Match!
Yang Du
University of Science and Technology of China
Machine learningDistributed computingComputer scienceCrowdsourcingReal-time computing
16Publications
3H-index
20Citations
What is this?
Publications 16
Newest
#1Yang DuH-Index: 3
#2Yu-E SunH-Index: 8
Last. Hansong GuoH-Index: 4
view all 7 authors...
With the proliferation of mobile devices, mobile crowd sensing (MCS) has emerged as a new data collection paradigm, which allows the crowd to act as sensors and contribute their observations about entities. Unfortunately, users with varied skills and motivations may provide conflicting information for the same entity. Existing work solves this problem by estimating user reliability and inferring the correct observations (i.e., truths). However, these methods assume that users’ expertise degrees ...
2 CitationsSource
#1Wenjian Yang (Soochow University (Suzhou))H-Index: 2
#2Yu-E Sun (Soochow University (Suzhou))H-Index: 8
Last. Yonglong Luo (Anhui Normal University)H-Index: 11
view all 7 authors...
Traffic volume estimation is critical to the transportation engineering. Persistent traffic volume reveals the amount of core, stable traffic at locations of interest, which is meaningful to many transportation applications, such as traffic flow guidance system. Unfortunately, most of the existing state-of-the-art studies that concentrate on the persistent traffic estimation issue only provide limited privacy preservation. To tackle this challenge, we first present two schemes with differential ...
1 CitationsSource
#1Yang Du (USTC: University of Science and Technology of China)H-Index: 3
#2Yu-E Sun (Soochow University (Suzhou))H-Index: 8
Last. Xiaocan Wu (Soochow University (Suzhou))H-Index: 1
view all 6 authors...
Abstract Crowdsourcing has been proven to be a useful tool for the tasks which are hard for computers. Unfortunately, workers with uneven expertise are likely to provide low-quality or even deliberately wrong data. A reliability model that precisely describes workers' performance on the tasks can benefit the development of both task assignment mechanism and truth discovery method. However, existing methods cannot model workers' fine-grained reliability levels accurately. In this paper, we consid...
1 CitationsSource
#1Xiaofeng Zhao (Soochow University (Taiwan))
#2Xiaocan Wu (Soochow University (Taiwan))H-Index: 1
Last. Zhen Cao (Soochow University (Taiwan))
view all 6 authors...
Real-time road condition monitoring, especially of severe road damage, is critical for driving safety. In this work, we propose a crowdsensing-based pothole detection and measurement system, called CPDM, which can accurately measure the depth and length of detected potholes in urban roads. CPDM learns road surface information by collecting the sensor data from the smartphones belonging to the passing drivers and passengers. The proposed system can detect potholes by observing the vibration signa...
Source
#1Runzhi Wang (Soochow University (Taiwan))
#2Yu-E Sun (Soochow University (Taiwan))H-Index: 8
Last. Danlei Huang (Soochow University (Taiwan))H-Index: 1
view all 6 authors...
Crowdsensing is a promising sensing paradigm to efficiently collect and monitor the physical world by using the embedded sensors in mobile devices. However, the observations (sensory data) submitted by mobile device users may not be reliable. For the same sensing task, users with different reliabilities may submit conflicting information. Thus, we need to estimate the truth based on the submitted observations. Temporal and spatial correlations among tasks are widely observed in crowdsensing appl...
Source
#1Wenjian Yang (Soochow University (Taiwan))H-Index: 2
#2Yu-E Sun (Soochow University (Taiwan))H-Index: 8
Last. Yonglong Luo (Anhui Normal University)H-Index: 11
view all 7 authors...
Traffic volume estimation is critical to the transportation engineering. Persistent traffic volume reveals the amount of core, stable traffic at locations of interest, which is meaningful to many transportation applications, such as traffic flow guidance system. Unfortunately, most of the existing state-of-the-art studies that concentrate on the persistent traffic estimation issue only provide limited privacy preservation. To tackle this challenge, we present two estimators with differential pri...
Source
Jul 1, 2019 in IJCNN (International Joint Conference on Neural Network)
#1Xiaojun Li (Soochow University (Suzhou))
#2Yu-E Sun (Soochow University (Suzhou))H-Index: 8
Last. He Huang (Soochow University (Suzhou))H-Index: 15
view all 7 authors...
Taxi recommender systems have remarkably benefited the taxi business by providing a sequence of pick-up points to reduce the passenger waiting time or the taxi cruising time. In reality, taxi drivers may have their preferred destination regions to avoid traffic jams or to execute arranged pickup orders. However, no prior work managed to maximize the profit of drivers and satisfy the requirements for destination regions at the same time. To tackle this challenge, we propose a PROfit Maximization ...
Source
#2Yu-E SunH-Index: 8
Last. Danlei HuangH-Index: 1
view all 5 authors...
Crowdsensing has emerged as an efficient and inexpensive way to perform specialized tasks by leveraging external crowds. In some crowdsensing systems, different tasks may have different requirements, and there may be precedence constraints among them, such as the Unmanned Aerial Vehicle (UAV) crowdsensing systems. Moreover, minimizing the total execution time is a regular target for finishing the crowdsensing tasks with precedence constraints. As far as we know, only a few existing studies consi...
Source
Dec 3, 2018 in AAIM (Algorithmic Applications in Management)
#1Yang Du (USTC: University of Science and Technology of China)H-Index: 3
#2Yu-E Sun (Soochow University (Suzhou))H-Index: 8
Last. Xiaocan Wu (Soochow University (Suzhou))H-Index: 1
view all 6 authors...
Crowdsourcing has been proven to be a useful tool for solving the tasks hard for computers. Due to workers’ uneven qualities, it is crucial to model their reliabilities for computing effective task assignment plans and producing accurate estimations of truths. However, existing reliability models either cannot accurately estimate workers’ fine-grained reliabilities or require external information like text description. In this paper, we consider dividing tasks into clusters (i.e., topics) based ...
Source
Dec 1, 2018 in MSN (Mobile Ad-hoc and Sensor Networks)
#1Yu Bao (USTC: University of Science and Technology of China)H-Index: 2
#2Yu-E Sun (Soochow University (Suzhou))H-Index: 8
Last. Liusheng Huang (USTC: University of Science and Technology of China)H-Index: 27
view all 8 authors...
Forecasting taxi demand is of great significance to the intelligent transportation systems in a smart city. Traditional demand prediction methods mostly considered about inter-regional traffic, events, activities, and weather, while they overlooked the influence of other travel modes, such as metro. In this paper, we propose a Deep Taxi-Metro Spatial-Temporal Network framework, namely TMST-Net, to model the spatiotemporal relationships between the taxi demand and the metro crowd flows. In detail...
Source
12