Daqing Zhang

Bio: Daqing Zhang is an academic researcher from Peking University. The author has contributed to research in topics: Context (language use) & Mobile computing. The author has an hindex of 67, co-authored 331 publications receiving 16675 citations. Previous affiliations of Daqing Zhang include Institut Mines-Télécom & Institute for Infocomm Research Singapore.

TripPlanner: Personalized Trip Planning Leveraging Heterogeneous Crowdsourced Digital Footprints

Abstract: Planning an itinerary before traveling to a city is one of the most important travel preparation activities. In this paper, we propose a novel framework called TripPlanner , leveraging a combination of location-based social network (i.e., LBSN) and taxi GPS digital footprints to achieve personalized, interactive, and traffic-aware trip planning. First, we construct a dynamic point-of-interest network model by extracting relevant information from crowdsourced LBSN and taxi GPS traces. Then, we propose a two-phase approach for personalized trip planning. In the route search phase , TripPlanner works interactively with users to generate candidate routes with specified venues . In the route augmentation phase , TripPlanner applies heuristic algorithms to add user's preferred venues iteratively to the candidate routes, with the objective of maximizing the route score while satisfying both the venue visiting time and total travel time constraints. To validate the efficiency and effectiveness of the proposed approach, extensive empirical studies were performed on two real-world data sets from the city of San Francisco, which contain more than 391 900 passenger delivery trips generated by 536 taxis in a month and 110 214 check-ins left by 15 680 Foursquare users in six months.

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.

TaskMe: multi-task allocation in mobile crowd sensing

Abstract: Task allocation or participant selection is a key issue in Mobile Crowd Sensing (MCS). While previous participant selection approaches mainly focus on selecting a proper subset of users for a single MCS task, multi-task-oriented participant selection is essential and useful for the efficiency of large-scale MCS platforms. This paper proposes TaskMe, a participant selection framework for multi-task MCS environments. In particular, two typical multi-task allocation situations with bi-objective optimization goals are studied: (1) For FPMT (few participants, more tasks), each participant is required to complete multiple tasks and the optimization goal is to maximize the total number of accomplished tasks while minimizing the total movement distance. (2) For MPFT (more participants, few tasks), each participant is selected to perform one task based on pre-registered working areas in view of privacy, and the optimization objective is to minimize total incentive payments while minimizing the total traveling distance. Two optimal algorithms based on the Minimum Cost Maximum Flow theory are proposed for FPMT, and two algorithms based on the multi-objective optimization theory are proposed for MPFT. Experiments verify that the proposed algorithms outperform baselines based on a large-scale real-word dataset under different experiment settings (the number of tasks, various task distributions, etc.).

B-Planner: Planning Bidirectional Night Bus Routes Using Large-Scale Taxi GPS Traces

Abstract: Taxi GPS traces can inform us the human mobility patterns in modern cities. Instead of leveraging the costly and inaccurate human surveys about people's mobility, we intend to explore the night bus route planning issue by using taxi GPS traces. Specifically, we propose a two-phase approach for bidirectional night bus route planning. In the first phase, we develop a process to cluster “hot” areas with dense passenger pick up/drop off and then propose effective methods to split big hot areas into clusters and identify a location in each cluster as a candidate bus stop. In the second phase, given the bus route origin, destination, candidate bus stops, and bus operation time constraints, we derive several effective rules to build the bus route graph and prune invalid stops and edges iteratively. Based on this graph, we further develop a bidirectional probability-based spreading algorithm to generate candidate bus routes automatically. We finally select the best bidirectional bus route, which expects the maximum number of passengers under the given conditions and constraints. To validate the effectiveness of the proposed approach, extensive empirical studies are performed on a real-world taxi GPS data set, which contains more than 1.57 million night passenger delivery trips, generated by 7600 taxis in a month.

Context Aware Computing for The Internet of Things: A Survey

Abstract: As we are moving towards the Internet of Things (IoT), the number of sensors deployed around the world is growing at a rapid pace. Market research has shown a significant growth of sensor deployments over the past decade and has predicted a significant increment of the growth rate in the future. These sensors continuously generate enormous amounts of data. However, in order to add value to raw sensor data we need to understand it. Collection, modelling, reasoning, and distribution of context in relation to sensor data plays critical role in this challenge. Context-aware computing has proven to be successful in understanding sensor data. In this paper, we survey context awareness from an IoT perspective. We present the necessary background by introducing the IoT paradigm and context-aware fundamentals at the beginning. Then we provide an in-depth analysis of context life cycle. We evaluate a subset of projects (50) which represent the majority of research and commercial solutions proposed in the field of context-aware computing conducted over the last decade (2001-2011) based on our own taxonomy. Finally, based on our evaluation, we highlight the lessons to be learnt from the past and some possible directions for future research. The survey addresses a broad range of techniques, methods, models, functionalities, systems, applications, and middleware solutions related to context awareness and IoT. Our goal is not only to analyse, compare and consolidate past research work but also to appreciate their findings and discuss their applicability towards the IoT.

Membership Inference Attacks Against Machine Learning Models

Abstract: We quantitatively investigate how machine learning models leak information about the individual data records on which they were trained. We focus on the basic membership inference attack: given a data record and black-box access to a model, determine if the record was in the model's training dataset. To perform membership inference against a target model, we make adversarial use of machine learning and train our own inference model to recognize differences in the target model's predictions on the inputs that it trained on versus the inputs that it did not train on. We empirically evaluate our inference techniques on classification models trained by commercial "machine learning as a service" providers such as Google and Amazon. Using realistic datasets and classification tasks, including a hospital discharge dataset whose membership is sensitive from the privacy perspective, we show that these models can be vulnerable to membership inference attacks. We then investigate the factors that influence this leakage and evaluate mitigation strategies.