Abstract
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.
- Louis Atallah, Benny Lo, Rachel King, and Guang Zhong Yang. 2011. Sensor positioning for activity recognition using wearable accelerometers. IEEE Transactions on Biomedical Circuits and Systems 5, 4 (2011), 320--329.Google ScholarCross Ref
- Jonghun Baek, GeehyukLee, Wonbae Park, and Bj Yun. 2004. Accelerometer signal processing for user activity detection. Knowledge-Based Intelligent Information and Engineering Systems Lecture No (2004), 610--617.Google Scholar
- Jamali Firmat Banzi. 2014. A Sensor Based Anti-Poaching System in Tanzania. International Journal of Scientific and Research Publications 4, 4 (2014), 1--7.Google Scholar
- Ling Bao and Stephen S. Intille. 2004. Activity Recognition from User-Annotated Acceleration Data. In Pervasive Computing. Springer Berlin Heidelberg, Berlin, Heidelberg, 1--17.Google Scholar
- Pablo Bermejo, José A. Gámez, and José M. Puerta. 2014. Speeding up incremental wrapper feature subset selection with Naive Bayes classifier. Knowledge-Based Systems 55 (2014), 140--147. Google ScholarDigital Library
- Owen R. Bidder, Hamish A. Campbell, Agustina Gómez-Laich, Patricia Urge, James Walker, Yuzhi Cai, Lianli Gao, Flavio Quintana, and Rory P. Wilson. 2014. Love thy neighbour: Automatic animal behavioural classification of acceleration data using the k-nearest neighbour algorithm. PLoS ONE 9, 2 (2014), 1--7.Google ScholarCross Ref
- Greg Bishop-Hurley, Dave Henry, Daniel Smith, Ritaban Dutta, James Hills, Richard Rawnsley, Andrew Hellicar, Greg Timms, Ahsan Morshed, Ashfaqur Rahman, Claire D'Este, and Yanfeng Shu. 2014. An investigation of cow feeding behavior using motion sensors. In 2014 IEEE International Instrumentation and Measurement Technology Conference (I2MTC) Proceedings. IEEE, 1285--1290.Google ScholarCross Ref
- Steven J. Cooke, Scott G. Hinch, Martin Wikelski, Russel D. Andrews, Louise J. Kuchel, Thomas G. Wolcott, and Patrick J. Butler. 2004. Biotelemetry: A mechanistic approach to ecology. Trends in Ecology and Evolution 19, 6 (2004), 334--343.Google ScholarCross Ref
- Ritaban Dutta, Daniel Smith, Richard Rawnsley, Greg Bishop-Hurley, James Hills, Greg Timms, and Dave Henry. 2015. Dynamic cattle behavioural classification using supervised ensemble classifiers. Computers and Electronics in Agriculture 111 (2015), 18--28. Google ScholarDigital Library
- Jochen Fahrenberg, Friedrich Foerster, Manfred Smeja, and Wolfgang Müller. 1997. Assessment of posture and motion by multichannel piezoresistive accelerometer recordings. (1997).Google Scholar
- Davide Figo, Pedro C. Diniz, Diogo R. Ferreira, and João M P Cardoso. 2010. Preprocessing techniques for context recognition from accelerometer data. Personal and Ubiquitous Computing 14, 7 (2010), 645--662. Google ScholarDigital Library
- Blanca Florentino-Liaño, Niamh O'Mahony, and Antonio Artés-Rodríguez. 2012. Human Activity Recognition Using Inertial Sensors with Invariance to Sensor Orientation. In 2012 3rd International Workshop on Cognitive Information Processing (CIP). 1--6.Google ScholarCross Ref
- F Foerster and J Fahrenberg. 2000. Motion pattern and posture: correctly assessed by calibrated accelerometers. Behavior research methods, instruments, 8 computers: a journal of the Psychonomic Society, Inc 32, 3 (2000), 450--457.Google Scholar
- L A González, G J Bishop-hurley, R N Handcock, and C Crossman. 2015. Behavioral classification of data from collars containing motion sensors in grazing cattle. Computers and Electronics in Agriculture 110 (2015), 91--102. Google ScholarDigital Library
- Isabelle Guyon and André Elisseeff. 2003. An Introduction to Variable and Feature Selection. Journal of Machine Learning Research (JMLR)3, 3 (2003), 1157--1182. arXiv:1111.6189v1 Google ScholarDigital Library
- Tâm Huynh and Bernt Schiele. 2005. Analyzing features for activity recognition. In Proceedings of the 2005 joint conference on Smart objects and ambient intelligence: innovative context-aware services: usages and technologies (sOc-EUSAI '05). 159--163. Google ScholarDigital Library
- I Inza, P Larrañaga, R Etxeberria, and B Sierra. 1999. Feature subset selection by Bayesian networks based optimization. Artificial Intelligence 123 (1999), 157--184. Google ScholarDigital Library
- Jacob Kamminga. 2017. Goat Orientation Data. online. (05 2017). http://ps.ewi.utwente.nl/Datasets.phpGoogle Scholar
- Dean M. Karantonis, Michael R. Narayanan, Merryn Mathie, Nigel H. Lovell, and Branko G. Celler. 2006. Implementation of a real-time human movement classifier using a triaxial accelerometer for ambulatory monitoring. IEEE Transactions on Information Technology in Biomedicine 10, 1 (2006), 156--167. Google ScholarDigital Library
- S B Kotsiantis. 2007. Supervised Machine Learning: A Review of Classification Techniques. Informatica, An International Journal of Computing and Informatics 3176, 31 (2007), 249--268.Google Scholar
- Cassim Ladha, Nils Hammerla, Emma Hughes, Patrick Olivier, and Thomas Ploetz. 2013. Dog's life: Wearable Activity Recognition for Dogs. In Proceedings of the 2013 ACM international joint conference on Pervasive and ubiquitous computing - UbiComp '13. 415. Google ScholarDigital Library
- Jonathan Lester, Tanzeem Choudhury, and Gaetano Borriello. 2006. A Practical Approach to Recognizing Physical Activities. Pervasive Computing 3968 (2006), 1--16. Google ScholarDigital Library
- Yunji Liang, Xingshe Zhou, Zhiwen Yu, Bin Guo, and Yue Yang. 2012. Energy efficient activity recognition based on low resolution accelerometer in smart phones. Advances in Grid and Pervasive Computing (2012), 122--136. Google ScholarDigital Library
- Jacques Marais, Solomon Petrus, Le Roux, Riaan Wolhuter, and Thomas Niesler. 2014. Automatic classification of sheep behaviour using 3-axis accelerometer data. In Proceedings of the twenty-fifth annual symposium of the Pattern Recognition Association of South Africa (PRASA). 1--6.Google Scholar
- Paula Martiskainen, Mikko Järvinen, Jukka-Pekka Skön, Jarkko Tiirikainen, Mikko Kolehmainen, and Jaakko Mononen. 2009. Cow behaviour pattern recognition using a three-dimensional accelerometer and support vector machines. Applied Animal Behaviour Science 119, 1--2 (2009), 32--38.Google ScholarCross Ref
- B G Mathie, M. J., Coster, A. C., Lovell, N. H., 8 Celler. 2004. Accelerometry: providing an integrated, practical method for long-term, ambulatory monitoring of human movement. Physiological measurement 25, 2 (2004), R1.Google Scholar
- MATLAB. 2015. version 8.6.0 (R2015b). The MathWorks Inc., Natick, Massachusetts.Google Scholar
- Uwe Maurer, Anthony Rowe, Asim Smailagic, and Daniel Siewiorek. 2006. Location and Activity Recognition Using eWatch: A Wearable Sensor Platform. Ambient Intelligence in Everyday Life 3864 (2006), 86--102. Google ScholarDigital Library
- I Mierswa, M Wurst, R Klinkenberg, M Scholz, and T Euler. 2006. YALE: Rapid prototyping for complex data mining tasks. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 2006 (2006), 935--940. Google ScholarDigital Library
- Ran Nathan. 2008. An emerging movement ecology paradigm. Proceedings of the National Academy of Sciences of the United States of America 105, 49 (2008), 19050--19051.Google ScholarCross Ref
- Ran Nathan, Orr Spiegel, Scott Fortmann-Roe, Roi Harel, Martin Wikelski, and Wayne M Getz. 2012. Using tri-axial acceleration data to identify behavioral modes of free-ranging animals: general concepts and tools illustrated for griffon vultures. The Journal of experimental biology 215, Pt 6 (2012), 986--96.Google ScholarCross Ref
- Trung Thanh Ngo, Yasushi Makihara, Hajime Nagahara, Yasuhiro Mukaigawa, and Yasushi Yagi. 2015. Similar gait action recognition using an inertial sensor. Pattern Recognition 48, 4 (2015), 1285--1297. Google ScholarDigital Library
- Juha Pärkkä, Miikka Ermes, Panu Korpipää, Jani Mäntyjärvi, Johannes Peltola, and Ilkka Korhonen. 2006. Activity classification using realistic data from wearable sensors. IEEE transactions on information technology in biomedicine: a publication of the IEEE Engineering in Medicine and Biology Society 10, 1(2006), 119--128. Google ScholarDigital Library
- Julie K Petersen. 2002. Understanding Technologies Surveillance Spy Devices, Their Origins 8 Applications. CRC Press, Boca Raton.Google Scholar
- R. L. Plackett. 1983. Karl Pearson and the Chi-Squared Test. International Statistical Review /Revue Internationale de Statistique 51, 1 (1983), 59.Google ScholarCross Ref
- S.J. Preece, J.Y. Goulermas, L.P.J. Kenney, and D. Howard. 2009. A Comparison of Feature Extraction Methods for the Classification of Dynamic Activities From Accelerometer Data. IEEE Transactions on Biomedical Engineering 56, 3 (2009), 871--879.Google ScholarCross Ref
- Nishkam Ravi, Nikhil Dandekar, Preetham Mysore, and Ml Michael L Littman. 2005. Activity Recognition from Accelerometer Data. In Aaai. 1541--1546. Google ScholarDigital Library
- Sasank Reddy, Min Mun, Jeff Burke, Deborah Estrin, Mark Hansen, and Mani Srivastava. 2010. Using mobile phones to determine transportation modes. ACM Transactions on Sensor Networks 6, 2 (2010), 1--27. Google ScholarDigital Library
- Yasar Guneri Sahin. 2007. Animals as Mobile Biological Sensors for Forest Fire Detection. Sensors 7 (2007), 3084--3099.Google ScholarCross Ref
- Jeff Schneider. 1997. Cross Validation. online. (1997). https://www.cs.cmu.edu/~schneide/tut5/node42.htmlGoogle Scholar
- Emily L C Shepard, Rory P. Wilson, Flavio Quintana, Agustina Gomez Laich, Nikolai Liebsch, Diego A. Albareda, Lewis G. Halsey, Adrian Gleiss, David T. Morgan, Andrew E. Myers, Chris Newman, and David W. Macdonald. 2010. Identification of animal movement patterns using tri-axial accelerometry. Endangered Species Research 10, 1 (2010), 47--60.Google ScholarCross Ref
- Muhammad Shoaib, Stephan Bosch, Ozlem Incel, Hans Scholten, and Paul Havinga. 2015. A Survey of Online Activity Recognition Using Mobile Phones. Sensors 15, 1 (2015), 2059--2085.Google ScholarCross Ref
- Pekka Siirtola and Juha Röning. 2012. Recognizing Human Activities User-independently on Smartphones Based on Accelerometer Data. International Journal of Interactive Multimedia and Artificial Intelligence 1, 5 (2012), 38.Google ScholarCross Ref
- Daniel Smith, Bryce Little, Paul I. Greenwood, Philip Valencia, Ashfaqur Rahman, Aaron Ingham, Greg Bishop-Hurley, Md Sumon Shahriar, and Andrew Hellicar. 2015. A study of sensor derived features in cattle behaviour classification models. In 2015 IEEE SENSORS -Proceedings. IEEE, Busan, South Korea, 1--4.Google Scholar
- Daniel Smith, Ashfaqur Rahman, Greg J. Bishop-Hurley, James Hills, Sumon Shahriar, David Henry, and Richard Rawnsley. 2016. Behavior classification of cows fitted with motion collars: Decomposing multi-class classification into a set of binary problems. Computers and Electronics in Agriculture 131 (2016), 40--50.Google ScholarCross Ref
- J Sneddon and A Mason. 2014. Automated Monitoring of Foraging Behaviour in Free Ranging Sheep Grazing a Bio-diverse Pasture using Audio and Video Information. In 8th International Conference on Sensing Technology. 2--4.Google Scholar
- Inertia Technology. 2017. ProMove mini. online. (2017). http://inertia-technology.com/Google Scholar
- Jorge A. Vázquez Diosdado, Zoe E. Barker, Holly R. Hodges, Jonathan R. Amory, Darren P. Croft, Nick J. Bell, and Edward A. Codling. 2015. Classification of behaviour in housed dairy cows using an accelerometer-based activity monitoring system. Animal Biotelemetry 3, 1(2015), 15.Google ScholarCross Ref
- W3C. 2017. Motion Sensors Explainer. online. (08 2017). https://www.w3.org/TR/motion-sensors/Google Scholar
- Shinichi Watanabe, Masako Izawa, Akiko Kato, Yan Ropert-Coudert, and Yasuhiko Naito. 2005. A new technique for monitoring the detailed behaviour of terrestrial animals: A case study with the domestic cat. Applied Animal Behaviour Science 94, 1--2 (2005), 117--131.Google ScholarCross Ref
- Rory P. Wilson, E. L C Shepard, and N. Liebsch. 2008. Prying into the intimate details of animal lives: Use of a daily diary on animals. Endangered Species Research 4, 1--2(2008), 123--137.Google ScholarCross Ref
- Xiuxin Yang, A Dinh, and Li Chen. 2010. Implementation of a wearerable real-time system for physical activity recognition based on naive Bayes classifier. Bioinformatics and Biomedical Technology (ICBBT), 2010 International Conference on (2010), 101--105.Google ScholarCross Ref
- K. Yoda, Katsufumi Sato, Y. Niizuma, M. Kurita, Charles-André Bost, Yvon Le Maho, and Y. Naito. 1999. Precise monitoring of porpoising behaviour of Adélie penguins determined using acceleration data loggers. The Journal of experimental biology 202, Pt 22 (1999), 3121--3126.Google Scholar
- Mi Zhang and Alexander a Sawchuk. 2011. A feature selection-based framework for human activity recognition using wearable multimodal sensors. In Proceedings of the 6th International Conference on Body Area Networks. 92--98. Google ScholarDigital Library
Index Terms
- Robust Sensor-Orientation-Independent Feature Selection for Animal Activity Recognition on Collar Tags
Recommendations
Generic online animal activity recognition on collar tags
UbiComp '17: Proceedings of the 2017 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2017 ACM International Symposium on Wearable ComputersAnimal behaviour is a commonly-used and sensitive indicator of animal welfare. Moreover, the behaviour of animals can provide rich information about their environment. For online activity recognition on collar tags of animals, fundamental challenges ...
Effective hybrid feature subset selection for multilevel datasets using decision tree classifiers
Feature selection is one of the most significant procedures in machine learning algorithms. It is particularly to improve the performance and prediction accuracy for complex data classification. This paper discusses a hybrid feature selection technique ...
An effective feature selection approach driven genetic algorithm wrapped Bayes naïve
In this paper, an advanced novel feature selection FS algorithm is presented, the hybrid genetic algorithm GA with Bayes naïve BN, which selects the most relevant optimum feature subset to increase the classification accuracy performance and ...
Comments