Activities per year
Fundamental challenges faced by real-time animal activity recognition include variation in motion data due to changing sensor orientations, numerous features, and energy and processing constraints of animal tags. This paper aims at finding small optimal feature sets that are lightweight and robust to the sensor's orientation. Our approach comprises four main steps. First, 3D feature vectors are selected since they are theoretically independent of orientation. Second, the least interesting features are suppressed to speed up computation and increase robustness against overfitting. Third, the features are further selected through an embedded method, which selects features through simultaneous feature selection and classification. Finally, feature sets are optimized through 10-fold cross-validation. We collected real-world data through multiple sensors around the neck of five goats. The results show that activities can be accurately recognized using only accelerometer data and a few lightweight features. Additionally, we show that the performance is robust to sensor orientation and position. A simple Naive Bayes classifier using only a single feature achieved an accuracy of 94 % with our empirical dataset. Moreover, our optimal feature set yielded an average of 94 % accuracy when applied with six other classifiers. This work supports embedded, real-time, energy-efficient, and robust activity recognition for animals.
|Number of pages||27|
|Journal||Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies|
|Publication status||Published - 25 Mar 2018|
- Animal Activity Recognition, Decision Tree, Embedded Systems, Machine Learning, Naive Bayes, Sensor Orientation
FingerprintDive into the research topics of 'Robust Sensor-Orientation-Independent Feature Selection for Animal Activity Recognition on Collar Tags'. Together they form a unique fingerprint.
- 1 Participating in a conference, workshop, ...
2018 ACM International Joint Conference and 2018 International Symposium on Pervasive and Ubiquitous Computing and Wearable Computers
Jacob Wilhelm Kamminga (Participant)8 Oct 2018 → 11 Oct 2018
Activity: Participating in or organising an event › Participating in a conference, workshop, ...
Multi Sensor-Orientation Movement Data of Goats
Kamminga, J. W. (Creator), DANS , 26 Mar 2018
DOI: 10.17026/dans-xhn-bsfb, http://www.persistent-identifier.nl/?identifier=urn:nbn:nl:ui:13-q7-esw9
- 1 PhD Thesis - Research UT, graduation UT
Hiding in the Deep: Online Animal Activity Recognition using Motion Sensors and Machine LearningKamminga, J. W., 9 Sep 2020, Enschede: University of Twente. 225 p.
Research output: Thesis › PhD Thesis - Research UT, graduation UTOpen AccessFile545 Downloads (Pure)