Muhammad Zubair
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Muhammad Zubair has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Jianqiang Li
School of Computer Science, Beijing University of Technology, Beijing 100124, China
3 shared publications Ali Haider Khan
Faculty of Information Technology, Beijing University of Technology , Beijing 100124
1 shared publication- Changwei Song
School of Computer Science, Beijing University of Technology, Beijing 100124, China
1 shared publication - Hongzhi Qi
College of Computer Science, Beijing University of Technology, Beijing, China
1 shared publication Jianqiang Li
1 shared publication- Jinjia Li
School of Computer Science and Information Engineering, Changzhou Institute of Technology, Changzhou, China
1 shared publication
Latest Publications
- Open Access
- 29 June 2026
- Published by Elsevier in SSRN Electronic Journal
An Intelligent Knowledge-Driven Expert System for Parallel Simulation Task Scheduling: The Zero-Step Decoupling Strategy
Task scheduling in large-scale parallel simulations, wherein each task is formally represented as a simulation model, is inherently constrained by complex Directed Acyclic Graph (DAG) dependencies, which dictate rigid execution sequences and induce severe synchronization blocking. Traditional meta-heuristic scheduling paradigms often suffer from prohibitive optimization overheads and rigidly force models to passively await predecessor availability, resulting in severe resource starvation and elongated per-step makespans. To resolve this bottleneck, this paper proposes an intelligent expert system centered on a novel Zero-Step Decoupling Strategy, comprising two core components: First, a knowledge-driven Zero-Step Decoupling Strategy, which leverages K-Means clustering for optimal resource matching ($\mathcal{O}(|\mathcal{M}|)$ complexity) and transforms rigid spatial DAG dependencies into asynchronous inter-step temporal fetches. This mechanism allows all models to achieve absolute pipeline concurrency from the first physical simulation step, effectively replacing structural blocking with pipeline execution. Second, an Adaptive Model Migration mechanism realizes dynamic fault-tolerance and intelligent load re-equilibration. By leveraging the decoupling of the Zero-Step strategy, migrated models can "hot-swap" across heterogeneous virtual machines (VMs) with near-zero topological re-synchronization overhead, ensuring system-wide robustness. Extensive empirical evaluations on a heterogeneous distributed testbed featuring 1,000 concurrent models demonstrate that the proposed expert system significantly outperforms traditional paradigms. Specifically, it compresses scheduling overhead to 29.3 ms, maintains an outstanding CPU saturation of 88.5%, and restricts the passive wait time ratio to 1.1%, thereby delivering a speedup ratio of 2.86 and reducing the overall makespan by 60.7% compared to the gold-standard HEFT algorithm. This intelligent, robust, and deterministic expert system provides a critical foundation for advanced, high-availability industrial simulation applications.
- 29 June 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessAn Intelligent Knowledge-Driven Expert System for Parallel Simulation Task Scheduling: The Zero-Step Decoupling Strategy
Task scheduling in large-scale parallel simulations, wherein each task is formally represented as a simulation model, is inherently constrained by complex Directed Acyclic Graph (DAG) dependencies, which dictate rigid execution sequences and induce severe synchronization blocking. Traditional meta-heuristic scheduling paradigms often suffer from prohibitive optimization overheads and rigidly force models to passively await predecessor availability, resulting in severe resource starvation and elongated per-step makespans. To resolve this bottleneck, this paper proposes an intelligent expert system centered on a novel Zero-Step Decoupling Strategy, comprising two core components: First, a knowledge-driven Zero-Step Decoupling Strategy, which leverages K-Means clustering for optimal resource matching ($\mathcal{O}(|\mathcal{M}|)$ complexity) and transforms rigid spatial DAG dependencies into asynchronous inter-step temporal fetches. This mechanism allows all models to achieve absolute pipeline concurrency from the first physical simulation step, effectively replacing structural blocking with pipeline execution. Second, an Adaptive Model Migration mechanism realizes dynamic fault-tolerance and intelligent load re-equilibration. By leveraging the decoupling of the Zero-Step strategy, migrated models can "hot-swap" across heterogeneous virtual machines (VMs) with near-zero topological re-synchronization overhead, ensuring system-wide robustness. Extensive empirical evaluations on a heterogeneous distributed testbed featuring 1,000 concurrent models demonstrate that the proposed expert system significantly outperforms traditional paradigms. Specifically, it compresses scheduling overhead to 29.3 ms, maintains an outstanding CPU saturation of 88.5%, and restricts the passive wait time ratio to 1.1%, thereby delivering a speedup ratio of 2.86 and reducing the overall makespan by 60.7% compared to the gold-standard HEFT algorithm. This intelligent, robust, and deterministic expert system provides a critical foundation for advanced, high-availability industrial simulation applications.
- 26 February 2026
- Published by Elsevier in Computational Biology and Chemistry
- Vol. 123, 108984
Signature-aware deep learning reveals distinct driver gene programs and mutational processes in glioblastoma and colon adenocarcinoma
- 26 February 2026
- Published by Elsevier in Computational Biology and Chemistry
- Vol. 123, 108984
Signature-aware deep learning reveals distinct driver gene programs and mutational processes in glioblastoma and colon adenocarcinoma
- Open Access
- 1 November 2025
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 26 (6)
Deep learning approaches for resolving genomic discrepancies in cancer: a systematic review and clinical perspective
Discrepancies in cancer sequencing data continue to pose significant challenges for accurate mutation detection, potentially resulting in misdiagnoses and suboptimal treatment strategies. Although deep learning (DL) has emerged as a transformative approach for identifying and rectifying these errors, there remains a lack of comprehensive evaluation of DL architectures, performance benchmarks, and clinical translation. In this systematic review of 78 studies (2015–2024), We synthesize recent advancements in DL methodologies for identifying genomic discrepancies, demonstrating that convolutional and graph-based architectures currently achieve state-of-the-art performance in variant calling and tumor stratification. DL models reduce false-negative rates by 30%–40% compared to traditional pipelines, with methods such as MAGPIE prioritizing pathogenic variants with 92% accuracy. However, challenges such as data scarcity, batch effects, and the interpretability of “black-box” models persist. We propose a future research roadmap advocating federated learning to enhance data privacy and attention mechanisms to improve model transparency. By bridging bioinformatics and oncology, this review offers actionable insights to expedite the deployment of DL in precision cancer therapy.
- 1 November 2025
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 26 (6)
Open AccessDeep learning approaches for resolving genomic discrepancies in cancer: a systematic review and clinical perspective
Discrepancies in cancer sequencing data continue to pose significant challenges for accurate mutation detection, potentially resulting in misdiagnoses and suboptimal treatment strategies. Although deep learning (DL) has emerged as a transformative approach for identifying and rectifying these errors, there remains a lack of comprehensive evaluation of DL architectures, performance benchmarks, and clinical translation. In this systematic review of 78 studies (2015–2024), We synthesize recent advancements in DL methodologies for identifying genomic discrepancies, demonstrating that convolutional and graph-based architectures currently achieve state-of-the-art performance in variant calling and tumor stratification. DL models reduce false-negative rates by 30%–40% compared to traditional pipelines, with methods such as MAGPIE prioritizing pathogenic variants with 92% accuracy. However, challenges such as data scarcity, batch effects, and the interpretability of “black-box” models persist. We propose a future research roadmap advocating federated learning to enhance data privacy and attention mechanisms to improve model transparency. By bridging bioinformatics and oncology, this review offers actionable insights to expedite the deployment of DL in precision cancer therapy.