Generating maps of indoor environments beyond the line-of-sight finds applications in several areas such as planning, navigation, and security. While researchers have previously explored the use of RF signals to generate maps, prior work has two important limitations: (i) it requires moving the mapping setup along the entire lengths of the sides of the building, and (ii) it generates maps that are not fully connected, rather are scatter plots of locations from where some obstacles reflected the signals. Thus, prior approaches require human interpretation to locate the walls and determine how they merge. In this article, we address these limitations and propose RFMap, which generates fully connected maps, and does not require the measurement setup to be moved along the sides of the buildings. To generate the map, RFMap first transmits RF signals in many different directions and then measures the distances of different reflectors inside the building. Next, it identifies these reflectors and classifies them into various types based on the properties of the reflections. A key challenge is that RFMap does not receive reflections from all the directions due to the specular nature of the reflectors. Due to this, it only gets sparse data about the objects in the environment. To address this challenge, RFMap trains a deep generative adversarial network (GAN) to intelligently predict the missing information. At runtime, it feeds the locations and types of the detected reflectors to the trained GAN and generates complete and accurate map. We implemented RFMap using software defined radios and extensively evaluated it in several real-world environments. Our results show that RFMap generated the maps of all the buildings that we tested it on with high accuracy.

Among the efforts to overcome the problem of rapidly saturating RF bands, visible light communication (VLC) is garnering a renewed interest as it can be enabled using commodity LED lamps. As indoor spaces are typically illuminated by multiple lamps comprising multiple LEDs each, a natural approach to efficiently utilize the bandwidth of all the LEDs is to use MIMO communication. The state of the art approach to decode MIMO streams is to use channel matrix. Although channel matrix based decoding method (CMDM) works very well in conventional RF technologies, when used in VLC, it suffers from several limitations, such as high sensitivity to environmental conditions, and need for sophisticated receivers. To overcome these limitations, we propose PCDM, a novel parallelogram - clustering based decoding method, which is fundamentally different from CMDM and achieves an order of magnitude lower bit error rate compared to CMDM. We implement and extensively evaluate these two methods using a real VLC MIMO testbed. Our results show that PCDM outperformed CMDM in all scenarios.

WiFi based gesture recognition has received significant attention overthe past few years. However, the key limitation of prior WiFi based gesture recognition systems is that they cannot recognize the gestures of multiple users performing them simultaneously. In this article, we address this limitation and propose WiMU, a WiFi based Multi-User gesture recognition system. The key idea behind WiMU is that when it detects that some users have performed some gestures simultaneously, it first automatically determines the number of simultaneously performed gestures (Na) and then, using the training samples collected from a single user, generates virtual samples for various plausible combinations of Na gestures. The key property of these virtual samples is that the virtual samples for any given combination of gestures are identical to the real samples that would result from real users performing that combination of gestures. WiMU compares the detected sample against these virtual samples and recognizes the simultaneously performed gestures. We implemented and extensively evaluated WiMU using commodity WiFi devices. Our results show that WiMU recognizes 2, 3, 4, 5, 6, 7, and 8 simultaneously performed gestures with accuracies of 95.6, 94.9, 93.9, 92.7, 91.6, 91.0, and 90.1 percent, respectively.

Generating maps of indoor environments beyond the line of sight finds applications in several areas such as planning, navigation, and security. While researchers have previously explored the use of RF signals to generate maps, prior work has two important limitations: (i) it requires moving the mapping setup along the entire lengths of the sides of the building, and (ii) it generates maps that are not fully connected, rather are scatter plots of locations from where some obstacles reflected the signals. Thus, prior approaches require human interpretation to locate the walls and determine how they merge. In this paper, we address these limitations and propose RFMap, which generates fully connected maps, and does not require the measurement setup to be moved along the sides of the buildings. To generate the map, RFMap first transmits RF signals in many different directions by rotating the antennas while keeping them at the same location and then measures the distances of different reflectors inside the building. Next, it identifies these reflectors and classifies them into various types based on the properties of the reflections. A key challenge is that RFMap does not receive reflections from all the directions due to the specular nature of the reflectors. Due to this, it only gets sparse data about the objects in the environment. To address this challenge, RFMap trains deep generative adversarial network (GAN) to intelligently predict the missing information. At runtime, it feeds the locations and types of the detected reflectors to the trained GAN and generates the complete and accurate map. We implemented RFMap using software defined radios and extensively evaluated it in several real world environments. Our results show that RFMap generated the maps of all the buildings that we tested it on with high accuracy.

Typical home security systems monitor homes for intrusions by installing contact sensors on doors and windows and motion sensors inside the house. Unfortunately, due to the high deployment and operational costs of today's home security systems, only a small fraction of homes have security systems installed (e.g., only 17% in the US and 15% in China). In this paper, we propose a WiFi based Home Security system (WiHS) that uses commodity WiFi devices, which most modern households already have, to perform the three primary tasks of typical home security systems: 1) detect when a door/window is opened/closed, 2) identify which door/window has been opened/closed, and 3) detect movements inside the house. The design of WiHS is based on our intuitive and theoretical understanding of the impacts of the movements of doors and windows on WiFi signals, which we will develop and present in this paper. We extensively evaluated WiHS using commodity WiFi devices in 3 different houses. WiHS detected intrusions with over 95% accuracy and identified the exact door/window that moved with just 4.5% average error.

Accurately measuring the distance traveled by an object or odometry, in indoor environments is important in many applications such as video-game controller tracking or robot route guidance. While the distance traveled by an object can be simply measured using an accelerometer, it is wellknown that distances measured with accelerometers suffer from large drift errors. In this paper, we demonstrate WIO, a WiFi-assisted Inertial Odometry technique that uses WiFi signals as an auxiliary source of information to correct such drift errors. The key intuition behind WIO is that, among multiple paths of a transmitted WiFi signal that arrive at a moving object equipped with a WiFi receiver, WIO can isolate the path that is most parallel to the object's direction of motion and use the change in the length of that path as an estimate of the traversed distance. WIO then fuses this distance estimate with the distance measured from an accelerometer on-board the object to correct drift errors. We implement WIO using commodity devices, and evaluate it on a robot car. Our results demonstrate an average error of just 4.37% in estimating the distance traversed by the car.

With the advent of the Internet of Things (IoT), sensor and actuator networks, subsequently referred to as IoT networks (IoTNs), are proliferating at an unprecedented rate in several newfound areas such as smart cities, health care, and transportation, and consequently, securing them is of paramount importance. We present NLSec, a fully distributed and lightweight framework that can detect arbitrary network layer (NL) attacks in any given IoTN, localize (i.e., identify) the compromised nodes, and mitigate the attacks by isolating the compromised nodes automatically. We also present insights obtained from an exploratory study on the effects of NL attacks on IoTNs, which guided us in designing NLSec.

WiFi based gesture recognition has received significant attention over the past few years. However, the key limitation of prior WiFi based gesture recognition systems is that they cannot recognize the gestures of multiple users performing them simultaneously. In this paper, we address this limitation and propose WiMU, a WiFi based Multi-User gesture recognition system. The key idea behind WiMU is that when it detects that some users have performed some gestures simultaneously, it first automatically determines the number of simultaneously performed gestures (Na) and then, using the training samples collected from a single user, generates virtual samples for various plausible combinations of Na gestures. The key property of these virtual samples is that the virtual samples for any given combination of gestures are identical to the real samples that would result from real users performing that combination of gestures. WiMU compares the detected sample against these virtual samples and recognizes the simultaneously performed gestures. We implemented and extensively evaluated WiMU using commodity WiFi devices. Our results show that WiMU recognizes 2, 3, 4, 5, and 6 simultaneously performed gestures with accuracies of 95.0, 94.6, 93.6, 92.6, and 90.9%, respectively.