Touseef Sadiq

• Gul, Faqir; Shah, Mohsin; Ali, Mushtaq; Hussain, Lal; Sadiq, Touseef & Abbasi, Adeel Ahmed [Vis alle 8 forfattere av denne artikkelen] (2025). A hybrid multi-panel image segmentation framework for improved medical image retrieval system. PLOS ONE. 20(2). doi: 10.1371/journal.pone.0315823. Fulltekst i vitenarkiv Vis sammendrag

  Multi-panel images play an essential role in medical diagnostics and represent approximately 50% of the medical literature. These images serve as important tools for physicians to align various medical data (e.g., X-rays, MRIs, CT scans) of a patient into a Consolidated image. This consolidated multi-panel image, represented by its component sub-images, contributes to a thorough representation of the patient’s case during diagnosis. However, extracting sub-images from the multi-panel images poses significant challenges for Medical image retrieval systems, especially when dealing with regular and irregular image layouts. To address these challenges, this paper presents a novel hybrid framework that significantly enhances sub-image retrieval. The framework classifies medical images, employs advanced computer vision and image processing techniques including image projection profiles and morphological operations, and performs efficient segmentation of various multipanel image types including regular and irregular medical images. The hybrid approach ensures accurate indexing and facilitates fast retrieval of sub-images by medical image retrieval systems. To validate the proposed framework, experiments were conducted on a set of medical images from publicly available datasets, including ImageCLEFmed 2013 to ImageCLEFmed 2016. The results show better performance compared to other methods, attaining an accuracy of 90.50% in image type identification and 91% and 92% in regular and irregular multi-panel image segmentation tasks, respectively. By achieving accurate and efficient segmentation across diverse multi-panel image types, our framework demonstrates significant potential to improve the performance of medical image retrieval systems.

• Diao, Su; Wan, Yajie; Huang, Danyi; Huang, Shijia; Sadiq, Touseef & Khan, Mohammad Shahbaz [Vis alle 9 forfattere av denne artikkelen] (2025). Optimizing Bi-LSTM networks for improved lung cancer detection accuracy. PLOS ONE. 20(2). doi: 10.1371/journal.pone.0316136. Fulltekst i vitenarkiv Vis sammendrag

  Lung cancer remains a leading cause of cancer-related deaths worldwide, with low survival rates often attributed to late-stage diagnosis. To address this critical health challenge, researchers have developed computer-aided diagnosis (CAD) systems that rely on feature extraction from medical images. However, accurately identifying the most informative image features for lung cancer detection remains a significant challenge. This study aimed to compare the effectiveness of both hand-crafted and deep learning-based approaches for lung cancer diagnosis. We employed traditional hand-crafted features, such as Gray Level Co-occurrence Matrix (GLCM) features, in conjunction with traditional machine learning algorithms. To explore the potential of deep learning, we also optimized and implemented a Bidirectional Long Short-Term Memory (Bi-LSTM) network for lung cancer detection. The results revealed that the highest performance using hand-crafted features was achieved by extracting GLCM features and utilizing Support Vector Machine (SVM) with different kernels, reaching an accuracy of 99.78% and an AUC of 0.999. However, the deep learning Bi-LSTM network surpassed both methods, achieving an accuracy of 99.89% and an AUC of 1.0000. These findings suggest that the proposed methodology, combining hand-crafted features and deep learning, holds significant promise for enhancing early lung cancer detection and ultimately improving diagnosis systems.

• Ahmed, Muhammad Waqas; Alazeb, Abdulwahab; Mudawi, Naif Al; Sadiq, Touseef; Alabdullah, Bayan & Rehman, Hammed Ur [Vis alle 8 forfattere av denne artikkelen] (2025). Perception of Natural Scenes: Objects Detection and Segmentations using Saliency Map with AlexNet. The International Arab Journal of Information Technology (IAJIT). ISSN 1683-3198. doi: 10.34028/iajit/22/3/4. Fulltekst i vitenarkiv
• Ashraf, Muhammad Abrar; Najam, Shaheryar; Sadiq, Touseef; Algamdi, Shabbab; Aljuaid, Hanan & Rahman, Hameedur [Vis alle 7 forfattere av denne artikkelen] (2025). A Novel Telerehabilitation System for Physical Exercise Monitoring in Elderly Healthcare. IEEE Access. 13, s. 9120–9133. doi: 10.1109/ACCESS.2025.3526710. Fulltekst i vitenarkiv Vis sammendrag

  The increasing demand for remote healthcare solutions has driven the need for effective telerehabilitation systems to support elderly individuals recovering from chronic conditions or post-operative impairments. Existing rehabilitation methods face limitations such as restricted access to specialized care, overburdened healthcare providers, and the need for consistent, real-time monitoring. To address these challenges, we propose a novel telerehabilitation system that processes depth video frames using a multi-stage methodology. The pipeline begins with noise and floor removal, followed by 3D connected component labeling (CCL) to identify the human subject and extract the human silhouette. Next, skeleton joint points are estimated, and features are extracted from both the joints and silhouette. These multimodal features are fused and input into a deep learning model for classification and correctness assessment. Advanced feature extraction techniques, including Synchrosqueezing Transform (SST) and Hilbert-Huang Transform (HHT), are employed to capture dynamic time-frequency characteristics of human actions. The proposed system classifies nine distinct exercises and assesses the correctness of movements. Experimental evaluation on the IRDS dataset demonstrates a classification accuracy of 91% for exercise recognition and 82% for movement correctness assessment. These results highlight the system’s potential to deliver scalable, cost-effective, real-time rehabilitation, reducing the need for in-person clinical visits and supporting healthcare services for elderly populations.

• Liu, Ziang; Jian, Xiangzhou; Sadiq, Touseef; Shaikh, Zaffar Ahmed; Alfarraj, Osama & Alblehai, Fahad [Vis alle 7 forfattere av denne artikkelen] (2025). Efficient control of spider-like medical robots with capsule neural networks and modified spring search algorithm. Scientific Reports. 15. doi: 10.1038/s41598-025-95288-0. Fulltekst i vitenarkiv Vis sammendrag

  This study introduces an innovative method for gesture recognition in medical robotics, utilizing Capsule Neural Networks (CNNs) in conjunction with the Modified Spring Search Algorithm (MSSA). This approach achieves remarkable efficiency in gesture identification, facilitating precise control over medical robots. The proposed system undergoes thorough evaluation through both simulations and practical experiments, showing its capability to enhance patient outcomes in robotic surgical procedures. The primary contributions of this research include the creation of a unique CNN-MSSA architecture for gesture recognition, an extensive assessment of the system’s performance, and evidence of its potential to advance patient care. The findings indicate that the system attains an accuracy rate of 95% with a processing duration of 0.5 s, surpassing existing methodologies. These results carry significant implications for the advancement of autonomous medical robots and the enhancement of patient care in robotic surgery, underscoring the technology’s potential to improve the precision and efficiency of medical interventions.

• Saad, Syed; Rasheed, Kumeel; Ammad, Syed; Hasnain, Muhammad; Ullah, Habib & Qureshi, Abdul Hannan [Vis alle 9 forfattere av denne artikkelen] (2025). Offsite modular construction adoption in developing countries: Partial least square approach for sustainable future. Ain Shams Engineering Journal. ISSN 2090-4479. 16(1). doi: 10.1016/j.asej.2024.103228. Fulltekst i vitenarkiv Vis sammendrag

  The construction industry is significant in the economic growth of developing countries and is recognized globally for its high potential in sustainable development. Offsite Modular Construction (OMC) has the potential to revolutionize this sector. However, the adoption of OMC in developing nations remains limited due to various barriers. This study fills a critical gap by developing a novel framework that integrates the analysis of Offsite Modular Adoption Barriers (OMABs), i.e. resource availability, process management, and issues/perceptions, with the pursuit of overall sustainable future needs (OSFN) in residential projects. For this study, 314 construction specialists in Malaysia, a developing country with high construction activity, were surveyed. The study further employs PLS-SEM for latent variable relationship identification between OMABs and OSFN, which has not been researched comprehensively in the literature. The study reveals that there is a moderate positive correlation between OMABs and 33.6 % of the sustainable outcomes in residential projects. The path coefficient (β = 0.316) also provides evidence of the importance of eliminating these barriers in improving sustainability goals. This research is innovative in its approach as it seeks to address both the issues of OMC and sustainability in the developing nations. It is highly beneficial for policymakers as it provides a clear guideline on how to improve the OMC usage and promote sustainable construction. The SEM model can be used as a reference for other developing economies that are interested in the modernization of the construction industry for sustainable development.

• Ahmed, Muhammad Waqas; Sadiq, Touseef; Rahman, Hameedur; Alateyah, Sulaiman Abdullah; Alnusayri, Mohammed & Alatiyyah, Mohammed [Vis alle 7 forfattere av denne artikkelen] (2025). MAPE-ViT: multimodal scene understanding with novel wavelet-augmented Vision Transformer. PeerJ Computer Science. 11. doi: 10.7717/peerj-cs.2796. Fulltekst i vitenarkiv Vis sammendrag

  This article introduces Multimodal Adaptive Patch Embedding with Vision Transformer (MAPE-ViT), a novel approach for RGB-D scene classification that effectively addresses fundamental challenges of sensor misalignment, depth noise, and object boundary preservation. Our framework integrates maximally stable extremal regions (MSER) with wavelet coefficients to create comprehensive patch embedding that capture both local and global image features. These MSER-guided patches, incorporating original pixels and multi-scale wavelet information, serve as input to a Vision Transformer, which leverages its attention mechanisms to extract high-level semantic features. The feature discrimination capability is further enhanced through optimization using the Gray Wolf algorithm. The processed features then flow into a dual-stream architecture, where an extreme learning machine handles multi-object classification, while conditional random fields (CRF) manage scene-level categorization. Extensive experimental results demonstrate the effectiveness of our approach, showing significant improvements in classification accuracy compared to existing methods. Our system provides a robust solution for RGB-D scene understanding, particularly in challenging conditions where traditional approaches struggle with sensor artifacts and noise.

• Khurshid, Muhammad Rizwan; Manzoor, Sadaf; Sadiq, Touseef; Hussain, Lal; Khan, Mohammed Shahbaz & Dutta, Ashit Kumar (2025). Unveiling diabetes onset: Optimized XGBoost with Bayesian optimization for enhanced prediction. PLOS ONE. 20(1). doi: 10.1371/journal.pone.0310218. Fulltekst i vitenarkiv Vis sammendrag

  Diabetes, a chronic condition affecting millions worldwide, necessitates early intervention to prevent severe complications. While accurately predicting diabetes onset or progression remains challenging due to complex and imbalanced datasets, recent advancements in machine learning offer potential solutions. Traditional prediction models, often limited by default parameters, have been superseded by more sophisticated approaches. Leveraging Bayesian optimization to fine-tune XGBoost, researchers can harness the power of complex data analysis to improve predictive accuracy. By identifying key factors influencing diabetes risk, personalized prevention strategies can be developed, ultimately enhancing patient outcomes. Successful implementation requires meticulous data management, stringent ethical considerations, and seamless integration into healthcare systems. This study focused on optimizing the hyperparameters of an XGBoost ensemble machine learning model using Bayesian optimization. Compared to grid search XGBoost (accuracy: 97.24%, F1-score: 95.72%, MCC: 81.02%), the XGBoost with Bayesian optimization achieved slightly improved performance (accuracy: 97.26%, F1-score: 95.72%, MCC:81.18%). Although the improvements observed in this study are modest, the optimized XGBoost model with Bayesian optimization represents a promising step towards revolutionizing diabetes prevention and treatment. This approach holds significant potential to improve outcomes for individuals at risk of developing diabetes.

• Baloch, Amanullah; Ali, Mushtaq; Hussain, Lal; Sadiq, Touseef & Alkahtani, Badr S. (2025). Urdu Lip Reading Systems for Digits in Controlled and Uncontrolled Environment. IEEE Access. 13, s. 24906–24927. doi: 10.1109/ACCESS.2025.3531640. Fulltekst i vitenarkiv Vis sammendrag

  Lip reading technology can significantly benefit various domains, such as enhancing communication for the hearing impaired person, assisting in noisy environments, and improving security with silent password inputs. Despite advancements in lip reading for several languages, there has been limited success in developing an effective model for Urdu lip reading due to the lack of an appropriate dataset and the challenges faced by earlier models, such as the unsuccessful adaptation of the LipNet model to Urdu. To address these issues, we contribute by introducing the ULRD dataset, employing diverse data augmentation techniques, and comparing three DNN models: a Hybrid 2D-3D CNN-LSTM model, a LipNet-based 2D CNN-LSTM model, and a baseline 3D CNN-GRU model. Each model is evaluated in both controlled and uncontrolled environments, using both seen and unseen data. Results indicate that the LipNet-based 2D CNN-LSTM model achieves overall 92.15 % high accuracy in all conditions, but the Hybrid model demonstrates impressive generalization with an overall 90.00 % accuracy on unseen data due to its enhanced spatiotemporal feature extraction capability. Additionally, the precision: 0.91, recall: 0.91, and F1-Score: 0.91 results of LipNet-based 2D CNN-LSTM model are also high, then its other competitors models. The other various findings highlight the effectiveness of different DNN architectures and the potential improvements offered by the ULRD dataset for Urdu lip reading research.

Se alle arbeider i NVA

• Sadiq, Touseef (2026). Engineering Multimodal Retrieval Systems for Urban Traffic Scenes: Architectures, Fusion, and Performance Trade-offs. Universitetet i Agder. ISSN 9788284273358. Fulltekst i vitenarkiv Vis sammendrag

  Smarte byer er i økende grad avhengige av heterogene sensormodaliteter, som trafikkvideostrømmer og tekstlige beskrivelser, for ˚a støtte intelligente transportsystemer (ITS) og urban beslutningsstøtte. Gjenfinning av trafikkscener basert på naturlig språk gjør det mulig for operatører ˚a identifisere kjøretøy eller hendelser ved hjelp av menneskelig forst˚aelige forespørsler, men forblir utfordrende på grunn av modalitetenes heterogenitet, domene-spesifikk tvetydighet og begrenset robusthet i både unimodale og svakt justerte multimodale tilnærminger. Denne avhandlingen adresserer utfordringen ved å konstruere et enhetlig multimodalt gjenfinningsrammeverk for urbane trafikkscener som systematisk integrerer representasjonslæring, innebyggingsjustering og strukturert fusjon på beslutningsnivå. Hovedbidraget er å vise at robust gjenfinningsytelse krever koordinert systemdesign på tvers av komponenter, snarere enn isolerte modellforbedringer. Forskningen utvikles gjennom stadig mer raffinerte gjenfinningsarkitekturer, med et modulært baseline-system som kombinerer konvolusjonsbaserte visuelle trekk, transformerbaserte tekstrepresentasjoner og siamesisk likhetslæring for å etablere et tydelig referansepunkt for videre forbedringer. Kryssmodal justering styrkes deretter gjennom kontrastiv læring i et delt innebyggingsrom, og en multimodal fundamentmodell (LLaVA) tilpasses trafikkdomenet for å forbedre semantisk samspill utover konvensjonelle dual-encoder-arkitekturer. Til slutt analyseres og optimaliseres innebyggingsvalg og strukturert beslutningsnivå-fusjon for å forbedre gjenfinningskvalitet, rangstabilitet, tolkbarhet og beregningsmessig effektivitet. Det foreslåtte rammeverket integrerer multimodal semantisk generering, innebyggingsbasert gjenfinning og eksplisitte konsistensbegrensninger for attributter og bevegelse. Eksperimentell evaluering på CityFlow-NL-benchmarken viser at det komplette systemet oppnår en gjennomsnittlig reciprok rangering (MRR) på opptil 0,80, og leverer ytelse som er konkurransedyktig med sterke tidligere tilnærminger, samtidig som praktisk deployerbarhet ivaretas. Samlet viser avhandlingen at gjenfinning av urbane trafikkscener i stor grad er et systemdesignproblem som krever prinsipiell integrasjon av multimodale representasjoner, bevisst valg av innebygginger og strukturert fusjon som balanserer nøyaktighet, stabilitet og beregningskostnad, og som resulterer i et deployerbart og tolkbart rammeverk for ITS og bredere smarte urbane applikasjoner.

Se alle arbeider i NVA