Showing papers by "Daqing Zhang published in 2018"

From Fresnel Diffraction Model to Fine-grained Human Respiration Sensing with Commodity Wi-Fi Devices

Abstract: Non-intrusive respiration sensing without any device attached to the target plays a particular important role in our everyday lives. However, existing solutions either require dedicated hardware or employ special-purpose signals which are not cost-effective, significantly limiting their real-life applications. Also very few work concerns about the theory behind and can explain the large performance variations in different scenarios. In this paper, we employ the cheap commodity Wi-Fi hardware already ubiquitously deployed around us for respiration sensing. For the first time, we utilize the Fresnel diffraction model to accurately quantify the relationship between the diffraction gain and human target's subtle chest displacement and thus successfully turn the previously considered "destructive" obstruction diffraction in the First Fresnel Zone (FFZ) into beneficial sensing capability. By not just considering the chest displacement at the frontside as the existing solutions, but also the subtle displacement at the backside, we achieve surprisingly matching results with respect to the theoretical plots and become the first to clearly explain the theory behind the performance distinction between lying and sitting for respiration sensing. With two cheap commodity Wi-Fi cards each equipped with just one antenna, we are able to achieve higher than 98% accuracy of respiration rate monitoring at more than 60% of the locations in the FFZ. Furthermore, we are able to present the detail heatmap of the sensing capability at each location inside the FFZ to guide the respiration sensing so users clearly know where are the good positions for respiration monitoring and if located at a bad position, how to move just slightly to reach a good position.

Multi-Task Allocation in Mobile Crowd Sensing with Individual Task Quality Assurance

Abstract: Task allocation is a fundamental research issue in mobile crowd sensing. While earlier research focused mainly on single tasks, recent studies have started to investigate multi-task allocation, which considers the interdependency among multiple tasks. A common drawback shared by existing multi-task allocation approaches is that, although the overall utility of multiple tasks is optimized, the sensing quality of individual tasks may become poor as the number of tasks increases. To overcome this drawback, we re-define the multi-task allocation problem by introducing task-specific minimal sensing quality thresholds, with the objective of assigning an appropriate set of tasks to each worker such that the overall system utility is maximized. Our new problem also takes into account the maximum number of tasks allowed for each worker and the sensor availability of each mobile device. To solve this newly-defined problem, this paper proposes a novel multi-task allocation framework named MTasker. Different from previous approaches which start with an empty set and iteratively select task-worker pairs, MTasker adopts a descent greedy approach, where a quasi-optimal allocation plan is evolved by removing a set of task-worker pairs from the full set. Extensive evaluations based on real-world mobility traces show that MTasker outperforms the baseline methods under various settings, and our theoretical analysis proves that MTasker has a good approximation bound.

FullBreathe: Full Human Respiration Detection Exploiting Complementarity of CSI Phase and Amplitude of WiFi Signals

Abstract: Human respiration detection based on Wi-Fi signals does not require users to carry any device, hence it has drawn a lot of attention due to better user acceptance and great potential for real-world deployment. However, recent studies show that respiration sensing performance varies in different locations due to the nature of Wi-Fi radio wave propagation in indoor environments, i.e., respiration detection may experience poor performance at certain locations which we call "blind spots". In this paper, we aim to address the blind spot problem to ensure full coverage of respiration detection. Basically, the amplitude and phase of Wi-Fi channel state information (CSI) are orthogonal and complementary to each other, so they can be combined to eliminate the blind spots. However, accurate CSI phase cannot be obtained from commodity Wi-Fi due to the clock-unsynchronized transceivers. Thus, we apply conjugate multiplication (CM) of CSI between two antennas to remove the phase offset and construct two orthogonal signals--new "amplitude and phase" which are still complementary to each other. In this way, we can ensure full human respiration detection. Based on these ideas, We design and implement a real-time respiration detection system with commodity Wi-Fi devices. We conduct extensive experiments to validate our model and design. The results show that, with only one transceiver pair and without leveraging multiple sub-carriers, our system enables full location coverage with no blind spot, showing great potential for real deployment.

C-FMCW Based Contactless Respiration Detection Using Acoustic Signal

Abstract: Recent advances in ubiquitous sensing technologies have exploited various approaches to monitoring vital signs. One of the vital signs is human respiration which typically requires reliable monitoring with low error rate in practice. Previous works in respiration monitoring however either incur high cost or suffer from poor error rate. In this paper, we propose a Correlation based Frequency Modulated Continuous Wave method (C-FMCW) which is able to achieve high ranging resolution. Based on C-FMCW, we present the design and implementation of an audio-based highly-accurate system for human respiration monitoring, leveraging on commodity speaker and microphone widely available in home environments. The basic idea behind the audio-based method is that when a user is close to a pair of speaker and microphone, body movement during respiration causes periodic audio signal changes, which can be extracted to obtain the respiration rate. However, several technical challenges exist when applying C-FMCW to detect respiration with commodity acoustic devices. First, the sampling frequency offset between speakers and microphones if not being corrected properly would cause high ranging errors. Second, the uncertain starting time difference between the speaker and microphone varies over time. Moreover, due to multipath effect, weak periodic components due to respiration can easily be overwhelmed by strong static components in practice. To address those challenges, we 1) propose an algorithm to compensate dynamically acoustic signal and counteract the offset between speaker and microphone; 2) co-locate speaker and microphone and use the received signal without reflection (self-interference) as a reference to eliminate the starting time difference; and 3) leverage the periodicity of respiration to extract weak periodic components with autocorrelation. Extensive experimental results show that our system detects respiration in real environments with the median error lower than 0.35 breaths/min, outperforming the state-of-the-arts.

Task Allocation in Mobile Crowd Sensing: State-of-the-Art and Future Opportunities

Abstract: Mobile crowd sensing (MCS) is the special case of crowdsourcing, which leverages the smartphones with various embedded sensors and user’s mobility to sense diverse phenomenon in a city. Task allocation is a fundamental research issue in MCS, which is crucial for the efficiency and effectiveness of MCS applications. In this paper, we specifically focus on the task allocation in MCS systems. We first present the unique features of MCS allocation compared to generic crowdsourcing, and then provide a comprehensive review for diversifying problem formulation and allocation algorithms together with future research opportunities.

Energy Saving Techniques in Mobile Crowd Sensing: Current State and Future Opportunities

Abstract: With the prevalence of sensor-rich smartphones, MCS has become an emerging paradigm to perform urban sensing tasks in recent years. In MCS systems, it is important to minimize the energy consumption on devices of mobile users, as high energy consumption severely reduces their participation willingness. In this article, we provide a comprehensive review of energy saving techniques in MCS and identify future research opportunities. Specifically, we analyze the main causes of energy consumption in MCS and present a general energy saving framework named ESCrowd that we use to describe the different detailed MCS energy saving techniques. We further present how the various energy saving techniques are utilized and adopted within MCS applications and point out their existing limitations, which inform and guide future research directions.

Boosting fine-grained activity sensing by embracing wireless multipath effects

Abstract: With a big success in data communication, wireless signals are now exploited for fine-grained contactless activity sensing including human respiration monitoring, finger gesture recognition, subtle chin movement tracking when speaking, etc. Different from coarsegrained body and limb movements, these fine-grained movements are in the scale of millimetres and are thus difficult to be sensed. While good sensing performance can be achieved at one location, the performance degrades dramatically at a very nearby location. In this paper, by revealing the effect of static multipaths in sensing, we propose a novel method to add man-made "virtual" multipath to significantly improve the sensing performance. With carefully designed "virtual" multipath, we are able to boost the sensing performance at each location purely in software without any extra hardware.We demonstrate the effectiveness of the proposed method on three fine-grained sensing applications with just one Wi-Fi transceiver-pair, each equipped with a single antenna. For respiration monitoring, we can remove the "blind spots" and achieve full coverage respiration sensing. For finger gesture recognition, our system can significantly increase the recognition accuracy from 33% to 81%. For chin movement tracking, we are able to count the number of spoken syllables in a sentence at an accuracy of 92.8%.

Training-Free Human Vitality Monitoring Using Commodity Wi-Fi Devices

Abstract: Device-free sensing using ubiquitous Wi-Fi signals has recently attracted lots of attention. Among the sensed information, two important basic contexts are (i) whether a target is still or not and (ii) where the target is located. Continuous monitoring of these contexts provides us with rich datasets to obtain important high-level semantics of the target such as living habits, physical conditions and emotions. However, even to obtain these two basic contexts, offline training and calibration are needed in traditional methods, limiting the real-life adoption of the proposed sensing systems. In this paper, using the commodity Wi-Fi infrastructure, we propose a training-free human vitality sensing platform, WiVit. It could capture these two contexts together with the target's movements speed information in real-time without any human effort in offline training or calibration. Based on our extensive experiments in three typical indoor environments, the precision of activity detection is higher than 98% and the area detection accuracy is close to 100%. Moreover, we implement a short-term activity recognition system on our platform to recognize 4 types of actions, and we can reach an average accuracy of 94.2%. We also take a feasibility study of monitoring long-term activities of daily living to show our platform's potential applications in practice.

Cell Selection with Deep Reinforcement Learning in Sparse Mobile Crowdsensing

Abstract: Sparse Mobile CrowdSensing (MCS) is a novel MCS paradigm where data inference is incorporated into the MCS process for reducing sensing costs while its quality is guaranteed. Since the sensed data from different cells (sub-areas) of the target sensing area will probably lead to diverse levels of inference data quality, cell selection (i.e., choose which cells of the target area to collect sensed data from participants) is a critical issue that will impact the total amount of data that requires to be collected (i.e., data collection costs) for ensuring a certain level of quality. To address this issue, this paper proposes a Deep Reinforcement learning based Cell selection mechanism for Sparse MCS, called DR-Cell. We properly model the key concepts in reinforcement learning including state, action, and reward, and then propose to use a deep recurrent Q-network for learning the Q-function that can help decide which cell is a better choice under a certain state during cell selection. Experiments on various real-life sensing datasets verify the effectiveness of DR-Cell over the state-of-the-art cell selection mechanisms in Sparse MCS by reducing up to 15% of sensed cells with the same data inference quality guarantee.

RADAR: Road Obstacle Identification for Disaster Response Leveraging Cross-Domain Urban Data

Abstract: Typhoons and hurricanes cause extensive damage to coast cities annually, demanding urban authorities to take effective actions in disaster response to reduce losses. One of the first priority in disaster response is to identify and clear road obstacles, such as fallen trees and ponding water, and restore road transportation in a timely manner for supply and rescue. Traditionally, identifying road obstacles is done by manual investigation and reporting, which is labor intensive and time consuming, hindering the timely restoration of transportation. In this work, we propose RADAR, a low-cost and real-time approach to identify road obstacles leveraging large-scale vehicle trajectory data and heterogeneous road environment sensing data. First, based on the observation that road obstacles may cause abnormal slow motion behaviors of vehicles in the surrounding road segments, we propose a cluster direct robust matrix factorization (CDRMF) approach to detect road obstacles by identifying the collective anomalies of slow motion behaviors from vehicle trajectory data. Then, we classify the detected road obstacles leveraging the correlated spatial and temporal features extracted from various road environment data, including satellite images and meteorological records. To address the challenges of heterogeneous features and sparse labels, we propose a semi-supervised approach combining co-training and active learning (CORAL). Real experiments on Xiamen City show that our approach accurately detects and classifies the road obstacles during the 2016 typhoon season with precision and recall both above 90%, and outperforms the state-of-the-art baselines.

Crowd-Powered Sensing and Actuation in Smart Cities: Current Issues and Future Directions

Abstract: With the advent of seamless connection of human, machine, and smart things, there is an emerging trend to leverage the power of crowds (e.g., citizens, mobile devices, and smart things) to monitor what is happening in a city, understand how the city is evolving, and further take actions to enable better quality of life, which is referred to as Crowd-Powered Smart City (CPSC). In this article, we provide a literature review for CPSC and identify future research opportunities. Specifically, we first define the concepts with typical CPSC applications. Then, we present the main characteristics of CPSC and further highlight the research issues. In the end, we point out existing limitations which can inform and guide future research directions.

A Fresnel Diffraction Model Based Human Respiration Detection System Using COTS Wi-Fi Devices

Abstract: Recent work has revealed the sensing theory of human respiration outside the First Fresnel Zone (FFZ) using commodity Wi-Fi devices. However, there is still no theoretical model to guide human respiration detection when the subject locates in the FFZ. In our work [10], we propose a diffraction-based sensing model to investigate how to effectively sense human respiration in FFZ. We present this demo system to show human respiration sensing performance varies based on different human locations and postures. By deploying the respiration detection system using COTS Wi-Fi devices, we can observe that the respiration sensing results match the theoretical model well.

WiFit: Ubiquitous Bodyweight Exercise Monitoring with Commodity Wi-Fi Devices

Abstract: Bodyweight exercises are effective and efficient ways to improve one's balance, flexibility, and strength without machinery or extra equipment. Prior works have been successful in monitoring aerobic exercises and free-weight exercises, but are not suitable for ubiquitous bodyweight exercise monitoring in order to provide fine-grained repetition counting information in each exercise set. In this work, we propose WiFit, a bodyweight exercises monitoring system that supports accurate repetition counting using a pair of commodity Wi-Fi devices without attaching anything to the human body. We first analyze the movement patterns of bodyweight exercises and couple them with detailed Doppler effect modeling to determine the most effective system settings. Then, by leveraging the human activity Doppler displacement stream extracted from Wi-Fi CSI signal, we have developed an impulse-based method to segment and count the number of repetitions, and analyzed specific features for classifying different types of bodyweight exercises. Extensive experiments show that WiFit achieves 99% accuracy for repetition counting and 95.8% accuracy for exercise type classification.

A Simple but Quantifiable Approach to Dynamic Price Prediction in Ride-on-demand Services Leveraging Multi-source Urban Data

Abstract: Ride-on-demand (RoD) services such as Uber and Didi are becoming increasingly popular, and in these services dynamic prices play an important role in balancing the supply and demand to benefit both drivers and passengers. However, dynamic prices also create concerns. For passengers, the "unpredictable" prices sometimes prevent them from making quick decisions: one may wonder if it is possible to get a lower price if s/he chooses to wait a while. It is necessary to provide more information to them, and predicting the dynamic prices is a possible solution. For the transportation industry and policy makers, there are also concerns about the relationship between RoD services and their more traditional counterparts such as metro, bus, and taxi: whether they affect each other and how. In this paper we tackle these two concerns by predicting the dynamic prices using multi-source urban data. Price prediction could help passengers understand whether they could get a lower price in neighboring locations or within a short time, thus alleviating their concerns. The prediction is based on urban data from multiple sources, including the RoD service itself, taxi service, public transportation, weather, the map of a city, etc. We train a simple linear regression model with high-dimensional composite features to perform the prediction. By combining simple basic features into composite features, we compensate for the loss of expressiveness in a linear model due to the lack of non-linearity. Additionally, the use of multi-source data and a linear model enables us to quantify and explain the relationship between multiple means of transportation by examining the weights of different features in the model. Our hope is that the study not only serves as an accurate prediction to make passengers more satisfied, but also sheds light on the concern about the relationship between different means of transportation for either the industry or policy makers.

CrowdExpress: A Probabilistic Framework for On-Time Crowdsourced Package Deliveries

Abstract: Speed and cost of logistics are two major concerns to on-line shoppers, but they generally conflict with each other in nature To alleviate the contradiction, we propose to exploit existing taxis that are transporting passengers on the street to relay packages collaboratively, which can simultaneously lower the cost and accelerate the speed Specifically, we propose a probabilistic framework containing two phases called CrowdExpress for the on-time package express deliveries In the first phase, we mine the historical taxi GPS trajectory data offline to build the package transport network In the second phase, we develop an online adaptive taxi scheduling algorithm to find the path with the maximum arriving-on-time probability "on-the-fly" upon real- time requests, and direct the package routing accordingly Finally, we evaluate the system using the real-world taxi data generated by over 19,000 taxis in a month in the city of New York, US Results show that around 9,500 packages can be delivered successfully on time per day with the success rate over 94%, moreover, the average computation time is within 25 milliseconds

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

Abstract: 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.

A Full Human Respiration Detection System Using Commodity Wi-Fi Devices

Abstract: In recent years, human respiration detection based on Wi-Fi signals has drawn a lot of attention due to better user acceptance and great potential for real-world deployment. However, latest studies show that respiration sensing performance varies at different locations due to the nature of Wi-Fi radio wave propagation in indoor environments, i.e., respiration detection may experience poor performance at certain locations which we call "blind spots". In this demo, we will demonstrate a human respiration detection system which enables full location coverage with no blind spot.

Social-Network-Assisted Worker Recruitment in Mobile Crowd Sensing

Abstract: Worker recruitment is a crucial research problem in Mobile Crowd Sensing (MCS). While previous studies rely on a specified platform with a pre-assumed large user pool, this paper leverages the influenced propagation on the social network to assist the MCS worker recruitment. We first select a subset of users on the social network as initial seeds and push MCS tasks to them. Then, influenced users who accept tasks are recruited as workers, and the ultimate goal is to maximize the coverage. Specifically, to select a near-optimal set of seeds, we propose two algorithms, named Basic-Selector and Fast-Selector, respectively. Basic-Selector adopts an iterative greedy process based on the predicted mobility, which has good performance but suffers from inefficiency concerns. To accelerate the selection, Fast-Selector is proposed, which is based on the interdependency of geographical positions among friends. Empirical studies on two real-world datasets verify that Fast-Selector achieves higher coverage than baseline methods under various settings, meanwhile, it is much more efficient than Basic-Selector while only sacrificing a slight fraction of the coverage.

Cell Selection with Deep Reinforcement Learning in Sparse Mobile Crowdsensing.

Abstract: Sparse Mobile CrowdSensing (MCS) is a novel MCS paradigm where data inference is incorporated into the MCS process for reducing sensing costs while its quality is guaranteed. Since the sensed data from different cells (sub-areas) of the target sensing area will probably lead to diverse levels of inference data quality, cell selection (i.e., choose which cells of the target area to collect sensed data from participants) is a critical issue that will impact the total amount of data that requires to be collected (i.e., data collection costs) for ensuring a certain level of quality. To address this issue, this paper proposes a Deep Reinforcement learning based Cell selection mechanism for Sparse MCS, called DR-Cell. First, we properly model the key concepts in reinforcement learning including state, action, and reward, and then propose to use a deep recurrent Q-network for learning the Q-function that can help decide which cell is a better choice under a certain state during cell selection. Furthermore, we leverage the transfer learning techniques to reduce the amount of data required for training the Q-function if there are multiple correlated MCS tasks that need to be conducted in the same target area. Experiments on various real-life sensing datasets verify the effectiveness of DR-Cell over the state-of-the-art cell selection mechanisms in Sparse MCS by reducing up to 15% of sensed cells with the same data inference quality guarantee.

A Training-Free Contactless Human Vitality Monitoring Platform Using Commodity Wi-Fi Devices

Abstract: Human vitality information is pivotal to many sensing applications. By vitality, we mean the status of a human target in a multi-room environment: whether he/she is still and which room he/she is located in. Continuous monitoring of human vitality helps us obtain important high-level contexts like one's emotions, living habits, and physical conditions. Unlike the most existing solutions that require human efforts in offline training or calibration, in this demo, we present WiVit, a training-free contactless Wi-Fi based sensing platform that can capture human vitality information in 7*24 hours. In typical indoor environments, WiVit can achieve 98% accuracy of vitality detection and nearly 100% accuracy of area detection.

Task Allocation in Mobile Crowd Sensing: State of the Art and Future Opportunities

Abstract: Mobile Crowd Sensing (MCS) is the special case of crowdsourcing, which leverages the smartphones with various embedded sensors and user's mobility to sense diverse phenomenon in a city. Task allocation is a fundamental research issue in MCS, which is crucial for the efficiency and effectiveness of MCS applications. In this article, we specifically focus on the task allocation in MCS systems. We first present the unique features of MCS allocation compared to generic crowdsourcing, and then provide a comprehensive review for diversifying problem formulation and allocation algorithms together with future research opportunities.

HyTasker: Hybrid Task Allocation in Mobile Crowd Sensing

Abstract: Task allocation is a major challenge in Mobile Crowd Sensing (MCS). While previous task allocation approaches follow either the opportunistic or participatory mode, this paper proposes to integrate these two complementary modes in a two-phased hybrid framework called HyTasker. In the offline phase, a group of workers (called opportunistic workers) are selected, and they complete MCS tasks during their daily routines (i.e., opportunistic mode). In the online phase, we assign another set of workers (called participatory workers) and require them to move specifically to perform tasks that are not completed by the opportunistic workers (i.e., participatory mode). Instead of considering these two phases separately, HyTasker jointly optimizes them with a total incentive budget constraint. In particular, when selecting opportunistic workers in the offline phase of HyTasker, we propose a novel algorithm that simultaneously considers the predicted task assignment for the participatory workers, in which the density and mobility of participatory workers are taken into account. Experiments on a real-world mobility dataset demonstrate that HyTasker outperforms other methods with more completed tasks under the same budget constraint.