Advancements in automation and artificial intelligence have significantly impacted accessibility for individuals with visual impairments, particularly in the realm of bus public transportation. Effective bus detection and bus point-of-view (POV) classification are crucial for enhancing the independence of visually impaired individuals. This study introduces the Improved-YOLOv10, a novel model designed to tackle challenges in bus identification and pov classification by integrating Coordinate Attention (CA) and Adaptive Kernel Convolution (AKConv) into the YOLOv10 framework. The Improved YOLOv10 advances the YOLOv10 architecture through the incorporation of CA, which enhances long-range dependency modeling and spatial awareness, and AKConv, which dynamically adjusts convolutional kernels for superior feature extraction. These enhancements aim to improve both detection accuracy and efficiency, essential for real-time applications in assistive technologies. Evaluation results demonstrate that the Improved-YOLOv10 offers significant improvements in detection performance, including better Accuracy, Precision and Recall compared to YOLOv10. The model also exhibits reduced computational complexity and storage requirements, highlighting its efficiency. While the classification results show some trade-offs, with slightly decreased overall F1 score, the complexity of Giga Floating Point Operations (GFLOPs), Parameters, and Weight/MB in the Improved-YOLOv10 remains advantageous for classification tasks. The model’s architectural improvements contribute to its robustness and efficiency, making it a suitable choice for real-time applications and assistive technologies.

Players’ engagement intensity in computer games is influenced by the level of difficulty the game offers. Traditional game-level plots adopt linear increases that sometimes do not match the users’ skill growth, causing boredom and hampering the users’ further skill growth. In this study, a nonlinear level adjustment scenario was proposed based on the Fibonacci sequence that provides gradual increases in the early stages of the games but more drastic changes in later phases. Here, the game’s difficulty level was automatically decided by a machine learning method. To test the proposed method, comparisons between four level adjustments in computer games: traditional plots, self-selected plots, linear adaptive plots, and the proposed nonlinear adaptive plots were run. The experiment was carried out with 40 testers. The experiment results show that the best player’s peak level in the proposed nonlinear adjustment was twice as high as that of linear adjustment. Also, the number of stages required to reach the peak under the proposed scenario was half that of linear games. This high playing performance goes hand in hand with deep playing engagement. The results demonstrate the efficiency of the proposed level adjustment algorithm.

In recent years, with the increase of online learning platforms, obtaining learning behavior data from students, are becoming easy. However, analyzing the data In recent years, with the increase of online learning platforms, obtaining learning behavior data from students, are becoming easy. However, analyzing the data

Technology is being utilized by everyone in the age of globalization to perform or complete routine tasks that are vital for survival. However, some parts of the human population are unable to carry out daily activities due to a lack or inability to move the body's locomotors, such as the hands and feet. Smart wheelchairs that can accept input using only eye movements combined with facial landmark methods have been the focus of previous research. Regrettably, it did no longer produce the predicted level of accuracy considering previous research only focused on the eye area, which does no longer take into consideration the opportunity of disabled humans having abnormalities in the eye area as well. As a result, this lookup used to be carried out by making use of head movement whilst nonetheless being integrated with facial landmarks, and based totally on the distance of the head and camera on the wheelchair to be able to direct and manipulate the clever wheelchair in order for it to be used properly. The focal point of this find out about was on managing head actions as inputs to direct the wheelchair closer to four directions, such as Turn left, turn right, straight forward, and stopping, with the integration of minimum (30 cm), fantastic (30-40 Cm), and maximum (50-60) distances in the experiment. This study generates a fairly exceptional stage of accuracy at a distance of 30-40 cm, ensuing in an increasingly extraordinary accuracy rate of 98%..

This paper presents the design, implementation, and field evaluation of RSV Emas, a compact, solar-powered, remotely operated surface vehicle (RSV) developed for autonomous water quality monitoring. The system introduces a novel integration of three key technologies: renewable energy harvesting for extended mission endurance, a fuzzy-PID hybrid control algorithm for adaptive navigation, and embedded piezoelectric actuators for real-time stabilization in dynamic aquatic conditions. RSV Emas is equipped with a multi-sensor suite capable of measuring temperature, pH, turbidity, and total dissolved solids, with data transmitted wirelessly to a remote dashboard. Field experiments in a controlled freshwater pond demonstrate that the vehicle can operate autonomously for over six hours under moderate sunlight, maintain stable trajectory with less than 0.5 m path deviation, and reduce tilt oscillations by up to 38% through smart material-based stabilization. These results confirm that RSV Emas offers a cost-effective, energy-efficient, and scalable platform for real-time water quality assessment, with potential applicability in environmental management and early pollution detection.