No abstract

Over the last few years, indoor localization has been a very dynamic research area that has drawn great attention. Many methods have been proposed for indoor positioning as well as navigation services. A big number of them were based on Radio frequency (RF) technology and Radio Signal Strength Indicator (RSSI) for their simplicity of use. The main issues of the studies conducted in this field are related to the improvement of localization factors like accuracy, computational complexity, easiness of deployment and cost. In our study, we used Bluetooth Low Energy (BLE) technology for indoor localization in the context of a smart home where an elderly person can be located using an hybrid system that combines radio, light and sound information. In this paper, we propose a model that averages the received signal strength indication (RSSI) at any distance domain which offered accuracy down to 0.4 meters, depending on the deployment configuration

In this research, the photoplethysmogram (PPG) waveform analysis is utilized to develop a logistic regression-based predictive model for the classification of diabetes. The classifier has three predictors age, b/a, and SP indices in which they achieved an overall accuracy of 92.3% in the prediction of diabetes. In this study, a total of 587 subjects were enrolled. A total of 459 subjects were used for model training and development, while the rest of the 128 subjects were used for model testing and validation. The classifier was able to diagnose 63 patients correctly as diabetes while 27 subjects were wrongly classified as nondiabetes with an accuracy of 70%. Again, the model classified 479 subjects as nondiabetes correctly while it incorrectly classified 18 subjects as diabetes with an accuracy of 96.4%. Finally, the proposed model revealed an overall predictive accuracy of 92.3% which makes it a reliable surrogate measure for diabetes classification and prediction in clinical settings.

Coverage is one of the most important performance metrics for sensor networks that reflects how well a sensor field is monitored. In this paper, we are interested in studying the positioning and placement of sensor nodes in a WSN in order to maximize the coverage area and to optimize the audio localization in wireless sensor networks. First, we introduce the problem of deployment. Then we propose a mathematical formulation and a genetic based approach to solve this problem. Finally, we present the results of experimentations. This paper presents a genetic algorithm which aims at searching for an optimal or near optimal solution to the coverage holes problem. Compared with random deployment as well as existing methods, our genetic algorithm shows significant performance improvement in terms of quality.

Unemployment remains a serious issue for both developed and developing countries and a driving force to lose their monetary and financial impact. The estimation of the unemployment rate has drawn researchers' attention in recent years. This investigation's key objective is to inquire about the impact of COVID-19 on the unemployment rate in selected, developed and developing countries of Asia. For experts and policymakers, effective prediction of the unemployment rate is an influential test that assumes an important role in planning the monetary and financial development of a country. Numerous researchers have recently utilized conventional analysis tools for unemployment rate prediction. Notably, unemployment data sets are nonstationary. Therefore, modeling these time series by conventional methods can produce an arbitrary mistake. To overcome the accuracy problem associated with conventional approaches, this investigation assumes intelligent-based prediction approaches to deal with the unemployment data and to predict the unemployment rate for the upcoming years more precisely. These intelligent-based unemployment rate strategies will force their implications by repeating diversity in the unemployment rate. For illustration purposes, unemployment data sets of five advanced and five developing countries of Asia, essentially Japan, South Korea, Malaysia, Singapore, Hong Kong, and five agricultural countries (i.e., Pakistan, China, India, Bangladesh and Indonesia) are selected. The hybrid ARIMA-ARNN model performed well among all hybrid models for advanced countries of Asia, while the hybrid ARIMA-ANN outperformed for developing countries aside from China, and hybrid ARIMA-SVM performed well for China. Furthermore, for future unemployment rate prediction, these selected models are utilized. The result displays that in developing countries of Asia, the unemployment rate will be three times higher as compared to advanced countries in the coming years, and it will take double the time to address the impacts of Coronavirus in developing countries than in developed countries of Asia.