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.

Transfer learning is a valuable tool for the effective assistance of gastroenterologists in the powerful diagnosis of medical images with fast convergence. It also intends to minimize the time and estimated effort required for improved gastrointestinal tract (GIT) diagnosis. GIT abnormalities are widely known to be fatal disorders leading to significant mortalities. It includes both upper and lower GIT disorders. The challenges of addressing GIT issues are complex and need significant study. Multiple challenges exist regarding computer-aided diagnosis (CAD) and endoscopy including a lack of annotated images, dark backgrounds, less contrast, noisy backgrounds, and irregular patterns. Deep learning and transfer learning have assisted gastroenterologists in effective diagnosis in various ways. The goal of proposed framework is the effective classification of endoscopic GIT images with enhanced accuracy. The proposed research aims to formulate a transfer learning-based deep ensemble model, accurately classifying GIT disorders for therapeutic purposes. The proposed model is based on weighted voting ensemble of the two state-of-the-art (STA) base models, NasNet-Mobile and EfficientNet. The extraction of regions of interest, specifically the sick portions, have been performed using images captured from endoscopic procedure. Performance evaluation of the proposed model is performed with cross-dataset evaluation. The datasets utilized include the training dataset HyperKvasir and two test datasets, Kvasir v1 and Kvasir v2. However, the dataset alone cannot create a robust model due to the unequal distribution of images across categories, making transfer learning a promising approach for model development. The evaluation of the proposed framework has been conducted by cross-dataset evaluation utilizing accuracy, precision, recall, Area under curve (AUC) score and F1 score performance metrics. The proposed work outperforms much of the existing transfer learning-based models giving 97.83% on Kvasir v1 and 98.45% accuracy on Kvasir v2.

Land use land cover classification from satellite images (remote sensing) has shown many efforts from the last decade due to ecological surveillance, rapid urbanization, law enforcement, climate change, agriculture drought, and disaster recovery. The low-resolution remote sensing images impact on the accurate prediction; therefore, the high-resolution deep learning architecture is widely required. This article proposes a new deep network-level fusion approach that merges a stacked residual self-attention CNN (SRAN3) with a lightweight ViT based on 4-encoders to enhance the model performance while reducing computational costs. The SRAN3 model is proposed for extracting sophisticated prominent features, while the 4-encoder-based ViT facilitates effective learning with reduced computation time. These networks are fused using a depth concatenation approach that effectively integrates the strengths of both architectures. The fused model hyperparameters are selected through Bayesian optimization, significantly improving the learning process. The trained model is later utilized in the testing phase, extracting features from the depth-concatenation layer. The extracted features are fed to neural network classifiers and obtain the final prediction. Two publicly available datasets, EuroSAT and NWPU_RESIS45, are employed to obtain improved testing and validation accuracy. The proposed SRAN3 + WNN (Wide Neural Network) and 4-encoder ViT + WNN obtained 96.9% and 92.6% of accuracy; however, the proposed fused network + WNN achieved the highest accuracy of 98.4% on EuroSAT and 94.7% accuracy on the NWPU_RESIS45 dataset, respectively. Also, the proposed fused model interpretation is performed using the explainable artificial technique (XAI), which has shown improved land use and land cover classification.

Hyperspectral images (HSIs) are highly complex, containing an enhanced spectral dimension compared to conventional images. Deep learning methods are increasingly being applied to process this three-dimensional data for hyperspectral image classification (HSIC). Existing convolutional and transformer-based methods often struggle with capturing fine-grained spectral-spatial dependencies, achieving high accuracy while balancing computational complexity. In order to solve these problems, we propose a novel SXSFormer network for HSIC. This novel approach integrates Squeeze and Expansion (SX) blocks into the Swin Transformer architecture to enhance feature extraction and attention mechanisms in the model. At its core, the novel SX Block recalibrates channel-wise features by temporarily expanding and then compressing channel dimensionality, allowing the model to focus on informative spectral bands and capture complex interdependencies. The SXSFormer, equipped with window-based multi-head self-attention, efficiently captures long-range dependencies with reduced computational complexity by partitioning input data into non-overlapping windows. Additionally, the SX block’s integration within the Swin Transformer enables improved global contextual understanding by selectively weighting the feature maps. We further refine the architecture using various components, such as patch extraction and embedding layers, and a patch merging strategy, ensuring efficient multi-scale feature extraction. Extensive experiments on four benchmark HSI datasets (SA, IP, PU, and KSC) demonstrate that the proposed model achieves remarkable test accuracies of 99.97%, 98.15%, 99.63%, and 98.14%, respectively, outperforming existing state-of-the-art methods. Our proposed approach also shows good generalization ability when applied to new datasets. Overall, our proposed approach represents a promising direction for HSIC.

Integrating Generative AI (GenAI) into Intelligent Transportation Systems (ITS) raises both enormous opportunities and major worries, especially in the areas of privacy and cybersecurity, which are already at the forefront of these developments. Developing and implementing robust security measures to secure sensitive data and address new cyber threats is of utmost importance, especially with the growing dependence on AI technology in transportation networks. This article looks at GenAI and how it may improve ITS intelligence and efficiency while addressing the risks of using it a lot. It delves into the difficulties of protecting AI-driven systems against hostile assaults (AI-MA), particularly emphasizing transportation infrastructure security, intrusion detection, and data privacy. The research stresses the significance of modern encryption methods, real-time monitoring threats, and adaptive security frameworks to ensure ITS are secure and resilient. In addition, it delves into how transportation systems are affected by ever-changing cyber threats, offering proactive security solutions to combat these dangers and strengthen ITS. This paper’s overarching goal is to lay out a course of action for integrating GenAI into ITS in a way that strikes a good balance between fostering innovation and ensuring privacy and security via thorough analysis. The proposed AI-MA model achieves a high threat detection accuracy of 96.2%, a privacy protection score of 91.8%, a computational efficiency of 92.9%, a resilience score of 97.8%, and a network reliability ratio of 92.6% compared to other existing models.