Skip to main content

Research Repository

Advanced Search

Professor Adil Khan's Outputs (27)

DiffFormer: a Differential Spatial-Spectral Transformer for Hyperspectral Image Classification (2025)
Journal Article
Ahmad, M., Mazzara, M., Distefano, S., Khan, A. M., & Ullo, S. L. (in press). DiffFormer: a Differential Spatial-Spectral Transformer for Hyperspectral Image Classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 18, 10419-10428. https://doi.org/10.1109/JSTARS.2025.3558889

Hyperspectral image classification (HSIC) presents significant challenges due to spectral redundancy and spatial discontinuity, both of which can negatively impact classification performance. To mitigate these issues, this work proposes the Different... Read More about DiffFormer: a Differential Spatial-Spectral Transformer for Hyperspectral Image Classification.

Spatial-spectral morphological mamba for hyperspectral image classification (2025)
Journal Article
Ahmad, M., Butt, M. H. F., Khan, A. M., Mazzara, M., Distefano, S., Usama, M., Roy, S. K., Chanussot, J., & Hong, D. (online). Spatial-spectral morphological mamba for hyperspectral image classification. Neurocomputing, Article 129995. https://doi.org/10.1016/j.neucom.2025.129995

Recent advancements in transformers, specifically self-attention mechanisms, have significantly improved hyperspectral image (HSI) classification. However, these models often have inefficiencies, as their computational complexity scales quadratically... Read More about Spatial-spectral morphological mamba for hyperspectral image classification.

TOA and TDOA Based Asynchronous Self-Localization: Three Stage Framework for Simultaneous Localization of Microphones and Audio Sources (2025)
Thesis
Cao, F. (2025). TOA and TDOA Based Asynchronous Self-Localization: Three Stage Framework for Simultaneous Localization of Microphones and Audio Sources. (Thesis). University of Hull. https://hull-repository.worktribe.com/output/5086296

Self-localization, a pivotal aspect explored in this research, holds significant relevance across various applications, including human-robot interaction and surveillance for aging individuals. Traditional localization methods relying on GPS signals... Read More about TOA and TDOA Based Asynchronous Self-Localization: Three Stage Framework for Simultaneous Localization of Microphones and Audio Sources.

Multi-head spatial-spectral mamba for hyperspectral image classification (2025)
Journal Article
Ahmad, A., Butt, M. H. F., Usama, M., Altuwaijri, H. A., Mazzara, M., Distefano, S., & Khan, A. M. (2025). Multi-head spatial-spectral mamba for hyperspectral image classification. Remote Sensing Letters, 16(4), 15-29. https://doi.org/10.1080/2150704X.2025.2461330

Spatial-Spectral Mamba (SSM) improves computational efficiency and captures long-range dependencies, addressing the limitations of transformers. However, traditional Mamba models often overlook the rich spectral information in hyperspectral images (H... Read More about Multi-head spatial-spectral mamba for hyperspectral image classification.

LLM Based Cross Modality Retrieval to Improve Recommendation Performance (2024)
Presentation / Conference Contribution
Anwaar, F., Khan, A. M., & Khalid, M. (2024, August). LLM Based Cross Modality Retrieval to Improve Recommendation Performance. Presented at 2024 29th International Conference on Automation and Computing (ICAC), Sunderland, UK

The metadata of items and users play an important role in improving the decision-making process in the Recom-mender System. In recent times, web scraping-based techniques have been widely utilized to extract explicit user and item meta-data from diff... Read More about LLM Based Cross Modality Retrieval to Improve Recommendation Performance.

Improving Generalization for Hyperspectral Image Classification: The Impact of Disjoint Sampling on Deep Models (2024)
Journal Article
Ahmad, M., Mazzara, M., Distefano, S., Khan, A. M., & Altuwaijri, H. A. (2024). Improving Generalization for Hyperspectral Image Classification: The Impact of Disjoint Sampling on Deep Models. Computers, Materials & Continua, 81(1), 503-532. https://doi.org/10.32604/cmc.2024.056318

Disjoint sampling is critical for rigorous and unbiased evaluation of state-of-the-art (SOTA) models e.g., Attention Graph and Vision Transformer. When training, validation, and test sets overlap or share data, it introduces a bias that inflates perf... Read More about Improving Generalization for Hyperspectral Image Classification: The Impact of Disjoint Sampling on Deep Models.

Leveraging Deep Reinforcement Learning and Healthcare Devices for Active Travelling in Smart Cities (2024)
Journal Article
Kazmi, S. M. A., Khan, Z., Khan, A., Mazzara, M., & Khattak, A. M. (online). Leveraging Deep Reinforcement Learning and Healthcare Devices for Active Travelling in Smart Cities. IEEE Transactions on Consumer Electronics, https://doi.org/10.1109/tce.2024.3470978

Smart cities are increasingly challenged by population growth and the environmental emissions of urban transportation systems, necessitating sustainable urban planning to improve public health, environmental quality, and overall urban livability. A n... Read More about Leveraging Deep Reinforcement Learning and Healthcare Devices for Active Travelling in Smart Cities.

A hybrid contextual framework to predict severity of infectious disease: COVID-19 case study (2024)
Journal Article
Azam, M. M. B., Anwaar, F., Khan, A. M., Anwar, M., Ghani, H. B. A., Eisa, T. A. E., & Abdelmaboud, A. (2024). A hybrid contextual framework to predict severity of infectious disease: COVID-19 case study. Egyptian Informatics Journal, 27, Article 100508. https://doi.org/10.1016/j.eij.2024.100508

Infectious disease is a particular type of disorder triggered by organisms and transmitted directly or indirectly from an infected one like COVID-19. The global economy and public health are immensely affected by COVID-19, a recently emerging infecti... Read More about A hybrid contextual framework to predict severity of infectious disease: COVID-19 case study.

Global Knowledge, Local Impact: Domain Adaptation and Classification for Obesity in the UAE (2024)
Presentation / Conference Contribution
Raza, M., Khattak, A., Abbas, W., & Khan, A. (2024, June). Global Knowledge, Local Impact: Domain Adaptation and Classification for Obesity in the UAE. Presented at 37th IEEE International Symposium on Computer-Based Medical Systems (CBMS), Guadalajara, Mexico

Obesity, a global public health concern, is escalating rapidly, especially in the Middle East, with the United Arab Emirates (UAE) witnessing one of the highest prevalence rates among adults and children. This multifactorial health issue is influence... Read More about Global Knowledge, Local Impact: Domain Adaptation and Classification for Obesity in the UAE.

LLM-guided Instance-level Image Manipulation with Diffusion U-Net Cross-Attention Maps (2024)
Presentation / Conference Contribution
Palaev, A., Khan, A., & Kazmi, A. (2024, November). LLM-guided Instance-level Image Manipulation with Diffusion U-Net Cross-Attention Maps. Paper presented at The 35th British Machine Vision Conference, Glasgow

The advancement of text-to-image synthesis has introduced powerful generative models capable of creating realistic images from textual prompts. However, precise control over image attributes remains challenging, especially at the instance level. Whil... Read More about LLM-guided Instance-level Image Manipulation with Diffusion U-Net Cross-Attention Maps.

Spatial Spectral Transformer with Conditional Position Encoding for Hyperspectral Image Classification (2024)
Journal Article
Ahmad, M., Usama, M., Khan, A. M., Distefano, S., Altuwaijri, H. A., & Mazzara, M. (2024). Spatial Spectral Transformer with Conditional Position Encoding for Hyperspectral Image Classification. IEEE Geoscience and Remote Sensing Letters, 1-1. https://doi.org/10.1109/lgrs.2024.3431188

In Transformer-based Hyperspectral Image Classification (HSIC), predefined positional encodings (PEs) are crucial for capturing the order of each input token. However, their typical representation as fixed-dimension learnable vectors makes it challen... Read More about Spatial Spectral Transformer with Conditional Position Encoding for Hyperspectral Image Classification.

Not So Robust after All: Evaluating the Robustness of Deep Neural Networks to Unseen Adversarial Attacks (2024)
Journal Article
Garaev, R., Rasheed, B., & Khan, A. M. (2024). Not So Robust after All: Evaluating the Robustness of Deep Neural Networks to Unseen Adversarial Attacks. Algorithms, 17, Article 162. https://doi.org/10.3390/a17040162

Deep neural networks (DNNs) have gained prominence in various applications, but remain vulnerable to adversarial attacks that manipulate data to mislead a DNN. This paper aims to challenge the efficacy and transferability of two contemporary defense... Read More about Not So Robust after All: Evaluating the Robustness of Deep Neural Networks to Unseen Adversarial Attacks.

Pyramid Hierarchical Spatial-Spectral Transformer for Hyperspectral Image Classification (2024)
Journal Article
Ahmad, M., Butt, M. H. F., Mazzara, M., Distefano, S., Khan, A. M., & Altuwaijri, H. A. (2024). Pyramid Hierarchical Spatial-Spectral Transformer for Hyperspectral Image Classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 17, 17681-17689. https://doi.org/10.1109/jstars.2024.3461851

The Transformer model encounters challenges with variable-length input sequences, leading to efficiency and scalability concerns. To overcome this, we propose a pyramid-based hierarchical Spatial-Spectral Transformer (PyFormer). This innovative appro... Read More about Pyramid Hierarchical Spatial-Spectral Transformer for Hyperspectral Image Classification.

Exploring the Impact of Conceptual Bottlenecks on Adversarial Robustness of Deep Neural Networks (2024)
Journal Article
Rasheed, B., Abdelhamid, M., Khan, A., Menezes, I., & Masood Khatak, A. (2024). Exploring the Impact of Conceptual Bottlenecks on Adversarial Robustness of Deep Neural Networks. IEEE Access, 12, 131323-131335. https://doi.org/10.1109/ACCESS.2024.3457784

Deep neural networks (DNNs), while powerful, often suffer from a lack of interpretability and vulnerability to adversarial attacks. Concept bottleneck models (CBMs), which incorporate intermediate high-level concepts into the model architecture, prom... Read More about Exploring the Impact of Conceptual Bottlenecks on Adversarial Robustness of Deep Neural Networks.

Structure Estimation of Adversarial Distributions for Enhancing Model Robustness: A Clustering-Based Approach (2023)
Journal Article
Rasheed, B., Khan, A., & Masood Khattak, A. (2023). Structure Estimation of Adversarial Distributions for Enhancing Model Robustness: A Clustering-Based Approach. Applied Sciences, 13(19), Article 10972. https://doi.org/10.3390/app131910972

In this paper, we propose an advanced method for adversarial training that focuses on leveraging the underlying structure of adversarial perturbation distributions. Unlike conventional adversarial training techniques that consider adversarial example... Read More about Structure Estimation of Adversarial Distributions for Enhancing Model Robustness: A Clustering-Based Approach.

Learning Fair Representations through Uniformly Distributed Sensitive Attributes (2023)
Presentation / Conference Contribution
Kenfack, P., Rivera, A., Khan, A., & Mazzara, M. (2023, February). Learning Fair Representations through Uniformly Distributed Sensitive Attributes. Presented at 2023 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML), Raleigh, NC, USA

Machine Learning (ML) models trained on biased data can reproduce and even amplify these biases. Since such models are deployed to make decisions that can affect people's lives, ensuring their fairness is critical. One approach to mitigate possi... Read More about Learning Fair Representations through Uniformly Distributed Sensitive Attributes.

Overhead Based Cluster Scheduling of Mixed Criticality Systems on Multicore Platform (2023)
Journal Article
Ali, A., Khattak, A. M., Iqbal, S., Alfandi, O., Hayat, B., Siddiqi, M. H., & Khan, A. (2023). Overhead Based Cluster Scheduling of Mixed Criticality Systems on Multicore Platform. IEEE Access, 11, 142341-142359. https://doi.org/10.1109/ACCESS.2023.3330973

The cluster-based technique is gaining focus for scheduling tasks of mixed-criticality (MC) real-time multicore systems. In this technique, the cores of the MC system are distributed in groups known as clusters. When all cores are distributed in clus... Read More about Overhead Based Cluster Scheduling of Mixed Criticality Systems on Multicore Platform.

A Disjoint Samples-Based 3D-CNN With Active Transfer Learning for Hyperspectral Image Classification (2022)
Journal Article
Ahmad, M., Ghous, U., Hong, D., Khan, A. M., Yao, J., Wang, S., & Chanussot, J. (2022). A Disjoint Samples-Based 3D-CNN With Active Transfer Learning for Hyperspectral Image Classification. IEEE transactions on geoscience and remote sensing : a publication of the IEEE Geoscience and Remote Sensing Society, 60, 1-16. https://doi.org/10.1109/TGRS.2022.3209182

Convolutional neural networks (CNNs) have been extensively studied for hyperspectral image classification (HSIC). However, CNNs are critically attributed to a large number of labeled training samples, which outlays high costs in terms of time and res... Read More about A Disjoint Samples-Based 3D-CNN With Active Transfer Learning for Hyperspectral Image Classification.

Computing on Wheels: A Deep Reinforcement Learning-Based Approach (2022)
Journal Article
Ahsan Kazmi, S. M., Ho, T. M., Nguyen, T. T., Fahim, M., Khan, A., Piran, M. J., & Baye, G. (2022). Computing on Wheels: A Deep Reinforcement Learning-Based Approach. IEEE Transactions on Intelligent Transportation Systems, 23(11), 22535-22548. https://doi.org/10.1109/TITS.2022.3165662

Future generation vehicles equipped with modern technologies will impose unprecedented computational demand due to the wide adoption of compute-intensive services with stringent latency requirements. The computational capacity of the next generation... Read More about Computing on Wheels: A Deep Reinforcement Learning-Based Approach.

Hybrid Dense Network With Attention Mechanism for Hyperspectral Image Classification (2022)
Journal Article
Ahmad, M., Khan, A. M., Mazzara, M., Distefano, S., Roy, S. K., & Wu, X. (2022). Hybrid Dense Network With Attention Mechanism for Hyperspectral Image Classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 15, 3948-3957. https://doi.org/10.1109/JSTARS.2022.3171586

The nonlinear relation between the spectral information and the corresponding objects (complex physiognomies) makes pixelwise classification challenging for conventional methods. To deal with nonlinearity issues in hyperspectral image classification... Read More about Hybrid Dense Network With Attention Mechanism for Hyperspectral Image Classification.