
Scholar Citations

Scholarly Works

Research Output

Recent Publications

TRACE: Intervention-aware temporal representation learning for video understanding

Kulsoom F., Ashraf N., Chaudhry H.N., Aslam S., Mohsin S.M.
Publishing year: 2026
Journal article
Machine Learning with Applications, 2026, Volume 25
Scopus
Learning generalizable video representations from unlabeled data remains a fundamental challenge in computer vision, as existing self-supervised learning approaches primarily rely on modeling statistical correlations rather than capturing structured temporal dependencies in video data. While recent methods such as masked video modeling and contrastive learning achieve strong empirical performance, they often fail to explicitly account for how changes in motion influence future states, limiting robustness and generalization under distribution shifts. In this work, we propose TRACE, a self-supervised framework for learning intervention-aware spatiotemporal representations by incorporating temporal interventions and counterfactual learning objectives. TRACE operates in latent space by decomposing video representations into content and motion components, enabling targeted perturbations of motion variables while preserving semantic structure. A temporal intervention module generates alternative trajectories by modifying motion dynamics, and a counterfactual prediction objective enforces consistency between predicted and intervention-induced future representations. This formulation encourages the model to learn representations that are sensitive to intervention-induced changes rather than relying on spurious correlations. Extensive experiments demonstrate that TRACE consistently outperforms state-of-the-art self-supervised video learning methods across multiple benchmarks. In parti...

Predicting cryptocurrency prices with ML-DL models: A hybrid expert system approach

Javaid N., Riaz Y., Aslam S., Kamal R., Mustafa K., Jumani F., Kamal K., Nugent C.
Publishing year: 2026
Journal article
Expert Systems with Applications, 2026, Volume 299
Scopus
Cryptocurrency price prediction poses significant challenges due to the inherent volatility and nonlineardynamics of the market. This study introduces a hybrid stacked modeling framework that integrates machine learning (ML) and deep learning (DL) techniques, capitalizing on their complementary strengths-ML models are effective at capturing nonlinearfeature interactions in structured data, while DL architectures are adept at modeling temporal dependencies in sequential data. The proposed model leverages historical price data, technical indicators, macroeconomic variables, and sentiment metrics, with feature engineering applied to enhance predictive capability. Empirical evaluation was conducted through two experimental setups: (i) short-term, monthly segment analysis and (ii) long-term generalization via five-fold cross-validation. The hybrid model outperformed individual baseline models, achieving up to 18.3 % lower RMSE and 6.7 % higher directional accuracy. Additionally, it yielded superior risk-adjusted returns, with Sharpe Ratios reaching 0.094 on the Ethereum dataset. Beyond technical improvements, this research offers foresight into digital financial markets, providing a robust tool for investors, institutions, and policymakers navigating the evolving cryptocurrency landscape. The model supports more informed decision-making, enhances market oversight, and contributes to the development of adaptive regulatory frameworks for digital finance.

Multi-Task Disaster Tweet Classification Using Hybrid TF-IDF and Graph Convolutional Networks

Patra S.S., Chowdhury S., Aslam S., Alkhiri H., Mustafa K., Nath B., Sahoo D.
Publishing year: 2026
Journal article
Computers Materials and Continua, 2026, Volume 87, Issue 2
Scopus
Accurate, up to date, and quick information related to any disaster supports disaster management team/authorities to perform quick, easy, and cost-effective response to enhance rescue operations to alleviate the possible loss of lives, financial risks, and properties. Due to damaged infrastructure in disaster-affected areas, social media is the only way to share/ exchange real time information. Therefore, ‘X’ (formerly Twitter) has become a major platform for disseminating real-time information during disaster events or emergencies, i.e., floods and earthquake. Rapid identification of actionable content is critical for effective humanitarian response; however, the brief and noisy nature of tweets makes automated classification challenging. To tackle this problem, this study proposes a hybrid classification framework that integrates term frequency-inverse document frequency (TF-IDF) features with graph convolutional networks (GCNs) to enhance disaster-related tweet analysis. The proposed model performs three classification tasks: identifying disaster-related tweets (achieving 94.47% accuracy), categorizing disaster types (earthquake, flood, and non-disaster) with 91.78% accuracy, and detecting aid requests such as food, donations, and medical assistance (94.64% accuracy). By combining the statistical strengths of TF-IDF with the relational learning capabilities of GCNs, the model attains high accuracy while maintaining computational efficiency and interpretability. The results...

Intra-Video Temporal-Aware RAG: A Self-Contained Framework for Video-Based Question Answering

Shah M.A., Sohail A., Ejaz N., Aslam S., Kamal R., Shafiq S.
Publishing year: 2026
Journal article
Computers Materials and Continua, 2026, Volume 88, Issue 2
Scopus
Lecture videos are widely used in modern education, yet answering questions from them remains challenging. Relevant information is often distributed across time and expressed through multiple modalities, including speech, slides, and visual content. Existing VideoQA approaches, including recent retrieval-augmented generation (RAG) methods, typically rely on static text representations or global video features. Consequently, they may retrieve evidence that is semantically relevant but temporally misaligned, leading to inaccurate or weakly grounded responses. In addition, dependence on external knowledge sources can introduce hallucinations and reduce reliability in educational settings. To address these limitations, we propose a temporally aware, intra-video RAG framework tailored for lecture videos. The approach aligns automatic speech transcripts and visual captions into timestamped segments and performs retrieval constrained by temporal boundaries. Retrieved segments are further refined using a cross-encoder before answer generation, ensuring that responses are grounded in the correct portions of the video. We evaluate the proposed method on the LectQA-Vid dataset, consisting of 100 lecture videos and 3000 temporally annotated questions. Experimental results demonstrate improved factual alignment and robustness over non-temporal baselines, highlighting the importance of temporal grounding in lecture VideoQA.

Hybrid Kernel SVM and Boosting Approaches for Accurate Autism Spectrum Disorder Screening

Aslam S., Ali S., Mustafa K., Misbah , Ali U., Shahid S.
Publishing year: 2026
Conference paper
Lecture Notes in Networks and Systems, 2026, Volume 1744 LNNS
Scopus
Pages 178-187
Autism Spectrum Disorder (ASD) is a neurocognitive condition that affects social interaction, communication, expressive abilities, and behavioral patterns. The early diagnosis and intervention significantly improve learning, communication, and quality of life outcomes. This study aims to the early and accurate diagnosis of ASD using machine learning (ML) techniques based on behavioral and demographic data obtained from Kaggle. We used naïve Bayes (NB), k-nearest neighbors (KNN), and support vector machines (SVM) as base learners, as well as boosting-based ensembles (AdaBoost, LightGBM, XGBoost); a hybrid-kernel SVM variant; and a stacking ensemble. The results of the study indicate that among all methods, the stacking classifier outperformed all other methods, achieving an accuracy of 99.74%. These findings demonstrate the potential of stacking ensembles in developing intelligent systems to support early ASD diagnosis and intervention planning. Future research could focus on validating this approach on larger and more diverse clinical datasets (e.g., neuroimaging biomarkers, generative AI, or advanced ML frameworks) to enhance robustness, generalizability, and clinical applicability.

AI-driven blockchain technology in smart healthcare system: Opportunities, challenges and future implications

Liang J., Aslam S., Akber S.M.A., Sadiq M., Mohsin S.M., Mujlid H., Zhang Y.
Publishing year: 2026
Journal article
Computer Science Review, 2026, Volume 60
Scopus
Blockchain technology in conjunction with artificial intelligence (AI) is transforming smart healthcare systems, by providing enhanced data security, interoperability, and transparency. Integration of AI along with blockchain into smart healthcare systems offers numerous benefits, including supporting decision-making processes, reducing administrative burdens, improving coordination of patient care and automated, trust-based execution of healthcare agreements. This study presents applications of AI-based blockchain technology in the field of smart healthcare and analyzes the state of affairs, highlights the key issues, and identifies perspectives to strengthen the reliability and trustworthiness of future medical systems. The study uses a structured framework to analyze the effectiveness of blockchain in healthcare by contrasting its advantages and disadvantages. Blockchain systems benefit healthcare by improving data security, streamlining data processing, ensuring trust, facilitating telemedicine and remote monitoring, and enabling efficient consent management, automated workflows and medication traceability. In this context, the study introduces a conceptual model namely the trust–automation–interoperability (TAI) synergy framework to guide the design, analysis, and deployment of AI-enabled blockchain solutions for smart healthcare aiming to achieve a sustainable digital health ecosystem by strengthening three fundamental dimensions: trust, automation, and interoperability...

112
Unique publications
40.2%
Open access (45 publications; 50 without information)
21.4%
With other institutions (24 publications; 86 without information)

H-Index Reports

Index type Scopus Google Scholar Web of Science
H-index 8 16 1
H5-index 8 16 1
H10-index 8 16 1

Publications per year and source

No description yet.
Faculty
Faculty of Engineering and Technology
Department
Department of Electrical Engineering, Computer Engineering and Informatics
Title
Research Scientist