Chronic diseases such as chronic kidney disease (CKD), diabetes, and heart disease remain major causes of mortality worldwide, highlighting the need for accurate and interpretable diagnostic models. However, conventional machine learning methods often face challenges of limited generalization, feature redundancy, and class imbalance in medical datasets. This study proposes an integrated classification framework that unifies three complementary feature paradigms: classical tabular attributes, deep latent features extracted through an unsupervised Long Short-Term Memory (LSTM) encoder, and quantum-inspired features derived from a five-qubit circuit implemented in PennyLane. These heterogeneous features are fused using a feature-wise attention mechanism combined with an AdaBoost classifier to dynamically weight feature contributions and enhance decision boundaries. Experiments were conducted on three benchmark medical datasets—CKD, early-stage diabetes, and heart disease—under both balanced and imbalanced configurations using stratified five-fold cross-validation. All preprocessing and feature extraction steps were carefully isolated within each fold to ensure fair evaluation. The proposed hybrid model consistently outperformed conventional and ensemble baselines, achieving peak accuracies of 99.75% (CKD), 96.73% (diabetes), and 91.40% (heart disease) with corresponding ROC AUCs up to 1.00. Ablation analyses confirmed that attention-based fusion substantially improved both accuracy and recall, particularly under imbalanced conditions, while SMOTE contributed minimally once feature-level optimization was applied. Overall, the attention-guided AdaBoost framework provides a robust and interpretable approach for clinical risk prediction, demonstrating that integrating diverse quantum, deep, and classical representations can significantly enhance feature discriminability and model reliability in structured medical data.

Indoor positioning technology based on smartphones plays an important role in the current technological development context. Especially in applications such as warehouses, supermarkets, hospitals, or buildings. While the global positioning system (GNSS) is popular and effective outdoors, it has several limitations when operating in enclosed spaces, such as indoors, due to the complexity of these environments. Smartphones have many built-in sensors (such as light sensors, sound sensors, gyroscopes, accelerometers, and magnetic sensors) and support the connection of various types of wireless communication technologies such as Wi-Fi and Bluetooth. However, such sensors were not initially developed for positioning applications. This study addresses the positioning problem using the MUSIC technique in conjunction with the Time of Arrival (ToA) method. The effectiveness of the positioning solution is evaluated through the signal-to-noise ratio (SNR) index. The absolute error and squared error indices are evaluated through the cumulative distribution function (CDF) to indicate the effectiveness of the proposed solution. Additionally, we propose a Pedestrian Dead Reckoning method to determine a person's position in indoor environments continuously. Based on the segmentation of the moving process by turns, the direction measurements in each segment are processed using a Kalman filter, which is designed to enhance the results achieved by the system. We also discuss the challenges and some future research directions in the field of smartphone-based indoor positioning.

In many wireless sensor network (WSN) applications, nodes are randomly deployed and self-organize into a wireless network to perform tasks. In practice, recharging the batteries of network nodes after deployment is often difficult. Network nodes often operate autonomously, so the main focus is on increasing the node lifetime. Data redundancy is another limitation that makes nodes inefficient. In most cases, densely deployed nodes in a monitoring area will have redundant data from neighboring nodes. Therefore, we propose a clustering technique to select the Cluster Head (CH) node in small-scale WSNs. Since transmission consumes more energy than data collection, this protocol enables reactive routing, where transmission occurs only when a certain threshold is reached. In addition, based on their heterogeneous energy levels, nodes can be grouped into three categories: Normal, Intermediate, and Advanced. Simulation results in MATLAB/Simulink show that, after approximately 3000 rounds, the proposed method successfully transmitted about 3.1 × 104 packets to the base station, compared to 2.3 × 104 packets for the Low Energy Adaptive Clustering Hierarchy (LEACH) protocol. In addition, the time when the last node died was approximately 3,500 rounds, whereas the LEACH protocol only maintained about 1,500 rounds. The results have shown the effectiveness of this technique in reducing the dead node rate and increasing packet transmission efficiency.

This paper presents a vehicle detection, tracking, and counting system for urban traffic videos based on integrating YOLOv9s and DeepSORT. The proposed method aims to address challenges such as occlusions, high vehicle density, and identity consistency in surveillance video analysis. A private dataset consisting of annotated traffic videos recorded in Thai Nguyen, Vietnam, was used for evaluation. The YOLOv9s model was selected for its balance between speed and accuracy, while DeepSORT provides robust multi-object tracking using appearance features and Kalman filtering. Experimental results demonstrate that the system achieves a mean Average Precision (mAP at 0.5) of 91.4%, an mAP at 0.5-0.95 of 82.7%, and operates at an average speed of 12.9 frames per second (FPS). Vehicle counting was validated against manually annotated ground truth with an average error rate of less than 4%. These results indicate that the proposed approach is both accurate and efficient for real-time traffic monitoring applications.

Object detection for sensing images is one of the promising research directions in computer vision. Applications for object detection from remote sensing images play an important role in analyzing aerial or satellite imagery. Benefits include applications in monitoring buildings and infrastructure, transportation, supporting search and rescue or responding to natural disasters, and environmental research. However, detecting objects in remote sensing images is difficult due to the diversity of shapes and sizes, viewing angles of objects, and complex background environments. In this paper, the authors present a Deep Learning (DL)-based object detection process from remotely sensed images, the main goal of which is to improve the ability to detect small objects in high-resolution aerial images. Implement and evaluate the super-slicing inference technique in the YOLOv11 model to improve the ability to detect very small and extremely small objects. Many simulation results are tested experimentally in the problem of detecting and tracking vehicles in Vietnam (Thai Nguyen). The results show that the system can accurately detect small objects such as pedestrians, motorbikes, and cars at a distance, with confidence ranging from 0.31 to 0.90. Some detection situations are successful even when the object is located at the edge of the slice. Finally, the authors discuss potential future research directions and unaddressed formulations.

This paper presents recent research in the field of human face recognition and detection. Technology development has marked a clear transformation in the implementation of recognition tasks. It is a transition from classical methods to methods with AI and deep learning applications. We have reviewed the latest works in famous journals to evaluate this field. This paper provides a comprehensive taxonomy across detection, identification, and tracking. It offers a comparative analysis of state-of-the-art AI approaches and highlights their strengths, limitations, and practical considerations. We have evaluated the level of compliance, completeness, and methodology of related studies. According to the results of our evaluation, significant improvements and developments have occurred in this field. However, some challenges still need to be focused on, such as improving the efficiency of training models in different environmental conditions. The negative effects of lighting conditions, occlusion of faces, or distortions due to different shooting angles are overcome.

This paper offers a brief analysis highlighting the effectiveness of several well-known Artificial Intelligence (AI) technologies applied in education, particularly in teaching and learning. It provides an overview of how modern classrooms can benefit from more effective teaching strategies that encourage students to engage in hands-on learning. Advanced technologies are changing how knowledge is found and shared, as well as how teaching is delivered. Memorization has been emphasized in educational models as a crucial learning skill until relatively recently. The technologies alter how knowledge is accessed and taught in schools today. Based on that, most knowledge is readily available, quickly accessible, and available online. The skills of reading, sharing, listening, and acting are now prerequisites for schooling. Most recent developments in advanced technologies in education are provided. Some analyses related to opening issues and challenges are shown for future work.

Nowadays, robots in the modern world are playing an important and increasingly popular role. MRA (Mobile Robotic Assistant) is a type of mobile robot designed to support humans in many different fields, helping to improve efficiency and safety in daily activities, work, or medical treatment. The number of MRAs is increasing and diverse in function, in addition to the ability to collect and process data, MRAs also have the ability to physically interact with users. Therefore, security is one of the important issues to improve the safety and effective operation of MRA. In this paper, through a comprehensive literature review and detailed analysis of the prominent MRA security attacks in recent years (based on criteria such as: attack targets, technologies used, impact level, feasibility, and contribution to addressing overall MRA security issues), a systematic classification by MRA activity fields is conducted. Security attacks, threats, and vulnerabilities are examined from various perspectives, such as hardware attacks or network/system-level attacks, operating systems/application software. Additionally, corresponding security solutions are proposed, compared, and evaluated to enhance MRA security. The paper also addresses challenges and suggests open research directions for the future.