Towards Deep Unsupervised Representation Learning from Accelerometer Time Series for Animal Activity Recognition

The most compelling reason to use unsupervised representation learning as a feature extraction method for effective animal activity recognition is the ability to learn from unlabeled data. Obtaining labeled data is tedious, labor-intensive, and costly, while it is much easier to obtain raw unlabeled data. In this paper, we compare three unsupervised representation learning techniques with three conventional feature extraction methods that are simple and have excellent performance. To investigate the effect of the size of both labeled and unlabeled parts of the dataset on the quality of the representations, we train the representations and classifier using various sample sizes. Furthermore, we evaluate the effect of depth in feature architectures on the performance of the representation learning techniques. All evaluations are performed on two animal datasets that are diverse in terms of species, subjects, sensor-orientations, and sensor-positions. We demonstrate that unsupervised representation learning techniques approach and, in some cases, outperform engineered features in animal activity recognition.

[1]  C. A. van der Weerdt,et al.  Smart Dairy Farming , 2015 .

[2]  Michele Banko,et al.  Mitigating the Paucity-of-Data Problem: Exploring the Effect of Training Corpus Size on Classifier Performance for Natural Language Processing , 2001, HLT.

[3]  Jacob W. Kamminga.  Dataset: Multi Sensor-Orientation Movement Data of Goats , 2018 .

[4]  Peter Fedor,et al.  A tribute to Claude Shannon (1916-2001) and a plea for more rigorous use of species richness, species diversity and the 'Shannon-Wiener' Index , 2003 .

[5]  Jamali Firmat Banzi.  A Sensor Based Anti-Poaching System in Tanzania National Parks , 2014 .

[6]  Sotiris B. Kotsiantis,et al.  Supervised Machine Learning: A Review of Classification Techniques , 2007, Informatica.

[7]  Honglak Lee,et al.  Unsupervised feature learning for audio classification using convolutional deep belief networks , 2009, NIPS.

[8]  Honglak Lee,et al.  Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations , 2009, ICML '09.

[9]  Greg P. Timms,et al.  An investigation of cow feeding behavior using motion sensors , 2014, 2014 IEEE International Instrumentation and Measurement Technology Conference (I2MTC) Proceedings.

[10]  Bo Ding,et al.  Unsupervised Feature Learning for Human Activity Recognition Using Smartphone Sensors , 2014, MIKE.

[11]  Jonathon Shlens,et al.  A Tutorial on Principal Component Analysis , 2014, ArXiv.

[12]  Michael A. Tabak,et al.  Machine learning to classify animal species in camera trap images: applications in ecology , 2018, bioRxiv.

[13]  Nirvana Meratnia,et al.  Generic online animal activity recognition on collar tags , 2017, UbiComp/ISWC Adjunct.

[14]  Chen Sun,et al.  Revisiting Unreasonable Effectiveness of Data in Deep Learning Era , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[15]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[16]  Christopher C Wilmers,et al.  The golden age of bio-logging: how animal-borne sensors are advancing the frontiers of ecology. , 2015, Ecology.

[17]  Patrick J Butler,et al.  Biotelemetry: a mechanistic approach to ecology. , 2004, Trends in ecology & evolution.

[18]  Ling Bao,et al.  Activity Recognition from User-Annotated Acceleration Data , 2004, Pervasive.

[19]  Ran Nathan,et al.  An emerging movement ecology paradigm , 2008, Proceedings of the National Academy of Sciences.

[20]  Nirvana Meratnia,et al.  Dataset: Horse Movement Data and Analysis of its Potential for Activity Recognition , 2019, DATA@SenSys.

[21]  Ella Browning,et al.  Predicting animal behaviour using deep learning: GPS data alone accurately predict diving in seabirds , 2017 .

[22]  Patrick Olivier,et al.  Feature Learning for Activity Recognition in Ubiquitous Computing , 2011, IJCAI.

[23]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  Margaret Kosmala,et al.  Automatically identifying, counting, and describing wild animals in camera-trap images with deep learning , 2017, Proceedings of the National Academy of Sciences.

[25]  Yoshua Bengio,et al.  Greedy Layer-Wise Training of Deep Networks , 2006, NIPS.

[26]  Paul J. M. Havinga,et al.  A Survey of Online Activity Recognition Using Mobile Phones , 2015, Sensors.

[27]  Nirvana Meratnia,et al.  Horsing Around - A Dataset Comprising Horse Movement , 2019, Data.

[28]  Ying Wah Teh,et al.  Deep learning algorithms for human activity recognition using mobile and wearable sensor networks: State of the art and research challenges , 2018, Expert Syst. Appl..

[29]  Nirvana Meratnia,et al.  Robust Sensor-Orientation-Independent Feature Selection for Animal Activity Recognition on Collar Tags , 2018, Proc. ACM Interact. Mob. Wearable Ubiquitous Technol..

[30]  MartonosiMargaret,et al.  Energy-efficient computing for wildlife tracking , 2002 .

[31]  Mi Zhang,et al.  A feature selection-based framework for human activity recognition using wearable multimodal sensors , 2011, BODYNETS.

[32]  Kimiaki Shirahama,et al.  Comparison of Feature Learning Methods for Human Activity Recognition Using Wearable Sensors , 2018, Sensors.