{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T18:30:59Z","timestamp":1778524259166,"version":"3.51.4"},"reference-count":52,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2018,10,19]],"date-time":"2018-10-19T00:00:00Z","timestamp":1539907200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000268","name":"Biotechnology and Biological Sciences Research Council","doi-asserted-by":"publisher","award":["BB\/N014235\/1"],"award-info":[{"award-number":["BB\/N014235\/1"]}],"id":[{"id":"10.13039\/501100000268","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006041","name":"Innovate UK","doi-asserted-by":"publisher","award":["132164"],"award-info":[{"award-number":["132164"]}],"id":[{"id":"10.13039\/501100006041","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Grazing and ruminating are the most important behaviours for ruminants, as they spend most of their daily time budget performing these. Continuous surveillance of eating behaviour is an important means for monitoring ruminant health, productivity and welfare. However, surveillance performed by human operators is prone to human variance, time-consuming and costly, especially on animals kept at pasture or free-ranging. The use of sensors to automatically acquire data, and software to classify and identify behaviours, offers significant potential in addressing such issues. In this work, data collected from sheep by means of an accelerometer\/gyroscope sensor attached to the ear and collar, sampled at 16 Hz, were used to develop classifiers for grazing and ruminating behaviour using various machine learning algorithms: random forest (RF), support vector machine (SVM), k nearest neighbour (kNN) and adaptive boosting (Adaboost). Multiple features extracted from the signals were ranked on their importance for classification. Several performance indicators were considered when comparing classifiers as a function of algorithm used, sensor localisation and number of used features. Random forest yielded the highest overall accuracies: 92% for collar and 91% for ear. Gyroscope-based features were shown to have the greatest relative importance for eating behaviours. The optimum number of feature characteristics to be incorporated into the model was 39, from both ear and collar data. The findings suggest that one can successfully classify eating behaviours in sheep with very high accuracy; this could be used to develop a device for automatic monitoring of feed intake in the sheep sector to monitor health and welfare.<\/jats:p>","DOI":"10.3390\/s18103532","type":"journal-article","created":{"date-parts":[[2018,10,19]],"date-time":"2018-10-19T10:08:02Z","timestamp":1539943682000},"page":"3532","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":125,"title":["Feature Selection and Comparison of Machine Learning Algorithms in Classification of Grazing and Rumination Behaviour in Sheep"],"prefix":"10.3390","volume":"18","author":[{"given":"Nicola","family":"Mansbridge","sequence":"first","affiliation":[{"name":"School of Veterinary Medicine and Science, University of Nottingham, Sutton Bonington Campus, Leicestershire LE12 5RD, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jurgen","family":"Mitsch","sequence":"additional","affiliation":[{"name":"School of Computer Science, Jubilee Campus, University of Nottingham, Nottingham NG8 1BB, UK"},{"name":"Advanced Data Analysis Centre, University of Nottingham, Nottingham NG8 1BB, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicola","family":"Bollard","sequence":"additional","affiliation":[{"name":"School of Veterinary Medicine and Science, University of Nottingham, Sutton Bonington Campus, Leicestershire LE12 5RD, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keith","family":"Ellis","sequence":"additional","affiliation":[{"name":"Internet of Things Systems Research, Intel Labs, Leixlip W23 CX68, Ireland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2765-1324","authenticated-orcid":false,"given":"Giuliana G.","family":"Miguel-Pacheco","sequence":"additional","affiliation":[{"name":"School of Veterinary Medicine and Science, University of Nottingham, Sutton Bonington Campus, Leicestershire LE12 5RD, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tania","family":"Dottorini","sequence":"additional","affiliation":[{"name":"School of Veterinary Medicine and Science, University of Nottingham, Sutton Bonington Campus, Leicestershire LE12 5RD, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jasmeet","family":"Kaler","sequence":"additional","affiliation":[{"name":"School of Veterinary Medicine and Science, University of Nottingham, Sutton Bonington Campus, Leicestershire LE12 5RD, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2018,10,19]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1017\/S0021859600045809","article-title":"Studies in grazing behaviour of dairy cattle: II. Bloat in relation to grazing behaviour","volume":"45","author":"Hancock","year":"2009","journal-title":"J. Agric. Sci."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1016\/j.applanim.2016.05.026","article-title":"Using a three-axis accelerometer to identify and classify sheep behaviour at pasture","volume":"181","author":"Alvarenga","year":"2016","journal-title":"Appl. Anim. Behav. Sci."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1016\/j.applanim.2009.03.005","article-title":"Cow behaviour pattern recognition using a three-dimensional accelerometer and support vector machines","volume":"119","author":"Martiskainen","year":"2009","journal-title":"Appl. Anim. Behav. Sci."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1016\/j.applanim.2013.09.001","article-title":"Automatic registration of grazing behaviour in dairy cows using 3D activity loggers","volume":"148","author":"Nielsen","year":"2013","journal-title":"Appl. Anim. Behav. Sci."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1016\/j.smallrumres.2015.04.002","article-title":"Technical note: Validation of an automatic recording system to assess behavioural activity level in sheep (Ovis aries)","volume":"127","author":"McLennan","year":"2015","journal-title":"Small Rumin. Res."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"3121","DOI":"10.1242\/jeb.202.22.3121","article-title":"Precise monitoring of porpoising behaviour of Adelie penguins determined using acceleration data loggers","volume":"202","author":"Yoda","year":"1999","journal-title":"J. Exp. Biol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"427","DOI":"10.3758\/BF03192796","article-title":"Application testing of a new three-dimensional acceleration measuring system with wireless data transfer (WAS) for behavior analysis","volume":"38","author":"Scheibe","year":"2006","journal-title":"Behav. Res. Methods"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"R1","DOI":"10.1088\/0967-3334\/25\/2\/R01","article-title":"Accelerometry: Providing an integrated, practical method for long-term, ambulatory monitoring of human movement","volume":"25","author":"Merryn","year":"2004","journal-title":"Physiol. Meas."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1016\/j.compag.2014.12.002","article-title":"Dynamic cattle behavioural classification using supervised ensemble classifiers","volume":"111","author":"Dutta","year":"2015","journal-title":"Comput. Electron. Agric."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"382","DOI":"10.2111\/REM-D-11-00027.1","article-title":"Distinguishing Cattle Foraging Activities Using an Accelerometry-Based Activity Monitor","volume":"66","author":"Yoshitoshi","year":"2013","journal-title":"Rangel. Ecol. Manag."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1016\/j.compag.2014.10.018","article-title":"Behavioral classification of data from collars containing motion sensors in grazing cattle","volume":"110","author":"Handcock","year":"2015","journal-title":"Comput. Electron. Agric."},{"key":"ref_12","unstructured":"Bar, D., and Solomon, R. (2010, January 2\u20135). Rumination collars: What can they tell us. Proceedings of the First North American Conference on Precision Dairy Management, Toronto, ON, Canada."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Verdon, M., Rawnsley, R., Raedts, P., and Freeman, M. (2018). The Behaviour and Productivity of Mid-Lactation Dairy Cows Provided Daily Pasture Allowance over 2 or 7 Intensively Grazed Strips. Animals, 8.","DOI":"10.3390\/ani8070115"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1111\/j.1365-2494.1981.tb01545.x","article-title":"The development and use of equipment for the automatic recording of ingestive behaviour in sheep and cattle","volume":"36","author":"Chambers","year":"1981","journal-title":"Grass Forage Sci."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1016\/j.compag.2008.05.004","article-title":"An automated sensor-based method of simple behavioural classification of sheep in extensive systems","volume":"64","author":"Waterhouse","year":"2008","journal-title":"Comput. Electron. Agric."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"171442","DOI":"10.1098\/rsos.171442","article-title":"Evaluation of sampling frequency, window size and sensor position for classification of sheep behaviour","volume":"5","author":"Walton","year":"2018","journal-title":"R. Soc. Open Sci."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1016\/j.livsci.2016.12.011","article-title":"Automatic classification system for grazing, ruminating and resting behaviour of dairy sheep using a tri-axial accelerometer","volume":"196","author":"Giovanetti","year":"2017","journal-title":"Livest. Sci."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1249","DOI":"10.1017\/S175173111600255X","article-title":"Gait and posture discrimination in sheep using a tri-axial accelerometer","volume":"11","author":"Radeski","year":"2016","journal-title":"Animal"},{"key":"ref_19","unstructured":"Marais, J., Le Roux, S.P., Wolhuter, R., and Niesler, T. (2014, January 27\u201328). Automatic classification of sheep behaviour using 3-axis accelerometer data. Proceedings of the 25th Annual Symposium of the Pattern Recognition Association of South Africa (PRASA), Cape Town, South Africa."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1016\/j.anbehav.2016.12.005","article-title":"Applications of machine learning in animal behaviour studies","volume":"124","author":"Valletta","year":"2017","journal-title":"Anim. Behav."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"37","DOI":"10.3389\/fvets.2016.00037","article-title":"Lameness Affects Cow Feeding but Not Rumination Behavior as Characterized from Sensor Data","volume":"3","author":"Thorup","year":"2016","journal-title":"Front. Vet. Sci."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Tobola, A., Streit, F.J., Espig, C., Korpok, O., Sauter, C., Lang, N., Schmitz, B., Hofmann, C., Struck, M., and Weigand, C. (2015, January 9\u201312). Sampling rate impact on energy consumption of biomedical signal processing systems. Proceedings of the 2015 IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks (BSN), Cambridge, MA, USA.","DOI":"10.1109\/BSN.2015.7299392"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1136\/inpract.6.3.91","article-title":"Body condition scoring of sheep","volume":"6","author":"Russel","year":"1984","journal-title":"Practice"},{"key":"ref_24","unstructured":"(2017, July 06). Condition Scoring of Ewes. Available online: https:\/\/beefandlamb.ahdb.org.uk\/wp-content\/uploads\/2013\/06\/brp_l_Sheep_BCS_190713.pdf."},{"key":"ref_25","unstructured":"Foundation, P.S. (2017, July 06). Python Language Reference, Version 2.7. Available online: http:\/\/www.python.org."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Mehrotra, K.G., Mohan, C.K., and Huang, H. (2017). Anomaly Detection Principles and Algorithms, Springer International Publishing.","DOI":"10.1007\/978-3-319-67526-8"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Qasem, L., Cardew, A., Wilson, A., Griffiths, I., Halsey, L.G., Shepard, E.L.C., Gleiss, A.C., and Wilson, R. (2012). Tri-Axial Dynamic Acceleration as a Proxy for Animal Energy Expenditure; Should We Be Summing Values or Calculating the Vector?. PLoS ONE, 7.","DOI":"10.1371\/journal.pone.0031187"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"871","DOI":"10.1109\/TBME.2008.2006190","article-title":"A Comparison of Feature Extraction Methods for the Classification of Dynamic Activities from Accelerometer Data","volume":"56","author":"Preece","year":"2009","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"645","DOI":"10.1007\/s00779-010-0293-9","article-title":"Preprocessing techniques for context recognition from accelerometer data","volume":"14","author":"Figo","year":"2010","journal-title":"Pers. Ubiquitous Comput."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"3975","DOI":"10.1016\/j.jbiomech.2015.09.015","article-title":"Classification of team sport activities using a single wearable tracking device","volume":"48","author":"Wundersitz","year":"2015","journal-title":"J. Biomech."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Bao, L., and Intille, S.S. (2004, January 21\u201323). Activity recognition from user-annotated acceleration data. Proceedings of the International Conference Pervasive Computing, Vienna, Austria.","DOI":"10.1007\/978-3-540-24646-6_1"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Bergadano, F., and De Raedt, L. (1994). Estimating attributes: Analysis and extensions of RELIEF. Machine Learning: ECML-94, Springer.","DOI":"10.1007\/3-540-57868-4"},{"key":"ref_33","unstructured":"Kira, K., and Rendell, L.A. (1992, January 12\u201316). The feature selection problem: Traditional methods and a new algorithm. Proceedings of the Tenth National Conference on Artificial Intelligence, San Jose, CA, USA."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random Forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"2783","DOI":"10.1890\/07-0539.1","article-title":"Random forest for classification in ecology","volume":"88","author":"Cutler","year":"2007","journal-title":"Ecology"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Hastie, T., Tibshirani, R., and Friedman, J. (2009). The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Springer. [2nd ed.].","DOI":"10.1007\/978-0-387-84858-7"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"James, G., Witten, D., Hastie, T., and Tibshirani, R. (2013). An Introduction to Statistical Learning, Springer.","DOI":"10.1007\/978-1-4614-7138-7"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1080\/00031305.1992.10475879","article-title":"An introduction to kernel and nearest-neighbor nonparametric regression","volume":"46","author":"Altman","year":"1992","journal-title":"Am. Stat."},{"key":"ref_39","unstructured":"K\u00e9gl, B. (arXiv, 2013). The return of AdaBoost.MH: Multi-class Hamming trees, arXiv."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1006\/jcss.1997.1504","article-title":"A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting","volume":"55","author":"Freund","year":"1997","journal-title":"J. Comput. Syst. Sci."},{"key":"ref_41","unstructured":"Mitchell, T. (1997). Machine Learning, McGraw Hill."},{"key":"ref_42","first-page":"1137","article-title":"A study of cross-validation and bootstrap for accuracy estimation and model selection","volume":"Volume 2","author":"Kohavi","year":"1995","journal-title":"Proceedings of the 14th International Joint Conference on Artificial Intelligence"},{"key":"ref_43","unstructured":"Witten, I.H., Frank, E., Hall, M.A., and Pal, C.J. (2016). Data Mining: Practical Machine Learning Tools and Techniques, Morgan Kaufmann."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1016\/j.icte.2016.11.003","article-title":"Gyroscope vs. accelerometer measurements of motion from wrist PPG during physical exercise","volume":"2","author":"Casson","year":"2016","journal-title":"ICT Express"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"301","DOI":"10.3233\/AIC-140599","article-title":"Modeling and forecasting of electricity spot-prices: Computational intelligence vs classical econometrics","volume":"27","author":"Cincotti","year":"2014","journal-title":"AI Commun."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1159\/000330778","article-title":"AUC-RF: A New Strategy for Genomic Profiling with Random Forest","volume":"72","author":"Calle","year":"2011","journal-title":"Hum. Hered."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1002\/widm.14","article-title":"The use of classification trees for bioinformatics","volume":"1","author":"Chen","year":"2011","journal-title":"Wiley Interdiscip. Rev. Data Min. Knowl. Discov."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Menze, B.H., Kelm, B.M., Masuch, R., Himmelreich, U., Bachert, P., Petrich, W., and Hamprecht, F.A. (2009). A comparison of random forest and its Gini importance with standard chemometric methods for the feature selection and classification of spectral data. BMC Bioinform., 10.","DOI":"10.1186\/1471-2105-10-213"},{"key":"ref_49","unstructured":"Tang, J., Alelyani, S., and Liu, H. (2014). Feature selection for classification: A review. Data Classification: Algorithms and Applications, CRC Press."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1017\/S0962728600028402","article-title":"Chronic stress in sheep: Assessment tools and their use in different management conditions","volume":"13","author":"Dwyer","year":"2004","journal-title":"Anim. Welf."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1016\/S0893-6080(96)00048-2","article-title":"Multilayer Perceptrons to Approximate Quaternion Valued Functions","volume":"10","author":"Arena","year":"1997","journal-title":"Neural Netw."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1177\/014233129301500305","article-title":"Genetic algorithms and applications in system engineering: A survey","volume":"15","author":"Caponetto","year":"1993","journal-title":"Trans. Inst. Meas. Control"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/18\/10\/3532\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T15:26:38Z","timestamp":1760196398000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/18\/10\/3532"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10,19]]},"references-count":52,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2018,10]]}},"alternative-id":["s18103532"],"URL":"https:\/\/doi.org\/10.3390\/s18103532","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,10,19]]}}}