Global Positioning System Trajectory Data Research Articles

Smoothing and Interpolating Noisy GPS Data with Smoothing Splines

AbstractA comprehensive method is provided for smoothing noisy, irregularly sampled data with non-Gaussian noise using smoothing splines. We demonstrate how the spline order and tension parameter can be chosen a priori from physical reasoning. We also show how to allow for non-Gaussian noise and outliers that are typical in global positioning system (GPS) signals. We demonstrate the effectiveness of our methods on GPS trajectory data obtained from oceanographic floating instruments known as drifters.

Taxi Drivers’ Cruising Patterns—Insights from Taxi GPS Traces

In this paper, we seek to identify the different impacts of external and internal information on taxis’ cruising behaviors and to find effective methods to enhance taxis’ cruising efficiency. Through global positioning system trajectory data collected in Shenzhen, China, we determine the impacts of external factors (land use, traffic conditions, and road grade) and internal factors (previous pick-up experience) on cruising location choice using a zero-inflated negative binomial model. The results indicate that the external factors have a more significant influence than the internal ones. Specifically, traffic conditions, land use, urban expressways, and previous pick-up points are the major factors that influence drivers’ cruising decisions. The results also show that drivers follow different patterns during different times of day, i.e., relying on traffic conditions and land use in the morning/ evening peak hours but emphasizing land use and previous pick-up experience during non-peak hours. In addition, high-earning drivers and roaming drivers prefer to cruise in areas with high-density land use and optimal traffic conditions, whereas low-earning drivers and target drivers tend to cruise in areas with more previous pick-up points. These findings uncover the underlying mechanisms of cruising decisions and facilitate the development of strategies to minimize empty cruising time. Based on the study results, the external and internal information that was found to affect cruising decisions can be released to taxi drivers to improve their cruising efficiency. This information is also helpful to managers in deciding the overall layout of taxi service locations.

Statistical analysis of the stability of bus vehicles based on GPS trajectory data

High quality bus service is considered as an efficient way to mitigate traffic congestion in big cities. Global positioning system (GPS) data provide sufficient sources to evaluate the performance of bus vehicles that both passengers and operator concern about. This paper aims to propose a framework to assess the operational performance of bus routes based on the GPS trajectory data collected from Jinan, China. Several important indicators of bus operation including travel time of routes, section running time, dwell time and bus bunching have been studied. The results show that the travel time of routes follow right skewed distributions. Moreover, section running time between two consecutive stations varies in different time period and it is larger in evening peak hours. Additionally, the dwell time has been discussed and the results show that there is no big variation in most stations except some stations, which provides a help to identify the key stations. Furthermore, we propose an approach to detect the bunching points. The results indicate the bunching points are easy to occur in the peak hours and the congested road section.

Detecting Travel Modes Using Rule-Based Classification System and Gaussian Process Classifier

Travel modes are generally derived from Global Positioning System (GPS) data on the basis of either a rule-based or machine learning classification method. The rule-based classification approach is generally easy to understand, whereas the machine learning classification method has better generalization. However, studies that jointly explore both methods are limited. The present research proposes a two-stage method that aims to impute travel modes from GPS trajectory data. In the first stage, rules are employed to detect subway modes. In the second stage, a Gaussian process classifier based on sequential forward selection methods is utilized to derive the remaining travel modes. On the basis of the four selected features constituting the feature set (i.e., average speed, average acceleration, heading change, and low-speed point rate), over 97% of the samples with subway modes are correctly identified and 93.04% of segments in the walk-based balanced test subset are accurately detected. Over 92% of the car and bus samples are correctly detected for the training and test datasets. Results provide a new perspective in selecting classification methods for the detection of travel modes and other travel characteristics from GPS trajectory data. Furthermore, high differentiation is achieved between the bus and car modes without the bus transit geographic information system sources of bus networks. Therefore, reasonable extracted features contribute to the detection of travel modes, particularly between bus and car modes.

Navigation Application Programming Interface Route Fuel Saving Opportunity Assessment on Large-Scale Real-World Travel Data for Conventional Vehicles and Hybrid Electric Vehicles

The green-routing strategy instructing a vehicle to select a fuel-efficient route benefits the current transportation system with fuel-saving opportunities. This paper introduces a navigation application programming interface (API), route fuel-saving evaluation framework for estimating fuel advantages of alternative API routes based on large-scale, real-world travel data for conventional vehicles (CVs) and hybrid electric vehicles (HEVs). Navigation APIs, such as Google Directions API, integrate traffic conditions and provide feasible alternative routes for origin–destination pairs. This paper develops two link-based fuel-consumption models stratified by link-level speed, road grade, and functional class (local/non-local), one for CVs and the other for HEVs. The link-based fuel-consumption models are built by assigning travel from many global positioning system driving traces to the links in TomTom MultiNet and road grade data from the U.S. Geological Survey elevation data set. Fuel consumption on a link is computed by the proposed model. This paper envisions two kinds of applications: (1) identifying alternate routes that save fuel, and (2) quantifying the potential fuel savings for large amounts of travel. An experiment based on a large-scale California Household Travel Survey global positioning system trajectory data set is conducted. The fuel consumption and savings of CVs and HEVs are investigated. At the same time, the trade-off between fuel saving and travel time due to choosing different routes is also examined for both powertrains.

Activity space-based measures of the food environment and their relationships to food purchasing behaviours for young urban adults in Canada.

To examine the potential links between activity spaces, the food retail environment and food shopping behaviours for the population of young, urban adults. Participants took part in the Canada Food Study, which collected information on demographics, food behaviour, diet and health, as well as an additional smartphone study that included a seven-day period of logging GPS (global positioning system) location and food purchases. Using a time-weighted, continuous representation of participant activity spaces generated from GPS trajectory data, the locations of food purchases and a geocoded food retail data set, negative binomial regression models were used to explore what types of food retailers participants were exposed to and where food purchases were made. Toronto, Montreal, Vancouver, Edmonton and Halifax, Canada. Young adults aged 16-30 years (n 496). These participants were a subset of the larger Canada Food Study. Demographics, household food shopper status and city of residence were significantly associated with different levels of exposure to various types of food retailers. Food shopping behaviours were also statistically significantly associated with demographics, the activity space-based food environment, self-reported health and city of residence. The study confirms that food behaviours are related to activity space-based food environment measures, which provide a more comprehensive accounting of food retail exposure than home-based measures. In addition, exposure to food retail and food purchasing behaviours of an understudied population are described.

Optimizing Cruising Routes for Taxi Drivers Using a Spatio-Temporal Trajectory Model

Much of the taxi route-planning literature has focused on driver strategies for finding passengers and determining the hot spot pick-up locations using historical global positioning system (GPS) trajectories of taxis based on driver experience, distance from the passenger drop-off location to the next passenger pick-up location and the waiting times at recommended locations for the next passenger. The present work, however, considers the average taxi travel speed mined from historical taxi GPS trajectory data and the allocation of cruising routes to more than one taxi driver in a small-scale region to neighboring pick-up locations. A spatio-temporal trajectory model with load balancing allocations is presented to not only explore pick-up/drop-off information but also provide taxi drivers with cruising routes to the recommended pick-up locations. In simulation experiments, our study shows that taxi drivers using cruising routes recommended by our spatio-temporal trajectory model can significantly reduce the average waiting time and travel less distance to quickly find their next passengers, and the load balancing strategy significantly alleviates road loads. These objective measures can help us better understand spatio-temporal traffic patterns and guide taxi navigation.

Break‐taking behaviour pattern of long‐distance freight vehicles based on GPS trajectory data

This paper focuses on the break-taking behaviour pattern of long-distance freight vehicles, providing a new perspective on the study of behaviour patterns and simultaneously providing a reference for transport management departments and related enterprises. Based on Global Positioning System (GPS) trajectory data, we select stopping points as break-taking sites of long-distance freight vehicles and then classify the stopping points into three different classes based on the break-taking duration. We then explore the relationship of the distribution of the break-taking frequency between the three single classifications and their combinations, on the basis of the break-taking duration distribution. We find that the combination is a Gaussian distribution when each of the three individual classes is a Gaussian distribution, contrasting with the power-law distribution of the break-taking duration. Then we experimental analysis the distribution of the break-taking durations and frequencies, and find that, for the durations, the three single classifications can be fitted individually by an Exponential distribution and together by a Power-law distribution, for the frequencies, both the three single classifications and together can be fitted by a Gaussian distribution,so that can validate the above theoretical analysis. Key words: break-taking behaviour, long-distance freight vehicle, statistical analysis

Personalized travel route recommendation using collaborative filtering based on GPS trajectories

ABSTRACTTravelling is a critical component of daily life. With new technology, personalized travel route recommendations are possible and have become a new research area. A personalized travel route recommendation refers to plan an optimal travel route between two geographical locations, based on the road networks and users’ travel preferences. In this paper, we define users’ travel behaviours from their historical Global Positioning System (GPS) trajectories and propose two personalized travel route recommendation methods – collaborative travel route recommendation (CTRR) and an extended version of CTRR (CTRR+). Both methods consider users’ personal travel preferences based on their historical GPS trajectories. In this paper, we first estimate users’ travel behaviour frequencies by using collaborative filtering technique. A route with the maximum probability of a user’s travel behaviour is then generated based on the naïve Bayes model. The CTRR+ method improves the performances of CTRR by taking into account cold start users and integrating distance with the user travel behaviour probability. This paper also conducts some case studies based on a real GPS trajectory data set from Beijing, China. The experimental results show that the proposed CTRR and CTRR+ methods achieve better results for travel route recommendations compared with the shortest distance path method.

Unreliable Road Network Traffic Detection and Prevention

Traffic in the road network acting a major role in the society. Everyday traffic is increased because of moving vehicles in the shortest path even though government handle traffic signal is based on the timing condition. Because of that travel time is increased from source to destination. The existing system handles the vehicular traffic using a two stage routing algorithms are time dependent landmark graph model is used to estimate travel time between two landmarks and the next stage is variance entropy based clustering model is used to estimate the distribution of travel time between two landmarks in different time slots. By using this algorithm, cannot estimate the speed pattern of the road segment and traffic has not been predicted and prohibited. To address these limitations a proposed system uses two ways are one is weight propagation model, the weights that captures the travel time and traffic can be extracted from the GPS (Global Positioning System) trajectory data collected from the network and another one ant colony optimization algorithm to estimate the optimal path apart from the traffic. Using this proposed algorithm the road network traffic has been detected and prevented.

Statistical Vehicle Specific Power Profiling for Urban Freeways

Vehicle Specific Power (VSP) is conventionally defined to represent the instantaneous vehicle engine power. It has been widely utilized to reveal the impact of vehicle operating conditions on emission and energy consumption estimates that are dependent upon speed, roadway grade and acceleration or deceleration on the basis of the second-by-second vehicle operation. VSP has hence been incorporated into a key contributing factor in the vehicle emission models including MOVES. To facilitate the preparation of MOVES vehicle operating mode distribution inputs, an enhanced understanding and modeling of VSP distribution versus roadway grade become indispensable. This paper presents a study in which previous studies are extended by deeply investigating the characteristics of VSP distributions and their impacts due to varying freeway grades, as well as time-of-day factors. Afterwards, statistical distribution models with a scope of bins is identified through a goodness of fit testing approach by using the sample data collected from the interstate freeway segments in Cincinnati area. The Global Positioning System (GPS) data were collected at a selected length of 30km urban freeway for AM, PM and Mid-day periods. The datasets representing the vehicle operating conditions for VSP calculation are then extracted from the GPS trajectory data. The distribution fit modeling results demonstrated that the Wakeby distribution with five parameters dominates the most fitting parameters with the samples. In addition, the speed variation lies behind the time of day differences is also identified to be a contributing factor of urban freeway VSP distribution.

Navigation algorithm and implementation for blind based on GPS trajectory

This paper described an outdoor Global Positioning System(GPS) navigation algorithm for the blind by analyzing the GPS trajectory data received by the embedded platform Windows CE.Based on the data analysis of GPS trajectory,the algorithm introduced a method for the judgment of turning points and turning directions.During practical navigation,the blind can use the real-time voice prompt information for walking guidance.The experimental results show that the judgment of turning points can be realized in this algorithm effectively,and navigation information is effective and practical on helping users arrive at destinations safely and accurately.

Extracting road information from recorded GPS data using snap-drift neural network

Research towards an innovative solution to the problem of automated updating of road network databases is presented. It moves away from existing methods where vendors of road network databases either go through the time consuming and logistically challenging process of driving along roads to register changes or use update methods that rely on remote sensing images. The solution presented here would allow users of road network dependent applications (e.g. in-car navigation system or Sat Nav) to passively collect characteristics of any “unknown route” (departure from the known roads in the database) on behalf of the provider. These data would be processed either by an on-board artificial neural network (ANN) or transferred back to the Sat Nav provider and input into their ANN along with similar track data provided by other service users, to decide whether or not to automatically update (add) the “unknown road” to the road database. The solution presented here addresses the feasibility of identifying roads and assigning them into classes from recorded global positioning system (GPS) trajectory data. GPS trajectory data collected in London are analysed using a snap-drift neural network (SDNN) which categorises them into their strongest natural groupings, by combining clustering with feature detection in a single ANN. The key variables required are discussed. We have demonstrated that the SDNN offers a fast method of learning that preserves feature discovery. Using only GPS trajectory information, the SDNN is able to group collected points to reveal travelled road segments. The results showed that relying only on the winning node, a grouping accuracy of about 71% is achieved compared to 51% from learning vector quantisation (LVQ). On analysis and further experimentation with the SDNN d-nodes a grouping accuracy of nearly 100% was achieved, but with a high count of unique d-node combinations.