ZAZahangir Alam

Zahangir Alam

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Zahangir Alam has a total of 17 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • A Graph-Assisted Digital-Twin-Driven Multiagent Shared Offloading for Internet of Vehicles

    by Zahangir Alam, Suryaia Rahman, Asif Bin Khaled, Ashraful Islam, Abbas Jamalipour

    Vehicular Edge Computing (VEC) allows vehicles to process part of the tasks locally at the network edge while offloading the rest of the tasks to a centralized cloud server for processing. A massive volume of tasks generated by the Internet of Vehicles (IoVs) leads to buffer overflow that causes higher latency. Elevating latency, in turn, can increase network energy consumption. Both higher latency and energy consumption lead to a degradation of network performance. Therefore, VEC design requires a balance between latency and energy consumption tradeoff. To reduce overwhelming amount of offloading to edge servers, a cooperative cluster-based shared offloading strategy has been proposed in this work. We use digital twin technology in VEC for managing and adapting to environmental dynamic changes. Then, we leverage Lyapunov optimization to transform the stochastic offloading problem into a more manageable deterministic form. Finally, we present a decentralized coordination graph (CG)-driven Lyapunov-based multi-agent deep deterministic policy gradient (CG-LyMADDPG) algorithm that trains agents towards energy efficient optimal offloading policy while maintaining queue stability at a maximum delay constraint. The experimental result shows that the proposed learning significantly outperforms the baseline algorithms for energy savings while maintain queue stability.


  • Open Access

    Segment Anything Model (SAM 2) Unveiled: Functionality, Applications, and Practical Implementation Across Multiple Domains

    by Jahanggir Hossain Setu, Mahmudul Islam, Syed Tangim Pasha, Nabarun Halder, Ekram Hossain, Asif Mahmud, Ashraful Islam, Zahangir Alam, M. Ashraful Amin

    Segment Anything Model 2 (SAM 2) is a state-of-the-art development by Meta AI Research, designed to address the limitations of its predecessor, SAM, particularly in the realm of video segmentation. SAM 2 employs a transformer-based architecture enhanced with streaming memory, enabling real-time processing for both images and videos. This advancement is important given the exponential growth of multimedia content and the subsequent demand for efficient video analysis. Utilizing the SA-V dataset, SAM 2 excels in handling the intricate spatio-temporal dynamics inherent in video data, ensuring accurate and efficient segmentation. Key features of SAM 2 include its ability to provide real-time segmentation with minimal user interaction, maintaining robust performance even in dynamic and cluttered visual environments. This study provides a comprehensive overview of SAM 2, detailing its architecture, functionality, and diverse applications. It further explores the model's potential in improving practical implementations across various domains, emphasizing its significance in advancing real-time video analysis.


  • Multiagent Best Routing in High-Mobility Digital-Twin-Driven Internet of Vehicles (IoV)

    by Zahangir Alam, Komal S. Khan, Abbas Jamalipour

    Low-delay high-gain optimal multihop routing path is crucial to guarantee both the latency and reliability requirements for infotainment services in the high-mobility Internet of Vehicles (IoV) subject to queue stability. The high mobility in multihop IoV reduces reliability and energy efficiency, and becomes bottleneck for the optimal route solution using classical optimization methods. To a great extent, deep reinforcement learning (DRL)-based method is not applicable in IoV environment because of the continuously changing topology and space complexity, which grows exponentially with the number of state variables as well as the relaying hops. Usually, in multihop scenario, network reliability and latency are affected by mobility as well as average hop count, which limit the vehicle-to-vehicle (V2V) link connectivity. To cope with this problem, in this article, we formulate a minimum hop count delay-sensitive buffer-aided optimization problem in a dynamic complex multihop vehicular topology using a digital twin-enabled dynamic coordination graph (DCG). Particularly, for the first time, a DCG-based multiagent deep deterministic policy gradient (DCG-MADDPG) decentralized algorithm is proposed that combines the advantage of DCG and MADDPG to model continuously changing topology and find the optimal routing solutions by cooperative learning in the aforementioned communications. The proposed DCG-MADDPG coordinated learning trains each agent toward highly reliable and low-latency optimal decision-making path solutions while maintaining queue stability and convergence on the way to a desired state. Experimental results reveal that the proposed coordinated learning algorithm outperforms the existing learning in terms of energy consumption and latency at less computational complexity.


  • Multi-Agent DRL-Based Hungarian Algorithm (MADRLHA) for Task Offloading in Multi-Access Edge Computing Internet of Vehicles (IoVs)

    by Zahangir Alam, Abbas Jamalipour

    This paper investigates the computation offloading problem in a high mobility internet of vehicles (IoVs) environment, aiming to guarantee latency, energy consumption, and payment cost requirements. Both moving and parked vehicles are utilized as fog nodes. Vehicles in high mobility environments need collaborative interactions in a decentralized manner for better network performances, where agent action space grows exponentially with the number of vehicles. The vehicular mobility introduces additional dynamicity in the network, and the learning agent requires a joint cooperative behavior for establishing convergence. The traditional deep reinforcement learning (DRL)-based offloading in IoV ignores other agent’s actions during the training process as an independent learner, which makes a lack of robustness against the high mobility environment. To overcome it, we develop a cooperative three-layer, more generic decentralized vehicle-assisted multi-access edge computing (VMEC) network, where vehicles in associated RSU and neighbor RSUs are in the bottom fog layer, MEC servers are in the middle cloudlet layer, and cloud in the top layer. Then multi-agent DRL-based Hungarian algorithm (MADRLHA) in the bipartite graph maximum matching problem is applied to solve dynamic task offloading in VMEC. Extensive experimental results and comprehensive comparisons are conducted to illustrate the superiority of our proposed method.


  • SDP-IGD: An Iterative Power Allocation Technique for Cluster-Based Multihop Vehicular Communications

    by Zahangir Alam, Iwan Adhicandra, Komal S. Khan, Abbas Jamalipour

    This paper addresses the formulation of power allocation for cluster based multihop vehicular relaying communications in order to improve the network quality-of-services (QoS). The cluster-to-cluster (C2C) channel is completely depending on the power gain of vehicle-to-vehicle (V2V) channel that increases the difficulties of the power allocation problem. To meet this goal, we have derived a global channel obtained by the joint V2V and C2C cooperation. The most challenging aspect is however the joint V2V and C2C power allocation of the global channel due to the association of its multi-variables objective function. To solve this problem, we apply an alternative optimization to make the global problem into a series of sub-problems. Then we apply a semi-definite programming (SDP)-based iterative gradient descent (SDP-IGD) power allocation to assign power in each relay. Actually, the SDP-IGD power allocation algorithm has been extended from Lagrange Multiplier (LM) that provides better performance than separate LM technique. The minimum mean-square error (MMSE)-decision feedback equalizer (MMSE-DFE) is designed at the receiver to improve the signal detection capability under exact channel state information (CSI) in all forward-and-backward links. Finally, simulation results confirm that our proposed solution performs significantly superior compared to other solutions found in the literature.


  • Optimal Best Path Selection Algorithm for Cluster-Based Multi-Hop MIMO Cooperative Transmission for Vehicular Communications

    by Zahangir Alam, Iwan Adhicandra, Abbas Jamalipour

    Multiple-input multiple-output (MIMO) cooperation in cluster-to-cluster communication has shown improved network quality-of-services by utilizing less transmission power over the fading environment. This is an enhancement from the traditional cluster-based single-input single-output multi-hop relaying used in vehicular communications. In this paper, we deploy multi-hop MIMO clustering relay into vehicular communication for a two-lane road transportation scenario. We deploy precoder and receiver filter in each MIMO link that is characterized by a narrowband classical three dimensional time-varying channel. With the aid of the precoder and minimum-mean-square-error receiver filtering algorithm in MIMO communication, we derive the end-to-end network signal-to-noise ratio to find the optimal best path using max-min theory with equal power allocation in precoder matrices that minimizes the network mean-square-error. A low-cost close-optimal best path selection method is also proposed through mathematical modelling. Computer simulation results demonstrate the validity of the theoretical investigations in this work.