Node positioning or localization is a critical requisite for numerous position-based applications of wireless sensor network (WSN). Localization using the unmanned aerial vehicle (UAV) is preferred over localization using fixed terrestrial anchor node (FTAN) because of low implementation complexity and high accuracy. The conventional multilateration technique estimates the position of the unknown node (UN) based on the distance from the anchor node (AN) to UN that is obtained from the received signal strength (RSS) measurement. However, distortions in the propagation medium may yield incorrect distance measurement and as a result, the accuracy of RSS-multilateration is limited. Though the optimization based localization schemes are considered to be a better alternative, the performance of these schemes is not satisfactory if the distortions are non-linear. In such situations, the neural network (NN) architecture such as extreme learning machine (ELM) can be a better choice as it is a highly non-linear classifier. The ELM is even superior over its counterpart NN classifiers like multilayer perceptron (MLP) and radial basis function (RBF) due to its fast and strong learning ability. Thus, this paper provides a comparative review of various soft computing based localization techniques using both FTAN and aerial ANs for better acceptability.

In recent years, the deployment of massive multiuser multiple-input multiple-output (MU-MIMO) systems with hundreds or even thousands of antennas at the enhanced-mobile broadband station (e-MBBS) has gained considerable attention in the research community and industry for emerging applications such as millimeter-wave (mm-wave) communications, 5G and Beyond, Beamforming and spatial division multiple access (SDMA) and IoT and Wearable Devices. In this paper, we propose a novel low-complexity detection algorithm, namely lattice reduction associated reactive Tabu search (LR-RTS), capable of providing near-optimal detection performances by mitigating both the inter-antenna interference (IAI) and multi-user interference (MUI). The lattice reduction (LR)-based precoding scheme is first incorporated by the mobile user to suppress the IAI. Then, the novel LR-associated RTS detection algorithm is used at the e-MBBS to mitigate the MUI. The initial signal vector of this algorithm is chosen from the solution of the LR pre-coded ZF detector. Simulation results and comparisons with state-of-the-art methods show that the proposed solution outperforms heuristic search-based algorithms, namely likelihood ascent search (LAS) and linear detection methods like zero-forcing (ZF). In addition, our method offers a better tradeoff between performance and computational complexity for systems with a massive number of antennas and higher-order QAM modulations, showing a performance gain between 2dB and 9dB versus the conventional techniques.

The fact that cardiovascular disease (CVD) is a major cause of death worldwide highlights the significance of accurate prediction for successful preventative and treatment measures. Machine learning algorithms, which use the analysis of vast patient data to reveal hidden patterns and risk variables, have recently come to light as potential techniques for CVD prediction. This study intends to analyse how machine learning (ML) techniques are used in CVD prediction and evaluate how well they perform in comparison to conventional approaches. The study makes use of a sizable patient cohort's medical history, demographic data, and clinical factors in a complete dataset. Predictive models are built using a variety of machine learning algorithms, including support vector machine (SVM), gradient boosting, K-nearest neighbours, naive Bayes classifier, and logistic regression. To find the most important factors influencing CVD risk, feature selection techniques are used. Metrics like accuracy, sensitivity, specificity, and the area under the receiver operating characteristic curve are used to assess how well the machine learning models work. The outcomes are contrasted with well-known risk prediction models and clinical guidelines in order to assess the added value of machine learning methods. This work intends to improve CVD prediction capabilities and offer useful insights for better risk assessment and management strategies by utilizing the power of machine learning.