Search

MHealth systems establish a new way to transfer the health service to remote places. These systems offer significant benefits for continuous health monitoring. Motion activity recognition is one of the challenging mHealth use cases that incorporates continuous data collection and analysis of measurements. The main goal of this research is to analyze physical activity data. We employ measurements from the WISDM lab dataset ¹. These data are collected from participants performing motion activities. This data is then used by deep learning algorithms to predict special activities. In particular, CNN and CNN-LSTM algorithms are used to compare their accuracy, which resulted in approximately 95% and 97% respectively. Thus, the CNN-LSTM has higher accuracy in this analysis. [ABSTRACT FROM AUTHOR]

It has become widely accepted that the Internet of Things (IoT) devices and technologies are the key enablers for many emerging applications including remote health monitoring. Various physiological sensing devices have been designed and equipped with different radio technologies. The choice of radio hardware plays an important role on the overall performance of the system since it imposes some limitations on the delivered quality of service. Hence, it is critical to properly evaluate the embedded radio technology based on the application requirements. In this paper, we perform extensive experiments on Shimmer physiological sensors that is one of the leading providers of wearable wireless sensor products powered by Bluetooth classic radio. Shimmer sensors are designed and used for monitoring various human health information such as temperature, heart rate, movement, etc. We review and investigate different scenarios in which Shimmer devices are used by medical practitioners to monitor the ECG signal and the movement of a human. This study shows that the Shimmer device can provide reliable data delivery by using a specific configuration. For instance, employing a maximum number of seven Shimmer devices attached on a body at home environment within the range of at most 5 m and with the sampling rate of 512 Hz would result in a reasonable quality of service, while varying these parameters may degrade the overall performance. Mobility of human body, noisy environment, and higher packet transmission rates are some examples that will reduce the system quality. [ABSTRACT FROM AUTHOR]