Wi-Sense: a passive human activity recognition system using Wi-Fi and convolutional neural network and its integration in health information systems

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.

ReWiS: Reliable Wi-Fi Sensing Through Few-Shot Multi-Antenna Multi-Receiver CSI Learning

“…Based on this result, we conclude that higher frequency can be beneficial for detecting activities with micromovements like respiratory detection [16]. 3) Comparison of CNN vs. ReWiS: Figure 9 compares the performance of ReWiS learning framework with a baseline CNN classifier [6]. The classifier utilizes a CNN for feature extraction with the same structure as the one ReWiS uses for embedding function training, explained in Section III-C. Further, a 3-layer fully connected network is used for classification.…”

“…Figure 1 shows a high-level overview of ReWiS and its key operations. The fundamental difference of ReWiS with respect to existing work is that instead of relying on traditional convolutional neural network (CNN)-based learning [6,7], ReWiS tackles the key problem of generalization through an approach based on fewshot learning (FSL), which (i) reduces the need of extensive data collection; (ii) allows ReWiS to rapidly generalize to new tasks by only leveraging a few new samples. Moreover, ReWiS leverages spatial diversity (i.e., multiple receivers and multiple antennas per receiver), time diversity (i.e., multiple CSI measurements) and increased subcarrier resolution to significantly improve the robustness of the sensing process.…”

“…We perform an extensive data collection campaign in three different propagation environments with two human subjects (IRB approval available upon request). We evaluate the impact of each diversity component on the performance and compare ReWiS with a convolutional neural network (CNN) approach [6]. Experimental results (Section V) show that the ReWiS improves the performance by about 40% with respect to existing singleantenna low-resolution approaches.…”

Asynchronous federated learning system for human–robot touch interaction

“…As the reader might have perceived, the system bears some resemblance to human activity recognition (HAR) systems (Kumari et al, 2021;Morris et al, 2014;Muaaz et al, 2021) (mainly in the realtime signal processing phase) since the information extracted from a microphone could also be extracted from an HAR device such as an accelerometer. The main difference between this kind of system and the one described in this section is that HAR systems, as their name implies, gravitate around a person doing an activity, while in our case, the central reference point is a robot.…”

Unmanned Ship Target Recognition System Based on Association Rules

“…Unmanned ship target recognition system is mainly aimed at the Marine environment in the unattended situation can not be fully the design of the problems of ship target in real time supervision of a ship target intelligent platform, mainly includes video acquisition module, the intelligent identification function module, the abnormal behavior based on rule template management module, data storage and transmission function module [9][10]. The function module of unmanned ship target recognition system is shown in Figure 1.…”