scholarly journals Detecting Traffic Anomalies in Urban Areas Using Taxi GPS Data

2015 ◽  
Vol 2015 ◽  
pp. 1-13 ◽  
Author(s):  
Weiming Kuang ◽  
Shi An ◽  
Huifu Jiang
Keyword(s):  
Traffic Flow ◽  
Urban Areas ◽  
Large Scale ◽  
Detection Method ◽  
Principal Component ◽  
Transportation Systems ◽  
Gps Data ◽  
Metropolitan Cities ◽  
Gps Devices ◽  
Traffic Anomaly

Large-scale GPS data contain hidden information and provide us with the opportunity to discover knowledge that may be useful for transportation systems using advanced data mining techniques. In major metropolitan cities, many taxicabs are equipped with GPS devices. Because taxies operate continuously for nearly 24 hours per day, they can be used as reliable sensors for the perceived traffic state. In this paper, the entire city was divided into subregions by roads, and taxi GPS data were transformed into traffic flow data to build a traffic flow matrix. In addition, a highly efficient anomaly detection method was proposed based on wavelet transform and PCA (principal component analysis) for detecting anomalous traffic events in urban regions. The traffic anomaly is considered to occur in a subregion when the values of the corresponding indicators deviate significantly from the expected values. This method was evaluated using a GPS dataset that was generated by more than 15,000 taxies over a period of half a year in Harbin, China. The results show that this detection method is effective and efficient.

scholarly journals GNSS RUMS: GNSS Realistic Urban Multiagent Simulator for Collaborative Positioning Research

2021 ◽  
Vol 13 (4) ◽  
pp. 544
Author(s):  
Guohao Zhang ◽  
Bing Xu ◽  
Hoi-Fung Ng ◽  
Li-Ta Hsu
Keyword(s):  
Urban Area ◽  
Intelligent Transportation Systems ◽  
Urban Areas ◽  
Large Scale ◽  
Transportation Systems ◽  
Accurate Localization ◽  
Gnss Receivers ◽  
Multipath Signal ◽  
Scale Test ◽  
Error Behavior

Accurate localization of road agents (GNSS receivers) is the basis of intelligent transportation systems, which is still difficult to achieve for GNSS positioning in urban areas due to the signal interferences from buildings. Various collaborative positioning techniques were recently developed to improve the positioning performance by the aid from neighboring agents. However, it is still challenging to study their performances comprehensively. The GNSS measurement error behavior is complicated in urban areas and unable to be represented by naive models. On the other hand, real experiments requiring numbers of devices are difficult to conduct, especially for a large-scale test. Therefore, a GNSS realistic urban measurement simulator is developed to provide measurements for collaborative positioning studies. The proposed simulator employs a ray-tracing technique searching for all possible interferences in the urban area. Then, it categorizes them into direct, reflected, diffracted, and multipath signal to simulate the pseudorange, C/N0, and Doppler shift measurements correspondingly. The performance of the proposed simulator is validated through real experimental comparisons with different scenarios based on commercial-grade receivers. The proposed simulator is also applied with different positioning algorithms, which verifies it is sophisticated enough for the collaborative positioning studies in the urban area.

Make More Connections: Urban Traffic Flow Forecasting with Spatiotemporal Adaptive Gated Graph Convolution Network

2022 ◽  
Vol 13 (2) ◽  
pp. 1-25
Author(s):  
Bin Lu ◽  
Xiaoying Gan ◽  
Haiming Jin ◽  
Luoyi Fu ◽  
Xinbing Wang ◽  
...  
Keyword(s):  
Traffic Flow ◽  
Road Network ◽  
Large Scale ◽  
Transportation Systems ◽  
Urban Traffic ◽  
Propagation Mechanism ◽  
Urban Road ◽  
The Road ◽  
Traffic Flow Forecasting ◽  
Gating Mechanism

Urban traffic flow forecasting is a critical issue in intelligent transportation systems. Due to the complexity and uncertainty of urban road conditions, how to capture the dynamic spatiotemporal correlation and make accurate predictions is very challenging. In most of existing works, urban road network is often modeled as a fixed graph based on local proximity. However, such modeling is not sufficient to describe the dynamics of the road network and capture the global contextual information. In this paper, we consider constructing the road network as a dynamic weighted graph through attention mechanism. Furthermore, we propose to seek both spatial neighbors and semantic neighbors to make more connections between road nodes. We propose a novel Spatiotemporal Adaptive Gated Graph Convolution Network ( STAG-GCN ) to predict traffic conditions for several time steps ahead. STAG-GCN mainly consists of two major components: (1) multivariate self-attention Temporal Convolution Network ( TCN ) is utilized to capture local and long-range temporal dependencies across recent, daily-periodic and weekly-periodic observations; (2) mix-hop AG-GCN extracts selective spatial and semantic dependencies within multi-layer stacking through adaptive graph gating mechanism and mix-hop propagation mechanism. The output of different components are weighted fused to generate the final prediction results. Extensive experiments on two real-world large scale urban traffic dataset have verified the effectiveness, and the multi-step forecasting performance of our proposed models outperforms the state-of-the-art baselines.

scholarly journals GNSS RUMS: GNSS Realistic Urban Multi-agent Simulator for Collaborative Positioning Research

2020 ◽  
Author(s):  
Guohao Zhang ◽  
Bing Xu ◽  
Hoi-Fung Ng ◽  
Li-Ta Hsu
Keyword(s):  
Urban Area ◽  
Intelligent Transportation Systems ◽  
Urban Areas ◽  
Large Scale ◽  
Transportation Systems ◽  
Accurate Localization ◽  
Multipath Signal ◽  
Multi Agent ◽  
Scale Test ◽  
Error Behavior

Accurate localization of road agents is the basis of intelligent transportation systems, which is still difficult to achieve for GNSS positioning in urban areas due to the signal interferences from buildings. Various collaborative positioning techniques are recently developed to improve the positioning performance by the aid from neighboring agents. However, it is still challenging to study their performances comprehensively. The GNSS measurement error behavior is complicated in urban areas and unable to be represented by naive models. On the other hand, real experiment requiring numbers of devices is hard to be conducted, especially for a large-scale test. Therefore, a GNSS realistic urban measurement simulator is developed to provide measurements for collaborative positioning studies. The proposed simulator employs a ray-tracing technique searching for all possible interferences in the urban area. Then, it categorizes them into direct, reflected, diffracted, and multipath signal to simulate the pseudorange, carrier-phase, 〖C/N〗_0, and Doppler shift measurements correspondingly. The performance of the proposed simulator is validated through real experimental comparisons with different scenarios. The proposed simulator is also applied with different positioning algorithms, which verifies it is sophisticated enough for the collaborative positioning studies in the urban area.

scholarly journals Passive Wi-Fi monitoring in the wild: a long-term study across multiple location typologies

2020 ◽  
Author(s):  
Miguel Ribeiro ◽  
Nuno Nunes ◽  
Valentina Nisi ◽  
Johannes Schöning
Keyword(s):  
Public Transportation ◽  
Rural Areas ◽  
Urban Areas ◽  
Large Scale ◽  
Tracking System ◽  
Human Mobility ◽  
Transportation Systems ◽  
Mobility Patterns ◽  
Systematic Analysis ◽  
Long Term Study

Abstract In this paper, we present a systematic analysis of large-scale human mobility patterns obtained from a passive Wi-Fi tracking system, deployed across different location typologies. We have deployed a system to cover urban areas served by public transportation systems as well as very isolated and rural areas. Over 4 years, we collected 572 million data points from a total of 82 routers covering an area of 2.8 km2. In this paper we provide a systematic analysis of the data and discuss how our low-cost approach can be used to help communities and policymakers to make decisions to improve people’s mobility at high temporal and spatial resolution by inferring presence characteristics against several sources of ground truth. Also, we present an automatic classification technique that can identify location types based on collected data.

Multi-Week Travel Surveys Using GPS Devices

2014 ◽  
pp. 104-118 ◽  
Author(s):  
Tao Feng ◽  
Harry Timmermans
Keyword(s):  
Daily Activity ◽  
Large Scale ◽  
Bayesian Belief Network ◽  
Gps Data ◽  
Web Based ◽  
Gps Technology ◽  
Travel Diaries ◽  
One Year ◽  
Gps Devices ◽  
Basic Movement

Previous research has demonstrated that the value of GPS technology in collecting activity-travel data as an alternative to traditional travel surveys depends largely on the accuracy of data imputation and good survey management. In this chapter, the authors discuss experiences in the use of GPS-devices in a large-scale study aimed at collecting multi-week activity-travel diaries in two regions in The Netherlands. GPS devices were used to collect basic movement information, which was processed using Bayesian Belief Network to derive daily activity-travel diaries, and validated using a Web-based prompted recall instrument. The large-scale travel survey was administered across one year. The chapter addresses several issues regarding the design and management of GPS data collection. Reported experiences are expected to provide a useful source of reference for future multi-week travel surveys using GPS technology.

Analysis of Dynamic Impedance Functions in Urban Traffic Flow Guidance System

2012 ◽  
Vol 238 ◽  
pp. 503-506 ◽  
Author(s):  
Zhi Cheng Li
Keyword(s):  
Traffic Flow ◽  
Network Model ◽  
Large Scale ◽  
Choice Model ◽  
Transportation Systems ◽  
Urban Traffic ◽  
Guidance System ◽  
Traffic Network ◽  
Dynamic Traffic ◽  
Run Time

The successful application of Intelligent Transportation Systems (ITS) depends on the traffic flow at any time with high-precision and large-scale assessments, it is necessary to create a dynamic traffic network model to evaluate and forecast traffic. Dynamic route choice model sections of the run-time function are very important to the dynamic traffic network model. To simplify the dynamic traffic modeling, improve the calculation accuracy and save computation time, the flow on the section of the interrelationship between the exit flow and number of vehicles are analyzed, a run-time functions into the flow using only sections of the said sections are established.

scholarly journals Identification of Groundwater Contamination in a Rapidly Urbanized Area on a Regional Scale: A New Approach of Multi-Hydrochemical Evidences

2021 ◽  
Vol 18 (22) ◽  
pp. 12143
Author(s):  
Pan Bi ◽  
Lixin Pei ◽  
Guanxing Huang ◽  
Dongya Han ◽  
Jiangmin Song
Keyword(s):  
Groundwater Contamination ◽  
Organic Contaminants ◽  
Urban Areas ◽  
Large Scale ◽  
Regional Scale ◽  
Principal Component ◽  
Livestock Waste ◽  
New Approach ◽  
The Pearl River ◽  
Socioeconomic Data

Efficient identification of groundwater contamination is a major issue in the context of groundwater use and protection. This study used a new approach of multi-hydrochemical indicators, including the Cl-Br mass ratio, the hydrochemical facies, and the concentrations of nitrate, phosphate, organic contaminants, and Pb in groundwater to identify groundwater contamination in the Pearl River Delta (PRD) where there is large scale urbanization. In addition, the main factors resulting in groundwater contamination in the PRD were also discussed by using socioeconomic data and principal component analysis. Approximately 60% of groundwater sites in the PRD were identified to be contaminated according to the above six indicators. Contaminated groundwaters commonly occur in porous and fissured aquifers but rarely in karst aquifers. Groundwater contamination in porous aquifers is positively correlated with the urbanization level. Similarly, in fissured aquifers, the proportions of contaminated groundwater in urbanized and peri-urban areas were approximately two times that in non-urbanized areas. Groundwater contamination in the PRD was mainly attributed to the infiltration of wastewater from township-village enterprises on a regional scale. In addition, livestock waste was also an important source of groundwater contamination in the PRD. Therefore, in the future, the supervision of the wastewater discharge of township-village enterprises and the waste discharge of livestock should be strengthened to protect against groundwater contamination in the PRD.

scholarly journals Outlier detection for questionnaire data in biobanks

2019 ◽  
Vol 48 (4) ◽  
pp. 1305-1315 ◽  
Author(s):  
Rieko Sakurai ◽  
Masao Ueki ◽  
Satoshi Makino ◽  
Atsushi Hozawa ◽  
Shinichi Kuriyama ◽  
...  
Keyword(s):  
Outlier Detection ◽  
Large Scale ◽  
Detection Method ◽  
Principal Component ◽  
Machine Learning Method ◽  
Questionnaire Data ◽  
Considerable Effort ◽  
Manual Labour ◽  
Record Data ◽  
Regression Adjustment

Abstract Background Biobanks increasingly collect, process and store omics with more conventional epidemiologic information necessitating considerable effort in data cleaning. An efficient outlier detection method that reduces manual labour is highly desirable. Method We develop an unsupervised machine-learning method for outlier detection, namely kurPCA, that uses principal component analysis combined with kurtosis to ascertain the existence of outliers. In addition, we propose a novel regression adjustment approach to improve detection, namely the regression adjustment for data by systematic missing patterns (RAMP). Result Application to epidemiological record data in a large-scale biobank (Tohoku Medical Megabank Organization, Japan) shows that a combination of kurPCA and RAMP effectively detects known errors or inconsistent patterns. Conclusions We confirm through the results of the simulation and the application that our methods showed good performance. The proposed methods are useful for many practical analysis scenarios.

scholarly journals Impact of Culture on Rural Built Environment

2019 ◽  
Vol 8 (10S) ◽  
pp. 78-84
Keyword(s):  
Built Environment ◽  
Natural Resources ◽  
Rural Areas ◽  
Human Activities ◽  
Urban Areas ◽  
Large Scale ◽  
Future Generation ◽  
Transportation Systems ◽  
Rural Regions ◽  
The Common

The term “built environment” refers to the human made or modified physical surroundings in which people live, work and play. These places and spaces include our homes, communities, schools, workplaces, parks/recreations areas, business areas and transportation systems, and vary in size from large-scale urban areas to smaller rural developments. Based on human activities, the environment was created to obtain the basic needs of people. The regular human activities for many generations to prepare their needs are considered as culture. Hence based on culture, the environment was built and maintained for future generation. Regions are separated into two types based on production occurs in rural area and trading developed in urban. In olden days, most of the places are rural because of the undevelopment in transport system. The activities involved in preparing food, shelter and other needs are the common factors to build rural environment. Natural resources are the basic factor that decides the build environment and culture of human in rural regions. By analyzing the natural resources, the cultural impacts are determined based on building environment in rural areas

scholarly journals An Assessment of Age and Gender Characteristics of Mixed Traffic with Autonomous and Manual Vehicles: A Cellular Automata Approach

2020 ◽  
Vol 12 (7) ◽  
pp. 2922 ◽  
Author(s):  
Muhammad Tanveer ◽  
Faizan Ahmad Kashmiri ◽  
Hassan Naeem ◽  
Huimin Yan ◽  
Xin Qi ◽  
...  
Keyword(s):  
Cellular Automata ◽  
Traffic Flow ◽  
Traffic Congestion ◽  
Urban Areas ◽  
Autonomous Vehicles ◽  
Age Groups ◽  
Transportation Systems ◽  
Heterogeneous Traffic ◽  
And Gender ◽  
The Impact

Traffic congestion has become increasingly prevalent in many urban areas, and researchers are continuously looking into new ways to resolve this pertinent issue. Autonomous vehicles are one of the technologies expected to revolutionize transportation systems. To this very day, there are limited studies focused on the impact of autonomous vehicles in heterogeneous traffic flow in terms of different driving modes (manual and self-driving). Autonomous vehicles in the near future will be running parallel with manual vehicles, and drivers will have different characteristics and attributes. Previous studies that have focused on the impact of autonomous vehicles in these conditions are scarce. This paper proposes a new cellular automata model to address this issue, where different autonomous vehicles (cars and buses) and manual vehicles (cars and buses) are compared in terms of fundamental traffic parameters. Manual cars are further divided into subcategories on the basis of age groups and gender. Each category has its own distinct attributes, which make it different from the others. This is done in order to obtain a simulation as close as possible to a real-world scenario. Furthermore, different lane-changing behavior patterns have been modeled for autonomous and manual vehicles. Subsequently, different scenarios with different compositions are simulated to investigate the impact of autonomous vehicles on traffic flow in heterogeneous conditions. The results suggest that autonomous vehicles can raise the flow rate of any network considerably despite the running heterogeneous traffic flow.

Sign in / Sign up

Export Citation Format

Share Document