Global Positioning System Trajectory Data Research Articles

Identifying Truck Activity from Global Positioning System Data Based on Satellite Imagery

Road freight transportation plays a crucial role in fostering economic growth and enhancing logistics efficiency. Existing research primarily focuses on analyzing freight truck activity characteristics based on global positioning system (GPS) data of freight truck trajectories. Those studies proposed a variety of identification methods from different perspectives, but they mainly rely on rule-based methods and subjectively defined key threshold parameters, ignoring the complexity of truck freight activities and relying on long sequences of trajectory data. To bridge this gap, we propose the satellite image augmented truck activity recognition method, a structured framework that utilizes satellite imagery to identify truck activities from GPS data. Firstly, we categorize truck activities into three types: loading/unloading, resting, and driving. We extract geographic entities from the area of interest data to create the satellite image dataset of truck activity. Secondly, we evaluate the recognition accuracy of benchmark image classification models on our dataset, and ResNet50 achieves 98.04% accuracy on the test set. Thirdly, we apply the image classification model to identify truck activity from GPS trajectory data and use the recognition results of neighboring points to improve the identification results. The framework delineated in this paper entails the extraction of truck activities from GPS data at the satellite image level. Our approach holds promise in facilitating logistics operation fleets and traffic management authorities to maintain near real-time surveillance of the truck status, thereby fostering enhancements in both the efficiency and safety of freight transport.

Travel-mode inference based on GPS-trajectory data through multi-scale mixed attention mechanism

Identifying travel modes is essential for modern urban transportation planning and management. Recent advancements in data collection, especially those involving Global Positioning System (GPS) technology, offer promising opportunities for rapidly and accurately inferring users' travel modes. This study presents an innovative method for inferring travel modes from GPS trajectory data. The method utilizes multi-scale convolutional techniques to capture and analyze both temporal and spatial information of the data, thereby revealing the underlying spatiotemporal relationships inherent in user movement and behavior patterns. In addition, an attention mechanism is integrated into the model to enable autonomous learning. This mechanism enhances the model's capacity to identify and emphasize key information across different time periods and spatial locations, thus improving the accuracy of travel mode inference. Evaluation on the open-source GPS trajectory dataset, GeoLife, demonstrates that the proposed method attained an accuracy of 83.3%. This result highlights the effectiveness of the method, demonstrating that the model can more accurately understand and predict user travel modes through the integration of multi-scale convolutional technologies and attention mechanisms.

Intersection movements delay modelling based on crowd-sensed global positioning system trajectory data

Developing accurate large-scale transportation models, used to guide policy adoption and evaluate infrastructure alternatives or changes in sociodemographic conditions, is data and resource intensive. This research proposes a novel method for modeling intersection movement delay using crowd-sensed Global Positioning System (GPS) data. This is achieved by providing a general definition of turning movements and extracting travel times thought GPS trajectory data analysis. Additionally, a straightforward method is proposed to integrate the observed delays per movement type into volume-delay functions. The spatial definition provided for turning movements captured distinct speed profiles per turn type. The significant differences in mean speeds for different turn types highlights the importance of integrating turn penalty functions based on real observations and underscore the importance of crowd-sensed GPS data. A simple technique is also proposed to integrate the proposed method into the volume-delay functions used in large scale transport models.

Research and application of the global positioning system (GPS) clustering algorithm based on multilevel functions

With the rapid development and widespread adoption of wearable technology, a new type of lifelog data is being collected and used in numerous studies. We refer to these data as informative lifelog which usually contain GPS, images, videos, text, etc. GPS trajectory data in lifelogs is typically categorized into continuous and discrete trajectories. Finding a point of interest (POI) from discrete trajectories is a challenging task to do and has caught little attention so far. This paper suggests an LP-DBSCAN model for mining personal trajectories from discrete GPS trajectory data. It makes use of the hierarchical structure information implied in GPS trajectory data and it is suggested a variable-levels, variable-parameters clustering method (LP-DBSCAN) based on the DBSCAN algorithm to increase the precision of finding POI information. Finally, the Liu lifelog dataset is subjected to a systematic evaluation. In terms of GPS data that are not evenly distributed geographically, the experimental results demonstrated that the proposed algorithm could more accurately identify POI information and address the adverse effects caused by the global parameters of the traditional DBSCAN algorithm.

A Spatial Network-Based Assessment of Individual Exposure to COVID-19

This study seeks to examine the possible impacts of sociodemographic factors, individual mobility patterns, and daily activities on individual exposure to COVID-19 risk when assessed by different risk measures. Taking Hong Kong as the study area, we first model the risk of COVID-19 using a density-based approach and a network-based approach and reveal the differences in the spatial distributions of COVID-19 transmission risk they obtained. Then, using two-day individual Global Positioning System trajectory data and travel diaries collected from individuals in two communities, we measure individual exposure to COVID-19 transmission risk based on their mobility patterns and reveal the disparities in COVID-19 risk exposure among residents of different demographic groups and neighborhoods when conducting different activities. This study reveals the differences in the spatial patterns of COVID-19 transmission risk when the risk is conceptualized by density and network. It demonstrates the power of a spatial network approach in enhancing our understanding of individual exposure to infectious diseases. This study also advances the existing literature by exploring COVID-19 risk exposure, considering individual daily mobility and addressing the uncertain geographic context problem in analyzing individual COVID-19 risk exposure.

Identification of Stopping Points in GPS Trajectories by Two-Step Clustering Based on DPCC with Temporal and Entropy Constraints

The widespread adoption of intelligent devices has led to the generation of vast amounts of Global Positioning System (GPS) trajectory data. One of the significant challenges in this domain is to accurately identify stopping points from GPS trajectory data. Traditional clustering methods have proven ineffective in accurately identifying non-stopping points caused by trailing or round trips. To address this issue, this paper proposes a novel density peak clustering algorithm based on coherence distance, incorporating temporal and entropy constraints, referred to as the two-step DPCC-TE. The proposed algorithm introduces a coherence index to integrate spatial and temporal features, and imposes temporal and entropy constraints on the clusters to mitigate local density increase caused by slow-moving points and back-and-forth movements. Moreover, to address the issue of interactions between subclusters after one-step clustering, a two-step clustering algorithm is proposed based on the DPCC-TE algorithm. Experimental results demonstrate that the proposed two-step clustering algorithm outperforms the DBSCAN-TE and one-step DPCC-TE methods, and achieves an accuracy of 95.49% in identifying stopping points.

Mobility Based on GPS Trajectory Data and Interviews: A Pilot Study to Understand the Differences between Lower- and Higher-Income Older Adults in Hong Kong.

Few studies have examined mobility from a social exclusion perspective. Limited mobility can restrict opportunities to interact with others and therefore may lead to social exclusion. This pilot study was designed to test the feasibility of integrating Global Positioning System (GPS) trajectory data and interview data to understand the different mobility patterns between lower- and higher-income older adults in Hong Kong and the potential reasons for and impacts of these differences. Lower- (n = 21) and higher- (n = 24) income adults aged 60 years of age or older in Hong Kong were recruited based on purposive sampling. They were asked to wear a GPS device for 7 days. Seven measures of mobility (four dimensions) were created based on GPS data and compared between lower- and higher-income older adults, including extensity (standard deviation ellipse, standard distance between all locations), intensity (time spent out of home, doing activities), diversity (number of locations), and non-exclusivity (time spent in public open spaces and places with higher public service provisions). It then administered semi-structured interviews to understand the determined differences. The activity spaces for lower-income older adults were, on average, smaller than those for higher-income older adults, but lower-income older adults spent significantly more time participating in out-of-home activities. They were more likely to be exposed to environments with similar socioeconomic characteristics as their own. The interviews showed that limited social networks and expenditure on transport were the two main factors associated with lower-income older adults having relatively fewer activity spaces, which may lead to further social exclusion. We recommend using GPS in daily life as a feasible way to capture the mobility patterns and using interviews to deeply understand the different patterns between lower- and higher-income older adults. Policy strategies aiming to improve the mobility of older might be helpful for further improving the social inclusion of lower-income older adults.

Travel-mode classification based on GPS-trajectory data and geographic information using an XGBoost classifier

Massive Global Positioning System (GPS) trajectory datasets are being produced owing to the advances in mobile sensors, the Internet, and GPS devices. Accurately inferring travel modes from GPS trajectory data can be helpful in transportation planning and modeling, infrastructure design, etc. However, adverse factors such as data noise, differences in sampling rate, and inadequate features have a negative impact on the results of travel mode classification. In this paper, to address such issues, we first propose a preprocessing workflow, which includes data cleaning, segmentation, and resampling, to preprocess raw trajectories. Then, we add new features related to the road and bus stop information for travel mode classification using an XGBoost (eXtreme Gradient Boosting) classifier, along with various basic features of the trajectories. We conducted a set of experiments on the GeoLife dataset using a group of state-of-the-art methods. The results showed that the proposed methods can improve the classification accuracy by using all the classifiers we compared and the classification accuracy using the XGBoost classifier can reach a maximum of 90.41%.

A spatial modeling approach to estimating bike share traffic volume from GPS data

• Map-matched 2018 GPS trajectory data from Hamilton, Ontario's bike share system to a cycling network. • An ordinary least squares regression model is estimated for annual bike share trips (ABST) on each network link, with eigenvector spatial filtering used to remove autocorrelation. • Hub-trip accessibility is derived for predicting ABST and is found to outperform other accessibility measures. • ABST is higher on links with access to transportation infrastructure and bikeways physically separated from automobiles. • Model is used to evaluate the impact of three planned bikeway infrastructure projects. GPS-equipped bike-share fleets are a source of rich data that can be used to estimate cycling volumes to assist infrastructure investment decisions aimed at increasing ridership. Using global positioning system (GPS) trajectories collected between January 1st and December 31st, 2018 by Hamilton Bike Share (HBS), the volume of bike share trips on every traveled link in the HBS service area is modeled. A map-matching toolkit is used to generate users’ routes to derive the number of observed bike share trips on every traveled link. To model annual bike share traffic volumes, several variables were created at the link level including accessibility measures, distances to important locations in the city, proximity to transportation infrastructure, and bike infrastructure. A linear regression model was estimated, incorporating eigenvector spatial filtering to remove spatial autocorrelation. The results suggest that the largest positive predictors of bike share traffic volumes in terms of cycling infrastructure are those that are physically separated from automobiles by a space or barrier. Additionally, hub-trip distance accessibility, a novel measure, was significant in the model, outperforming other accessibility metrics. A demonstration of how the model can be used for planning cycling infrastructure upgrades is presented.

Transportation mode identification with GPS trajectory data and GIS information

Global Positioning System (GPS) trajectory data can be used to infer transportation modes at certain times and locations. Such data have important applications in many transportation research fields, for instance, to detect the movement mode of travelers, calculate traffic flow in an area, and predict the traffic flow at a certain time in the future. In this paper, we propose a novel method to infer transportation modes from GPS trajectory data and Geographic Information System (GIS) information. This method is based on feature extraction and machine learning classification algorithms. While using GIS information to improve inference accuracy, we ensure that the algorithm is simple and easy to use on mobile devices. Applied to GeoLife GPS trajectory dataset, our method achieves 91.1% accuracy while inferring transportation modes, such as walking, bike, bus, car, and subway, with random forest classification algorithm. GIS features in our method improved the overall accuracy by 2.5% while raising the recall of the bus and subway transportation mode categories by 3.4% and 18.5%. We believe that many algorithms used in detecting the transportation modes from GPS trajectory data that do not utilize GIS information can improve their inference accuracy by using our GIS features, with a slight increase in the consumption of data storage and computing resources.

Discovering spatiotemporal characteristics of passenger travel with mobile trajectory big data

Mobile trajectory big data, such as global positioning system (GPS) trajectories of taxicabs, have enormous social and economic values in intelligent transportation systems, and efficient mining and in-depth analysis of these data can provide beneficial decision-making for traffic operation and especially for passenger travel. To this end, in this paper, we discover the temporal, spatial, and spatiotemporal characteristics of passenger travel by analyzing the travel duration and the travel distance with large-scale taxi trajectory data, which can not only effectively reveal the resident travel patterns but also dynamically perceive the traffic conditions. Specifically, we propose an information framework to preprocess the taxi GPS trajectory data that can thoroughly identify passenger travel trajectories. Moreover, we develop a novel distribution model to explore the rules of citizen travel accurately. Finally, we put forward a parallel clustering approach on Spark, which can discover the spatiotemporal characteristics of passenger travel in a fine-grained manner, to obtain the characteristic changes of inhabitant travel at different periods of the day. In particular, the experimental results from an empirical study show that the travel duration and the travel distance follow a log-normal distribution, and the tail of the travel distance is highly fitting to a three-parameter gamma distribution and the long-distance travel of the day is mainly to the airport between 5:00 and 6:00 AM.

Using Taxi GPS Trajectory Data to Optimize the Spatial Layout of Urban Taxi Stands

The unreasonable layout of taxi stands (TS) in urban areas not only fails to provide bidirectional guidance for drivers and passengers but also wastes spatial resources and aggravates the surrounding traffic. This paper compares the performance of three classical location models in optimizing TS spatial layout, and develops an extended model integrating the p-median and distance factor to support TS site selection in urban planning from multiple perspectives. To this end, taxi demand with spatial–temporal dynamics is extracted from taxi global positioning system (GPS) data to uncover the restrictive distribution characteristics of the setting areas and specific locations of TS with GIS platform. Taxi demand is then subdivided, and potential service points are set up on the road network. With the constraints of the supply and demand environment, we design the TS location models (TSLM) based on the set covering problem (SCP), the maximal covering location problem (MCLP), and the p-median problem (PMP), respectively. Furthermore, the TSLM based on PMP is extended to consider the maximum acceptable distance for passengers. A genetic algorithm-based procedure is introduced for solving the extended TSLM. An experiment conducted in China compares the facility coverage capacity, taxi demand allocation, and passenger access willingness of the optimal layout schemes obtained from four TSLMs. The number of parking spaces at TS is also evaluated. The result demonstrates that extended TSLM outperforms the other three models in the validity of locating TS.

Traffic travel pattern recognition based on sparse Global Positioning System trajectory data

This article mainly uses sparse Global Positioning System trajectory data to identify traffic travel pattern. In this article, the data are preprocessed and the eigenvalues are calculated. Then, the Global Positioning System track points are identified and extracted by walking and non-walking segments. Finally, the three machine learning models of support-vector machine, decision tree, and convolutional neural network are used for comparison experiments. The innovation of this article is to propose a walking and non-walking identification method based on density-based spatial clustering of applications with noise clustering. The method takes into account the continuous state between the geographical distributions, and it has better noise immunity against the influence of external factors. In this process, this article directly achieves better conversion point recognition results through the Global Positioning System track point information, which lays a good foundation for the accuracy of travel pattern recognition. The experimental results of this article show that compared with threshold-based and multi-layer perceptron–based methods, the recognition method based on density-based spatial clustering of applications with noise clustering has the highest accuracy, reaching 82.20%. Then, support-vector machine, decision tree, and convolutional neural network are used for traffic travel pattern recognition. The F1-score of support-vector machine is the highest, reaching 0.84, and the F1-scores of decision tree and convolutional neural network are 0.78 and 0.80, respectively. Finally, the support-vector machine was used for the recognition test to achieve an accuracy of 76.83%.

Understanding the Competitive Advantages of Car Sharing from the Travel-Cost Perspective.

The emergence and development of car sharing can not only satisfy people’s diverse travel demands, but also can bring a new solution to facilitate urban low-carbon and green development. With the increasing acceptance of car sharing, the market competition between car sharing and traditional taxis is becoming increasingly fierce. Therefore, we explore the advantages of car sharing to travelers compared with taxis. In this paper, we first use the GPS (Global Positioning System) trajectory data of car sharing orders to construct a comparative advantage model based on travel-cost. Then, we take Beijing as the research area to explore the travel-cost advantages of car sharing in terms of the time and space dimensions compared with taxis, through calculating the travel-cost of car sharing and using simulation to calculate that of taxis. The results of the comparison between car sharing and taxis from the perspective of travel-cost are as follows: (1) Compared with short trips, the travel-cost advantage of car sharing is relatively higher in medium and long trips; for travelers, the taxi has a higher travel-cost advantage when the travel time is either very long or very short. (2) On weekdays, it is more cost-effective to travel by shared cars for travelers before the rush hours in the evening, and the travel-cost advantage of using taxis is greater after the evening peak. (3) Compared with weekdays, it is more cost-effective to travel by shared cars on weekends wherever travelers are living in the main urban areas or in the remote suburbs. It is suggested that relevant departments should understand the travelers’ preference and analyze the influence mechanism of other various factors on the market demand for car sharing as per the focus on the market on the travel-cost advantages of car sharing, so as to promote the healthy and sustainable development of urban shared transportation.

Mode Inference using enhanced Segmentation and Pre-processing on raw Global Positioning System data

Many applications use the Global Positioning System data that provide rich context information for multiple purposes. Easier availability and access of Global Positioning System data can facilitate various mobile applications, and one of such applications is to infer the mobility of a user. Most existing works for inferring users’ transportation modes need the combination of Global Positioning System data and other types of data such as accelerometer and Global System for Mobile Communications. However, the dependency of the applications to use data sources other than the Global Positioning System makes the use of application difficult if peer data source is not available. In this paper, we introduce a new generic framework for the inference of transportation mode by only using the Global Positioning System data. Our contribution is threefold. First, we propose a new method for Global Positioning System trajectory data preprocessing using grid probability distribution function. Second, we introduce an algorithm for the change point–based trajectory segmentation, to more effectively identify the single-mode segments from Global Positioning System trajectories. Third, we introduce new statistical-based topographic features that are more discriminative for transportation mode detection. Through extensive evaluation on the large trajectory data GeoLife, our approach shows significant performance improvement in terms of accuracy over state-of-the-art baseline models.

Convolutional LSTM based transportation mode learning from raw GPS trajectories

With the advancement of location acquisition technologies, a large amount of raw global positioning system (GPS) trajectory data is produced by many moving devices. Learning transportation modes from the GPS trajectory data is an important problem in the domain of trajectory data mining. Traditional supervised learning-based approaches rely heavily on data preprocessing and feature engineering, which require domain expertise and are time consuming. The authors propose a deep learning-based convolutional long short term memory (LSTM) model for transportation mode learning, in which the convolution neural network is first used to extract deep high-level features and then LSTM is used to learn the sequential patterns in the data that uses both GPS and weather features, thus making the full use of spatiotemporal operations. The authors have also analysed the impact of the geospatial region on human mobility. Experiments conducted on the Microsoft Geolife data set fused with the weather data set show that their model achieves the state-of-the-art results. The authors compare the performance of their model with the benchmark models, which shows the superiority of their model having 3% improvement in accuracy using only GPS features, and the accuracy is further improved by 4 and 7% on including the impact of geospatial region and weather attributes, respectively.

Bayesian models with spatial autocorrelation for bike sharing ridership variability based on revealed preference GPS trajectory data

Increasing bike sharing ridership to reduce traffic congestion and air pollution has become the major goal of policy makers and transportation planners. In this study, aggregated macro-level models are developed to investigate and quantify correlations of bike sharing ridership variability in the city of Seoul. The bike sharing kilometres travelled (BSKT) is introduced as the ridership measurement, and a revealed preference method for its estimation is proposed using more than five million trip trajectories of global positioning system (GPS) collected from the bike sharing system of Seoul city. Six different models grouped into three categories are estimated, including linear regression, Bayesian model without spatial effect and Bayesian models with spatial autocorrelation. Five categories of variables are used to explain the variability of BSKT in Seoul. The contribution of these variables in intra-zonal BSKT and inter-zonal BSKT are also modelled and compared. The findings suggest a strong correlation among BSKT, bike sharing stations and bicycle network variables. The model comparison results indicate that the performances of the models with spatial autocorrelation are considerably improved.

Analysis of Spatial and Temporal Characteristics of Citizens’ Mobility Based on E-Bike GPS Trajectory Data in Tengzhou City, China

Environmentally friendly shared transit systems have become ubiquitous at present. As a result, analyzing the ranges and tracts of human activities and gatherings based on bike share data is scientifically useful. This paper investigates the spatial and temporal travel characteristics of citizens based on real-time-extracted electric bikes (e-bikes) Global Positioning System (GPS) data from May to July in 2018 in the central area of Tengzhou City, Shandong Province, China. The research is conducive for the exploration of citizens’ changes in mobility behaviors, for the analysis of relationships between mobility changes and environmental or other possible factors, and for advancing policy proposals. The main conclusions of the study are as follows. First, in general, citizens’ travelling is featured by rides that are less than 10 min, shorter than 5 km, and with a speed between 5 km/h and 20 km/h. Second, in terms of temporal characteristics, monthly e-bike usage and citizens’ mobility are positively correlated with temperature in May and negatively correlated with temperature in July; an overall negative correlation is also manifested between the e-bike usage (mobility) and air quality index; daily usage reaches a trough on Tuesday and a peak on Friday, indicating the extent of mobility on respective days; e-bike usage and human outdoor behaviors are significantly lowered in rainy weather than in sunny weather; hourly rides reach a peak at 18:00 (more human activities) and a trough at 2:00 (less activities), and average hourly riding speed maximizes at 5:00 and minimizes around 8:00 and 17:00. Third, for spatial characteristics, destinations (D points) during morning rush hour and regions where e-bikes are densely employed are concentrated mainly in mid-north and middle parts of the central area (major human gatherings), and the rides have a diffusing pattern; e-bike origin–destination (O–D) trajectories radiate mostly towards the mid-north and the east during evening rush hour. In addition, 9.4% of the total trips to work areas during morning rush hour represent spillover commuting, indicating that separations between jobs and residential are not severe in the central area of Tengzhou City and commuting is relatively convenient.

Data‐driven next destination prediction and ETA improvement for urban delivery fleets

In an urban logistics system, predictions of the next destination and estimated time of arrival (ETA) are of paramount importance for efficient resource planning of delivery fleets and for providing a satisfactory client experience. The quality of prediction is limited by the information accessible to individual logistics business entities, and further complicated by the complex urban road system. Data collection under the auspices of smart city initiatives worldwide provides exciting new opportunities to overcome these limitations. In this study, the authors identify two areas of improvement through data-driven approaches, including a next destination predictor, based on the delivery fleet's historical global positioning system trajectory data using a non-linear autoregressive neural network, and a road incident detector for real-time ETA improvement. By comparing a range of machine learning classification algorithms for incident detection, XGBoost has been found to be the most practical choice, due to its performance and efficiency. The proposed framework can be utilised by government authorities who possess such data for better urban planning and providing advanced infrastructure, so as to improve the operational efficiency of the logistics industry.

A System of Mining Semantic Trajectory Patterns from GPS Data of Real Users

Positioning devices allow users’ movement to be recorded. The GPS (Global Positioning System) trajectory data typically consists of spatiotemporal points, which make up the major part of the big data concerning urban life. Existing knowledge extraction methods about the trajectory share a general limitation—they only investigate data from a spatiotemporal aspect, but fail to take the semantic information of trajectories into consideration. Therefore, extracting the semantic information of trajectories with the context of big data is challenging pattern recognition task that has practical application prospects. In this paper, a system is proposed to extract the semantic trajectory patterns of positioning device users. Firstly, a spatiotemporal threshold and clustering based pre-processing model is proposed to process the raw data. Then, we design a probabilistic generative model to annotate the semantic information of each trajectory after the pre-processing procedure. Finally, we apply the PrefixSpan algorithm to mine the semantic trajectory patterns. We verify our system on a large dataset of users’ real trajectories over a period of 5 years in Beijing, China. The results of the experiment indicate that our system produces meaningful patterns.