ANALYTiC: An Active Learning System for Trajectory Classification

The increasing availability and use of positioning devices has resulted in large volumes of trajectory data. However, semantic annotations for such data are typically added by domain experts, which is a time-consuming task. Machine-learning algorithms can help infer semantic annotations from trajectory data by learning from sets of labeled data. Specifically, active learning approaches can minimize the set of trajectories to be annotated while preserving good performance measures. The ANALYTiC web-based interactive tool visually guides users through this annotation process.

[1]  Vania Bogorny,et al.  A model for enriching trajectories with semantic geographical information , 2007, GIS.

[2]  Maarten van Someren,et al.  Machine learning for vessel trajectories using compression, alignments and domain knowledge , 2012, Expert Syst. Appl..

[3]  Maria Eugenia Ramirez-Loaiza,et al.  Active learning: an empirical study of common baselines , 2017, Data Mining and Knowledge Discovery.

[4]  Wei-Ying Ma,et al.  Understanding mobility based on GPS data , 2008, UbiComp.

[5]  Stefano Spaccapietra,et al.  Mobility Data: Modeling, Management, and Understanding , 2013, Mobility Data.

[6]  James J. Thomas,et al.  Defining Insight for Visual Analytics , 2009, IEEE Computer Graphics and Applications.

[7]  Jesús García,et al.  Trajectory classification based on machine-learning techniques over tracking data , 2006, 2006 9th International Conference on Information Fusion.

[8]  William A. Gale,et al.  A sequential algorithm for training text classifiers , 1994, SIGIR '94.

[9]  Marco A. Casanova,et al.  Enriching Mobility Data with Linked Open Data , 2016, IDEAS.

[10]  Xinchang Zhang,et al.  A Multi-Scale Residential Areas Matching Method Using Relevance Vector Machine and Active Learning , 2017, ISPRS Int. J. Geo Inf..

[11]  Nikos Pelekis,et al.  The Baquara2 knowledge-based framework for semantic enrichment and analysis of movement data , 2015, Data Knowl. Eng..

[12]  Naoki Abe,et al.  Query Learning Strategies Using Boosting and Bagging , 1998, ICML.

[13]  Vania Bogorny,et al.  Where Have You Been Today? Annotating Trajectories with DayTag , 2013, SSTD.

[14]  P Schneider,et al.  Multi-objective active machine learning rapidly improves structure–activity models and reveals new protein–protein interaction inhibitors† †Electronic supplementary information (ESI) available: Details about computational comparisons and all screening results. See DOI: 10.1039/c5sc04272k , 2016, Chemical science.

[15]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[16]  Daniel A. Keim,et al.  Visual Analytics: Definition, Process, and Challenges , 2008, Information Visualization.

[17]  Henry A. Kautz,et al.  Learning and inferring transportation routines , 2004, Artif. Intell..

[18]  Xing Xie,et al.  Learning transportation mode from raw gps data for geographic applications on the web , 2008, WWW.

[19]  Stefano Spaccapietra,et al.  Semantic trajectories modeling and analysis , 2013, CSUR.