Electrical & Computer Engineering Theses and Dissertations
Permanent URI for this collectionhttp://hdl.handle.net/1903/2765
Browse
2 results
Search Results
Item RADIO ANALYTICS FOR HUMAN ACTIVITY MONITORING AND INDOOR TRACKING(2018) Zhang, Feng; Liu, K. J. Ray; Electrical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)With the rapid development of the Internet of Things (IoT), wireless sensing has found wide applications from wellbeing monitoring, activity recognition, to indoor tracking. In this dissertation, we investigate the problem of wireless sensing for IoT applications using only ambient radio signals, e.g., WiFi, LTE, and 5G. In particular, our work mainly focuses on passive speed estimation, motion detection, sleep monitoring, and indoor tracking for wireless sensing. In this dissertation, we first study the problem of indoor speed estimation using WiFi channel state information (CSI). We develop the statistical electromagnetic (EM) wave theory for wireless sensing and establish a link between the autocorrelation function (ACF) of the physical layer CSI and the speed of a moving object. Based on the developed statistical EM wave theory for wireless sensing, we propose a universal low-complexity indoor speed estimation system leveraging CSI, which can work in both device-free and device-based situations. The proposed speed estimator differs from the other schemes requiring strong line-of-sight conditions between the source and observer in that it embraces the rich-scattering environment typical for indoors to facilitate highly accurate speed estimation. Moreover, as a calibration-free system, it saves the users' efforts from large-scale training and fine-tuning of system parameters. The proposed speed estimator can enable many IoT applications, e.g., gait monitoring, fall detection, and activity recognition. Then, we also study the problem of indoor motion detection using CSI. The statistical behaviors of the CSI dynamics when motion presents can be characterized by the developed statistical EM theory for wireless sensing. We formulate the motion detection problem as a hypothesis testing problem and also derive the relationship between the detection rate and false alarm rate for motion detection, which is independent of locations, environments and motion types. Thus, the proposed motion detection system can work in most indoor environments, without any scenario-tailored training efforts. Extensive experiments conducted in several facilities show that the proposed system can achieve better detection performance compared to the existing CSI-based motion detection systems while maintaining a much larger coverage and a much lower false alarm rate. This dissertation also focuses on sleep monitoring using CSI. First, we build a statistical model for maximizing the signal-to-noise (SNR) ratio of breathing signal, which accounts for all reflecting and scattering multipaths, allowing highly accurate and instantaneous breathing estimation with best-ever performance achieved on commodity devices. Our results demonstrate that the proposed breathing estimator yields a median absolute error of 0.47 bpm and a 95%-tile error of only 2.92 bpm for breathing estimation, and detects breathing robustly even when a person is 10m away from the WiFi link, or behind a wall. Then, we apply machine learning algorithms on the extracted features from the estimated breathing rates to classify different sleep stages, including wake, rapid eye movement (REM), and non-REM (NREM), which was previously only possible with dedicated hardware. Experimental results show that the proposed sleep monitoring system achieves sleep staging accuracy of 88%, outperforming advanced solutions using contact sensor or radar. The last work of this dissertation considers the problem of indoor tracking using CSI. First, we leverage a stationary and location-independent property of the time-reversal (TR) focusing effect of radio signals for highly accurate moving distance estimation, which plays a key role in the proposed indoor tracking system. Together with the direction estimation based on inertial measurement unit and location correction using the constraints from the floorplan, the proposed indoor tracking system is shown to be able to track a moving object with decimeter-level accuracy in different environments.Item Radio Analytics for Indoor Localization and Vital Sign Monitoring(2017) Chen, Chen; Liu, K. J. Ray; Electrical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Radio technology has been widely used for high-speed wireless communications. In the near future, radio technology would provide sensing capabilities to enable a diversified indoor applications in the era of Internet of Things (IoT). This is because that the electromagnetic (EM) wave, emitted from the transmitter propagates through multipath before arriving at the receiver, is varied by the environmental perturbations. Such variations in EM waves reveal important environmental changes useful for IoT applications. Thus, in IoT networks, radios are not only the ubiquitous communication interfaces but also exhibit augmented sensing potential. Despite the wide variety of IoT devices, most of them are equipped with WiFi which is a very mature and cost-effective connectivity solution and has evolved significantly ever since its standardization. Meanwhile, as people are spending more and more time indoors, most indoor spaces have been already equipped with WiFi infrastructures, which makes the IoT devices empowered by WiFi to blend into the existing WiFi infrastructures without efforts. Therefore, it is highly valuable to adopt radio analytics to analyze the WiFi radio signals to facilitate key IoT applications. In this dissertation, we explore the viability of using WiFi for two important IoT applications: indoor localization and vital sign monitoring. In the first part, we propose two indoor localization systems (IPSs) leveraging the time-reversal (TR) technique on off-the-shelf WiFi devices. The proposed IPSs utilize the location-specific features, i.e., the channel frequency response (CFR), which is a fine-grained information readily available on off-the-shelf devices that depicts the propagation of EM waves from the transmitter to different locations. The proposed IPSs consist of an offline phase which collects CFRs from locations-of-interest, and an online phase which compares the instantaneous CFRs with those captured in the offline phase. To calculate the similarities among locations, the TR focusing effect is evaluated quantitively between each pair of CFRs associated with these locations using the TR resonating strength (TRRS). Realizing that the bandwidth limit on mainstream WiFi devices could lead to location ambiguity, we exploit two diversities inherent in WiFi devices, i.e., frequency diversity and spatial diversity, to expand the effective bandwidth. Extensive experiments show a localization accuracy of 1 to 2 centimeters even under strong non-line-of-sight (NLOS) conditions as well as enhanced robustness against environmental dynamics. In the second part, we investigate the feasibility of high accuracy vital sign monitoring using CFRs. First of all, we present a highly accurate breathing monitoring system. Realizing that breathing injects tiny but periodic signals into the WiFi signal, we project the CFR time series onto the TRRS feature space to amplify such CFR perturbations. Integrated with machine learning techniques, the proposed scheme could distinguish breathing rates associated with different people. In addition, it could detect the presence of breathing and count the number of people. The performance is demonstrated by extensive experiments in multiple environments. Secondly, we present a lightweight vital sign monitoring solution with a much reduced computational complexity. Moreover, we supplement the proposed vital sign monitoring system with a finite state machine (FSM) to remedy the impact of motions on the monitoring performance. Extensive experimental results demonstrate the excellent performance of both breathing monitoring schemes.