Human emotion recognition (HER) has rapidly advanced, with applications in intelligent customer service, adaptive system training, human–robot interaction (HRI), and mental health monitoring. HER’s primary goal is to accurately recognize and classify emotions from digital inputs. Emotion recognition (ER) and feature extraction have long been core elements of HER, with deep neural networks (DNNs), particularly convolutional neural networks (CNNs), playing a critical role due to their superior visual feature extraction capabilities. This study proposes improving HER by integrating EfficientNet with transfer learning (TL) to train CNNs. Initially, an efficient R‐CNN accurately recognizes faces in online and offline videos. The ensemble classification model is trained by combining features from four CNN models using feature pooling. The novel VGG‐19 block is used to enhance the Faster R‐CNN learning block, boosting face recognition efficiency and accuracy. The model benefits from fully connected mean pooling, dense pooling, and global dropout layers, solving the evanescent gradient issue. Tested on CK+, FER‐2013, and the custom novel HER dataset (HERD), the approach shows significant accuracy improvements, reaching 89.23% (CK+), 94.36% (FER‐2013), and 97.01% (HERD), proving its robustness and effectiveness.

This study advances artificial intelligence by pioneering the classification of human emotions (for patients) with a healthcare mobile robot, anticipating human–robot interaction for humans (patients) admitted in hospitals or any healthcare environment. This study delves into the challenge of accurately classifying humans emotion as a patient emotion, which is a critical factor in understanding patients’ recent moods and situations. We integrate convolutional neural networks (CNNs), recurrent neural networks (RNNs), and multi-layer perceptrons (MLPs) to analyze facial emotions comprehensively. The process begins by deploying a faster region-based convolutional neural network (Faster R-CNN) to swiftly and accurately identify human emotions in real-time and recorded video feeds. This includes advanced feature extraction across three CNN models and innovative fusion techniques, which strengthen the improved Inception-V3 for superior accuracy and replace the improved Faster R-CNN feature learning module. This valuable replacement aims to enhance the accuracy of face detection in our proposed framework. Carefully acquired these datasets in a simulated environment. Validation on the EMOTIC, CK+, FER-2013, and AffectNet datasets all showed impressive accuracy rates of 98.01%, 99.53%, 99.27%, and 96.81%, respectively. These class-wise accuracy rates show that it has the potential to advance the medical environment and measures in the intelligent manufacturing of healthcare mobile robots.

This paper introduces a real-time head-pose detection and eye-gaze estimation system for Automatic Driver Assistance Technology (ADAT) aimed at enhancing driver safety by accurately collecting and transmitting data on the driver’s head position and eye gaze to mitigate potential risks. Existing methods are constrained by significant limitations, including reduced accuracy under challenging conditions such as varying head orientations and lighting, higher latency in real-time applications (e.g., Faster-RCNN and TPH-YOLOv5), and computational inefficiency, which hinders their deployment in resource-constrained environments. To address these challenges, we propose a novel framework using the Transformer Detection of Gaze Head - YOLOv7 (TDGH-YOLOv7) object detector. The key contributions of this work include the development of a reference image dataset encompassing diverse vertical and horizontal gaze positions alongside the implementation of an optimized detection system that achieves state-of-the-art performance in terms of accuracy and latency. The proposed system achieves superior precision, with a weighted accuracy of 95.02% and Root Mean Square Errors of 2.23 and 1.68 for vertical and horizontal gaze estimation, respectively, validated on the MPII-Gaze and DG-Unicamp datasets. A comprehensive comparative analysis with existing models, such as CNN, SSD, Faster-RCNN, and YOLOv8, underscores the robustness and efficiency of the proposed approach. Finally, the implications of these findings are discussed, and potential avenues for future research are outlined.

New technologies in human emotion recognition (HER) have drawn considerable attention to use in the fields of security, intelligent customer service, healthcare, educational, human-robot interaction (HRI), and adaptive system training. To identify human emotions, our model incorporates MobileNetV3, Vision Transformer (ViT), RegNet and SE-ResNeXt into a unique deep ensemble classification structure. A Novel Multi Module Neural Networks (MMNNs) architecture is designed in this research for HER for practical application the main purpose of is to identify the human emotions. An innovative approach to improve the performance of HER by integrating MMNNs with Transfer Learning (TL) to train CNNs is researched. The MMNNs classification model is trained by combining features from four CNN models using feature pooling. The key novelty of the model is the novel DEtection TRansformer (DETR) which enhances the CNN learning block. It consists of a CNN that learns low dimensional feature representation, an encoder decoder transformer and a simple Feed Forward Network (FFN) that outputs the final detection prediction, which ultimately boosts face recognition efficiency and accuracy. The MMNNs results are validated on AffectNet, CK + and a custom-made dataset (CMD) achieving accuracy of 91.07%, 87.03% and 96.98% respectively which is further increased by data augmentation technique to 95.09%, 89.15% and 98.13% respectively.

The exponential growth of multimedia content in the digital age has necessitated the development of advanced cross-lingual systems capable of understanding and interpreting visual information across different languages. However, current efforts have predominantly been focused on monolingual tasks, leaving a substantial gap in cross-lingual multimedia analysis, particularly for non-English languages. To address this gap, AraTraditions10k, a comprehensive and culturally rich dataset, has been introduced to enhance cross-lingual image annotation, retrieval, and tagging, with a specific focus on Arabic and English languages. The dataset consists of 10,000 carefully curated images representing diverse aspects of Arabic culture, each annotated with five captions in Modern Standard Arabic (MSA) and professionally translated into English. To maximize the utility of the dataset, advanced machine learning models, including a Multi-Layer Perceptron (MLP) for tag recommendation and an enhanced Word2VisualVec (W2VV) model for sentence recommendation, have been developed. These models have been augmented with attention mechanisms and contrastive loss functions, resulting in measurable performance improvements. Notably, the tag recommendation system achieved an overall top-1 accuracy of 93%, while the sentence recommendation system for the English language attained BLEU-4, METEOR, ROUGE-L, CIDEr, and SPICE scores of 78.2, 68.3, 75.8, 136.7, and 52.0, respectively. By addressing the linguistic and cultural gaps in existing datasets, AraTraditions10k establishes a new benchmark for the quality and inclusivity of multilingual datasets, contributing to the broader field of cross-lingual multimedia analysis and facilitating the development of more accessible and culturally sensitive multimedia technologies.

The Internet of Medical Things (IoMT) has revolutionized healthcare by enabling seamless connectivity among medical devices for real-time monitoring and diagnosis. However, the dynamic nature and resource constraints of IoMT networks present significant challenges in ensuring energy efficiency, reliable communication, and optimal performance. For addressing the mentioned issues and challenges, we propose a comprehensive routing framework, Improved Distance and Energy Aware Link Stability (IDEALS) protocol, designed to optimise distance, Energy Consumption (EC), and Link Stability (LS). Our protocol incorporates a distance-aware routing mechanism to minimize Path Loss (PL), an Energy-Efficient (EE) communication approach to extend Network Lifetime (NLT), and LS prediction algorithm for enhancing reliability in dynamic environments. Additionally, it considers the integration of Random Waypoint Mobility (RWM) and Gauss-Markov Mobility (GMM) models for static and dynamic mobility of the nodes within the network. The IDEALS protocol uses a smart decision-making method. This helps it manage key factors well regarding the node movement and static factors. It’s great for IoMT applications because it scales and adapts easily. The protocol is evaluated with state-of-the-art (SOTA) protocols regarding different evaluation metrics. Simulations show that IDEALS performs better than other protocols. It measures how quickly nodes fail and how well data is delivered. It also performs well in big networks, busy areas, and when devices are moving around. IDEALS is a solid choice for solving challenges in IoMT networks. It helps make healthcare delivery more efficient and reliable across different situations.