In this paper, we develop a semantic annotation technique for location-based social networks to automatically annotate all places with category tags which are crucial prerequisite location search, recommendation services, or data cleaning. Our algorithm learns binary support vector machine (SVM) classifier each tag in the space multi-label classification. Based on check-in behavior of users, extract features from i) explicit patterns (EP) individual and ii) implicit relatedness (IR) among...

Most previous research on location recommendation services in location-based social networks (LBSNs) makes recommendations without considering where the targeted user is currently located. Such may recommend a place near her hometown even if traveling out of town. In this paper, we study issues making for out-of-town users by taking into account preference, influence and geographical proximity. Accordingly, propose collaborative framework, called User Preference, Proximity Social-Based...

Feature types play a crucial role in understanding and analyzing geographic information. Usually, these are defined, standardized, controlled by domain experts cover features on the mesoscale level, e.g., populated places, forests, or lakes. While feature also underlie most Location-Based Services (LBS), assigning consistent typing schema for Points Of Interest (POI) across different data sets is challenging. In case of Volunteered Geographic Information (VGI), assigned as tags heterogeneous...

A traditional hybrid operational mode of a metro system usually combines the express and local trains. The stopping patterns trains are generally assumed to be same. To provide diverse service, this paper aims explore train timetable optimization method when have different patterns. passenger-oriented timetabling model for reducing passenger waiting time is established, which proved quadratic programming problem. Then, an Interior Point Method applied obtain best timetable. case study based...

Purpose The purpose of this paper is to propose a framework for data mining (DM)‐based anti‐money laundering (AML) research. Design/methodology/approach First, suspicion are prepared by using DM techniques. Also, methods compared with traditional investigation Next, rare transactional patterns further categorized as unusual/abnormal/anomalous and suspicious whose recognition also includes fraud/outlier detection. Then, in summarizing the reporting money (ML) crimes, an analysis made on ML...

Express/local mode is an innovation combined with both express train and local in metro system, which can offer conventional service for every station rapid selected stations. The traditional operation planning express/local often carried out sequentially, leading to sub-optimality the overall scheme even inability match passenger demand. This paper aims propose integrated optimization approach of timetable ratio mode. An event-driven model a decomposition method are introduced facilitate...

This study quantifies the impact of individual attributes, built environment, and travel characteristics on use bike-sharing willingness shifting to bike-sharing-related modes (bike-sharing combined with other public transportation such as bus subway) under different scenarios. The data are from an RP (Revealed Preference) survey SP (Stated in Nanjing, China. Three mixed logit models established: attribute–travel model, a various-factor usage frequency scenario–transfer model. It is found...

This study investigated the operational features in bicycle traffic flow on bicycle-only paths. A field investigation was conducted four paths vicinity of bottlenecks city Nanjing, China; two were one-lane and two-lane The cumulative curve method used to extract from videos information, such as speeds, flow, density. fundamental diagram with free-flow congested state constructed use actual data. Data analysis showed that capacity 3,960 bicycles per hour 8,100 hour, respectively. critical...

This paper focuses on how to minimize the total passenger travel time cost by computing and adjusting skip-sop patterns with given time-varying origin-to-destination demand matrices. A bi-objective nonlinear integer programming model linear constraints is proposed precisely formulate operating under minute-dependent from different origin–destination pairs. The implemented using genetic algorithm idea point optimization solvers, we show its effectiveness real world instance of Guangzhou Metro Line 8.

ABSTRACTProviding effective Through Train Services (TTSs) faces challenges due to complex infrastructure conditions, train performances and passenger demands. To enhance TTSs between two different classes of urban rail transit lines with variations in speed capacity, we propose a multi-objective Integer Non-Linear Programming (INLP) model. This model maximizes travel time savings average load utilization, develops an integrated approach simultaneously optimize the frequencies through express...

Many urban streets are designed with on-street bike lanes to provide right-of-way for bicycle traffic. However, when flow is large, extensive passing maneuvers could occupy vehicle and thus cause interferences The primary objective of this study evaluate how traffic affects operation on lanes. Data were collected six street segments in Nanjing, China. cumulative curves constructed extract information including individual speeds aggregated parameters such as density. results showed that...

To analyze the key factors related to workplace vertical violence among nursing interns in China and propose strategies improve practice environment.A cross-sectional study was conducted using Importance-Performance Analysis (IPA) method significance of for interns. The data were obtained by administering a survey, designed specifically this study, 120 at tertiary general hospital Zhejiang Province, China.The results demonstrated that variables "I ordered do something beyond my ability...

This study mainly studies the contributing factors on residents’ travel mode choices after emergence of bike‐sharing. In contrast to existing studies, authors divided travellers into commuters, students, and other by purposes, analysed their choice a mix logit model, respectively. It is found that have many similarities differences. Gender, private car ownership, cost, distance, time are common for all travellers; economy comfort preference affect commuters students; affected age, income,...

Nowadays, an express/local mode has be studied and applied in the operation of urban rail transit, it been proved to beneficial for long-distance travel. The optimization train patterns timetables is vital application mode. former one widely discussed various existing works, while study on timetable limited. In this study, a model proposed by minimizing total passenger waiting time at platforms. Further, genetic algorithm used solve minimization problems model. This uses data collected from...

Massive short-term passenger flow prediction models of urban rail transit stations have been used in different conditions. However, researchers encountered several challenges while selecting the optimal information input matrix and eliminating redundant original data. In this paper, we propose a learning network based on algorithm (MTFLN) method. Based attribute predicted target station correlation coefficient distribution characteristics stages, parameters (OPFIIA) are set reasonably. The...

Travel behaviors and activity patterns in the historic urban area of a city are expected to be different from overall situations area. The primary objective this study is analyze residents’ travel Based on survey data conducted Yangzhou, activities local residents whole day were classified into five types patterns. multinomial logit (MNL) model was developed evaluate impacts explanatory variables choices results showed that choice pattern significantly impacted by contributing factors...

The primary objective of this study is to analyze the characteristics commuting activities within historical districts in cities China. impacts various explanatory variables on commuters’ travels are evaluated using structural equation modeling (SEM) approach. household survey was conducted Yangzhou, Based data, individual and attributes were considered exogenous variables, while subsistence activity characteristics, travel times, numbers three typical home-based trip chains, mode as...

SUMMARY The goal of this project is to rapidly construct an order‐by‐order level snapshot financial markets with nanosecond resolution time stamps. We are particularly interested in understanding the impact high‐frequency traders on security, stability, and fairness these markets. In paper, we describe our computational approach, optimizations that were applied improve performance software by a factor more than 125×, new capabilities can be enabled using combination fast algorithms XSEDE...