Car sharing is a type of car rental service, by which consumers rent cars for short periods of time, often charged by hours. The analysis of urban traffic big data is full of importance and significance to determine locations of depots for car-sharing system. Taxi OD (Origin-Destination) is a typical dataset of urban traffic. The volume of the data is extremely large so that traditional data processing applications do not work well. In this paper, an optimization method to determine the depot locations by clustering taxi OD points with AP (Affinity Propagation) clustering algorithm has been presented. By analyzing the characteristics of AP clustering algorithm, AP clustering has been optimized hierarchically based on administrative region segmentation. Considering sparse similarity matrix of taxi OD points, the input parameters of AP clustering have been adapted. In the case study, we choose the OD pairs information from Beijing’s taxi GPS trajectory data. The number and locations of depots are determined by clustering the OD points based on the optimization AP clustering. We describe experimental results of our approach and compare it with standard K-means method using quantitative and stationarity index. Experiments on the real datasets show that the proposed method for determining car-sharing depots has a superior performance.
Group sensing is a kind of crowdsensing service where HD map producers motivate private cars in a local region to collect data from real world. Group sensing needs vehicles to communicate physically and drivers to collaborate strategically in a mobile or edgeassisted environment. First, we consider collaboration module that motivates drivers to be participants; centralized and distributed motivating methods are discussed. Secondly, we consider communication module; two VANET-based methods are proposed to achieve message relaying in edge infrastructure. To accomplish participants' selection, three combinations of two modules are proposed and simulated based on a flexible framework. The results show that centralized selection could motivate collaboration at a low price but brings heavy communication overhead. Clustered selection requires more incentives and less communication overhead than centralized selection. Distributed selection is usually the first class choice because of its fine performances on both communicating and motivating.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.