Muhammad Azeem Aslam
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Muhammad Azeem Aslam has a total of 35 co-authors. Here are the top co-authors by number of shared publications:
Nisar Ahmed
Department of Informatics and Systems, University of Management and Technology, Lahore, Pakistan
4 shared publicationsXu Wei
Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun, China
4 shared publicationsYimei Xu
School of Information Engineering, Xian Eurasia University, Xian, Shaanxi, China
4 shared publicationsHu Hongfei
School of Information Engineering, Xi’an Eurasia University, Xian, China
3 shared publications- Nisar Ahmed
Department of Informatics and Systems, University of Management and Technology Lahore, Pakistan
3 shared publications Xin Liu
School of Information Engineering, Xi’an Eurasia University, Xian, China
3 shared publications
Latest Publications
- Open Access
- 3 December 2025
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
A multi scale spatial attention based zero shot learning framework for low light image enhancement
Low-light image enhancement remains a challenging task, particularly in the absence of paired training data. In this study, we present LucentVisionNet, a novel zero-shot learning framework that addresses the limitations of traditional and deep learning-based enhancement methods. The proposed approach integrates multi-scale spatial attention with a deep curve estimation network, enabling fine-grained enhancement while preserving semantic and perceptual fidelity. To further improve generalization, we adopt a recurrent enhancement strategy and optimize the model using a composite loss function comprising six tailored components, including a novel no-reference image quality loss inspired by human visual perception. Extensive experiments on both paired and unpaired benchmark datasets demonstrate that LucentVisionNet consistently outperforms state-of-the-art supervised, unsupervised, and zero-shot methods across multiple full-reference and no-reference image quality metrics. Our framework achieves high visual quality, structural consistency, and computational efficiency, making it well-suited for deployment in real-world applications such as mobile photography, surveillance, and autonomous navigation.
- 3 December 2025
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Open AccessA multi scale spatial attention based zero shot learning framework for low light image enhancement
Low-light image enhancement remains a challenging task, particularly in the absence of paired training data. In this study, we present LucentVisionNet, a novel zero-shot learning framework that addresses the limitations of traditional and deep learning-based enhancement methods. The proposed approach integrates multi-scale spatial attention with a deep curve estimation network, enabling fine-grained enhancement while preserving semantic and perceptual fidelity. To further improve generalization, we adopt a recurrent enhancement strategy and optimize the model using a composite loss function comprising six tailored components, including a novel no-reference image quality loss inspired by human visual perception. Extensive experiments on both paired and unpaired benchmark datasets demonstrate that LucentVisionNet consistently outperforms state-of-the-art supervised, unsupervised, and zero-shot methods across multiple full-reference and no-reference image quality metrics. Our framework achieves high visual quality, structural consistency, and computational efficiency, making it well-suited for deployment in real-world applications such as mobile photography, surveillance, and autonomous navigation.
- Open Access
- 12 November 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-17
A hybrid attention network for accurate breast tumor segmentation in ultrasound images
Breast ultrasound (BUS) imaging is widely recognized as a non-invasive and cost-effective modality for the timely diagnosis of breast cancer. Despite its clinical importance, automatic tumor segmentation remains a highly challenging task because of speckle noise, varying lesion scale, and inherently indistinct boundaries between malignant and healthy tissue. To address these challenges, we introduce a novel hybrid attention-based segmentation framework, named HA-Net, tailored for BUS images. The proposed HA-Net uses a pre-trained DenseNet-121 backbone in the encoder to extract discriminative features, ensuring robustness against imaging artifacts. At the bottleneck, three complementary modules, Global Spatial Attention (GSA), Position Encoding (PE), and Scaled Dot-Product Attention (SDPA), are incorporated to capture long-range dependencies, preserve structural relationships, and model contextual interactions among features. Moreover, a Spatial Feature Enhancement Block (SFEB) is incorporated within the skip connections to refine spatial detail and emphasize tumor-relevant regions, thereby strengthening the decoder’s reconstruction capability. To further improve segmentation reliability, a composite loss function is employed by combining Binary Cross-Entropy (BCE) with Jaccard Index loss, ensuring balanced optimization across pixel-level classification and region-level overlap. In comparison to current state-of-the-art (SOTA) approaches, extensive experiments on publicly available BUS datasets show that the proposed HA-Net achieves competent performance, highlighting its potential as an efficient decision-support tool for radiologists.
- 12 November 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-17
Open AccessA hybrid attention network for accurate breast tumor segmentation in ultrasound images
Breast ultrasound (BUS) imaging is widely recognized as a non-invasive and cost-effective modality for the timely diagnosis of breast cancer. Despite its clinical importance, automatic tumor segmentation remains a highly challenging task because of speckle noise, varying lesion scale, and inherently indistinct boundaries between malignant and healthy tissue. To address these challenges, we introduce a novel hybrid attention-based segmentation framework, named HA-Net, tailored for BUS images. The proposed HA-Net uses a pre-trained DenseNet-121 backbone in the encoder to extract discriminative features, ensuring robustness against imaging artifacts. At the bottleneck, three complementary modules, Global Spatial Attention (GSA), Position Encoding (PE), and Scaled Dot-Product Attention (SDPA), are incorporated to capture long-range dependencies, preserve structural relationships, and model contextual interactions among features. Moreover, a Spatial Feature Enhancement Block (SFEB) is incorporated within the skip connections to refine spatial detail and emphasize tumor-relevant regions, thereby strengthening the decoder’s reconstruction capability. To further improve segmentation reliability, a composite loss function is employed by combining Binary Cross-Entropy (BCE) with Jaccard Index loss, ensuring balanced optimization across pixel-level classification and region-level overlap. In comparison to current state-of-the-art (SOTA) approaches, extensive experiments on publicly available BUS datasets show that the proposed HA-Net achieves competent performance, highlighting its potential as an efficient decision-support tool for radiologists.
- Open Access
- 3 July 2025
- Published by Springer Nature in Journal of King Saud University Computer and Information Sciences
- Vol. 37 (5) , 1-15
Underwater acoustic classification across diverse sea environments using adaptive regularization and knowledge encoding
- 3 July 2025
- Published by Springer Nature in Journal of King Saud University Computer and Information Sciences
- Vol. 37 (5) , 1-15
Open AccessUnderwater acoustic classification across diverse sea environments using adaptive regularization and knowledge encoding
- Open Access
Hybrid Attention Network for Accurate Breast Tumor Segmentation in Ultrasound Images
Breast ultrasound imaging is a valuable tool for early breast cancer detection, but automated tumor segmentation is challenging due to inherent noise, variations in scale of lesions, and fuzzy boundaries. To address these challenges, we propose a novel hybrid attention-based network for lesion segmentation. Our proposed architecture integrates a pre-trained DenseNet121 in the encoder part for robust feature extraction with a multi-branch attention-enhanced decoder tailored for breast ultrasound images. The bottleneck incorporates Global Spatial Attention (GSA), Position Encoding (PE), and Scaled Dot-Product Attention (SDPA) to learn global context, spatial relationships, and relative positional features. The Spatial Feature Enhancement Block (SFEB) is embedded at skip connections to refine and enhance spatial features, enabling the network to focus more effectively on tumor regions. A hybrid loss function combining Binary Cross-Entropy (BCE) and Jaccard Index loss optimizes both pixel-level accuracy and region-level overlap metrics, enhancing robustness to class imbalance and irregular tumor shapes. Experiments on public datasets demonstrate that our method outperforms existing approaches, highlighting its potential to assist radiologists in early and accurate breast cancer diagnosis.
Open AccessHybrid Attention Network for Accurate Breast Tumor Segmentation in Ultrasound Images
Breast ultrasound imaging is a valuable tool for early breast cancer detection, but automated tumor segmentation is challenging due to inherent noise, variations in scale of lesions, and fuzzy boundaries. To address these challenges, we propose a novel hybrid attention-based network for lesion segmentation. Our proposed architecture integrates a pre-trained DenseNet121 in the encoder part for robust feature extraction with a multi-branch attention-enhanced decoder tailored for breast ultrasound images. The bottleneck incorporates Global Spatial Attention (GSA), Position Encoding (PE), and Scaled Dot-Product Attention (SDPA) to learn global context, spatial relationships, and relative positional features. The Spatial Feature Enhancement Block (SFEB) is embedded at skip connections to refine and enhance spatial features, enabling the network to focus more effectively on tumor regions. A hybrid loss function combining Binary Cross-Entropy (BCE) and Jaccard Index loss optimizes both pixel-level accuracy and region-level overlap metrics, enhancing robustness to class imbalance and irregular tumor shapes. Experiments on public datasets demonstrate that our method outperforms existing approaches, highlighting its potential to assist radiologists in early and accurate breast cancer diagnosis.
- Open Access
- 17 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 188939-188954
Improving Arabic Multi-Label Emotion Classification Using Stacked Embeddings and Hybrid Loss Function
Multi-label emotion classification (MLEC) for low-resource languages like Arabic faces significant challenges due to class imbalance and label correlations, particularly in accurately predicting minority emotions. This study propose a novel framework combining stacked contextual embeddings, meta-learning, and a hybrid loss function to address these issues. First, we generate enriched embeddings by fine-tuning and stacking three Arabic language models (ArabicBERT, MarBERT, AraBERT). These embeddings are processed by a Bi-LSTM meta-learner for sequence learning, followed by a fully connected network for classification. To mitigate class imbalance and leverage label dependencies, we introduce a hybrid loss integrating contrastive learning (CL), label correlation matrices (LCM), and class weighting (CW). Extensive experiments on the SemEval-2018 Task 1-Ec-Ar dataset demonstrate state-of-the-art performance, with a Jaccard accuracy of 0.81, F1-score of 0.67, and Hamming loss of 0.15. Ablation studies confirm the contributions of each component, while class-wise analysis shows our hybrid loss reduces disparities between majority and minority classes by up to 22%. Beyond Arabic MLEC, this work offers a generalizable framework adaptable to other languages and domains, advancing emotion analysis in low-resource settings.
- 17 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 188939-188954
Open AccessImproving Arabic Multi-Label Emotion Classification Using Stacked Embeddings and Hybrid Loss Function
Multi-label emotion classification (MLEC) for low-resource languages like Arabic faces significant challenges due to class imbalance and label correlations, particularly in accurately predicting minority emotions. This study propose a novel framework combining stacked contextual embeddings, meta-learning, and a hybrid loss function to address these issues. First, we generate enriched embeddings by fine-tuning and stacking three Arabic language models (ArabicBERT, MarBERT, AraBERT). These embeddings are processed by a Bi-LSTM meta-learner for sequence learning, followed by a fully connected network for classification. To mitigate class imbalance and leverage label dependencies, we introduce a hybrid loss integrating contrastive learning (CL), label correlation matrices (LCM), and class weighting (CW). Extensive experiments on the SemEval-2018 Task 1-Ec-Ar dataset demonstrate state-of-the-art performance, with a Jaccard accuracy of 0.81, F1-score of 0.67, and Hamming loss of 0.15. Ablation studies confirm the contributions of each component, while class-wise analysis shows our hybrid loss reduces disparities between majority and minority classes by up to 22%. Beyond Arabic MLEC, this work offers a generalizable framework adaptable to other languages and domains, advancing emotion analysis in low-resource settings.
- Open Access
- 1 January 2025
- Published by Wiley in International Journal of Intelligent Systems
- Vol. 2025 (1)
Continual Learning Inspired by Brain Functionality: A Comprehensive Survey
Neural network–based models have shown tremendous achievements in various fields. However, standard AI‐based systems suffer from catastrophic forgetting when undertaking sequential learning of multiple tasks in dynamic environments. Continual learning has emerged as a promising approach to address catastrophic forgetting. It enables AI systems to learn, transfer, augment, fine‐tune, and reuse knowledge for future tasks. The techniques used to achieve continual learning are inspired by the learning processes of the human brain. In this study, we present a comprehensive review of research and recent developments in continual learning, highlighting key contributions and challenges. We discuss essential functions of the biological brain that are pivotal for achieving continual learning and map these functions to the recent machine‐learning methods to aid understanding. Additionally, we offer a critical review of five recent types of continual learning methods inspired by the biological brain. We also provide empirical results, analysis, challenges, and future directions. We hope that this study will benefit both general readers and the research community by offering a complete picture of the latest developments in this field.
- 1 January 2025
- Published by Wiley in International Journal of Intelligent Systems
- Vol. 2025 (1)
Open AccessContinual Learning Inspired by Brain Functionality: A Comprehensive Survey
Neural network–based models have shown tremendous achievements in various fields. However, standard AI‐based systems suffer from catastrophic forgetting when undertaking sequential learning of multiple tasks in dynamic environments. Continual learning has emerged as a promising approach to address catastrophic forgetting. It enables AI systems to learn, transfer, augment, fine‐tune, and reuse knowledge for future tasks. The techniques used to achieve continual learning are inspired by the learning processes of the human brain. In this study, we present a comprehensive review of research and recent developments in continual learning, highlighting key contributions and challenges. We discuss essential functions of the biological brain that are pivotal for achieving continual learning and map these functions to the recent machine‐learning methods to aid understanding. Additionally, we offer a critical review of five recent types of continual learning methods inspired by the biological brain. We also provide empirical results, analysis, challenges, and future directions. We hope that this study will benefit both general readers and the research community by offering a complete picture of the latest developments in this field.
- Open Access
- 29 October 2024
- Published by Springer Nature in Scientific Reports
- Vol. 14 (1) , 1-24
QualityNet: A multi-stream fusion framework with spatial and channel attention for blind image quality assessment
This study introduces a novel Blind Image Quality Assessment (BIQA) approach leveraging a multi-stream spatial and channel attention model. Our method addresses challenges posed by diverse image content and distortions by integrating feature maps from two distinct backbones. Through spatial and channel attention mechanisms, our algorithm prioritizes regions of interest, enhancing its ability to capture crucial image details. Extensive evaluations on four benchmark datasets demonstrate superior performance compared to existing methods, closely aligning with human perceptual assessment. Our approach exhibits exceptional generalization capabilities on both authentic and synthetic distortion databases. Moreover, it demonstrates a distinctive focus on perceptual foreground information, enhancing its practical applicability. Thorough quantitative analyses underscore the algorithm’s superior performance, establishing its dominance over existing methods.
- 29 October 2024
- Published by Springer Nature in Scientific Reports
- Vol. 14 (1) , 1-24
Open AccessQualityNet: A multi-stream fusion framework with spatial and channel attention for blind image quality assessment
This study introduces a novel Blind Image Quality Assessment (BIQA) approach leveraging a multi-stream spatial and channel attention model. Our method addresses challenges posed by diverse image content and distortions by integrating feature maps from two distinct backbones. Through spatial and channel attention mechanisms, our algorithm prioritizes regions of interest, enhancing its ability to capture crucial image details. Extensive evaluations on four benchmark datasets demonstrate superior performance compared to existing methods, closely aligning with human perceptual assessment. Our approach exhibits exceptional generalization capabilities on both authentic and synthetic distortion databases. Moreover, it demonstrates a distinctive focus on perceptual foreground information, enhancing its practical applicability. Thorough quantitative analyses underscore the algorithm’s superior performance, establishing its dominance over existing methods.
- Open Access
- 24 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 88264-88278
TQP: An Efficient Video Quality Assessment Framework for Adaptive Bitrate Video Streaming
The increasing popularity of video streaming services and the widespread accessibility of high-speed internet underscore the importance of delivering cost-effective and seamless streaming experiences. Shared internet connections may lead to varying speeds, impacting Quality of Experience (QoE). Rate adaptation techniques aim to ensure smooth video transmission, but overly optimistic adaptations can compromise user experience. Objective video quality assessment is crucial for efficient rate adaptation to ensure smooth QoE. This research proposes a novel method incorporating temporal channel shifting into Convolutional Neural Networks (CNN) for video quality assessment while maintaining the computational simplicity of a 2D CNN model. The proposed approach relies on the EfficientNet architecture, initially pre-trained on quality-aware images, and fine-tune it using datasets of rate-adaptive videos. The model is trained and evaluated on two benchmark datasets, namely "Waterloo sQoE III" and "LIVE Netflix II," which consist of rate-adaptive videos annotated with subjective quality scores. Experimental results encompass the evaluation of Pearson, Spearman, and Kendall correlation coefficients, along with the computation time ratio for the proposed approach. The outcomes reveal competitive scores of 0.795, 0.652, 0.772, and 0.216 for the "Live Netflix II dataset" and 0.782, 0.713, 0.721, and 0.230 for the "Waterloo sQoE III dataset." Our proposed method, compared to 24 approaches for "Waterloo sQoE III" and 25 for "LIVE Netflix II," attains the highest correlation scores while maintaining near-real-time processing efficiency. These results affirm the efficacy of our approach in accurately predicting human judgment (QoE) with computational efficiency.
- 24 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 88264-88278
Open AccessTQP: An Efficient Video Quality Assessment Framework for Adaptive Bitrate Video Streaming
The increasing popularity of video streaming services and the widespread accessibility of high-speed internet underscore the importance of delivering cost-effective and seamless streaming experiences. Shared internet connections may lead to varying speeds, impacting Quality of Experience (QoE). Rate adaptation techniques aim to ensure smooth video transmission, but overly optimistic adaptations can compromise user experience. Objective video quality assessment is crucial for efficient rate adaptation to ensure smooth QoE. This research proposes a novel method incorporating temporal channel shifting into Convolutional Neural Networks (CNN) for video quality assessment while maintaining the computational simplicity of a 2D CNN model. The proposed approach relies on the EfficientNet architecture, initially pre-trained on quality-aware images, and fine-tune it using datasets of rate-adaptive videos. The model is trained and evaluated on two benchmark datasets, namely "Waterloo sQoE III" and "LIVE Netflix II," which consist of rate-adaptive videos annotated with subjective quality scores. Experimental results encompass the evaluation of Pearson, Spearman, and Kendall correlation coefficients, along with the computation time ratio for the proposed approach. The outcomes reveal competitive scores of 0.795, 0.652, 0.772, and 0.216 for the "Live Netflix II dataset" and 0.782, 0.713, 0.721, and 0.230 for the "Waterloo sQoE III dataset." Our proposed method, compared to 24 approaches for "Waterloo sQoE III" and 25 for "LIVE Netflix II," attains the highest correlation scores while maintaining near-real-time processing efficiency. These results affirm the efficacy of our approach in accurately predicting human judgment (QoE) with computational efficiency.
- Top Cited PapersOpen Access
- 22 June 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 255
Underwater sound classification using learning based methods: A review
- 22 June 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 255
Top Cited PapersOpen AccessUnderwater sound classification using learning based methods: A review
- Open Access
- 7 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 2458-2473
VRL-IQA: Visual Representation Learning for Image Quality Assessment
The growing adoption of digital multimedia devices and the greater reliance on compression and wireless channels for data transmission has brought renewed focus to the traditional challenge of evaluating image quality. Image Quality Assessment (IQA) is needed to optimize bit rate, compression, or processing and communication strategies for these multimedia technologies. Visual representation learning enables the model to undertake upstream training on large-scale data and then fine-tune the model on downstream data using fewer training samples. Data annotation for IQA is expensive due to the difficulty of grading a picture’s quality, the need to gather quality labels from numerous observers, and the diversity of perceptual quality and content of the images. This challenge has limited the amount of the labeled training dataset for IQA to a few thousand. In this study, a deep Convolutional Neural Network is trained on a large-scale image dataset produced by simulating 165 distortion scenarios on 150,000 images resulting in 24.75 million distorted images. These images are labeled via an ensemble of full-reference quality assessment models which assign the quality rating to each distorted image by using its reference image. This trained model is fine-tuned on two datasets TID2013 and Kadid-10K datasets containing simulated distortions and two datasets KonIQ-10K and BIQ2021 containing authentic distortions. The fine-tuning performance has resulted in state-of-the-art IQA performance and yielded a Spearman’s correlation coefficient of 0.921, 0.893, 0.884, and 0.793, respectively. Moreover, comparison with the ImageNet pre-trained model revealed that the proposed VRL-IQA model provides higher performance in terms of Pearson and Spearman’s correlations and achieves the validation criteria with fewer epochs than the ImageNet pre-trained model. These findings contribute to the advancement of IQA, offering a promising approach for robust and accurate quality prediction in various applications.
- 7 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 2458-2473
Open AccessVRL-IQA: Visual Representation Learning for Image Quality Assessment
The growing adoption of digital multimedia devices and the greater reliance on compression and wireless channels for data transmission has brought renewed focus to the traditional challenge of evaluating image quality. Image Quality Assessment (IQA) is needed to optimize bit rate, compression, or processing and communication strategies for these multimedia technologies. Visual representation learning enables the model to undertake upstream training on large-scale data and then fine-tune the model on downstream data using fewer training samples. Data annotation for IQA is expensive due to the difficulty of grading a picture’s quality, the need to gather quality labels from numerous observers, and the diversity of perceptual quality and content of the images. This challenge has limited the amount of the labeled training dataset for IQA to a few thousand. In this study, a deep Convolutional Neural Network is trained on a large-scale image dataset produced by simulating 165 distortion scenarios on 150,000 images resulting in 24.75 million distorted images. These images are labeled via an ensemble of full-reference quality assessment models which assign the quality rating to each distorted image by using its reference image. This trained model is fine-tuned on two datasets TID2013 and Kadid-10K datasets containing simulated distortions and two datasets KonIQ-10K and BIQ2021 containing authentic distortions. The fine-tuning performance has resulted in state-of-the-art IQA performance and yielded a Spearman’s correlation coefficient of 0.921, 0.893, 0.884, and 0.793, respectively. Moreover, comparison with the ImageNet pre-trained model revealed that the proposed VRL-IQA model provides higher performance in terms of Pearson and Spearman’s correlations and achieves the validation criteria with fewer epochs than the ImageNet pre-trained model. These findings contribute to the advancement of IQA, offering a promising approach for robust and accurate quality prediction in various applications.