Discovery of driving patterns by trajectory segmentation

Moosavi, Sobhan; Ramnath, Rajiv; Nandi, Arnab

doi:10.1145/3003819.3003824

Cited by 11 publications

(9 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In urban movement data analysis, information mining and extraction of moving trajectories have always been the research focus of researchers [41], [42]. In the trajectory data mining work, the main research focuses on trajectory clustering, trajectory classifing, the region of interest, location recommendation, privacy protection, and other aspects [43], [44].…”

Section: Trajectory Data Mining and Querymentioning

confidence: 99%

A Graph-Based Visual Query Method for Massive Human Trajectory Data

et al. 2019

View full text Add to dashboard Cite

With the advance of location acquisition technologies nowadays, the human trajectory data, such as vehicles, phones and bicycles, is growing vastly and extending our imagination of new users. These trajectories have shown great values in supporting situation-aware exploration and prediction of human mobility, discovering movement patterns and monitoring the traffic situations. Query is an essential task for trajectory exploration. To do this, users should input spatial, temporal and other types of query conditionals to obtain a group of filtered trajectories. However, current visual query methods for urban data suffer from two main problems. First, it is a challenge for users without background knowledge to specify query conditions, such as selecting a popular entertainment area on the map as spatial condition. Second, there still needs a way to fuse the multi-source, heterogeneous, and large-scale urban data to partition the urban area, extract their semantic information, and provide intuitive, efficient trajectory queries. In this paper, we propose CBRG(cellular-based region growing) algorithm to make a preliminary region partition which tends to be a certain collection of similar regions. Then, we generate a semantic node for graph and provide a set of feasible clues and signs to explore and mine data from the aspects of spatio-temporal characteristics, inherent coupling of data, and human mobility. It is worth mentioning that our methodology is also universal for other heterogeneous data with spatio-temporal characteristics. INDEX TERMS Functional zones construction, human trajectory data, visual query, visual analysis.

show abstract

Section: Trajectory Data Mining and Querymentioning

confidence: 99%

A Graph-Based Visual Query Method for Massive Human Trajectory Data

et al. 2019

View full text Add to dashboard Cite

show abstract

“…dSegment is an adaptation of our previously proposed approach [10] to wisely partition a trajectory based on behavior of driver, such that each resulting segment corresponds to a meaningful driving pattern (e.g., turn, speed-up, etc.). A summary of fundamental parts of dSegment is provided as follows.…”

Section: Dsegment Componentmentioning

confidence: 99%

“…(iii) Equal Length, where we first assume all trajectories have the same number of segments (η) and then divide a trajectory to η equal size segments; and (iv) Random, where we find η segment borders at random to form η segments. In order to find the upper bound on the number of existing segments, i.e., K (see [10]), we set K = N 5 , where N is the length of the trajectory. The minimum length of a segment is assumed to be 5 (see [9]).…”

Section: Dsegment Evaluationmentioning

confidence: 99%

Characterizing Driving Context from Driver Behavior

Moosavi

Omidvar-Tehrani

Craig

et al. 2017

Proceedings of the 25th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems

Self Cite

View full text Add to dashboard Cite

Because of the increasing availability of spatiotemporal data, a variety of data-analytic applications have become possible. Characterizing driving context, where context may be thought of as a combination of location and time, is a new challenging application. An example of such a characterization is finding the correlation between driving behavior and traffic conditions. This contextual information enables analysts to validate observation-based hypotheses about the driving of an individual. In this paper, we present DriveContext, a novel framework to find the characteristics of a context, by extracting significant driving patterns (e.g., a slow-down), and then identifying the set of potential causes behind patterns (e.g., traffic congestion). Our experimental results confirm the feasibility of the framework in identifying meaningful driving patterns, with improvements in comparison with the state-of-the-art. We also demonstrate how the framework derives interesting characteristics for different contexts, through real-world examples.Comment: Accepted to be published at The 25th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (ACM SIGSPATIAL 2017

show abstract

“…In recent years, the proposed trajectory segmentation algorithms can be classified the supervised [9][10][11][12][13][14], unsupervised [15][16][17][18][19][20][21][22][23][24][25][26][27], and semisupervised [28].…”

Section: Introductionmentioning

confidence: 99%

Application of Artificial Intelligence in an Unsupervised Algorithm for Trajectory Segmentation Based on Multiple Motion Features

Dong

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

With the development of the wireless network, location-based services (e.g., the place of interest recommendation) play a crucial role in daily life. However, the data acquired is noisy, massive, it is difficult to mine it by artificial intelligence algorithm. One of the fundamental problems of trajectory knowledge discovery is trajectory segmentation. Reasonable segmentation can reduce computing resources and improvement of storage effectiveness. In this work, we propose an unsupervised algorithm for trajectory segmentation based on multiple motion features (TS-MF). The proposed algorithm consists of two steps: segmentation and mergence. The segmentation part uses the Pearson coefficient to measure the similarity of adjacent trajectory points and extract the segmentation points from a global perspective. The merging part optimizes the minimum description length (MDL) value by merging local sub-trajectories, which can avoid excessive segmentation and improve the accuracy of trajectory segmentation. To demonstrate the effectiveness of the proposed algorithm, experiments are conducted on two real datasets. Evaluations of the algorithm’s performance in comparison with the state-of-the-art indicate the proposed method achieves the highest harmonic average of purity and coverage.

show abstract

Discovery of driving patterns by trajectory segmentation

Cited by 11 publications

References 12 publications

A Graph-Based Visual Query Method for Massive Human Trajectory Data

A Graph-Based Visual Query Method for Massive Human Trajectory Data

Characterizing Driving Context from Driver Behavior

Application of Artificial Intelligence in an Unsupervised Algorithm for Trajectory Segmentation Based on Multiple Motion Features

Contact Info

Product

Resources

About