Search

The existing RF-based liquid identification methods commonly require a training network of liquid or the container information, such as material and width. Moreover, status quo methods are inapplicable when the solution height is lower than that of the antenna, which is generally unknown either. This paper proposes LiqRay, an RF-based solution, retaining non-invasive and fine-grained liquid recognition abilities, thus can recognize unknown solutions without prior knowledge. In dealing with the unknown container material and width, we utilize a dual-antenna model and craft a relative frequency response factor, exploring diversity of the permittivity in frequency domain. In tackling the unknown heights of solution and antenna, we devise the electric field distribution model at the receiving antenna, solving the unknown heights via spatio-differential model. Among eight different solvents, LiqRay can identify alcohol solutions with a concentration difference of 1% with 94.92% accuracy. Nevertheless, LiqRay can obtain the relative frequency response factor with a relative error of 6.7% without being affected by the height of the solution. Even if it is merely 4 cm, this is fairly lower than that of most antennas' heights, since the operating frequency is around 2 GHz. [ABSTRACT FROM AUTHOR]

Mobile-centric AI applications put forward high requirements for resource-efficiency of model inference. Input filtering is a promising approach to eliminate the redundancy in the input so as to reduce the cost of inference. Previous efforts have tailored effective solutions for many applications, but left two essential questions unanswered: (1) theoretical filterability of an inference workload to guide the application of input filtering techniques, thereby avoiding the trial-and-error cost for resource-constrained mobile applications; (2) robust discriminability of feature embedding to allow input filtering to be widely effective for diverse inference tasks and input content. To answer these questions, we first provide a generic formalization of the input filtering problem and theoretically compare the hypothesis complexity of inference models and their input filters to understand the optimization potential of applying input filtering. Then we propose the first end-to-end learnable input filtering framework that covers most state-of-the-art methods and surpasses them in feature embedding with robust discriminability. Based on our framework, we design and implement an input filtering system InFi supporting six input modalities. InFi is the first to support text and sensor signal inputs and model partitioning deployments widely adopted by under-resourced mobile systems. Comprehensive evaluations confirm our theoretical results and show that InFi outperforms strong baselines in applicability, accuracy, and efficiency, owing to its generality and end-to-end learnability. InFi can achieve 8.5x throughput and save 95% bandwidth, while keeping over 90% accuracy, for a video analytics app on mobile platforms. [ABSTRACT FROM AUTHOR]

This paper presents the design, implementation and evaluation of In-N-Out, a software-hardware solution for far-field wireless power transfer. In-N-Out can continuously charge a medical implant residing in deep tissues at near-optimal beamforming power, even when the implant moves around inside the human body. To accomplish this, we exploit the unique energy ball pattern of distributed antenna array and devise a backscatter-assisted beamforming algorithm that can concentrate RF energy on a tiny spot surrounding the medical implant. Meanwhile, the power levels on other body parts stay in low level, reducing the risk of overheating. We prototype In-N-Out on 21 software-defined radios and a printed circuit board (PCB). Extensive experiments demonstrate that In-N-Out achieves 0.37 mW average charging power inside a 10 cm-thick pork belly, which is sufficient to wirelessly power a range of commercial medical devices. Our head-to-head comparison with the state-of-the-art approach shows that In-N-Out achieves 5.4×-18.1× power gain when the implant is stationary, and 5.3×-7.4× power gain when the implant is in motion. [ABSTRACT FROM AUTHOR]

Sign language is a natural and fully-formed communication method for deaf or hearing-impaired people. Unfortunately, most of the state-of-the-art sign recognition technologies are limited by either high energy consumption or expensive device costs and have a difficult time providing a real-time service in a daily-life environment. Inspired by previous works on motion detection with wearable devices, we propose Sign-Speaker - a real-time, robust, and user-friendly American sign language recognition (ASLR) system with affordable and portable commodity mobile devices. SignSpeaker is deployed on a smartwatch along with a smartphone; the smartwatch collects the sign signals and the smartphone outputs translation through an inbuilt loudspeaker. We implement a prototype system and run a series of experiments that demonstrate the promising performance of our system. For example, the average translation time is approximately 1.1 seconds for a sentence with eleven words. The average detection ratio and reliability of sign recognition are 99.2% and 99.5%, respectively. The average word error rate of continuous sentence recognition is 1.04% on average. [ABSTRACT FROM AUTHOR]

One of the major challenges for fully enjoying the power of machine learning is the need for the high-quality labelled data. To tap-in the gold-mine of data generated by IoT devices with unprecedented volume and value, we discover and leverage the hidden connections among the multimodal data collected by various sensing devices. Different modal data can complete and learn from each other, but it is challenging to fuse multimodal data without knowing their perception (and thus the correct labels). In this work, we propose MultiSense, a paradigm for automatically mining potential perception, cross-labelling each modal data, and then improving the learning models over the set of multimodal data. We design innovative solutions for segmenting, aligning, and fusing multimodal data from different sensors. We implement our framework and conduct comprehensive evaluations on a rich set of data. Our results demonstrate that MultiSense significantly improves the data usability and the power of the learning models. [ABSTRACT FROM AUTHOR]

We propose a novel motion sensing/recognition system, called DF-Mose, which marries low-power wireless backscattering and device-free sensing in one clean sheet. DF-Mose is an accurate, interference tolerable motion-recognition system that counts repetitive motions without using scenario-dependent templates or profiles within 5% count error and enables multiuser to perform certain motions simultaneously based on the nature of backscattered signals and dedicated signal separation method. With little efforts in learning the patterns, our method could achieve 95.2% motion-recognition accuracy for a variety of 7 typical motions. [ABSTRACT FROM AUTHOR]

Traditional vibration inspection systems, equipped with separated sensing and communication modules, are either very expensive (e.g., hundreds of dollars) and/or suffer from occlusion and narrow field of view (e.g., laser). In this work, we present an RFID-based solution, Tagbeat, to inspect mechanical vibration using COTS RFID tags and readers. Making sense of micro and high-frequency vibration using random and lowfrequency readings of tag has been a daunting task, especially challenging for achieving sub-millisecond period accuracy. Our system achieves these three goals by discerning the change pattern of backscatter signal replied from the tag, which is attached on the vibrating surface and displaced by the vibration within a small range. This work introduces three main innovations. First, it shows how one can utilize COTS RFID to sense mechanical vibration and accurately discover its period with a few periods of short and noisy samples. Second, a new digital microscope is designed to amplify the micro-vibration-induced weak signals. Third, Tagbeat introduces compressive reading to inspect high-frequency vibration with relatively low RFID read rate. We implement Tagbeat using a COTS RFID device and evaluate it with a commercial centrifugal machine. Empirical benchmarks with a prototype show that Tagbeat can inspect the vibration period with a mean accuracy of 0.36ms and a relative error rate of 0.03%. We also study three cases to demonstrate how to associate our inspection solution with the specific domain requirements. [ABSTRACT FROM AUTHOR]

Recently a number of systems have been developed to implement and improve the visual communication over screen-camera links. In this paper we study an opposite problem: how to prevent unauthorized users from videotaping a video played on a screen, such as in a theater, while do not affect the viewing experience of legitimate audiences. We propose and develop a light-weight hardware-free system, called KALEIDO, that ensures these properties by taking advantage of the limited disparities between the screen-eye channel and the screen-camera channel. KALEIDO does not require any extra hardware and is purely based on re-encoding the original video frame into multiple frames used for displaying. We extensively test our system KALEIDO using a variety of smartphone cameras. Our experiments confirm that KALEIDO preserves the high-quality screen-eye channel while reducing the secondary screen-camera channel quality significantly. [ABSTRACT FROM AUTHOR]

In many applications, we have to identify an object and then locate the object to within high precision (centimeter- or millimeter-level). Legacy systems that can provide such accuracy are either expensive or suffering from performance degradation resulting from various impacts, e.g., occlusion for computer vision based approaches. In this work, we present an RFID-based system, Tagoram, for object localization and tracking using COTS RFID tags and read- ers. Tracking mobile RFID tags in real time has been a daunting task, especially challenging for achieving high precision. Our system achieves these three goals by leveraging the phase value of the backscattered signal, provided by the COTS RFID readers, to estimate the location of the object. In Tagoram, we exploit the tag's mobility to build a virtual antenna array by using readings from a few physical antennas over a time window. To illustrate the basic idea of our system, we firstly focus on a simple scenario where the tag is moving along a fixed rack known to the system. We propose Differential Augmented Hologram (DAH) which will facilitate the instant tracking of the mobile RFID tag to a high precision. We then devise a comprehensive solution to accurately recover the tag's moving trajectories and its locations, relaxing the assumption of knowing tag's track function in advance. We have implemented the Tagoram system using COTS RFID tags and readers. The system has been tested extensively in the lab environment and used for more than a year in real airline applications. For lab environment, we can track the mobile tags in real time with a millimeter accuracy to a median of 5mm and 7.29mm using linear and circular track respectively. In our year-long large scale baggage sortation systems deployed in two airports, our results from real deployments show that Tagoram can achieve a centimeter-level accuracy to a median of 6.35cm in these real deployments [ABSTRACT FROM AUTHOR]

In this work, we explore a new networking mechanism with smart glasses, through which users can express their interest and connect to a target simply by a gaze. Doing this, we attempt to let wearable devices understand human attention and intention, and pair devices carried by users according to such attention and intention. To achieve this ambitious goal, we propose a proof-of-concept system iGaze, a visual attention driven networking suite: an iGaze glass (hardware), and a networking protocol VAN (software). Our glass, iGaze glass, is a low-cost head-mounted glass with a camera, orientation sensors, microphone and speakers, which are embedded with our software for visual attention capture and networking. A visual attention driven networking protocol (VAN) is carefully designed and implemented. In VAN, we design an energy efficient and highly accurate visual attention determination scheme using single camera to capture user's communication interest and a double-matching scheme based on visual direction detection and Doppler effect of acoustic signal to lock the target devices. Using our system, we conduct a series of trials for various application scenarios to demonstrate the effectiveness of our system. [ABSTRACT FROM AUTHOR]

Recent studies show that WiFi interference has been a major problem for low power urban sensing technology ZigBee networks. Existing approaches for dealing with such interferences often modify either the ZigBee nodes or WiFi nodes. However, massive deployment of ZigBee nodes and uncooperative WiFi users call for innovative cross-technology coexistence without intervening legacy systems. In this work we investigate the WiFi and ZigBee coexistence when ZigBee is the interested signal. Mitigating short duration WiFi interference (called flash) in long duration ZigBee data (called smog) is challenging, especially when we cannot modify the WiFi APs and the massively deployed sensor nodes. To address these challenges, we propose ZIMO, a sink-based MIMO design for harmony coexistence of ZigBee and WiFi networks with the goal of protecting the ZigBee data packets. The key insight of ZIMO is to properly exploit opportunities resulted from differences between WiFi and ZigBee, and bridge the gap between interested data and cross technology signals. Also, extracting the channel coefficient of WiFi and ZigBee will enhance other coexistence technologies such as TIMO [1]. We implement a prototype for ZIMO in GNURadio-USRP N200. Our extensive evaluations under real wireless conditions show that ZIMO can improve up to 1.9x throughput for ZigBee network, with median gain of 1.5x, and 1.1x to 1.9x for WiFi network as byproduct in ZigBee signal recovery. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel clock calibration approach called FLIGHT, which leverages the fact that the fluorescent light intensity changes with a stable period that equals half of the alternating current's. By tuning to the light emitted from indoor fluorescent lamps, FLIGHT can intelligently extract the light period information and achieve network wide time calibration by referring to such a common time reference. We address a series of practical challenges and implement FLIGHT in TelosB motes. We conduct comprehensive experiments using a 12-node test-bed in both static and mobile environments. Over one-week measurement suggests that compared with existing technologies, FLIGHT can achieve tightly synchronized time with low energy consumption. [ABSTRACT FROM AUTHOR]

In this paper we study the online spectrum scheduling using a market driven approach. We assume that each new arrival spectrum request, when it arrives, requests for the exclusive usage of some channels for a certain time interval. The spectrum owner has to decide immediately whether to grant its exclusive usage or not. If it is granted, the secondary user will be charged a payment. We assume that existing running requests can be preempted with a penalty depending on its bid value, its requested time duration and the remaining unserved time. For various possible known information, we present efficient scheduling algorithms to schedule requests and prove that the competitive ratios of our methods are asymptotically optimum, i.e., within small constant factors of the optimum online methods. Our extensive simulations show that our algorithms perform almost optimum: most of our methods can get a total profit that is more than 80% of the optimum. [ABSTRACT FROM AUTHOR]

In this paper, we study the multicast capacity of a large scale random wireless network. We simply consider the extended multihop network, where a number of wireless nodes vi(1 ≤ i ≤ n) are randomly located in a square region with side-length a = √n, by use of Poisson distribution with density 1. All nodes transmit at constant power P, and the power decays along path, with attenuation exponent α > 2. The data rate of a transmission is determined by the SINR as B log(1 + SINR). There are ns randomly and independently chosen multicast sessions. Each multicast has k randomly chosen terminals. We show that, when k ≤ θ1 n/(log n)2α+6, and ns ≥ θ2n1/2+β, the capacity that each multicast session can achieve, with high probability, is at least c8 √n/ns√k, where θ1, θ2, and c8 are some special constants and β > 0 is any positive real number. Our result generalizes the unicast capacity [3] for random networks using percolation theory. [ABSTRACT FROM AUTHOR]

Locating objects labeled with RFID tags is an important issue which should be addressed in many applications, such as warehouse management, goods management in supermarket and finding of lost objects. Some existing works use large numbers of reference tags which involve lots of manpower to deploy them. Others achieve high accuracy, but rely on sophisticated equipments which are hardly available in large scale to the industry. This work exploits the radiation pattern of existing directional panel antenna which is steerable and derives angle-of-arrival(AoA) information from the energy reflected by the target tag when the antenna is rotating. We use Commercial Off-The-Shelf (COTS) equipments and get median position accuracy of 29cm in our preliminary experiment. [ABSTRACT FROM AUTHOR]

In this demo, we propose a proof-of-concept networking system for smart glasses, through which users can express their interest and connect to a target simply by a gaze. Our system iGaze is a visual attention driven networking suite: an iGaze glass (hardware) and a networking protocol VAN (software). Our glass is a low-cost head-mounted glass with a camera, orientation sensors, microphone and speakers, which are embedded with our software for visual attention capture and networking. A visual attention driven networking protocol (VAN) is carefully designed and implemented. In VAN, we design an energy efficient and highly accurate visual attention determination scheme using single camera to capture user's communication interest and a double-matching scheme based on visual direction detection and Doppler effect of acoustic signal to lock the target devices. iGaze has separated and modularized hardware and software design. It can run on top of existing networking protocols, e.g., Wi-Fi. [ABSTRACT FROM AUTHOR]

In many applications, we have to identify an object and then locate the object to within high precision (centimeter- or millimeter-level). Tracking mobile RFID tags in real time has been a daunting task, especially challenging for achieving high precision. We achieve these three goals by leveraging the phase value of the backscattered signal, provided by the COTS RFID readers, to estimate the location of the object. To illustrate the basic idea of our system, we firstly focus on a simple scenario where the tag is moving along a fixed track known to the system. We propose Differential Augmented Hologram (DAH) which will facilitate the instant tracking of the mobile RFID tag to a high precision. We then devise a comprehensive solution to accurately recover the tag's moving trajectory and its locations, relaxing the assumption of knowing tag's track function in advance. [ABSTRACT FROM AUTHOR]

In this work, we address a critical task of detecting the user behavior of driving and texting simultaneously using smartphones. We propose, design, and implement TEXIVE which achieves the goal of distinguishing drivers and passengers, and detecting texting operations during driving utilizing irregularities and rich micromovements of users. Without relying on any external infrastructures and additional devices, and no need to bring any modification to vehicles, TEXIVE is able to successfully detect dangerous operations with good sensitivity, specificity and accuracy. We conduct experimental study of TEXIVE with the help of a number of volunteers using various vehicles and smartphones. Our results indicate that TEXIVE has a classification accuracy of 87.18%, and precision of 96.67%. [ABSTRACT FROM AUTHOR]

We present SmartLoc, a localization system to estimate the location and the traveling distance by leveraging the lower-power inertial sensors embedded in smartphones as a supplementary to GPS. To minimize the negative impact of sensor noises, SmartLoc exploits the intermittent strong GPS signals and uses the linear regression to build a prediction model which is based on the trace estimated from inertial sensors and the one computed from the GPS. Furthermore, we utilize landmarks (e.g., bridge, traffic lights) detected automatically and special driving patterns (e.g., turning, uphill, and downhill) from inertial sensory data to improve the localization accuracy when the GPS signal is weak. Our evaluations of SmartLoc in the city demonstrates its technique viability and significant localization accuracy improvement compared with GPS and other approaches: the error is approximately 20m for 90% of time while the known mean error of GPS is 42.22m. [ABSTRACT FROM AUTHOR]

In this work, we present SilentSense, a framework to authenticate users silently and transparently by exploiting the user touch behavior biometrics and leveraging the integrated sensors to capture the micro-movement of the device caused by user's screen-touch actions. By tracking the fine-detailed touch actions of the user, we build a "touch-based biometrics" model of the owner by extracting some principle features, and then verify whether the current user is the owner or guest/attacker. When using the smartphone, the unique operating pattern of the user is detected and learnt by collecting the sensor data and touch events silently. When users are mobile, the micro-movement of mobile devices caused by touch is suppressed by that due to the large scale user-movement which will render the touch-based biometrics ineffective. To address this, we integrate a movement-based biometrics for each user with previous touch-based biometrics. We conduct extensive evaluations of our approaches on the Android smartphone, we show that the user identification accuracy is over 99%. [ABSTRACT FROM AUTHOR]

In this demo, we propose a novel clock calibration approach called FLIGHT, which leverages the fact that the fluorescent light intensity changes with a stable period that equals half of the alternating current's. By tuning to the light emitted from indoor fluorescent lamps, FLIGHT can intelligently extract the light period information and achieve network wide time calibration by referring to such a common time reference. We address a series of practical challenges and implement FLIGHT in TelosB motes. In this demonstration, we will show that by taking advantage of the stability of the AC frequency, the detected light intensity, even from different lamps, exhibits a consistent and stable period. FLIGHT can achieve tightly synchronized time with low energy consumption. In addition, since FLIGHT is independent to the network message exchange, time synchronization can be retained even when the network is temporarily disconnected. Such characteristics particularly suit various mobility-enabled scenarios. [ABSTRACT FROM AUTHOR]