This study presents a machine learning (ML)-based localization method for improving location estimation accuracy in wireless networks, especially in challenging environments where traditional techniques often fall short. Conventional methods rely on a limited number of multipath components (MPCs), leading to inaccurate localization in complex environments. By leveraging a novel dataset generated from ray-tracing simulations in urban and campus environments, we propose a deep neural network (DNN)-based method that incorporates rich channel metrics such as angle of arrival (AoA), time of arrival (ToA), and received signal strength (RSS). The DNN is trained on diverse scenarios, including both line-of-sight (LoS) and non-line-of-sight (NLoS) conditions, and outperforms traditional MPC-based methods, reducing localization error by up to 20%. Our approach challenges the conventional use of only 3 MPCs for localization and demonstrates that a larger number of MPCs enhances accuracy, particularly in urban and obstructed environments. This research provides important insights into the potential of ML-driven solutions for improving localization accuracy in next-generation wireless systems , such as 5G and beyond.

Abstract Within the domain of image encryption, an intrinsic trade-off emerges between computational complexity and the integrity of data transmission security. Protecting digital images often requires extensive mathematical operations for robust security. However, this computational burden makes real-time applications unfeasible. The proposed research addresses this challenge by leveraging machine learning algorithms to optimize efficiency while maintaining high security. This methodology involves categorizing image pixel blocks into three classes: high-information, moderate-information, and low-information blocks using a support vector machine (SVM). Encryption is selectively applied to high and moderate information blocks, leaving low-information blocks untouched, significantly reducing computational time. To evaluate the proposed methodology, parameters like precision, recall, and F1-score are used for the machine learning component, and security is assessed using metrics like correlation, peak signal-to-noise ratio, mean square error, entropy, energy, and contrast. The results are exceptional, with accuracy, entropy, correlation, and energy values all at 97.4%, 7.9991, 0.0001, and 0.0153, respectively. Furthermore, this encryption scheme is highly efficient, completed in less than one second, as validated by a MATLAB tool. These findings emphasize the potential for efficient and secure image encryption, crucial for secure data transmission in rea-time applications.

The healthcare industry is currently seeing a significant rise in the use of mobile devices. These devices not only provide ways for communication and sharing of multimedia information, such as clinical notes and medical records, but also offer new possibilities for people to detect, monitor, and manage their health from anywhere at any time. Digital health technologies have the potential to improve patient care by making it more efficient, effective, and cost-effective. Utilizing digital devices and technologies can have a positive impact on many health conditions. This research focuses on dysphonia, a change in the sound of the voice that affects around one-third of individuals at some point in their lives. Voice disorders are becoming more common, despite being often overlooked. Mobile healthcare systems can provide quick and efficient assistance for detecting voice disorders. To make these systems reliable and accurate, it is important to develop an algorithm that can classify intelligently healthy and pathological voices. To achieve this task, we utilized a combination of several datasets such as Saarbruecken voice dataset (SVD), the Massachusetts Eye and Ear Infirmary database (MEEI), and a few private datasets of various voices (healthy and pathological) Additionally, we applied multiple machine learning algorithms, including decision tree, random forest, and support vector machine, to evaluate and determine the most effective algorithm among them for the detection of voice disorders. The experimental analyses are performed in terms of sensitivity, accuracy, receiver operating characteristic area, specificity, F-score and recall. The results demonstrated that the support vector machine algorithm, depending on the features selected by using appropriate feature selection methods, proved to be the most accurate in detecting voice diseases.