Search

With widespread deployment of GPS devices, massive spatiotemporal trajectories became more accessible. This booming trend paved the solid data ground for researchers to discover the regularities or patterns of human mobility. However, there are still three challenges in semantic pattern extraction including semantic absence, semantic bias and semantic complexity. In this paper, we invent and apply a novel data structure namely City Semantic Diagram to overcome above three challenges. First, our approach resolves semantic absence by exactly identifying semantic behaviours from raw trajectories. Second, the design of semantic purification helps us to detect semantic complexity from human mobility. Third, we avoid semantic bias using objective data source such as ubiquitous GPS trajectories. Comprehensive and massive experiments have been conducted based on real taxi trajectories and points of interest in Shanghai. Compared with existing approaches, City Semantic Diagram is able to discover fine-grained semantic patterns effectively and accurately. [ABSTRACT FROM AUTHOR]

Individuals driving private cars in the urban environments to fulll their travel needs have become one of the major daily activities. In particular, unlike the travel with floating cars such as taxis or ride-hailing vehicles, the travel behaviors of private cars exhibit a certain degree of regularity based on daily travel demands. Understanding such travel behavior facilitates many applications, e.g., intelligent transportation, smart city planning, and location-based services (LBS). In this paper, we focus on extracting the regular travel behavior of private cars based on trajectory data analysis. Specifically, first, we construct a trajectory similarity matrix since the similarity of trajectories reflects regular travel behavior. To achieve this, we introduce the stay time and propose an Improved Edit distance with Real Penalty (IERP) to measure the temporal-spatial distance between trajectories. Then, we employ Kernel Principal Component Analysis (KPCA) to reduce the feature dimension of the similarity matrix. Finally, to identify the travel regularity from large set of unlabeled trajectory data, we propose a classification method based on transfer learning to migrate existing knowledge with the purpose of solving learning problems in the target domain with only a small amount of labeled trajectory data or even no data. Extensive experiments using large-scale real-world trajectory data demonstrate that the proposed method can effectively identify the regular travel pattern of private cars and obtain superior accuracy when compared with the existing methods. Our findings on discovering regular travel behaviors of private cars can be directly applied to applications including destination prediction, PoI recommendation and route planning. [ABSTRACT FROM AUTHOR]

Human mobility data refers to records of human movements, such as cellphone traces, vehicle GPS trajectories, geo-tagged posts, and photos. While successfully mining human mobility data can benefit many applications such as city planning, transportation, urban economics, and public safety, it is very challenging to model large-scale Heterogeneous Human Mobility Data (HHMD) that are generated from different resources. In this paper, we develop a general collective learning approach to model HHMD at an individual level towards identifying and quantifying the urban forms of residential communities. Specifically, our proposed method exploits two geographic regularities among HHMD. First, we jointly capture the correlations among residential communities, urban functions, temporal effects, and user mobility patterns by analogizing communities as documents and mobility patterns as words. Also, we further combine explicit LASSO analysis and significant testing into latent representation learning as a regularization term by analogizing compatible Point-of-Interests (POIs) as the meta-data of communities. In this way, we can learn the urban forms, including a mix of functions and corresponding portfolios, of residential communities from HHDM and POIs. We further leverage these learned results to address two application problems: real estate ranking and restaurant popularity prediction. Finally, we conduct intensive evaluations with a variety of real-world data, where experimental results demonstrate the effectiveness of our proposed modeling method and its successful applications for other problems. [ABSTRACT FROM AUTHOR]

Advanced technology in GPS and sensors enables us to track physical events, such as human movements and facility usage. Periodicity analysis from the recorded data is an important data mining task which provides useful insights into the physical events and enables us to report outliers and predict future behaviors. To mine periodicity in an event, we have to face real-world challenges of inherently complicated periodic behaviors and imperfect data collection problem. Specifically, the hidden temporal periodic behaviors could be oscillating and noisy, and the observations of the event could be incomplete. In this paper, we propose a novel probabilistic measure for periodicity and design a practical algorithm, ePeriodicity, to detect periods. Our method has thoroughly considered the uncertainties and noises in periodic behaviors and is provably robust to incomplete observations. Comprehensive experiments on both synthetic and real datasets demonstrate the effectiveness of our method. [ABSTRACT FROM AUTHOR]

Map services, e.g., Google Maps, are gaining popularity for vehicle navigation. However, map service users have to provide sensitive information like precise geographic locations or detailed addresses, which are susceptible to accidental leakage or even data mining in the future. We find existing general-purposed location privacy protection mechanisms (LPPMs) not effective, when applied to map service on smartphones. This paper presents ShiftRoute, a new LPPM specially designed for map services on smartphones. ShiftRoute enables smartphone users to query a route between two endpoints on the map, without revealing any meaningful location information. The basic idea is to strategically shift the endpoints to nearby ones, such that: 1) the semantic meanings encoded in these endpoints (e.g., their addresses) change much, i.e., location privacy is largely protected; 2) the routes returned by map services change little, i.e., service usability is preserved. Specifically, we design a protocol to allow a mobile client to retrieve point of interests (POIs) close to the original endpoints, and an algorithm that selects shifted endpoints from these POIs, that achieves the privacy property of geo-indistinguishability. We implement an application of ShiftRoute on Android, and conduct experiments with real traces from a production map service. Experimental results show that ShiftRoute strikes a good tradeoff between location privacy and service usability. [ABSTRACT FROM PUBLISHER]

Road-based mass transit systems are an effective means to combat the negative impact of transport that is based on private vehicles. Providing quality of service in this type of transit system is a priority for transport authorities. In these systems, travel time (TT) is a basic factor in quality of service. This paper presents a methodology, based on data mining, for analyzing TT in a mass transit system that is planned by timetable. The objective of the methodology is to understand the behavior patterns of TTs on the different routes of the transport network, as well as the factors that influence these patterns. To achieve this objective, the methodology uses clustering techniques to process the GPS data provided by the vehicles of the public transport fleet. The results that were obtained when implementing this methodology in a public transport company are presented as a use case, demonstrating its validity.

In the research of P2P lending data, the study of borrower characteristics is of great value for the establishment of target customers and risk management. Because of high dimensionality, mixed attributes, different importance, and different generation time of information, P2P lending data often leads to the mining results unable to reflect the important borrower characteristics that affect the approval results and the approval loan amount. In this article, we are the first to propose the attributes partition of lending data considering the business process to classify variables into different types. Furthermore, we propose a multiangle data mining method for lending data by attributes partition considering the business process to discover the characteristics of P2P borrowers from multiple perspectives. Experimental results on the real dataset demonstrate that the method depicts the important characteristics of borrowers that affect the approval results and the loan amount, makes the research on P2P borrower characteristics more comprehensive and specific, and provides new ideas for the research on high-dimensional lending data. [ABSTRACT FROM AUTHOR]

Ride hailing is a representative practice of rapidly developing sharing economy, which not only brings people convenience on mobility, but also benefits the utilization of vehicular resources. For ride-hailing service providers, it is necessary to supervise the demands of customers so that they could carry out reasonable dispatches. To achieve it, a number of data mining methods have been applied. But most of these predicting methods only consider this problem from the temporal aspect, neglecting the connection inter and intra blocks of the city. Blocks are the outputs of region partition, which divides the whole city into a series of divisions. At the same time, the partitioned map, specifying borders of blocks, is useful for platforms to improve the process of supervising, dispatching, and recommending. However, the majority of current partition methods is static and cannot effectively utilize features extracted from historical and geographical operational data. In this work, we propose to conduct partition task with taking distinct situations in different blocks into consideration. In particular, we propose a novel region partition assisted long short term memory neural network for ride-hailing service demand prediction. This is a two-phase model, consisting of the grid-merging region partition and the application of artificial neural network. In experiment part, we show how the region partition method assists LSTM to better forecast the demands, and compare it with other partition techniques. Finally, for evaluating the performance of RPA-LSTM, we conduct extensive experiments on a real-world dataset provided by Didi Chuxing. The experimental results clearly demonstrate that our method can effectively improve the accuracy of prediction. [ABSTRACT FROM AUTHOR]

Understanding how people move in the urban area is important for solving urbanization issues, such as traffic management, urban planning, epidemic control, and communication network improvement. Leveraging recent availability of large amounts of diverse crowdsensed data, many studies have made contributions to this field in various aspects. They need proper review and summary. In this article, therefore, we first review these recent studies with a proper taxonomy with corresponding examples. Then, based on the experience learned from the studies, we provide a comprehensive tutorial for future research, which introduces and discusses popular crowdsensed data types, different human mobility subjects, and common data preprocessing and analysis methods. Special emphasis is placed on the matching between data types and mobility subjects. Finally, we present two research projects as case studies to demonstrate the entire process of understanding urban human mobility through crowdsensed data on a city-wide scale and a building-wide scale, respectively. Beyond demonstration purposes, the two case studies also make contributions to their category of certain crowdsensed data types and mobility subjects. [ABSTRACT FROM AUTHOR]

The process of scientific discovery is traditionally assumed to be entirely executed by humans. This article highlights how increasing data volumes and human cognitive limits are challenging this traditional assumption. Relevant examples are found in observational astronomy and geoscience, disciplines that are undergoing transformation due to growing networks of space-based and ground-based sensors. The authors outline how intelligent systems for computer-aided discovery can routinely complement and integrate human scientists in the insight generation loop in scalable ways for next-generation science. The pragmatics of model-based computer-aided discovery systems go beyond feature detection in empirical data to answer fundamental questions, such as how empirical detections fit into hypothesized models and model variants to ease the scientist's work of placing large ensembles of detections into a theoretical context. The authors demonstrate successful applications of this paradigm in several areas, including ionospheric studies, volcanics, astronomy, and planetary landing site identification for spacecraft and robotic missions. [ABSTRACT FROM PUBLISHER]