Ghulam Mujtaba

Dr. Ghulam Mujtaba

orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
26 September 2022 in IEEE Access
Verified
Journal Article
Open access
GMGhulam Mujtaba
Ghulam Mujtaba
AMAdeel Malik
Adeel Malik
EREun-Seok Ryu
Eun-Seok Ryu
This paper proposes a novel lightweight thumbnail container-based summarization (LTC-SUM) framework for full feature-length videos. This framework generates a personalized keyshot summary for concurrent users by using the computational resource of the end-user device. State-of-the-art methods that acquire and process entire video data to generate video summaries are highly computationally intensive. In this regard, the proposed LTC-SUM method uses lightweight thumbnails to handle the complex process of detecting events. This significantly reduces computational complexity and improves communication and storage efficiency by resolving computational and privacy bottlenecks in resource-constrained end-user devices. These improvements were achieved by designing a lightweight 2D CNN model to extract features from thumbnails, which helped select and retrieve only a handful of specific segments. Extensive quantitative experiments on a set of full 18 feature-length videos (approximately 32.9 h in duration) showed that the proposed method is significantly computationally efficient than state-of-the-art methods on the same end-user device configurations. Joint qualitative assessments of the results of 56 participants showed that participants gave higher ratings to the summaries generated using the proposed method. To the best of our knowledge, this is the first attempt in designing a fully client-driven personalized keyshot video summarization framework using thumbnail containers for feature-length videos. Our code and trained models are publicly available at https://github.com/iamgmujtaba/LTC-SUM .

29 July 2023 in arXiv
Verified
Preprint
Open access
PDF file
Shabir AhmadShabir Ahmad
Shabir Ahmad
SUSabina Umirzakova
Sabina Umirzakova
GMGhulam Mujtaba
Ghulam Mujtaba
MAMuhammad Sadiq Amin
Muhammad Sadiq Amin
TWTaegkeun Whangbo
Taegkeun Whangbo
We are currently in a post-pandemic era in which life has shifted to a digital world. This has affected many aspects of life, including education and learning. Education 5.0 refers to the fifth industrial revolution in education by leveraging digital technologies to eliminate barriers to learning, enhance learning methods, and promote overall well-being. The concept of Education 5.0 represents a new paradigm in the field of education, one that is focused on creating a learner-centric environment that leverages the latest technologies and teaching methods. This paper explores the key requirements of Education 5.0 and the enabling technologies that make it possible, including artificial intelligence, blockchain, and virtual and augmented reality. We analyze the potential impact of these technologies on the future of education, including their ability to improve personalization, increase engagement, and provide greater access to education. Additionally, we examine the challenges and ethical considerations associated with Education 5.0 and propose strategies for addressing these issues. Finally, we offer insights into future directions for the development of Education 5.0, including the need for ongoing research, collaboration, and innovation in the field. Overall, this paper provides a comprehensive overview of Education 5.0, its requirements, enabling technologies, and future directions, and highlights the potential of this new paradigm to transform education and improve learning outcomes for students.

11 August 2018 in Wireless Personal Communications
Verified
Journal Article
Closed access
PDF file
GMGhulam Mujtaba
Ghulam Mujtaba
MTMuhammad Tahir
Muhammad Tahir
MSMuhammad Hanif Soomro
Muhammad Hanif Soomro

25 July 2017 in Epidemiology and Infection
Verified
Journal Article
Open access
PDF file
MAM. Angez
M. Angez
SSS. Shaukat
S. Shaukat
RZRabaab Zahra
Rabaab Zahra
MAM Mahbub Alam
M Mahbub Alam
SSS. Sharif
S. Sharif
SZS. S. Z. Zaidi
S. S. Z. Zaidi
Pakistan is at the verge of polio eradication but isolation of non-polio enteroviruses (NPEVs) from acute flaccid paralysis (AFP) cases may result in serious or even fatal outcome. Many enteroviruses share similar symptoms and epidemiology as is the case with poliovirus and coxsackievirus (CV). The present study was designed to genetically characterize coxsackievirus B (CV-B) serotypes isolated from non-polio acute flaccid paralytic children, as well as to understand their probable role in paralysis. A total of 63 (20·1%) out of 313 stool samples during 2013 were found positive for NPEVs in rhabdomyosarcoma cells. Only 24 (38·0%) NPEVs were typed as CV-B by microneutralization assay and were further characterized by sequencing of the viral protein 1 (VP1) gene. Molecular phylogenetic analyses classified the study strains into six coxsackievirus B serotypes (coxsackievirus B1 to B6) with their respective prototype strains with evidence of epidemiological linkage and distinct clusters. Moreover, four major differences were found within the amino acid sequences of BC-loop in VP1 of CV-B strains. In conclusion, this study presented the molecular evolutionary genetic overview and distinct phylogenetic pattern of CV-B isolates from AFP cases in Pakistan, and explored the possible link between CV-B infections and AFP cases. Furthermore, our data reveal that these viruses might contribute to the incidence of paralysis in population and there is need of time to establish an enterovirus surveillance system for better understanding of epidemiological and virological characteristics of NPEV infections associated with AFP cases in the country.

25 March 2020 in IEEE Access
Verified
Journal Article
Open access
GMGhulam Mujtaba
Ghulam Mujtaba
EREun-Seok Ryu
Eun-Seok Ryu
Movie trailers are prepared using a one-size-fits-all framework. These days, however, streaming platforms seek to overcome this problem and provide personalized trailers via the investigation of centralized server-side solutions. This can be achieved by analyzing personal user data, and can lead to two major issues: privacy violation and enormous demand in computational resources. This paper proposes an innovative, low-power, client-driven method to facilitate the personalized trailer generation process. It tackles the complex process of detecting personalized actions in real-time from lightweight thumbnail containers. The HTTP live streaming (HLS) server and client are locally configured to validate the proposed method. The system is designed to support a wide range of client hardware with different computational capabilities and has the flexibility to adapt to network conditions. To test the effectiveness of this method, twenty-five broadcast movies, specifically in the western and sports genres, are evaluated. To the best of our knowledge, this is the first-ever client-driven framework that uses thumbnail containers as input to facilitate the trailer generation process.

2 June 2025 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
GMGhulam Mujtaba
Ghulam Mujtaba
SKSunder Ali Khowaja
Sunder Ali Khowaja
KDKapal Dev
Kapal Dev
Social media has become integral to minors’ daily lives and is used for various purposes, such as making friends, exploring shared interests, and engaging in educational activities. However, the increase in screen time has also led to heightened challenges, including cyberbullying, online grooming, and exploitations posed by malicious actors. Traditional content moderation techniques have proven ineffective against exploiters’ evolving tactics. To address these growing challenges, we propose the EdgeAIGuard content moderation approach that is designed to protect minors from online grooming and various forms of digital exploitation. The proposed method comprises a multi-agent architecture deployed strategically at the network edge to enable rapid detection with low latency and prevent harmful content targeting minors. The experimental results show the proposed method is significantly more effective than the existing approaches.