A5101492843- Privacy-Preserving Technologies in Data
- Human Mobility and Location-Based Analysis
- Privacy, Security, and Data Protection
- Cryptography and Data Security
- Traffic Prediction and Management Techniques
- Data Management and Algorithms
- Domain Adaptation and Few-Shot Learning
- Mobile Crowdsensing and Crowdsourcing
- Advanced Graph Neural Networks
- Internet Traffic Analysis and Secure E-voting
- Neurological disorders and treatments
- Transportation Planning and Optimization
- Transportation and Mobility Innovations
- Functional Brain Connectivity Studies
- Multimodal Machine Learning Applications
- Geographic Information Systems Studies
- Power Systems and Renewable Energy
- Topic Modeling
- Traffic control and management
- Text and Document Classification Technologies
- Complex Network Analysis Techniques
- Advanced Neuroimaging Techniques and Applications
- Anomaly Detection Techniques and Applications
- Vehicular Ad Hoc Networks (VANETs)
- Time Series Analysis and Forecasting
The Affiliated Yongchuan Hospital of Chongqing Medical University
2022-2025
Chongqing Medical University
2022-2025
Shijiazhuang Tiedao University
2013-2024
Xi’an University of Posts and Telecommunications
2019
Wuhan University
2017-2019
Shandong Normal University
2016
Xidian University
2014
National University of Defense Technology
2009-2013
Renmin University of China
2008-2011
Wuhan University of Science and Technology
2009
Privacy protection has recently received considerable attention in location-based services. A large number of location cloaking algorithms have been proposed for protecting the privacy mobile users. In this paper, we consider scenario where different query requests are continuously issued by users while they moving. We show that most existing k-anonymity concerned with snapshot user locations only and cannot effectively prevent location-dependent attacks when users' updated. Therefore,...
Bicycle-sharing systems, which can provide shared bike usage services for the public, have been launched in many big cities. In bicycle-sharing people borrow and return bikes at any stations service region very conveniently. Therefore, systems are normally used as a short distance trip supplement private vehicles well regular public transportation. Meanwhile, located different places region, usages be quite skewed imbalanced. Some too incoming get jammed without enough docks upcoming bikes,...
Privacy preservation has recently received considerable attention for location-based mobile services. Various location cloaking approaches have been proposed to protect the privacy of users. However, existing are ill-suited continuous queries. In view disclosure and poor QoS (Quality Service) under query anonymization, in this paper, we propose a δp-privacy model δq-distortion balance tradeoff between user QoS. Furthermore, two incremental utility-based algorithms --- bottom-up hybrid...
Document representation is the basis of language modeling. Its goal to turn natural text that flows into a structured form can be stored and processed by computer. The bag-of-words model used most text-representation methods are currently available. And yet, they do not consider how phrases in text, which hurts performance tasks use processing later on. Representing meaning promising area future research, but it hard well because organized hierarchy mining efficiency low. In this paper, we...
The accuracy of user location information is inversely proportional to the user's privacy preserving degree k, and quality query service. In order balance conflict between security caused by information, a clustering algorithm aiming at eliminating outliers based on k-anonymity model proposed, which used realize establishment anonymous group in model. distribution optimized. idea replacing center proposed. number repeated queries reduced, service improved premise ensuring through...
Bicycle-sharing systems (BSSs) which provide short-term shared bike usage services for the public are becoming very popular in many large cities. The accelerating traveling demands from have driven several significant expansions of BSSs to place additional bikes and stations their extended service regions. Meanwhile, capture individuals' needs more precisely, expansion, set up online websites receive station location suggestions public. In this paper, we will study re-deployment problem...
Privacy preservation has recently received considerable attention for location-based mobile services. In this paper, we present location-dependent attack resulting from continuous and dependent location updates propose an incremental clique-based cloaking algorithm, called ICliqueCloak, to defend against attack. The main idea is incrementally maintain maximal cliques in un-directed graph that takes into consideration the effect of updates.
Domain adaptation refers to the process of learning prediction models in a target domain by making use data from source domain. Many classic methods solve problem establishing common latent space, which may cause loss many important properties across both domains. In this manuscript, we develop novel method, transfer representation (TLR), learn better space. Specifically, design an objective function based on simple linear autoencoder derive representations The encoder aims project domains...
With the development of global positioning technology, sensor networks, and smart mobile terminal, a large number trajectory data are accumulated. Trajectory contains wealth information, including spatiality, time series, other external descriptive attributes (i.e., features, travelling mode, so on). analysis mining show great value. The research similarity measurement is basis management mining, which plays an important role in computing. Most work only focuses on spatial-temporal features....
Bicycle-sharing systems, which can provide shared bike usage services for the public, have been launched in many big cities. In bicycle-sharing people borrow and return bikes at any stations service region very conveniently. Therefore, systems are normally used as a short-distance trip supplement private vehicles well regular public transportation. Meanwhile, located different places region, usages be quite skewed imbalanced. Some too incoming get jammed without enough docks upcoming bikes,...
Essential tremor (ET) is a common movement syndrome, and the pathogenesis mechanisms, especially brain network topological changes in ET are still unclear. The combination of graph theory (GT) analysis with machine learning (ML) algorithms provides promising way to identify from healthy controls (HCs) at individual level, further help reveal ET.Resting-state functional magnetic resonance imaging (fMRI) data were obtained 101 105 HCs. properties analyzed by using GT analysis, metrics under...
In resource planning scenarios, reverse <inline-formula><tex-math notation="LaTeX">$k$</tex-math></inline-formula> nearest neighbor search plays an important role. However, the existing on trajectories only supports spatial features of trajectories. this article, we introduce neighbors query semantic (R NNST). Given a point from set geo-textual objects (e.g., POIs), finds those that take as one their correlative objects. To efficiently answer R NNST queries, propose novel index IMC-tree,...
Clustering algorithm is often used to analyze the communication data for network intrusion detection system. However, are mixed, e.g., numerical and categorical data. So, at first, this paper put forward a method representing cluster center (prototype) of mixed-type Then respectively in combination with continuity characteristic attributes semantic feature attributes, dissimilarity measurement formula was improved by use Gauss kernel function, on base which, defined objective function. After...