Tariq Qayyum

Mr. Tariq Qayyum


Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
5 August 2024 in IEEE Open Journal of the Communications Society
Verified
Journal Article
Open access
Asadullah TariqAsadullah Tariq
Asadullah Tariq
MSMohamed Adel Serhani
Mohamed Adel Serhani
Farag SallabiFarag Sallabi
Farag Sallabi
EBEzedin S. Barka
Ezedin S. Barka
TQTariq Qayyum
Tariq Qayyum
Khaled ShuaibKhaled Shuaib
Khaled Shuaib
Federated Learning (FL) emerged as a significant advancement in the field of Artificial Intelligence (AI), enabling collaborative model training across distributed devices while maintaining data privacy. As the importance of FL and its application in various areas increased, addressing trustworthiness issues in its various aspects became crucial. In this survey, we provided a comprehensive overview of the state-of-the-art research on Trustworthy FL, exploring existing solutions and key foundations relevant to Trustworthiness in FL. There has been significant growth in the literature on trustworthy centralized Machine Learning (ML) and Deep Learning (DL). However, there is still a need for more focused efforts toward identifying trustworthiness pillars and evaluation metrics in FL. In this paper, we proposed a taxonomy encompassing five main classifications for Trustworthy FL, including Interpretability and Explainability, Transparency, Privacy and Robustness, Fairness, and Accountability. Each category represents a dimension of trust and is further broken down into different sub-categories. Moreover, we addressed trustworthiness in a Decentralized FL (DFL) setting. Communication efficiency is essential for ensuring Trustworthy FL. This paper also highlights the significance of communication efficiency within various Trustworthy FL pillars and investigates existing research on communication-efficient techniques across these pillars. Our survey comprehensively addresses trustworthiness challenges across all aspects within the Trustworthy FL settings. We also proposed a comprehensive architecture for Trustworthy FL, detailing the fundamental principles underlying the concept, and provided an in-depth analysis of trust assessment mechanisms. In conclusion, we identified key research challenges related to every aspect of Trustworthy FL and suggested future research directions. This comprehensive survey served as a valuable resource for researchers and practitioners working on the development and implementation of Trustworthy FL systems, contributing to a more secure and reliable AI landscape.

17 January 2020 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
Asad MalikAsad Malik
Asad Malik
ARAnis Rahman
Anis Rahman
TQTariq Qayyum
Tariq Qayyum
SRSri Devi Ravana
Sri Devi Ravana
The concept of smart farming has led to the use of technology to enhance agricultural productivity. With access to low-cost sensors and management systems, more farmers are adopting this technology to achieve sustainable growth. However, in literature, there are no simulation platforms to help researchers and users understand sensor deployment, and data collection and processing. In this paper, we propose a framework designed to provide a complete farming ecosystem. The toolkit facilitates users to simulate custom farming scenarios, specifically to identify sensor placement, coverage area, line of sight deployment, data gathering through relay mechanism or airborne systems, mobility models for mobile nodes, energy models for on-ground sensors and airborne vehicles, and backend computing support using fog computing paradigm. Furthermore, in most of the existing works network parameters are ignored, which can impact the overall performance of any deployed system. Therefore, the proposed framework also provides a benchmark in terms of transmission delay, packet delivery ratio, energy consumption, and system resources usage.

18 October 2023 in IEEE Access
Verified
Journal Article
Open access
MIMaria Iqbal
Maria Iqbal
Asadullah TariqAsadullah Tariq
Asadullah Tariq
MAMuhammad Adnan
Muhammad Adnan
IDIrfan Ud Din
Irfan Ud Din
TQTariq Qayyum
Tariq Qayyum
Privacy-preserving methods and techniques aim to safeguard the privacy of individuals and groups while facilitating data sharing for specific purposes. Federated Learning (FL) is a machine learning approach that allows multiple devices or systems to collaboratively train a model without directly sharing their data with each other or a central server. This paper proposes an Optimized Differential Privacy (ODP) approach to ensure the privacy of individual data points while enabling the extraction of valuable information. The proposed model is validated using the MNIST dataset and is analyzed with the FedAvg aggregator. Differential Privacy (DP) with FL is optimized by varying the noise and delta values. The analysis of data privacy is conducted in three phases: the first phase evaluates simple FL, and the second and third phases utilize different DP parameters to achieve optimized results. These optimized results show improved accuracy and privacy, confirming the efficacy of the proposed FL-ODP approach.

28 October 2022 in Journal of Cloud Computing
Verified
Journal Article
Open access
PDF file
TQTariq Qayyum
Tariq Qayyum
ZTzouheir trabelsi
zouheir trabelsi
Asad MalikAsad Malik
Asad Malik
Kadhim HayawiKadhim Hayawi
Kadhim Hayawi
The Industrial Internet of Things (IIoTs) is an emerging area that forms the collaborative environment for devices to share resources. In IIoT, many sensors, actuators, and other devices are used to improve industrial efficiency. As most of the devices are mobile; therefore, the impact of mobility can be seen in terms of low-device utilization. Thus, most of the time, the available resources are underutilized. Therefore, the inception of the fog computing model in IIoT has reduced the communication delay in executing complex tasks. However, it is not feasible to cover the entire region through fog nodes; therefore, fog node selection and placement is still the challenging task. This paper proposes a multi-level hierarchical fog node deployment model for the industrial environment. Moreover, the scheme utilized the IoT devices as a fog node; however, the selection depends on energy, path/location, network properties, storage, and available computing resources. Therefore, the scheme used the location-aware module before engaging the device for task computation. The framework is evaluated in terms of memory, CPU, scalability, and system efficiency; also compared with the existing approach in terms of task acceptance rate. The scheme is compared with xFogSim framework that is capable to handle workload upto 1000 devices. However, the task acceptance ratio is higher in the proposed framework due to its multi-tier model. The workload acceptance ratio is 85% reported with 3000 devices; whereas, in xFogsim the ratio is reduced to approx. 68%. The primary reason for high workload acceptation is that the proposed solution utilizes the unused resources of the user devices for computations.

22 December 2021 in Sensors
Verified
Journal Article
Open access
PDF file
TQTariq Qayyum
Tariq Qayyum
ZTzouheir trabelsi
zouheir trabelsi
Asad MalikAsad Malik
Asad Malik
Kadhim HayawiKadhim Hayawi
Kadhim Hayawi
Unmanned aerial vehicles (UAVs) play an important role in facilitating data collection in remote areas due to their remote mobility. The collected data require processing close to the end-user to support delay-sensitive applications. In this paper, we proposed a data collection scheme and scheduling framework for smart farms. We categorized the proposed model into two phases: data collection and data scheduling. In the data collection phase, the IoT sensors are deployed randomly to form a cluster based on their RSSI. The UAV calculates an optimum trajectory in order to gather data from all clusters. The UAV offloads the data to the nearest base station. In the second phase, the BS finds the optimally available fog node based on efficiency, response rate, and availability to send workload for processing. The proposed framework is implemented in OMNeT++ and compared with existing work in terms of energy and network delay.

18 September 2020 in IEEE Transactions on Sustainable Computing
Verified
Journal Article
Closed access
Asad MalikAsad Malik
Asad Malik
TQTariq Qayyum
Tariq Qayyum
ARAnis Rahman
Anis Rahman
MKMuazzam A. Khan
Muazzam A. Khan
OKOsman Khalid
Osman Khalid
Samee U. KhanSamee U. Khan
Samee U. Khan
Streaming large amounts of data to cloud data centers cause network congestion resulting in high network and energy consumption. The concept of fog computing is introduced to reduce workload from backbone networks and support delay-sensitive Internet of Things (IoT) applications. The concept places compute, storage, and network services closer to the source of the requests. In general fog-based simulators are used for better understanding and optimum fog resource allocation. Unfortunately, most of the simulators lack core features like network delay, latency, packet error rate, energy consumption, and distributed fog node management. In this paper, we propose a fog simulation framework termed as xFogSim to support latency-sensitive applications at the fog layer with multi-objective optimization to trade-off cost, availability, and performance among the fog federation. Moreover, during peak load, the framework provides locality-aware distributed broker node management that enables borrowing resources from nearby fog locations to meet service and energy requirements. The results show that the framework is lightweight, configurable, and scalable, capable of handling a large number of user requests using dynamic resource provisioning across the fog federation.