Shazia Samoon
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Shazia Samoon has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Yasir Arfat Malkani
Institute of Mathematics and Computer Science, University of Sindh, Jamshoro, Pakistan
2 shared publications - Atia Bano Memon
Department of Computer Science at the University of Sindh, Jamshoro, Pakistan
1 shared publication - Farah Naveen Issani
Department of Information Technology Center, Sindh Agricultural University Tandojam, 70060, Pakistan
1 shared publication - Gulsher Laghari
Institute of Mathematics and Computer Science, University of Sindh, Jamshoro, Pakistan
1 shared publication Saima Sheikh
Information Technology Centre, Sindh Agriculture University, Tandojam, Pakistan
1 shared publication- Syed Akbar Ali Shah Akbar
Institute of Mathematics and Computer Science, University of Sindh, Jamshoro, Pakistan
1 shared publication
Latest Publications
- Open Access
- 1 August 2025
- Published by VFAST Research Platform in VAWKUM Transactions on Computer Sciences
- Vol. 13 (2) , 36-49
HAR-AttenNet: Multi-Head Transformer for Precise Human Activity Recognition Using Wearable Devices
Human Activity Recognition has become inevitable in wearable technology in healthcare and fitness tracking applications. Precise recognition of daily routine human activities using wearable sensors remains a challenging task due to sensor modality, placement, and environmental factors. Indeed, Machine Learning and Deep Learning models have become robust in human activity recognition, yet these face numerous challenges in precisely recognizing the daily human activities. One major challenge is the variability in sensors readings where the same activity may lead to different sensor readings, intra-class variability, as different people perform the same activity differently or use different devices. To address this, we propose a multi-head transformer model with a multi-head attention mechanism that explicitly handles the intra-class variability. We demonstrate that the multi-head Transformer model exhibits enhanced robustness and performs better even in the face of such variability, although variability is a major problem in the popular PAMAP2 dataset, since it directly impacts the performance of deep learning models.
- 1 August 2025
- Published by VFAST Research Platform in VAWKUM Transactions on Computer Sciences
- Vol. 13 (2) , 36-49
Open AccessHAR-AttenNet: Multi-Head Transformer for Precise Human Activity Recognition Using Wearable Devices
Human Activity Recognition has become inevitable in wearable technology in healthcare and fitness tracking applications. Precise recognition of daily routine human activities using wearable sensors remains a challenging task due to sensor modality, placement, and environmental factors. Indeed, Machine Learning and Deep Learning models have become robust in human activity recognition, yet these face numerous challenges in precisely recognizing the daily human activities. One major challenge is the variability in sensors readings where the same activity may lead to different sensor readings, intra-class variability, as different people perform the same activity differently or use different devices. To address this, we propose a multi-head transformer model with a multi-head attention mechanism that explicitly handles the intra-class variability. We demonstrate that the multi-head Transformer model exhibits enhanced robustness and performs better even in the face of such variability, although variability is a major problem in the popular PAMAP2 dataset, since it directly impacts the performance of deep learning models.
- Open Access
- 7 December 2023
- Published by Asian Academy of Business and Social Science Research in The Asian Bulletin of Big Data Management
- Vol. 3 (2) , 1-17
Perceptions of Students towards the Implementation of Pervasive Learning at Higher Education Institutes: A Data Driven Case Study
The current paper deals with the perceptions of students towards the adoption of pervasive learning paradigm at the higher education institutions of Sindh region of Pakistan. Owing to the various drawbacks of Face-to-Face learning paradigm such as time and place dependency and limited access to the distributed and student specific resources, pervasive learning is currently being adopted at higher education institutes throughout world to offer context-aware and learner specific education. However, in the developing countries such as Pakistan, adoption of pervasive learning is still in incepting stage. In this regard, the current study is conducted in three stages. Firstly, a pervasive learning acceptance model is constructed to identify the relevant constructs. Following this, a Moodle-based learning management system (SUCL LMS) is developed. Finally, the usability testing of developed platform is conducted through a well-structured questionnaire from the students of distant rural area campus of well-established university in Sindh region of Pakistan. The study employs a quantitative method whereby SPSS and AMOS software are used to analyze the resultant data. The results of this study indicate that context awareness, adaptability, facilitating conditions, personalization, social influence, effort expectancy, and performance expectancy are the factors that influence the adoption of pervasive learning paradigm at the higher education institutes of Pakistan
- 7 December 2023
- Published by Asian Academy of Business and Social Science Research in The Asian Bulletin of Big Data Management
- Vol. 3 (2) , 1-17
Open AccessPerceptions of Students towards the Implementation of Pervasive Learning at Higher Education Institutes: A Data Driven Case Study
The current paper deals with the perceptions of students towards the adoption of pervasive learning paradigm at the higher education institutions of Sindh region of Pakistan. Owing to the various drawbacks of Face-to-Face learning paradigm such as time and place dependency and limited access to the distributed and student specific resources, pervasive learning is currently being adopted at higher education institutes throughout world to offer context-aware and learner specific education. However, in the developing countries such as Pakistan, adoption of pervasive learning is still in incepting stage. In this regard, the current study is conducted in three stages. Firstly, a pervasive learning acceptance model is constructed to identify the relevant constructs. Following this, a Moodle-based learning management system (SUCL LMS) is developed. Finally, the usability testing of developed platform is conducted through a well-structured questionnaire from the students of distant rural area campus of well-established university in Sindh region of Pakistan. The study employs a quantitative method whereby SPSS and AMOS software are used to analyze the resultant data. The results of this study indicate that context awareness, adaptability, facilitating conditions, personalization, social influence, effort expectancy, and performance expectancy are the factors that influence the adoption of pervasive learning paradigm at the higher education institutes of Pakistan