Afzaal Hussain
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Afzaal Hussain has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Abdul Rauf Baig
Department of Information Systems, College of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh, Saudi Arabia
2 shared publications - Kashif Zafar
National University of Computer and Emerging Sciences, Lahore, Pakistan
2 shared publications ChenSi Zhuo
Hunan University of Arts and Science
1 shared publicationDing Luai
Hunan Institute of Science and Engineering
1 shared publication- Faria Kanwal
Department of Computer Science, Faculty of Engineering and Technology, Lahore College for Women University, Lahore 54600, Pakistan
1 shared publication - Fengli Zhang
School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 610054, China
1 shared publication
Latest Publications
- Open Access
- 7 October 2026
- Published by Cosmos S.A. in Global Nest Journal
Firm-Level Digital and Sustainability Indicators and Sustainability Outcomes: Evidence from Chinese Listed Industrial Firms under Environmental Regulation
This study examined the associations between digital and organizational capabilities and sustainability outcomes among 200 industrial firms listed on the Shanghai Stock Exchange in China from 2013 to 2023. The study applied the theory of Dynamic Capabilities and Institutional Theory to explore the digital transformation, corporate sustainability culture, cultural capital and digital media literacy, and their relationship with environmental performance and sustainability innovation. Media coverage intensity and the financial support of sustainability initiatives were investigated as possible indirect pathways and environmental regulation as a moderating institutional condition. Firm and year fixed-effects models were supplemented with dynamic System GMM and bootstrapped indirect-effect analysis, moderation analysis, and robustness specifications. The findings indicate that digital transformation, corporate sustainability culture, and digital media literacy were positively associated with both environmental performance and sustainability innovation, whereas cultural capital was positively associated with sustainability innovation but not environmental performance. Media coverage intensity and financial support for sustainability initiatives showed statistically supported indirect associations for digital transformation, corporate sustainability culture, and digital media literacy, but not cultural capital. Environmental regulation generally strengthened the positive capability–sustainability associations, while its negative interaction with cultural capital for sustainability innovation provided only tentative evidence of a weakening association, as the interaction was significant only at the 10% level. These findings contribute to the Dynamic Capabilities Theory by bringing into focus capability-specific sustainability associations and the Institutional Theory by establishing differentiated regulatory conditions. The indirect effects and relationships estimated are therefore viewed as associative in nature for the purpose of the observational panel design.
- 7 October 2026
- Published by Cosmos S.A. in Global Nest Journal
Open AccessFirm-Level Digital and Sustainability Indicators and Sustainability Outcomes: Evidence from Chinese Listed Industrial Firms under Environmental Regulation
This study examined the associations between digital and organizational capabilities and sustainability outcomes among 200 industrial firms listed on the Shanghai Stock Exchange in China from 2013 to 2023. The study applied the theory of Dynamic Capabilities and Institutional Theory to explore the digital transformation, corporate sustainability culture, cultural capital and digital media literacy, and their relationship with environmental performance and sustainability innovation. Media coverage intensity and the financial support of sustainability initiatives were investigated as possible indirect pathways and environmental regulation as a moderating institutional condition. Firm and year fixed-effects models were supplemented with dynamic System GMM and bootstrapped indirect-effect analysis, moderation analysis, and robustness specifications. The findings indicate that digital transformation, corporate sustainability culture, and digital media literacy were positively associated with both environmental performance and sustainability innovation, whereas cultural capital was positively associated with sustainability innovation but not environmental performance. Media coverage intensity and financial support for sustainability initiatives showed statistically supported indirect associations for digital transformation, corporate sustainability culture, and digital media literacy, but not cultural capital. Environmental regulation generally strengthened the positive capability–sustainability associations, while its negative interaction with cultural capital for sustainability innovation provided only tentative evidence of a weakening association, as the interaction was significant only at the 10% level. These findings contribute to the Dynamic Capabilities Theory by bringing into focus capability-specific sustainability associations and the Institutional Theory by establishing differentiated regulatory conditions. The indirect effects and relationships estimated are therefore viewed as associative in nature for the purpose of the observational panel design.
- Open Access
- 22 October 2025
- Published by MDPI AG in Information
- Vol. 16 (11) , 928
Optimizer-Aware Fine-Tuning of Whisper Small with Low-Rank Adaption: An Empirical Study of Adam and AdamW
Whisper is a transformer-based multilingual model that has illustrated state-of-the-art behavior in numerous languages. However, the efficiency remains persistent with the limited computational resources. To address this issue, an experiment was performed on librispeech-train-clean-100 for training purposes. The test-clean set was utilized to evaluate its performance. To enhance efficiency and to cater the computational needs, a parameter-efficient fine-tuning technique, i.e., Low-Rank Adaptation, was employed to add a limited number of trainable parameters into the frozen layers of the model. The results showed that Low-Rank Adaptation attained excellent Automatic Speech Recognition results while using fewer computational resources, showing its effectiveness for resource-saving adaptation. The research work emphasizes the promise of Low-Rank Adaptation as a lightweight and scalable fine-tuning strategy for large speech models using a transformer architecture. The baseline Whisper Small model achieved a word error rate of 16.7% without any parameter-efficient adaptation. In contrast, the Low-Rank Adaptation enhanced fine-tuned model achieved a lower word error rate of 6.08%, demonstrating the adaptability of the proposed parameter-efficient approach.
- 22 October 2025
- Published by MDPI AG in Information
- Vol. 16 (11) , 928
Open AccessOptimizer-Aware Fine-Tuning of Whisper Small with Low-Rank Adaption: An Empirical Study of Adam and AdamW
Whisper is a transformer-based multilingual model that has illustrated state-of-the-art behavior in numerous languages. However, the efficiency remains persistent with the limited computational resources. To address this issue, an experiment was performed on librispeech-train-clean-100 for training purposes. The test-clean set was utilized to evaluate its performance. To enhance efficiency and to cater the computational needs, a parameter-efficient fine-tuning technique, i.e., Low-Rank Adaptation, was employed to add a limited number of trainable parameters into the frozen layers of the model. The results showed that Low-Rank Adaptation attained excellent Automatic Speech Recognition results while using fewer computational resources, showing its effectiveness for resource-saving adaptation. The research work emphasizes the promise of Low-Rank Adaptation as a lightweight and scalable fine-tuning strategy for large speech models using a transformer architecture. The baseline Whisper Small model achieved a word error rate of 16.7% without any parameter-efficient adaptation. In contrast, the Low-Rank Adaptation enhanced fine-tuned model achieved a lower word error rate of 6.08%, demonstrating the adaptability of the proposed parameter-efficient approach.
- 26 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 71 (4) , 12215-12225
VDO-Fit: Energy-Efficient OFDM Scheduling for Deadline-Constrained Transmission in Vehicular Networks
Efficient and timely data transmission is critical in real-time systems with limited battery capacity, such as consumer electronics and vehicular communication systems, especially in the dynamic and fluctuating environments of OFDM-based networks. In this study, we address the problem of minimizing the total transmission energy required to transmit a fixed-size data payload within a strict delay constraint over a multi-slot Orthogonal Frequency Division Multiplexing (OFDM) channel. The inherent uncertainty of wireless channel gains motivates the formulation of a finite-horizon stochastic dynamic optimization problem, where transmission decisions must adapt to time-varying subcarrier conditions. To overcome the intractability of classical dynamic programming due to high-dimensional state spaces and expectation evaluations, we propose Vehicular Deadline-Oriented Fading-Informed Transmission (VDO-Fit), a surrogate-based scheduling system with low complexity. VDO-Fit replaces the stochastic expectation with a deterministic rate-fit loss function and performs real-time rate allocation per slot by gradient-based optimization of a scalar parameter β. The method is inherently GPU-accelerated and adapts the transmission rates according to the current channel state, the remaining data and the remaining deadline budget. We derive two theorems that determine the convergence and the probability of success of the deadline and provide three supporting propositions that analyse the feasibility, the performance limits and the algorithmic complexity. Comprehensive simulations confirm that VDO-Fit achieves the lowest energy consumption in all tested scenarios, including variations in packet size, number of subcarriers, time slots and mobility level. In contrast to the basic strategies, the failure rate for tight deadlines is close to zero. These results confirm the practical feasibility and theoretical soundness of the proposed scheduler for OFDM real-time systems in vehicles. The proposed VDO-Fit framework not only improves compliance with deadlines and energy efficiency but is also suitable for real-time use in vehicle networks.
- 26 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 71 (4) , 12215-12225
VDO-Fit: Energy-Efficient OFDM Scheduling for Deadline-Constrained Transmission in Vehicular Networks
Efficient and timely data transmission is critical in real-time systems with limited battery capacity, such as consumer electronics and vehicular communication systems, especially in the dynamic and fluctuating environments of OFDM-based networks. In this study, we address the problem of minimizing the total transmission energy required to transmit a fixed-size data payload within a strict delay constraint over a multi-slot Orthogonal Frequency Division Multiplexing (OFDM) channel. The inherent uncertainty of wireless channel gains motivates the formulation of a finite-horizon stochastic dynamic optimization problem, where transmission decisions must adapt to time-varying subcarrier conditions. To overcome the intractability of classical dynamic programming due to high-dimensional state spaces and expectation evaluations, we propose Vehicular Deadline-Oriented Fading-Informed Transmission (VDO-Fit), a surrogate-based scheduling system with low complexity. VDO-Fit replaces the stochastic expectation with a deterministic rate-fit loss function and performs real-time rate allocation per slot by gradient-based optimization of a scalar parameter β. The method is inherently GPU-accelerated and adapts the transmission rates according to the current channel state, the remaining data and the remaining deadline budget. We derive two theorems that determine the convergence and the probability of success of the deadline and provide three supporting propositions that analyse the feasibility, the performance limits and the algorithmic complexity. Comprehensive simulations confirm that VDO-Fit achieves the lowest energy consumption in all tested scenarios, including variations in packet size, number of subcarriers, time slots and mobility level. In contrast to the basic strategies, the failure rate for tight deadlines is close to zero. These results confirm the practical feasibility and theoretical soundness of the proposed scheduler for OFDM real-time systems in vehicles. The proposed VDO-Fit framework not only improves compliance with deadlines and energy efficiency but is also suitable for real-time use in vehicle networks.
- Open Access
Sensor-Based Gym Physical Exercise Recognition: Data Acquisition and Experiments
Automatic tracking and quantification of exercises not only helps in motivating people but also contributes towards improving health conditions. Weight training, in addition to aerobic exercises, is an important component of a balanced exercise program. Excellent trackers are available for aerobic exercises but, in contrast, tracking free weight exercises is still performed manually. This study presents the details of our data acquisition effort using a single chest-mounted tri-axial accelerometer, followed by a novel method for the recognition of a wide range of gym-based free weight exercises. Exercises are recognized using LSTM neural networks and the reported results confirm the feasibility of the proposed approach. We train and test several LSTM-based gym exercise recognition models. More specifically, in one set of experiments, we experiment with separate models, one for each muscle group. In another experiment, we develop a universal model for all exercises. We believe that the promising results will potentially contribute to the vision of an automated system for comprehensive monitoring and analysis of gym-based exercises and create a new experience for exercising by freeing the exerciser from manual record-keeping.
Open AccessSensor-Based Gym Physical Exercise Recognition: Data Acquisition and Experiments
Automatic tracking and quantification of exercises not only helps in motivating people but also contributes towards improving health conditions. Weight training, in addition to aerobic exercises, is an important component of a balanced exercise program. Excellent trackers are available for aerobic exercises but, in contrast, tracking free weight exercises is still performed manually. This study presents the details of our data acquisition effort using a single chest-mounted tri-axial accelerometer, followed by a novel method for the recognition of a wide range of gym-based free weight exercises. Exercises are recognized using LSTM neural networks and the reported results confirm the feasibility of the proposed approach. We train and test several LSTM-based gym exercise recognition models. More specifically, in one set of experiments, we experiment with separate models, one for each muscle group. In another experiment, we develop a universal model for all exercises. We believe that the promising results will potentially contribute to the vision of an automated system for comprehensive monitoring and analysis of gym-based exercises and create a new experience for exercising by freeing the exerciser from manual record-keeping.
- Open Access
- 13 May 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 74168-74179
Fog-Centric IoT Based Framework for Healthcare Monitoring, Management and Early Warning System
Internet of things (IoT) and machine learning based systems incorporating smart wearable technology are rapidly evolving to monitor and manage healthcare and physical activities. This paper is focused on the proposition of a fog-centric wireless, real-time, smart wearable and IoT-based framework for ubiquitous health and fitness analysis in a smart gym environment. The proposed framework aims to aid in the health and fitness industry based on body vitals, body movement and health related data. The framework is expected to assist athletes, trainers and physicians with the interpretation of multiple physical signs and raise alerts in case of any health hazard. We proposed a method to collect and analyze exercise specific data which can be used to measure exercise intensity and its benefit to athlete's health and serve as recommendation system for upcoming athletes. We determined the validity of the proposed framework by giving a six weeks workout plan with six days a week for workout activity targeting all muscles followed by one day for recovery. We recorded the electrocardiogram, heart rate, heart rate variability, breath rate, and determined athlete's movement using a 3D-acceleration. The collected data in the research is used in two modules. A Health zone module implemented on body vitals data which categorizes athlete's health state into various categories. Hzone module is responsible for health hazards identification and alarming. Outstandingly, the Hzone module is able to identify an athlete's physical state with 97% accuracy. A gym activity recognition (GAR) module is implemented to recognize workout activity in real-time using body movements and body vitals data. The purpose of the GAR module is to collect and analyze exercise specific data. The GAR module achieved an accuracy of above 89% on athlete independent model based on muscle group.
- 13 May 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 74168-74179
Open AccessFog-Centric IoT Based Framework for Healthcare Monitoring, Management and Early Warning System
Internet of things (IoT) and machine learning based systems incorporating smart wearable technology are rapidly evolving to monitor and manage healthcare and physical activities. This paper is focused on the proposition of a fog-centric wireless, real-time, smart wearable and IoT-based framework for ubiquitous health and fitness analysis in a smart gym environment. The proposed framework aims to aid in the health and fitness industry based on body vitals, body movement and health related data. The framework is expected to assist athletes, trainers and physicians with the interpretation of multiple physical signs and raise alerts in case of any health hazard. We proposed a method to collect and analyze exercise specific data which can be used to measure exercise intensity and its benefit to athlete's health and serve as recommendation system for upcoming athletes. We determined the validity of the proposed framework by giving a six weeks workout plan with six days a week for workout activity targeting all muscles followed by one day for recovery. We recorded the electrocardiogram, heart rate, heart rate variability, breath rate, and determined athlete's movement using a 3D-acceleration. The collected data in the research is used in two modules. A Health zone module implemented on body vitals data which categorizes athlete's health state into various categories. Hzone module is responsible for health hazards identification and alarming. Outstandingly, the Hzone module is able to identify an athlete's physical state with 97% accuracy. A gym activity recognition (GAR) module is implemented to recognize workout activity in real-time using body movements and body vitals data. The purpose of the GAR module is to collect and analyze exercise specific data. The GAR module achieved an accuracy of above 89% on athlete independent model based on muscle group.