Visual impairment affects millions worldwide, creating significant barriers to environmental interaction and independence. Existing assistive technologies often rely on cloud-based processing, raising privacy concerns and limiting accessibility in resource-constrained environments. This paper explores the integration and potential of open-source AI models in developing a fully offline assistive system that can be locally set up and operated to support visually impaired individuals. Built on a Raspberry Pi 5, the system combines real-time object detection (YOLOv8), optical character recognition (Tesseract), face recognition with voice-guided registration, and offline voice command control (VOSK), delivering hands-free multimodal interaction without dependence on cloud infrastructure. Audio feedback is generated using Piper for real-time environmental awareness. Designed to prioritize user privacy, low latency, and affordability, the platform demonstrates that effective assistive functionality can be achieved using only open-source tools on low-power edge hardware. Evaluation results in controlled conditions show 75–90% detection and recognition accuracies, with sub-second response times, confirming the feasibility of deploying such systems in privacy-sensitive or resource-constrained environments.

The prediction of new COVID-19 cases is crucial for decision makers in many countries. Researchers are continually proposing new models to forecast the future tendencies of this pandemic, among which long short-term memory (LSTM) artificial neural networks have exhibited relative superiority compared to other forecasting techniques. Moreover, the correlation between the spread of COVID-19 and exogenous factors, specifically weather features, has been explored to improve forecasting models. However, contradictory results have been reported regarding the incorporation of weather features into COVID-19 forecasting models. Therefore, this study compares uni-variate with bi- and multi-variate LSTM forecasting models for predicting COVID-19 cases, among which the latter models consider weather features. LSTM models were used to forecast COVID-19 cases in the six Gulf Cooperation Council countries. The root mean square error (RMSE) and coefficient of determination ($R^2$) were employed to measure the accuracy of the LSTM forecasting models. Despite similar weather conditions, the weather features that exhibited the strongest correlation with COVID-19 cases differed among the six countries. Moreover, according to the statistical comparisons that were conducted, the improvements gained by including weather features were insignificant in terms of the RMSE values and marginally significant in terms of the $R^2$ values. Consequently, it is concluded that the uni-variate LSTM models were as good as the best bi- and multi-variate LSTM models; therefore, weather features need not be included. Furthermore, we could not identify a single weather feature that can consistently improve the forecasting accuracy.

Numerous research studies have emphasized the significance of accurately detecting head impacts and implementing safety measures. This study addresses this crucial need by utilizing machine learning algorithms applied to data from piezoelectric sensors on a simulated head model. Employing a systematic approach, this work utilizes Random Forest (RF) and Extreme Gradient Boosting (XGBoost) models to process the normalized sensor data, aiming to pinpoint impact locations with high precision. Through rigorous k-fold cross-validation and comprehensive performance analysis, the study reveals that the XGBoost model slightly outperforms the RF model, achieving an RMSE of 0.4764 and an R^2 of 0.9485. Feature importance evaluations suggest an optimal sensor placement strategy, potentially reducing the model complexity while retaining predictive accuracy. The superior performance of the XGBoost model, combined with strategic sensor placement, highlights the study’s contribution to enhancing head impact safety measures in sports and industrial settings. The findings pave the way for future research into the deployment of intelligent safety systems, leveraging the synergy between wearable technology and machine learning.

In the rapidly evolving field of radio frequency (RF) engineering, precise antenna alignment remains a critical challenge, directly influencing communication performance and reliability. This study presents a comprehensive comparative analysis of three advanced machine learning models—Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN), and Multilayer Perceptron (MLP)—to predict antenna alignments based on S-parameter measurements. By addressing the complexities of both distance and angle predictions, our approach demonstrates the efficacy of these neural network architectures in automating alignment tasks traditionally reliant on manual intervention. The results reveal that the MLP and LSTM models excel in distance prediction, achieving a remarkable accuracy of 97%, while the CNN model outperforms in angle prediction with an accuracy of 86%. The study further highlights the strengths and limitations of each model, offering valuable insights into their applicability for RF engineering tasks. By providing a robust machine learning framework, this research contributes significantly to advancing automated alignment processes, reducing dependency on manual methods, and paving the way for future innovations in RF systems. These findings have far-reaching implications for the development of intelligent and scalable solutions in wireless communication systems.