A Visual Analytic System for the Classification of Multi-Dimensional Time-Series Data

Biologists studying animals in their natural environment are increasingly using sensors such as accelerometers in animal-attached ‘smart’ tags because it is widely acknowledged that this approach can enhance the understanding of ecological and behavioural processes. The potential of such tags is tempered by the difficulty of extracting animal behaviour from the sensors which is currently primarily dependent on the manual inspection of multiple time-series graphs. This is time-consuming and error-prone for the domain expert and is now the limiting factor for realising the value of tags in this area. We introduce TimeClassifier, a visual analytic system for the classification of time-series data for movement ecologists. We deploy our system with biologists and report two real-world case studies of its use.

[1]  Rory P. Wilson,et al.  Diving Birds in Cold Water: Do Archimedes and Boyle Determine Energetic Costs? , 1992, The American Naturalist.

[2]  Steven W. Smith,et al.  The Scientist and Engineer's Guide to Digital Signal Processing , 1997 .

[3]  Jarke J. van Wijk,et al.  Cluster and Calendar Based Visualization of Time Series Data , 1999, INFOVIS.

[4]  Marc Alexa,et al.  Visualizing time-series on spirals , 2001, IEEE Symposium on Information Visualization, 2001. INFOVIS 2001..

[5]  Eamonn Keogh.  Exact Indexing of Dynamic Time Warping , 2002, VLDB.

[6]  Y. Naito,et al.  Why do macaroni penguins choose shallow body angles that result in longer descent and ascent durations? , 2004, Journal of Experimental Biology.

[7]  Y. Naito,et al.  Regulation of stroke and glide in a foot-propelled avian diver , 2005, Journal of Experimental Biology.

[8]  Ben Shneiderman,et al.  Interactive pattern search in time series , 2005, IS&T/SPIE Electronic Imaging.

[9]  Shigeru Makino,et al.  QueryLines: approximate query for visual browsing , 2005, CHI 2005.

[10]  Eamonn J. Keogh,et al.  Visualizing and Discovering Non-Trivial Patterns in Large Time Series Databases , 2005, Inf. Vis..

[11]  R. M. Alexander.  Models and the scaling of energy costs for locomotion , 2005, Journal of Experimental Biology.

[12]  Umeshwar Dayal,et al.  Importance-driven visualization layouts for large time series data , 2005, IEEE Symposium on Information Visualization, 2005. INFOVIS 2005..

[13]  Rory P. Wilson,et al.  Trends and perspectives in animal‐attached remote sensing , 2005 .

[14]  Colin Ware,et al.  Visualizing the underwater behavior of humpback whales , 2006, IEEE Computer Graphics and Applications.

[15]  E. Shepard.  Identification of animal movement patterns using tri-axial accelerometry , 2008 .

[16]  Rory P. Wilson,et al.  Prying into the intimate details of animal lives: use of a daily diary on animals , 2008 .

[17]  Robert S. Laramee,et al.  Smooth Graphs for Visual Exploration of Higher-Order State Transitions , 2009, IEEE Transactions on Visualization and Computer Graphics.

[18]  Gerik Scheuermann,et al.  Visual Exploration of Climate Variability Changes Using Wavelet Analysis , 2009, IEEE Transactions on Visualization and Computer Graphics.

[19]  Nuno Constantino Castro,et al.  Time Series Data Mining , 2009, Encyclopedia of Database Systems.

[20]  S. Wanless,et al.  Can Ethograms Be Automatically Generated Using Body Acceleration Data from Free-Ranging Birds? , 2009, PloS one.

[21]  Robert S. Laramee,et al.  Visualisation of Sensor Data from Animal Movement , 2009, Comput. Graph. Forum.

[22]  Steven K. Feiner,et al.  Relaxed selection techniques for querying time-series graphs , 2009, UIST '09.

[23]  Robert Kincaid,et al.  SignalLens: Focus+Context Applied to Electronic Time Series , 2010, IEEE Transactions on Visualization and Computer Graphics.

[24]  Emmanuel Pietriga,et al.  Exploratory Analysis of Time-Series with ChronoLenses , 2011, IEEE Transactions on Visualization and Computer Graphics.

[25]  Jarke J. van Wijk,et al.  BaobabView: Interactive construction and analysis of decision trees , 2011, 2011 IEEE Conference on Visual Analytics Science and Technology (VAST).

[26]  Rory P. Wilson,et al.  Making overall dynamic body acceleration work: on the theory of acceleration as a proxy for energy expenditure , 2011 .

[27]  R. W. Baird,et al.  Swim Speed and Acceleration Measurements of Short-Finned Pilot Whales (Globicephala macrorhynchus) in Hawai'i , 2011 .

[28]  Robert S. Laramee,et al.  Visualization of Large, Time-Dependent, Abstract Data with Integrated Spherical and Parallel Coordinates , 2012, EuroVis.

[29]  Rory P. Wilson,et al.  Correction: On Higher Ground: How Well Can Dynamic Body Acceleration Determine Speed in Variable Terrain? , 2014, PLoS ONE.

[30]  Hung-Hsuan Huang,et al.  Time Series Classification Method Based on Longest Common Subsequence and Textual Approximation , 2012, Seventh International Conference on Digital Information Management (ICDIM 2012).

[31]  T. Katzner,et al.  Flight responses by a migratory soaring raptor to changing meteorological conditions , 2012, Biology Letters.

[32]  Manish Marwah,et al.  Visual exploration of frequent patterns in multivariate time series , 2012, Inf. Vis..

[33]  Ben Shneiderman,et al.  Shape Identification in Temporal Data Sets , 2012, Expanding the Frontiers of Visual Analytics and Visualization.

[34]  Ran Nathan,et al.  Using tri-axial acceleration data to identify behavioral modes of free-ranging animals: general concepts and tools illustrated for griffon vultures , 2012, Journal of Experimental Biology.

[35]  Stefan Wesarg,et al.  Opening up the “black box” of medical image segmentation with statistical shape models , 2013, The Visual Computer.

[36]  Mengchen Liu,et al.  A survey on information visualization: recent advances and challenges , 2014, The Visual Computer.

[37]  Jane Hunter,et al.  A Web-based semantic tagging and activity recognition system for species' accelerometry data , 2013, Ecol. Informatics.

[38]  Rory P. Wilson,et al.  Love Thy Neighbour: Automatic Animal Behavioural Classification of Acceleration Data Using the K-Nearest Neighbour Algorithm , 2014, PloS one.

[39]  Matthew D. Taylor,et al.  From physiology to physics: are we recognizing the flexibility of biologging tools? , 2014, Journal of Experimental Biology.

[40]  Gilles Venturini,et al.  Visual mining of time series using a tubular visualization , 2014, The Visual Computer.

[41]  Gert R. G. Lanckriet,et al.  A random forest classifier for the prediction of energy expenditure and type of physical activity from wrist and hip accelerometers , 2014, Physiological measurement.