Muhammad Usman Shams

Muhammad Usman Shams

Auto-generated profile, based on publicly available information

Muhammad Usman Shams

Institute of Computer & Software Engineering, Khwaja Fareed University of Engineering and Information Technology, Pakistan

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
4 September 2025 in Journal of Clinical Practice and Medical Research
Verified
Journal Article
Open access
PDF file
GDGhulam Muhayyu Din
Ghulam Muhayyu Din
MSMuhammad Usman Shams
Muhammad Usman Shams
ARAhmad Nesaar Rahmani
Ahmad Nesaar Rahmani
ARAbdul Rehman
Abdul Rehman
MAMuhammad Abdullah Ahmed
Muhammad Abdullah Ahmed
MSMuhammad Adnan Shoukat
Muhammad Adnan Shoukat
The emergence of digital twin technology in medicine signifies a paradigm shift toward personalized healthcare and precision therapeutics. A human digital twin (HDT) is a dynamic, virtual representation of an individual’s physiological state, constructed and continuously updated via real-time data streams from wearable sensors, advanced imaging, and molecular diagnostics. This paper comparatively analyses the capacity of HDTs to enable high-fidelity simulation of patient-specific disease conditions, thereby optimizing therapeutic intervention, surgical planning, and predictive health management. By integrating advancements in artificial intelligence, machine learning, and the Internet of Things (IoT), HDTs facilitate the modeling of complex, multi-scale biological interactions, from genetic and molecular pathways to systemic organ function. We review current computational frameworks for HDT development, address critical challenges including data integration, model interoperability, and validation, and consider the transformative impact on clinical workflows. Concurrently, we examine the imperative ethical considerations and data security protocols required for responsible clinical deployment. The realization of personal digital twins holds the potential to revolutionize medical practice by facilitating truly individualized therapeutic strategies, improving patient outcomes, and accelerating biomedical discovery.

1 December 2024 in Scientia. Technology, Science and Society
Verified
Journal Article
Open access
PDF file
ASAhmad Sarwar
Ahmad Sarwar
DSDua Sarwar
Dua Sarwar
MSMuhammad Usman Shams
Muhammad Usman Shams
MIMuhammad Islam
Muhammad Islam
MAMuhammad Jahanzaib Afzal
Muhammad Jahanzaib Afzal
AYAmsh Bin Yasir
Amsh Bin Yasir
This paper proposes a new problem diagnosis method for smart and heavy manufacturing bearings. Instead of feature extraction, the suggested method processes defect signals with a convolutional neural network (CNN). It solves the problems of weak fault signals and high background noise, which lower diagnostic accuracy. The approach also quantifies diagnostic results, making fault severity assessment easier. To eliminate manual knowledge in existing methods, a one-dimensional convolutional deep neural network model is constructed to intelligently derive defect characteristics from intelligent manufacturing industry 4.0 bearing vibration data. The accuracy of this method was compared to wavelet threshold denoising and ensemble empirical mode decomposition data denoising for diagnostic recognition. This technology has engineering merit in identifying smart industry 4.0/5.0 bearing concerns.

27 October 2026 in European Journal of Applied Science, Engineering and Technology
Verified
Journal Article
Open access
MAMuhammad Abdullah Ahmed
Muhammad Abdullah Ahmed
MSMuhammad Usman Shams
Muhammad Usman Shams
ZHZeenat Hassan
Zeenat Hassan
ZHZakriya Hussain
Zakriya Hussain
MSMuhammad Jawad Shams
Muhammad Jawad Shams
MIMuhammad Rizwan Iqbal
Muhammad Rizwan Iqbal
Automated support systems need to be able to tell the difference between normal transactional conversation and actual distress, and be able to recognize when a thing has fallen into a bad state, for the purposes of human intervention. We propose a decision-support pipeline, Multi-Signal Dynamic Escalation Detection (MS-DED), that combines multilingual transformer sentiment, typographical hints, a threat lexicon, an exponentially weighted frustration trajectory, and suppressing benign commercial terms from the context. A two-part policy: empathy-first (at a lower threshold) and human takeover (at a higher threshold) are driven by a weighted score. On the reported 3,000-message benchmark (1,000 escalation, 1,000 benign keyword-trap, and 1,000 normal messages), MS-DED achieves precision 0.9953, recall 0.8410, F1 0.9117, ROC-AUC 0.9960, PR-AUC 0.9925, and a 0.30% trap false-alarm rate. The other operational protocol was reported with a precision of 0.934, a recall of 0.912, an F1 of 0.923, and 4.2% of trap false alarms. A threshold-grid snapshot reports F1=0.925 at and . Illustrative traces indicate that it is 2.3 turns ahead of reactive keyword escalation, and workload estimates estimate 342 hours of agent time saved with 10,000 monthly tickets. These results are based on separate protocols and simulations, and do not form part of any interchangeable results or any independently verified production results. It is an auditable policy that implements temporal affect tracking and domain specific false-positive control. Further validation on the conversation level is still required.