Abstract
A human activity recognition (HAR) system acts as the backbone of many human-centric applications, such as active assisted living and in-home monitoring for elderly and physically impaired people. Although existing Wi-Fi-based human activity recognition methods report good results, their performance is affected by the changes in the ambient environment. In this work, we present Wi-Sense—a human activity recognition system that uses a convolutional neural network (CNN) to recognize human activities based on the environment-independent fingerprints extracted from the Wi-Fi channel state information (CSI). First, Wi-Sense captures the CSI by using a standard Wi-Fi network interface card. Wi-Sense applies the CSI ratio method to reduce the noise and the impact of the phase offset. In addition, it applies the principal component analysis to remove redundant information. This step not only reduces the data dimension but also removes the environmental impact. Thereafter, we compute the processed data spectrogram which reveals environment-independent time-variant micro-Doppler fingerprints of the performed activity. We use these spectrogram images to train a CNN. We evaluate our approach by using a human activity data set collected from nine volunteers in an indoor environment. Our results show that Wi-Sense can recognize these activities with an overall accuracy of 97.78%. To stress on the applicability of the proposed Wi-Sense system, we provide an overview of the standards involved in the health information systems and systematically describe how Wi-Sense HAR system can be integrated into the eHealth infrastructure.
Highlights
The world demographics reveal that the elderly population is rapidly increasing across the globe
We presented the Wi-Sense human activity recognition (HAR) system, which combines radio frequency (RF) sensing and deep learning techniques to recognize human activities including falls
The testing data set was used to evaluate the performance of the convolutional neural network (CNN)
Summary
The world demographics reveal that the elderly population is rapidly increasing across the globe. Vision-based HAR systems are generally considered very accurate in recognizing human activities, but they do not cope well with changes in the ambient environment. Wearable sensor–based HAR systems use inertial sensors to capture the user’s dynamic body movements while performing different activities. Wearable sensor–based HAR systems can be considered as a viable alternative to vision-based HAR systems because they are immune to changes in the ambient environment and do not suffer from privacy risks. RF-based HAR systems work on the principle that human bodies reflect RF signals, and human movements introduce variations in the frequencies of the RF signals due to the physical phenomenon known as the Doppler effect These variation-enriched RF signals are used to recognize human activities. Since last few years, researchers have been diligently exploring and developing RF-based HAR techniques
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call