In recent years, wireless sensing has been exploited as a promising research direction for contactless human activity recognition. However, one major issue hindering the real deployment of these systems is that the signal variation patterns induced by the human activities with different devices and environmental settings are neither stable nor consistent, resulting in unstable system performance. The existing machine learning based methods usually take the "black box" approach and fails to achieve consistent performance. In this paper, we argue that a deep understanding of radio signal propagation in wireless sensing is needed, and it may be possible to develop a deterministic sensing model to make the signal variation patterns predictable. With this intuition, in this paper we investigate: 1) how wireless signals are affected by human activities taking transceiver location and environment settings into consideration; 2) a new deterministic sensing approach to model the received signal variation patterns for different human activities; 3) a proof-of-concept prototype to demonstrate our approach and a case study to detect diverse activities. In particular, we propose a diffraction-based sensing model to quantitatively determine the signal change with respect to a target's motions, which eventually links signal variation patterns with motions, and hence can be used to recognize human activities. Through our case study, we demonstrate that the diffraction-based sensing model is effective and robust in recognizing exercises and daily activities. In addition, we demonstrate that the proposed model improves the recognition accuracy of existing machine learning systems by above 10%.

Towards a Diffraction-based Sensing Approach on Human Activity Recognition

Recent research has shown great potential of exploiting Channel State Information (CSI) retrieved from commodity Wi-Fi devices for contactless human sensing in smart homes. Despite much work on Wi-Fi based indoor localization and motion/intrusion detection, no prior solution is capable of detecting a person entering a room with a precise sensing boundary, making room-based services infeasible in the real world. In this paper, we present WiBorder, an innovative technique for accurate determination of Wi-Fi sensing boundary. The key idea is to harness antenna diversity to effectively eliminate random phase shifts while amplifying through-wall amplitude attenuation. By designing a novel sensing metric and correlating it with human's through-wall discrimination, WiBorder is able to precisely determine Wi-Fi sensing boundaries by leveraging walls in our daily environments. To demonstrate the effectiveness of WiBorder, we have developed an intrusion detection system and an area detection system. Extensive results in real-life scenarios show that our intrusion detection system achieves a high detection rate of 99.4% and a low false alarm rate of 0.68%, and the area detection system's accuracy can be as high as 97.03%. To the best of our knowledge, WiBorder is the first work that enables precise sensing boundary determination via through-wall discrimination, which can immediately benefit other Wi-Fi based applications.

WiBorder: Precise Wi-Fi based Boundary Sensing via Through-wall Discrimination

The growing physical (PHY) layer capabilities of Wi-Fi have made it possible to use Wi-Fi signals for both communication and human sensing. Wi-Fi channel state information (CSI) in PHY layer can be obtained from commodity Wi-Fi devices. As CSI can detect the minute environment changes that alter signal propagation, it is thus capable of capturing the subtle human activities to provide cost-effective and easy-to-use human sensing. However, the limited bandwidth of each individual Wi-Fi channel fundamentally constrains the resolution of signals, resulting in poor performance of human sensing. In this paper, we present WiRIM, a resolution improving mechanism for Wi-Fi based human sensing. We design a channel switching and aggregation algorithm to extend the effective bandwidth of commodity Wi-Fi signals and improve the performance and efficiency of human sensing applications. With aggregated CSI, WiRIM constructs feature images which contain rich frequency, temporal and spatial characteristics, and then uses a deep learning method to process the extracted features. We propose a cross-location human activity recognition (CLHAR) scenario as a case study. The CLHAR scenario requires a high enough resolution of the Wi-Fi signals to accurately recognize different activities under the interference of tiny changes in human location. The experiments demonstrate the generality and effectiveness of the proposed mechanism.

/pdf/wirim-resolution-improving-mechanism-for-human-sensing-with-1kub9e9hio.pdf

WiRIM: Resolution Improving Mechanism for Human Sensing With Commodity Wi-Fi

The invention discloses a wireless signal Doppler frequency shift method for determining moving object direct reflection. The wireless signal Doppler frequency shift method can use channel state information on two antennas (namely CSI) to perform conjugate multiplying to eliminate random phase shift caused by non-synchronous wireless transmit-receive devices, and can obtain complete Doppler frequency shift information from the phase information of the channel state information which includes sizes and directions. The wireless signal Doppler frequency shift method for determining moving object direct reflection eliminates interference on the Doppler shift which is caused by frequency information of a static path so as to obtain more accurate frequency estimation. The wireless signal Doppler frequency shift method for determining moving object direct reflection can use multiple signal classification algorithm (MUSIC) to estimate a frequency spectrum according to a practical sampling interval and avoid an effect on the frequency estimation accuracy which is caused by uniform sampling by the practical wireless transmit-receive system.

Wireless signal Doppler frequency shift method for determining moving object direction reflection

Intrusion detection plays a rather important role in many applications, like asset protection and elder caring. Since we cannot make any requirements on the intruder, a device-free passive way of intrusion detection is much more promising and practical. In order to achieve robust passive intrusion detection, various techniques have been proposed, including video-based, infra-based and sensor-based approaches, among which dedicated device installation is often required. In this work, we present a real-time and robust device-free intrusion detection system, named RR-Alarm. By reusing the existing Wi-Fi signals, RR-Alarm is able to detect human intrusion in real time, at the same time, requiring no additional facilities installation. By utilizing the Doppler effects incurred by human motion on multiple Wi-Fi devices, RR-Alarm is not only able to accurately detect the intrusion without any extra human efforts but also avoids a large number of false alarms caused by the human motion from outside the house. A long-term trial in a nursing home verifies the effectiveness of our Wi-Fi based RR-Alarm system.

/pdf/a-real-time-and-robust-intrusion-detection-system-with-1vutg0290v.pdf

A real-time and robust intrusion detection system with commodity wi-fi

The invention discloses a non-contact perceptive positioning method A transmitting end is WiFi signal transmitting equipment; a receiving end is a WiFi signal receiver corresponding to the transmitting end; an antenna array is constructed to receive signals; based on the difference between antennas, and by utilization of signal coherence, the arrival angle of a reflected signal of a moving target is identified; simultaneously, the relative lengths of various reflection paths of the dynamic target are estimated by utilizing the difference between carriers having different frequencies; and the arrival angle of a signal of one of the reflection paths is selected and used as the angle of the positioning target relative to receiving equipment According to the non-contact perceptive positioning method disclosed by the invention, the positioning target does not need to carry any equipment; accurate non-contact perceptive positioning of a dynamic object can be realized by utilizing a WiFi network card; the position of the target can be determined by only needing one WiFi transmitting end and two WiFi receiving ends at least; the missing measurement value is complemented by utilizing the spatial and time continuities of movement simultaneously; and thus, the perceptible range is enlarged

Non-contact perceptive positioning method

Bodyweight exercises, such as push-up, sit-up, and squat, are effective forms of strength training to maintain good health. In order to improve people's exercise experience and provide feedback, lots of work has been done to monitor the bodyweight exercise by requiring people to wear special sensors on body. Different from traditional ways, a non-intrusive system WiFit is shown in this demo which uses surrounding Wi-Fi signals to monitor the bodyweight exercises without any attachment requirements. It not only could recognize the exercise type but also count the repetition number of exercise for diverse population even in different environments.

WiFit: A Bodyweight Exercise Monitoring System with Commodity Wi-Fi

The invention discloses an indoor activity detection method and system. The indoor activity detection method comprises the following steps: receiving wireless signals at two receiving points to obtainchannel state information; making difference between the phases in the channel state information of the two receiving points to obtain a phase difference signal sequence, and then performing interpolation processing on the phase difference; performing band-pass filtering on the phase difference after the interpolation processing; extracting features from the phase difference signal after the band-pass filtering, and calculating the standard deviation of the phase difference that the signal sequence is normalized through the manner of sliding window; and judging whether an activity exists in the current environment or not according to the standard deviation. According to the indoor activity detection method, the real-time mobile behavior detection can be realized by means of a commercial WiFi network card; and when the environment changes, the indoor activity detection method can automatically adapt to the environmental changes through the manner of self-learning without manual assistance; in addition, a number of novel processing mechanisms are provided by the invention to eliminate the interference caused by common scenes in life, therefore, the robustness of the mobile behaviordetection method is increased in general.

Indoor activity detection method and system

The invention discloses a moving object-reflected wireless signal identifying method. An emitting end in a wireless transmission environment is a wireless signal emitting device, and a receiving end in the wireless transmission environment is a wireless signal receiver corresponding to the emitting end. The moving object-reflected wireless signal identifying method is characterized in that devices at the wireless signal emitting end and the wireless signal receiving end are not required, signals can be received via an antenna array of the wireless signal receiving end, a direct path signal and a static object reflection path signal are combined into a static path signal via a signal processing method, an arrival angle of the static path signal and an arrival angle of a moving object reflection path signal can be automatically identified in signal identifying processes, and therefore a moving object-reflected wireless signal can be identified. A technical solution of the moving object-reflected wireless signal identifying method is low in equipment requirements, hardware change is not required, the method can be implemented in common commercial wireless equipment, rapid and convenient implementation can be achieved, and low cost and high benefits can be realized.

Moving object-reflected wireless signal identifying method

The invention discloses a contactless fitness exercise monitoring method. The method comprises the steps that receiving equipment with at least two antennas receives signals from transmitting equipment with at least one antenna in a wireless transmission mode; channel state information (CSI) of wireless transmission is measured, a CSI signal stream, a Doppler velocity flow and a Doppler shift floware obtained by processing the CSI; cutting is carried out on movement based on the obtained Doppler shift flow; based on cutting of the movement, classification features are extracted from the CSI signal flow, the Doppler velocity flow and the Doppler shift flow; the movement is classified based on the classification features to determine the type of the fitness exercise.

Li Xiang

Papers

Non-contact perceptive positioning method

WiFit: A Bodyweight Exercise Monitoring System with Commodity Wi-Fi

Indoor activity detection method and system

Moving object-reflected wireless signal identifying method

Unarmed fitness exercise monitoring method without contact perception