{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T05:28:46Z","timestamp":1773984526791,"version":"3.50.1"},"reference-count":54,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2021,6,12]],"date-time":"2021-06-12T00:00:00Z","timestamp":1623456000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Horizon 2020","award":["810775"],"award-info":[{"award-number":["810775"]}]},{"DOI":"10.13039\/501100000268","name":"Biotechnology and Biological Sciences Research Council","doi-asserted-by":"publisher","award":["BB \/ M027333 \/ 1"],"award-info":[{"award-number":["BB \/ M027333 \/ 1"]}],"id":[{"id":"10.13039\/501100000268","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Monitoring cattle behaviour is core to the early detection of health and welfare issues and to optimise the fertility of large herds. Accelerometer-based sensor systems that provide activity profiles are now used extensively on commercial farms and have evolved to identify behaviours such as the time spent ruminating and eating at an individual animal level. Acquiring this information at scale is central to informing on-farm management decisions. The paper presents the development of a Convolutional Neural Network (CNN) that classifies cattle behavioural states (\u2018rumination\u2019, \u2018eating\u2019 and \u2018other\u2019) using data generated from neck-mounted accelerometer collars. During three farm trials in the United Kingdom (Easter Howgate Farm, Edinburgh, UK), 18 steers were monitored to provide raw acceleration measurements, with ground truth data provided by muzzle-mounted pressure sensor halters. A range of neural network architectures are explored and rigorous hyper-parameter searches are performed to optimise the network. The computational complexity and memory footprint of CNN models are not readily compatible with deployment on low-power processors which are both memory and energy constrained. Thus, progressive reductions of the CNN were executed with minimal loss of performance in order to address the practical implementation challenges, defining the trade-off between model performance versus computation complexity and memory footprint to permit deployment on micro-controller architectures. The proposed methodology achieves a compression of 14.30 compared to the unpruned architecture but is nevertheless able to accurately classify cattle behaviours with an overall F1 score of 0.82 for both FP32 and FP16 precision while achieving a reasonable battery lifetime in excess of 5.7 years.<\/jats:p>","DOI":"10.3390\/s21124050","type":"journal-article","created":{"date-parts":[[2021,6,14]],"date-time":"2021-06-14T22:25:46Z","timestamp":1623709546000},"page":"4050","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":54,"title":["Classification of Cattle Behaviours Using Neck-Mounted Accelerometer-Equipped Collars and Convolutional Neural Networks"],"prefix":"10.3390","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9811-9485","authenticated-orcid":false,"given":"Dejan","family":"Pavlovic","sequence":"first","affiliation":[{"name":"BioSense Institute, 21101 Novi Sad, Serbia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9450-1791","authenticated-orcid":false,"given":"Christopher","family":"Davison","sequence":"additional","affiliation":[{"name":"Department of Electronic and Electrical Engineering, University of Strathclyde, Glasgow G1 1RD, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8436-8325","authenticated-orcid":false,"given":"Andrew","family":"Hamilton","sequence":"additional","affiliation":[{"name":"Department of Electronic and Electrical Engineering, University of Strathclyde, Glasgow G1 1RD, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6683-7178","authenticated-orcid":false,"given":"Oskar","family":"Marko","sequence":"additional","affiliation":[{"name":"BioSense Institute, 21101 Novi Sad, Serbia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6206-2229","authenticated-orcid":false,"given":"Robert","family":"Atkinson","sequence":"additional","affiliation":[{"name":"Department of Electronic and Electrical Engineering, University of Strathclyde, Glasgow G1 1RD, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5132-4572","authenticated-orcid":false,"given":"Craig","family":"Michie","sequence":"additional","affiliation":[{"name":"Department of Electronic and Electrical Engineering, University of Strathclyde, Glasgow G1 1RD, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vladimir","family":"Crnojevi\u0107","sequence":"additional","affiliation":[{"name":"BioSense Institute, 21101 Novi Sad, Serbia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9093-5245","authenticated-orcid":false,"given":"Ivan","family":"Andonovic","sequence":"additional","affiliation":[{"name":"Department of Electronic and Electrical Engineering, University of Strathclyde, Glasgow G1 1RD, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1849-5788","authenticated-orcid":false,"given":"Xavier","family":"Bellekens","sequence":"additional","affiliation":[{"name":"Department of Electronic and Electrical Engineering, University of Strathclyde, Glasgow G1 1RD, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9150-6805","authenticated-orcid":false,"given":"Christos","family":"Tachtatzis","sequence":"additional","affiliation":[{"name":"Department of Electronic and Electrical Engineering, University of Strathclyde, Glasgow G1 1RD, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2021,6,12]]},"reference":[{"key":"ref_1","unstructured":"AHDB Dairy (2020, October 12). AHDB Dairy Statistics. Available online: https:\/\/ahdb.org.uk\/dairy."},{"key":"ref_2","unstructured":"Michie, C., Andonovic, I., Gilroy, M., Ross, D., Duthie, C.A., and Nicol, L. (2013, January 10\u201312). Oestrus Detection in Free Roaming Beef Cattle. Proceedings of the European Conference on Precision Livestock Farming\u2014EC-PLF 2013, Posters, Lueven, Belgium."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Fricke, P.M., Carvalho, P.D., Giordano, J.O., Valenza, A., Lopes, G., and Amundson, M.C. (2014). Expression and detection of estrus in dairy cows: The role of new technologies. Animal.","DOI":"10.1017\/S1751731114000299"},{"key":"ref_4","first-page":"498","article-title":"Estrus detection tools and their applicability in cattle: Recent and perspectival situation","volume":"12","author":"Roelofs","year":"2015","journal-title":"Anim. Reprod."},{"key":"ref_5","unstructured":"Afimilk\/NMR (2012). Silent Herdsman\/Better Performing Cows, NMR."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Stangaferro, M., Wijma, R., Caixeta, L., Al-Abri, M., and Giordano, J. (2016). Use of rumination and activity monitoring for the identification of dairy cows with health disorders: Part III. Metritis. J. Dairy Sci.","DOI":"10.3168\/jds.2016-11352"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Wolfger, B., Timsit, E., Pajor, E.A., Cook, N., Barkema, H.W., and Orsel, K. (2015). Technical note: Accuracy of an ear tag-attached accelerometer to monitor rumination and feeding behavior in feedlot cattle. J. Anim. Sci.","DOI":"10.2527\/jas.2014-8802"},{"key":"ref_8","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_9","doi-asserted-by":"crossref","unstructured":"Pahl, C., Hartung, E., Mahlkow-Nerge, K., and Haeussermann, A. (2015). Feeding characteristics and rumination time of dairy cows around estrus. J. Dairy Sci.","DOI":"10.3168\/jds.2014-8025"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Hamilton, A.W., Davison, C., Tachtatzis, C., Andonovic, I., Michie, C., Ferguson, H.J., Somerville, L., and Jonsson, N.N. (2019). Identification of the rumination in cattle using support vector machines with motion-sensitive bolus sensors. Sensors, 19.","DOI":"10.3390\/s19051165"},{"key":"ref_11","unstructured":"Uberoi, E. (2020). UK Dairy Industry Statistics. House of Commons: Brief Paper, House of Commons Library."},{"key":"ref_12","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_13","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1016\/j.rvsc.2017.10.005","article-title":"On the use of on-cow accelerometers for the classification of behaviours in dairy barns","volume":"125","author":"Benaissa","year":"2019","journal-title":"Res. Vet. Sci."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1016\/j.compag.2017.02.021","article-title":"System specification and validation of a noseband pressure sensor for measurement of ruminating and eating behavior in stable-fed cows","volume":"136","author":"Zehner","year":"2017","journal-title":"Comput. Electron. Agric."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1016\/j.compag.2018.12.023","article-title":"Classification of multiple cattle behavior patterns using a recurrent neural network with long short-term memory and inertial measurement units","volume":"157","author":"Peng","year":"2019","journal-title":"Comput. Electron. Agric."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Rahman, A., Smith, D., Hills, J., Bishop-Hurley, G., Henry, D., and Rawnsley, R. (2016, January 24\u201329). A comparison of autoencoder and statistical features for cattle behaviour classification. Proceedings of the 2016 International Joint Conference on Neural Networks (IJCNN), Vancouver, BC, Canada.","DOI":"10.1109\/IJCNN.2016.7727573"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Gonz\u00e1lez, L.A., Bishop-Hurley, G.J., Handcock, R.N., and Crossman, C. (2015). Behavioral classification of data from collars containing motion sensors in grazing cattle. Comput. Electron. Agric.","DOI":"10.1016\/j.compag.2014.10.018"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1016\/j.compag.2017.01.030","article-title":"Predicting bull behavior events in a multiple-sire pasture with video analysis, accelerometers, and classification algorithms","volume":"136","author":"Abell","year":"2017","journal-title":"Comput. Electron. Agric."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1016\/j.applanim.2018.12.003","article-title":"Classification of ingestive-related cow behaviours using RumiWatch halter and neck-mounted accelerometers","volume":"211","author":"Benaissa","year":"2019","journal-title":"Appl. Anim. Behav. Sci."},{"key":"ref_20","first-page":"1","article-title":"Classification of behaviour in housed dairy cows using an accelerometer-based activity monitoring system","volume":"3","author":"Diosdado","year":"2015","journal-title":"Anim. Biotelemetry"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Kasfi, K.T., Hellicar, A., and Rahman, A. (2016, January 5). Convolutional Neural Network for Time Series Cattle Behaviour Classification. Proceedings of the Workshop on Time Series Analytics and Applications\u2014TSAA \u201916, Hobart, Tasmania.","DOI":"10.1145\/3014340.3014342"},{"key":"ref_22","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_23","doi-asserted-by":"crossref","unstructured":"Rahman, A., Smith, D.V., Little, B., Ingham, A.B., Greenwood, P.L., and Bishop-Hurley, G.J. (2018). Cattle behaviour classification from collar, halter, and ear tag sensors. Inf. Process. Agric.","DOI":"10.1016\/j.inpa.2017.10.001"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1016\/j.compag.2009.03.002","article-title":"Evaluation of three-dimensional accelerometers to monitor and classify behavior patterns in cattle","volume":"67","author":"Robert","year":"2009","journal-title":"Comput. Electron. Agric."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1016\/j.compag.2016.10.006","article-title":"Behavior classification of cows fitted with motion collars: Decomposing multi-class classification into a set of binary problems","volume":"131","author":"Smith","year":"2016","journal-title":"Comput. Electron. Agric."},{"key":"ref_26","unstructured":"ITIN+HOCH (2020, October 12). RumiWatchSystem: Measurement System for Automatic Health Monitoring in Ruminants. Available online: https:\/\/www.rumiwatch.com\/."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.applanim.2019.04.009","article-title":"Are automated sensors a reliable tool to estimate behavioural activities in grazing beef cattle?","volume":"216","author":"Poulopoulou","year":"2019","journal-title":"Appl. Anim. Behav. Sci."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"7458","DOI":"10.3168\/jds.2015-10843","article-title":"A validation of technologies monitoring dairy cow feeding, ruminating, and lying behaviors","volume":"99","author":"Borchers","year":"2016","journal-title":"J. Dairy Sci."},{"key":"ref_29","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref_30","unstructured":"Ioffe, S., and Szegedy, C. (2015). Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. arXiv."},{"key":"ref_31","unstructured":"Glorot, X., Bordes, A., and Bengio, Y. (2011, January 11\u201313). Deep sparse rectifier neural networks. Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, Fort Lauderdale, FL, USA."},{"key":"ref_32","unstructured":"Loshchilov, I., and Hutter, F. (2019, January 6\u20139). Decoupled Weight Decay Regularization. Proceedings of the International Conference on Learning Representations, New Orleans, LA, USA."},{"key":"ref_33","unstructured":"Smith, L.N. (2018). A disciplined approach to neural network hyper-parameters: Part 1\u2014Learning rate, batch size, momentum, and weight decay. arXiv."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Prechelt, L. (1998). Early stopping-but when. Neural Networks: Tricks of the Trade, Springer.","DOI":"10.1007\/3-540-49430-8_3"},{"key":"ref_35","unstructured":"Waskom, M., Botvinnik, O., O\u2019Kane, D., Hobson, P., Lukauskas, S., Gemperline, D.C., and Qalieh, A. (2021, June 12). Mwaskom\/Seaborn. Available online: https:\/\/zenodo.org\/record\/3767070#.YMQgCUwRWUl."},{"key":"ref_36","unstructured":"Denton, E.L., Zaremba, W., Bruna, J., LeCun, Y., and Fergus, R. (2014). Exploiting linear structure within convolutional networks for efficient evaluation. arXiv."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Jaderberg, M., Vedaldi, A., and Zisserman, A. (2014, January 1\u20135). Speeding up Convolutional Neural Networks with Low Rank Expansions. Proceedings of the British Machine Vision Conference, Nottingham, UK.","DOI":"10.5244\/C.28.88"},{"key":"ref_38","unstructured":"Hinton, G., Vinyals, O., and Dean, J. (2015). Distilling the knowledge in a neural network. arXiv."},{"key":"ref_39","unstructured":"Han, S., Mao, H., and Dally, W.J. (2015). Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Rastegari, M., Ordonez, V., Redmon, J., and Farhadi, A. (2016, January 11\u201314). Xnor-net: Imagenet classification using binary convolutional neural networks. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"ref_41","unstructured":"Gong, Y., Liu, L., Yang, M., and Bourdev, L. (2014). Compressing deep convolutional networks using vector quantization. arXiv."},{"key":"ref_42","unstructured":"Blalock, D., Ortiz, J.J.G., Frankle, J., and Guttag, J. (2020). What is the state of neural network pruning?. arXiv."},{"key":"ref_43","first-page":"1135","article-title":"Learning both weights and connections for efficient neural networks","volume":"2015","author":"Han","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_44","unstructured":"Frankle, J., and Carbin, M. (2018). The lottery ticket hypothesis: Finding sparse, trainable neural networks. arXiv."},{"key":"ref_45","unstructured":"LeCun, Y., Denker, J.S., and Solla, S.A. (1990). Optimal brain damage. Advances in Neural Information Processing Systems, Morgan Kaufmann."},{"key":"ref_46","unstructured":"Hassibi, B., and Stork, D.G. (1993). Second order derivatives for network pruning: Optimal brain surgeon. Advances in Neural Information Processing Systems, Morgan Kaufmann."},{"key":"ref_47","unstructured":"Li, H., Kadav, A., Durdanovic, I., Samet, H., and Graf, H.P. (2016). Pruning filters for efficient convnets. arXiv."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"He, Y., Zhang, X., and Sun, J. (2017, January 22\u201329). Channel pruning for accelerating very deep neural networks. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.155"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Luo, J.H., Wu, J., and Lin, W. (2017, January 22\u201329). Thinet: A filter level pruning method for deep neural network compression. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.541"},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Liu, Z., Li, J., Shen, Z., Huang, G., Yan, S., and Zhang, C. (2017, January 22\u201329). Learning efficient convolutional networks through network slimming. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.298"},{"key":"ref_51","unstructured":"Zhu, M., and Gupta, S. (2017). To prune, or not to prune: Exploring the efficacy of pruning for model compression. arXiv."},{"key":"ref_52","unstructured":"ST Microelectronics (2021, June 12). UM2526: Introduction Getting Started with X-CUBE-AI Expansion Package for Artificial Intelligence (AI) UM2526 User Manual. Available online: https:\/\/www.st.com\/resource\/en\/user_manual\/dm00570145-getting-started-with-xcubeai-expansion-package-for-artificial-intelligence-ai-stmicroelectronics.pdf."},{"key":"ref_53","unstructured":"Saft Batteries (2020, October 03). LS14500 Datasheet. Available online: https:\/\/www.saftbatteries.com\/products-solutions\/products\/ls-lsh-lsp\/."},{"key":"ref_54","unstructured":"InvenSense (2013). MPU-6000 and MPU-6050 Product Specification Revision 3.4, InvenSense Inc."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/12\/4050\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:13:37Z","timestamp":1760163217000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/12\/4050"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,12]]},"references-count":54,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2021,6]]}},"alternative-id":["s21124050"],"URL":"https:\/\/doi.org\/10.3390\/s21124050","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,6,12]]}}}