Deep Learning Analysis of Location Sensor Data for Human‐Activity Recognition
Hariprasath Manoharan, Ganesan Sivarajan, Subramanian Srikrishna · 2021
For improving the working efficiency of sensors and for testing them under different conditions, a predictive algorithm is essential. This is possible only when deep learning methods are used, where different strategies are followed when any problem occurs on the network. The health-monitoring system has been integrated with SDAE, and the results are simulated using MATLAB encoder toolbox. The simulation setup for health monitoring using SDAE has been executed, and similar works of other researchers that include artificial neural networks have been investigated, and the results are also compared. The results are simulated by considering parameters such as path loss, cost, energy, and lifetime. The efficiency of SDAE was tested with four deep learning techniques, including SAE, LTS, K-nearest neighbor, and neural network methods, and SDAE proved very efficient in terms of sensor integration for monitoring the health of individuals when different sensor nodes are placed in the human body.