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.

Where is the Largest Market: Ranking Areas by Popularity from Location Based Social Networks

Abstract: Ranking areas by popularity of a business category is an essential problem for business planning. Traditional approaches rely on economic and demographic factors nearby. However, the acquisition of relevant data is usually expensive. In this paper we propose a novel approach to address this problem by exploiting user-generated contents from location based social networks, which are cheap, fine-grained, and abundant. Particularly, by analyzing a dataset collected from Foursquare in Paris, we attain the customer distribution across all categories in each area. With the help of data mining methods, the popularity (i.e., the number of customers) of a particular business category can be estimated from popularities of other nearby categories, and then can be ranked accordingly. The evaluation shows that these methods significantly outperform the passenger volume based method.

Mining Personal Frequent Routes via Road Corner Detection

Abstract: Frequent route is an important individual outdoor behavior pattern that many trajectory-based applications rely on. In this paper, we propose a novel framework for extracting frequent routes from personal GPS trajectories. The key idea of our design is to accurately detect road corners and utilize these new metaphors to tackle the problem of frequent route extraction. Concretely, our framework contains three phases: 1) characteristic point (CP) extraction; 2) corner detection; and 3) trajectory mapping. In the first phase, we present a linear fitting-based algorithm to extract CPs. In the second phase, we develop a multiple density level DBSCAN (density-based spatial clustering of applications with noise) algorithm to locate road corners by clustering CPs. In the third phase, we convert each trajectory into an ordered sequence of road corners and obtain all routes that have been traversed by an individual for at least ${F}$ (frequency threshold) times. We evaluate the framework using real-world trajectory datasets of individuals for one year and the experimental results demonstrate that our framework outperforms the baseline approach by 7.8% on average in terms of precision and 21.9% in terms of recall.

Cross-domain community detection in heterogeneous social networks

Abstract: With the recent surge of location-based social networks (LBSNs), e.g., Foursquare and Facebook Places, huge amount of human digital footprints that people leave in the cyber-physical space become accessible, including users' profiles, online social connections, and especially the places that they have checked in. Different from social networks (e.g., Flickr, Facebook) which have explicit groups for users to subscribe or join, LBSNs usually have no explicit community structure. Meanwhile, unlike social networks which only contain a single type of social interaction, the coexistence of online/offline social interactions and user/venue attributes in LBSNs makes the community detection problem much more challenging. In order to capitalize on the large number of potential users/venues as well as the huge amount of heterogeneous social interactions, quality community detection approach is needed. In this paper, by exploring the heterogenous digital footprints of LBSNs users in the cyber-physical space, we come out with a novel edge-centric co-clustering framework to discover overlapping communities. By employing inter-mode as well as intra-mode features, the proposed framework is able to group like-minded users from different social perspectives. The efficacy of our approach is validated by intensive empirical evaluations based on the collected Foursquare dataset.

User preference learning for multimedia personalization in pervasive computing environment

Abstract: Pervasive computing environment and users' demand for multimedia personalization precipitate a need for personalization tools to help people access desired multimedia content at anytime, anywhere, through any devices. User preference learning plays an important role in multimedia personalization. In this paper, we propose a learning approach to acquire and update user preference for multimedia personalization in pervasive computing environment. The approach is based on Master-Slave architecture, of which master device is a device with strong capabilities, such as PC, TV with STB (set-on-box) or PDR (Personal Digital Recorder), etc, and slave devices are pervasive terminals with limited resources. The preference learning and update is done in the master device by utilizing overall user feedback information collected from different devices as opposed to other traditional learning methods that just use partial feedback information in one device. The slave devices are responsible for observing user behavior and uploading feedback information to the master device. The master device is designed to support multiple learning methods: explicit input/modification and implicit learning. The implicit user preference learning algorithm, which applies relevance feedback and Naive Bayes classifier approach, is described in detail.

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.