Dynamic signal segmentation for activity recognition

Activity recognition is an essential task in many ambient assisted living applications. Activities are commonly recognized using data streams from onbody sensors such as accelerometers. An important subtask in activity recognition is signal segmentation: a procedure for dividing the data into intervals. These intervals are then used as instances for machine learning. We present a novel signal segmentation method, which utilizes a segmentation scheme based on dynamic signal partitioning. To validate the method, experimental results including 6 activities and 4 transitions between activities from 11 subjects are presented. Using a Random forest algorithm, an accuracy of 97.5% was achieved with dynamic signal segmentation method, 94.8% accuracy with non-overlapping and 95.3% with overlapping sliding window method.

[1]  H. S. Wolff,et al.  iRun: Horizontal and Vertical Shape of a Region-Based Graph Compression , 2022, Sensors.

[2]  Thomas G. Dietterich.  What is machine learning? , 2020, Archives of Disease in Childhood.

[3]  Ari Y. Benbasat,et al.  An Inertial Measurement Unit for User Interfaces , 2000 .

[4]  C. Goose,et al.  Glossary of Terms , 2004, Machine Learning.

[5]  Loren Olson,et al.  A gesture-driven multimodal interactive dance system , 2004, 2004 IEEE International Conference on Multimedia and Expo (ICME) (IEEE Cat. No.04TH8763).

[6]  Paul Lukowicz,et al.  Continuous recognition of arm activities with body-worn inertial sensors , 2004, Eighth International Symposium on Wearable Computers.

[7]  Gerhard Tröster,et al.  Detection of eating and drinking arm gestures using inertial body-worn sensors , 2005, Ninth IEEE International Symposium on Wearable Computers (ISWC'05).

[8]  Michael L. Littman,et al.  Activity Recognition from Accelerometer Data , 2005, AAAI.

[9]  Chittaranjan A. Mandal,et al.  Automatic Detection of Human Fall in Video , 2007, PReMI.

[10]  Rafael Morales Bueno,et al.  Learning in Environments with Unknown Dynamics: Towards more Robust Concept Learners , 2007, J. Mach. Learn. Res..

[11]  T. Kuroda,et al.  Human Activity Recognition from Environmental Background Sounds for Wireless Sensor Networks , 2007, 2007 IEEE International Conference on Networking, Sensing and Control.

[12]  Ricard Gavaldà,et al.  Learning from Time-Changing Data with Adaptive Windowing , 2007, SDM.

[13]  Matjaz Gams,et al.  Classifying Posture Based on Location of Radio Tags , 2009, AMIF.

[14]  Ian H. Witten,et al.  The WEKA data mining software: an update , 2009, SKDD.

[15]  Pekka Siirtola,et al.  Activity recognition using a wrist-worn inertial measurement unit: A case study for industrial assembly lines , 2009, 2009 17th Mediterranean Conference on Control and Automation.

[16]  Angelo M. Sabatini,et al.  Machine Learning Methods for Classifying Human Physical Activity from On-Body Accelerometers , 2010, Sensors.