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


Zain Anwar Ali has a total of 137 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    UGSA-Net: Uncertainty-Gated Attention and Self-Supervised Alignment for Calibration-Aware Hyperspectral Image Classification

    by Houari Youcef Moudjib, Haibin Duan, Zain Anwar Ali, Adam A. Q. Mohammed

    Uniform spatial weighting in patch-based hyperspectral classifiers indiscriminately aggregates spectral information, even when individual pixels are already class-diagnostic, degrading accuracy and interpretability. We propose UGSA-Net, an ambiguity-guided spatial–spectral transformer that infers a per-pixel ambiguity field without direct label supervision. A lightweight ambiguity head maps each token to a scalar in (0,1), trained end-to-end with no target of its own, so that the field is shaped only by the training losses that reach it through the token mixer. This field dually modulates the token mixer: it biases query and key projections with a spectral angle mapper (SAM) prior to emphasise spectrally similar patches, and rescales token outputs to amplify contributions from ambiguous locations. The value pathway remains unmodulated, so the network reweights spatial information without distorting the spectral content entering the mixture. The ambiguity head and the classification backbone are trained end-to-end, following a self-supervised latent-alignment stage that uses no labels; model selection jointly scores overall accuracy (OA), few-shot accuracy and expected calibration error (ECE) on validation data. Across six benchmark scenes from four sensors, under a stratified pixel-level split in which training and test windows overlap, UGSA-Net exceeds 98.9% OA on every scene over three runs, and on Indian Pines it is comparable to competing architectures retrained under the same protocol. These values are upper bounds rather than estimates for new scenes: on two of the six scenes, almost no labelled pixel has a competing class inside the 9×9 input window. A single validation-tuned temperature reduces ECE from 0.24–0.28 to below 0.016 without changing any prediction, revealing that residual miscalibration is governed by the decision head rather than by the data representations. The benefit of ambiguity gating emerges when labels are scarce: with a reduced training set on Indian Pines, gating raised OA over the ungated model on all three partitions, in either direction, whereas, with the full training set, component effects fall within run-to-run variation.

  • Open Access

    Hybrid Ant-Swarm Coverage and Routing Optimization for Wireless Sensor Networks

    by Nimrah Ahmed, Miguel Angel Luque Nieto, Zain Anwar Ali

    In Wireless Sensor Networks (WSNs), effective network coverage, energy-aware routing and reliable data delivery are major challenges. This paper addresses an intelligent optimized WSN using a two-phase hybrid network, thereby tackling these challenges. In the first phase, a proposed Improved Particle Swarm Optimization (IPSO) algorithm locates the collector node in the best position to achieve full coverage. In the second phase, the proposed Modified Elitist Ant Colony Optimization (MEACO) is used to determine the optimized multi-hop routing paths in terms of energy and delay. To evaluate the strength of the proposed framework, a patient network scenario is formulated where patients and collectors are placed to check baseline performance. In addition, a priority-based QoS Scheduling mechanism is introduced for data transfer, in which priority patients are monitored with the least end-to-end delay, while maintaining network lifetime. Reliable delivery of physiological information is challenged by packet loss and unstable wireless links. The proposed framework improves reliability through link quality evaluation, bounded retransmissions, and route recovery. The simulation results show that the proposed IPSO-MEACO approach improves network coverage by 13.2%, minimizes energy utilization by 14.7%, and drastically reduces end-to-end delay by 58.2% compared with classical algorithms. The results also affirm that the algorithm is suitable for full coverage with minimum end-to-end delay and energy consumption.

  • Open Access

    A learning-based position tracking method for excavator bucket

    by Zhi Chen, Tongyao Wang, Zain Anwar Ali, Quang Phuc Ha, Qing Sun

  • Open Access

    PGD–PPM: A Hybrid Framework for Enhancing Adversarial Robustness in Traffic Sign Recognition System

    by Raiyah Rub, Shaheena Noor, Irfan Ahmed Usmani, Zain Anwar Ali

    Traffic Sign Recognition (TSR) models based on Deep Learning are highly vulnerable to adversarial perturbations where often imperceptible changes to the input can significantly mislead model predictions and posing serious safety concerns in autonomous driving. This paper presents PGD–PPM, a hybrid defense framework designed to enhance adversarial robustness of TSR models by combining Projected Gradient Descent–based Adversarial Training (PGD-AT) with Pyramid Pooling Module (PPM) integration. The proposed architecture improves multi-scale contextual feature aggregation to resist adversarial perturbations while maintaining high clean accuracy. Four Convolutional Neural Network (CNN) architectures, VGG16, VGG19, ResNet50 and EfficientNetB0 were evaluated on two benchmark datasets GTSRB) and BelgiumTSC datasets under gradient based white-box attacks FGSM, IFGSM and PGD at various perturbation strengths (ϵ=0.1-2.0). The proposed models exhibit significant improvement in clean and adversarial accuracies. For instance, EfficientNetB0 with PGD-PPM achieves the most significant improvement in clean accuracy of 92.57% (up from 87.55%), VGG16 and VGG19 also increase by +4.29% and +3.10%, respectively, whereas EfficientNetB0 maintaining robustness with improved adversarial accuracy of 89% and 87% under strong adversarial condition (PGD attack at, ϵ = 0.1, 0.2). However, ResNet50 achieves the highest adversarial accuracy of 90% and 88% under PGD attack at ϵ = 0.1 and 0.2, which is significantly higher than the corresponding baseline model. The experimental results indicates that proposed framework not only possess a strong improvement in adversarial accuracy but it also improves the clean accuracy which mitigates the accuracy-robustness trade-off, contributing to safer and more reliable intelligent systems.


  • Open Access

    Hybrid Channel Attention Regression U-Net (ARU-Net): An Enhanced Architecture for Brain Tumour Segmentation in Magnetic Resonance Imaging

    by Noman Ahmed Siddiqui, Muhammad Tahir Qadri, Zain Anwar Ali, Muhammad Ovais Akhter, Ahmed Alsanad, Areej Abdullah Alhogail, Abdul H. Gumaei

    This research presents an accurate segmentation of brain tumours which is important in diagnosis and treatment planning of magnetic resource imaging (MRI) scans. Despite existing methodologies based on deep learning models, it remains difficult to distinguish between a tumour region and a normal brain tissue. To tackle this problem, a recent work proposed a new brain tumour segmentation technique on MRI, known as the Hybrid Attention Regression U-Net (ARU-Net) architecture. To enhance the effectiveness of segmentation, the proposed architecture utilises modern approaches including attention mechanisms, feature fusion processes, and regression-based output layer. It specifically uses Spatial and channel-wise attention mechanisms to capture important regions and inter channel dependencies. Spatial attention module in this architecture is based on improved Convolutional Block Attention Module which constrain attention on informative areas and suppress irrelevant or noisy ones. On the other hand, the channel-wise attention part, the Squeeze-and-Excitation (SE) blocks, recalibrates channel-wise feature responses for higher emphasis on salient features. The performance of proposed method has been evaluated comprehensively on the BraTS-2021 dataset where it shows enhanced accuracy over existing methods in detecting the tumour area. From the point of epoch curve, F1 score, the area under the curve, specificity, sensitivity, and accuracy in augmented and non-augmented datasets validated the stability of the proposed ARU-Net. This underlines its roles in segmentation of brain tumour, which if optimally developed holds the promise to significantly contribute for diagnosis and treatment planning.


  • Top Cited Papers
    Open Access

    Digital twins: cornerstone to circular economy and sustainability goals

    by Zain Anwar Ali, Mahreen Zain, Raza Hasan, Muhammad Salman Pathan, Hussain AlSalman, Faisal Abdulaziz Almisned

    Accurate information is a prerequisite for circulation and greater longevity of materials and products, enabling the economically and environmentally successful transition of circular economy (CE) in the aspiration towards sustainable development. However, a lack of appropriate digital tools is noticed in supplying relevant information and supporting recyclability, reusability, and reducibility processes. This study focuses on a building block of evolving technologies anointed the digital twin (DT). It aims to conceptualize DT as a cornerstone for the CE paradigm, positively influencing sustainability. It also endeavors to scrutinize remarkable implementations of DT-driven CE, accomplishing sustainable development goals (SDGs) in Ireland. An iterative methodology based on four steps is adopted to review an explosion of relevant, recent literature published in 2019–2024 and multiple case studies of Irish construction and manufacturing sectors. By analyzing the literature, this study discovers the evolution and taxonomy of DT, other technologies essential for its deployment, its proactive role in implementing CE and SDGs, and some challenges. Key findings of case studies reveal the current trajectory of employing DT with other digital products, upholding the CE practices within the bounds of the SDGs in Irish companies. In conclusion, DT is a conceivable means for advancing CE solutions and attaining SDGs towards social, economic, and environmental sustainability. The implications of this study are both theoretically and practically significant, encouraging industrialists and academia to adopt DT. It will help scholars gain a thorough understanding and guide industrialists to downsize their carbon footprint and waste, accomplishing SDGs. It will inspire managers with DT-driven information for decision-making and facilitate government and policymakers to collaborate in designing essential policies. Graphical Abstract


  • Open Access

    Adaptive Ruminant Optimization With LoRa-Based Communication for Formation Control of Multiple UAVs

    by Muhammad Aamir Khan, Zain Anwar Ali, Muhammad Haris Muneer, Raza Hasan

    In a dynamic environment with mountains and hazardous peaks, avoiding collisions and maintaining the desired formation is a crucial problem. This paper addresses this problem by presenting a novel formation control strategy of a cluster of UAVs in three different scenarios. The first scenario is designed to test the designed algorithm and hence contains no obstacles. The second scenario introduces some obstacles in the form of mountains to see whether the proposed algorithm can avoid the obstacles while maintaining the formation. In the last scenario, all the UAVs join together in one big cluster and have to avoid the obstacles while maintaining the formation. To design the environment for the scenarios, this study uses graph theory. To address the aforementioned scenarios, this paper offers a novel strategy by integrating a bio-inspired algorithm called the Adaptive Ruminant Optimization Algorithm (AROA) with the Long Range (LoRa) communication to achieve the formation control of multiple UAVs. Initially, AROA offers the best agents of each of the swarm. Then, the proposed method helps choose the best agent to be the leader for each of the swarm. The leader of each swarm finds the best trajectory for each swarm. LoRa-based networking technique is used for the connectivity between the UAVs. In addition, this study uses basis splines (B-splines) to smooth the planned trajectories of UAVs. Lastly, simulations demonstrate the better convergence and efficiency of the designed strategy by comparing it with classic algorithms. The simulations also show that the proposed method successfully maintains formation control in all three scenarios.

  • Open Access

    Intelligent Planning of UAV Flocks via Transfer Learning and Multi-objective Optimization

    by Fahad Farooq, Zain Anwar Ali, Muhammad Shafiq, Amber Israr, Raza Hasan

    Multiple UAVs have been extensively deployed recently to reduce human workload, resulting in increased automation and efficiency. Path planning of numerous UAVs is a challenging optimization problem and a key component in various applications. Traditional strategies cannot provide accurate, optimal solutions rapidly in complex mission settings. In this context, flocks of birds exhibit intricate patterns of group escape when faced with predators. Local group interactions may lead to the autonomy of these patterns. However, most nature-inspired intelligent planning techniques have slow search speeds and easily fall into local areas. An intelligent planning method emulating the behavior of pigeons to achieve intelligence, safety, and consistency in UAV flocks in a complicated environment is designed. The combinatorial approach of pigeon-inspired optimization and transfer learning (TL-PIO) is the focus of the multi-objective optimization task. On the one hand, path planning and formation control of individual clusters with a dynamic agent are dealt with combinatorial efforts of multi-agent systems (MAS) and flocking model. On the other hand, swapping and synchronization of individual clusters construct flocks in a dynamic environment. Specifically, interaction and swapping positions of the best members among all clusters are involved to plan optimized paths and configure agents in one flock. Experimental results have been validated through a detailed numerical analysis of proposed algorithm over other combinatorial approaches, namely social learning pigeon-inspired optimization (SL-PIO), social learning particle swarm optimization (SL-PSO), and social learning ant colony optimization (SL-ACO). TL-PIO achieves an improvement of 25% over SL-PIO and 18% over SL-ACO in seven test functions and 15% over SL-PSO but only in five test functions. Outcomes reveal the developed approach has the fastest convergence rate and high local optimal avoidance and exploration ability, significantly reducing costs and illustrating supremacy over other methods. The presented work practically implies researchers and practitioners adopt it for distinct benefits in real-world applications.