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.

How Long a Passenger Waits for a Vacant Taxi -- Large-Scale Taxi Trace Mining for Smart Cities

Abstract: To achieve smart cities, real-world trace data sensed from the GPS-enabled taxi system, which conveys underlying dynamics of people movements, could be used to make urban transportation services smarter. As an example, it will be very helpful for passengers to know how long it will take to find a taxi at a spot, since they can plan their schedule and choose the best spot to wait. In this paper, we present a method to predict the waiting time for a passenger at a given time and spot from historical taxi trajectories. The arrival model of passengers and that of vacant taxis are built from the events that taxis arrive at and leave a spot. With the models, we could simulate the passenger waiting queue for a spot and infer the waiting time. The experiment with a large-scale real taxi GPS trace dataset is carried out to verify the proposed method.

MHS: A Multimedia System for Improving Medication Adherence in Elderly Care

Abstract: Due to its proven capability in customizing information according to the patients' needs, multimedia has been regarded as a promising technology for home healthcare. In this paper, we present our study on improving medication adherence of the elderly with the support of ubiquitous multimedia services. A multimedia healthcare system (MHS) is built based on a comprehensive understanding of the requirements of the elderly care. It provides the continuous medication monitoring, context aware prompting, adaptive multimedia presentation, and flexible medicine management. The experimental results show that the MHS can improve the medication adherence of the elderly effectively.

WiMorse: A Contactless Morse Code Text Input System Using Ambient WiFi Signals

Abstract: Recent years have witnessed advances of Internet of Things (IoT) technologies and their applications to enable contactless sensing and human–computer interaction in smart homes. For people with motor neurone disease (MND), their motion capabilities are severely impaired and they have difficulties interacting with IoT devices and even communicating with other people. As the disease progresses, most patients lose their speech function eventually which makes the widely adopted voice-based solutions fail. In contrast, most of the patients can still move their fingers slightly even after they have lost the control of their arms and hands. Thus, we propose to develop a Morse code-based text input system, called WiMorse , which allows patients with minimal single-finger control to input and communicate with other people without attaching any sensor to their fingers. WiMorse leverages ubiquitous commodity WiFi devices to track subtle finger movements contactlessly and encode them as Morse code input. In order to sense the very subtle finger movements, we propose to employ the ratio of the channel state information (CSI) between two antennas to enhance the signal to noise ratio. To address the severe location dependency issue in wireless sensing with accurate theoretical underpinning and experiments, we propose a signal transformation mechanism to automatically convert signals based on the input position, achieving stable sensing performance. Comprehensive experiments demonstrate that WiMorse can achieve higher than 95% recognition accuracy for finger generated Morse code, and is robust against input position, environment changes, and user diversity.

WiFi-Sleep: Sleep Stage Monitoring Using Commodity Wi-Fi Devices

Abstract: Sleep monitoring is essential to people’s health and wellbeing, which can also assist in the diagnosis and treatment of sleep disorder. Compared with contact-based solutions, contactless sleep monitoring does not attach any device to the human body; hence, it has attracted increasing attention in recent years. Inspired by the recent advances in Wi-Fi-based sensing, this article proposes a low-cost and nonintrusive sleep monitoring system using commodity Wi-Fi devices, namely, WiFi-Sleep. We leverage the fine-grained channel state information from multiple antennas and propose advanced fusion and signal processing methods to extract accurate respiration and body movement information. We introduce a deep learning method combined with clinical sleep medicine prior knowledge to achieve four-stage sleep monitoring with limited data sources (i.e., only respiration and body movement information). We benchmark the performance of WiFi-Sleep with polysomnography, the gold reference standard. Results show that WiFi-Sleep achieves an accuracy of 81.8%, which is comparable to the state-of-the-art sleep stage monitoring using expensive radar devices.

An OSGi-based infrastructure for context-aware multimedia services

Abstract: This article proposes an OSGi-based infrastructure for context-aware multimedia services in a smart home environment. A context-aware multimedia middleware (CMM), which supports multimedia content filtering, recommendation, and adaptation according to changing context is presented. It also performs context aggregation, reasoning, and learning. To foster device and service interoperability, CMM is integrated with an OSGi service platform. We envisage the OSGi-based infrastructure to fill the niche of three gateways in a smart home: network connecting, context provisioning, and multimedia personalizing

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.