Non-Invasive Localization Using Software-Defined Radios

Abstract

Non-invasive indoor human activity detection using radio waves has attracted the interest of researchers, contributing to a range of new applications including smart healthcare. Localisation of activities can assist in developing advanced healthcare systems able to identify the location of patients. Radio frequencies have been shown in numerous studies as a non-invasive method to identify human activity. This is achieved by observing the signal propagation described in the Channel State Information (CSI). This paper presents experimental results using Universal Software-Defined Radio Peripheral (USRP) devices to identify and localise a single human subject performing activities by utilizing the CSI of radio frequencies. The experiments are carried out to retrieve CSI samples observing a single subject perform no-activity, sitting, standing, and leaning forward actions in various positions in a room. Additional CSI is captured for the subject walking in two directions across the observed area. Giving a total of 6 activities spanning the monitored area. CSI is also collected while the monitored area is empty for further comparison. Artificial intelligence is used to make classifications on collected CSI. The proposed approach uses a Super Learner (SL) algorithm that can identify the location of different activities with 96% accuracy, outperforming existing benchmark approaches.

Software-Defined Radio-Based Contactless Localization for Diverse Human Activity Recognition

“…Recent studies assert that WiFi transmissions can distinguish between even the tiniest movements of the human body, including those generated by the mouth, the fingertips on a keypad and the heart rate and respiratory rate [43]. Moreover, authors in [44] explored a novel approach towards localization-based activity recognition using CSI and made the dataset publicly available, which inspired our research to conduct analysis.…”

Radio frequency sensing and its innovative applications in diverse sectors: A comprehensive study

“…After collecting the data, they were fed into a deep learning algorithm and 83% accuracy was found in terms of multi-subject with 16 classification categories. Khan et al (2022) proposed noninvasive indoor human activity detection for smart home applications which is shown in Figure 12. The main focus of this study was to break the limit of localization and find the location of patients using universal software-defined radio peripheral (USRP) devices.…”

“…Block diagram demonstrating non-invasive indoor human activity detection for smart home applications using software-defined radios (Khan et al, 2022).…”

Channel State Information for Human Activity Recognition with Low Sampling Rates

“…One of these promising device-free sensing techniques is radio frequency-based sensing through channel state information in the Wi-Fi frequency range. It has been a steadily growing field over the past decade and is applicable in many domains of human activity recognition [1]- [3], vital sign monitoring [4]- [6], and localization [7]- [9]. Wi-Fi channel state information leverages the multi-path propagation of Wi-Fi point-to-point networks, as the same signal can traverse different paths and arrive multiple times at the same endpoint, albeit with different phases and amplitudes.…”