An approach to detect human body movement using different channel models and machine learning techniques

Abstract

Worldwide, 16.7 million people die each year due to cardiovascular disease. These statistics raise demand of devices like sensor-based pacemakers (PM) which are not just doing heart rate augmentation but also capable to transmit information via wireless link to on body sensor and support remote monitoring of such patients. As per the world health organization WHO reports there are more than 3 million functioning PMs and about 600,000 pacemakers are implanted each year in world. On an average, 70–80% of PMs are implanted in aged patients around 65 years or older. In addition to continuous monitoring of cardiovascular parameters, detection of physical movement of such patients may be helpful to assess their well-being. This paper has been formulated with an aim to highlight an approach which may be used to detect the physical movement of the patient using information signal received from implanted PM. The transmitted signal will experience a pathloss offered by wireless human body channel, which will affect the link quality parameters namely Signal to Noise Ratio (SNR) and Bit Error Rate (BER) and received signal strength indicator (RSSI). In the current work mathematical model has been formulated considering in body and on body channel propagation conditions and received power, received energy, pathloss, SNR, BER, bit rate, energy per bit and RSSI have been evaluated using IEEE802.15.6 channel models CM2 and CM3. Data set has been created and human body movement has been detected using Machine Learning (ML) techniques. Prediction accuracy of Multilayer Perceptron (MLP), k-Nearest Neighbours (kNN) and Random Forest have been compared. The analysis performed depicts that human body movement can be detected using different channel models and ML techniques such as MLP, kNN and Random Forest with an accuracy of 65.3%, 72.8% and 93.4% respectively. The critical comparison of the result indicates that the performance of Random Forest is better than MLP and kNN. This approach will be helpful in remote detection of human body movement of patients.