Yasir Shahzad

Yasir Shahzad

Auto-generated profile, based on publicly available information

Yasir Shahzad

Department of Computer Science, University of Peshawar, Peshawar, Pakistan

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
20 February 2025 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
HFHaleem Farman
Haleem Farman
YSYasir Shahzad
Yasir Shahzad
BJBilal Jan
Bilal Jan
MNMoustafa M. Nasralla
Moustafa M. Nasralla
KSKaram M. Sallam
Karam M. Sallam
AJAbbas Jamalipour
Abbas Jamalipour
Machine Learning (ML) with 5G technology has revolutionized smart healthcare. It has helped improve the quality of care, such as real-time analysis, decision-making, patient monitoring, and personalized treatments. In this paper, a 5G aware real-time diabetes prediction framework is proposed using optimized Bidirectional Long Short-Term Memory (Bi-LSTM) with Deep Reinforcement Learning (DRL). Bi-LSTM can analyze time-series data in forward and backward passes on patient health metrics, such as Blood Glucose (BG) levels of a diabetic patient, to identify patterns and trends and make predictions about future health outcomes. A local dataset using a wearable sensor is collected of 10 Type-2 diabetic patients, encompassing daily BG levels at different times, alongside additional parameters such as blood pressure and body weight. The proposed framework leverages a dataset of 1,830 data points to forecast glucose levels for the following day. It also harnesses DRL to improve and optimize the model’s future predictive performance. The obtained results are evaluated with other ML algorithms to validate the effectiveness of the proposed framework, which shows an improvement from 93.1% to 98.6% accuracy. The patient’s diabetic condition is categorized using the Surveillance Error Grid (SEG) to increase the clinical impact of glucose prediction and make informed decisions. The results show that Bi-LSTM-DRL is an effective approach to predicting glucose levels in real-time and can adapt to health-related changes and optimize its predictions accordingly.

19 August 2022 in IEEE Access
Verified
Journal Article
Open access
YSYasir Shahzad
Yasir Shahzad
HJHuma Javed
Huma Javed
HFHaleem Farman
Haleem Farman
ZKZahid Khan
Zahid Khan
MNMoustafa M. Nasralla
Moustafa M. Nasralla
AKAnis Koubaa
Anis Koubaa
The Internet of Healthcare Things has significantly altered traditional patient-doctor relationships by allowing essential healthcare treatment from the comfort of one’s home. The wireless body area network is an IEEE 802.15.6 standard that focuses on healthcare data, necessitating various cross-layer and thermal-aware protocols. However, most cross-layer protocols have long convergence delays and a single failure point. Moreover, these protocols exploit excessive broadcasts and handshake acknowledgments, causing communication and processing overheads. Furthermore, thermal-aware protocols focus on thermal variations, disperse data collection, and do not support cross-layer techniques. To address these limitations, this study proposes an optimal distributive cross-layer and thermal-aware convergecast protocol. The proposed protocol enforces a novel hybrid convergecast using probability and both minimum attenuation strategies to collect data from leaf nodes to the root to improve data flow and adaptability in the network. In addition, it accelerates the convergence process by reducing recurrent broadcasts and unnecessary acknowledgments, resulting in improved energy efficiency and thermal control. The proposed protocol supports a distributive hierarchy by establishing multiple parent-child relationships to avoid a single root point failure. A multi-parameter maximum benefit-cost function is used to calculate the next hop according to the extracted weights. Packet loss probability validates the number and sequence of packets received at the sink node. The simulation results demonstrate that cross-layer and thermal-aware protocols can coexist effectively. The proposed protocol reduces delays to 19.4%, improves throughput from 8% to 13.75%, and retains a packet loss probability of 0.3% by keeping the thermal rise within bounds.