Scholarly record
RECOGNISING DAIRY COWS' BEHAVIOUR WITH LSTM MODEL TO IMPROVE FARM MANAGEMENT PRACTICES
Abstract
This paper focuses on recognizing the activity of dairy cows using a non-invasive approach that monitors four key behaviors: licking, feeding, standing, and lying. The study used IoT devices with accelerometers and gyroscopes attached to the cow's neck to continuously monitor its movements. The data collection process aimed to capture the dynamic and static nature of dairy cow behaviors, providing a valuable data set for subsequent analysis. To efficiently process the raw data, we analyzed it and then used long short-term memory (LSTM) neural networks, a type of recurrent neural network (RNN) suitable for sequential data processing. The LSTM model was trained on the collected sensor data to recognize and classify the four target activities. The model achieved an accuracy of 96%, indicating its robust ability to accurately identify dairy cow activity. Furthermore, the model consistently maintained a low loss value hovering around 0.25, demonstrating its generalization and predictive performance. This research has important implications for dairy production and animal welfare. Accurate real-time recognition of dairy cow activities can help improve farm management practices, enabling timely interventions when needed.
Publication Impact Profile
- Captures
- Mendeley - Readers: 5
Publication details
References13
Konfo T.R.C., Djouhou F.M.C., Hounhouigan M.H., Dahouenon-Ahoussi E.,Avlessi F., Sohounhloue C.K.D. Recent advances in the use of digital technologies inagri-food processing: A short review, Applied Food Research, 3(2), 2023, 100329,DOI: 10.1016/j.afres.2023.100329
Danev, V. The Internet of Things: Description, Applications, Development,Challenges. Problems of Engineering Cybernetics and Robotics, 76, 2021,DOI: 10.7546/PECR.76.21.01, 3-24
Khan Y, Su�ud MBM, Alam MM, Ahmad SF, Ahmad AYAB, Khan N. Applicationof Internet of Things (IoT) in Sustainable Supply Chain Management. Sustainability.2023; 15(1):694. DOI: 10.3390/su15010694
Marchiori, M. Happy Cows, Happy Milk: Smart Cows and Quality Factors. 2019IEEE Smart World, Ubiquitous Intelligence & Computing, Advanced & TrustedComputing, Scalable Computing & Communications, Cloud & Big Data Computing,Internet of People and Smart City Innovation. 2019. DOI: 10.1109/smartworld-uic-atc-scalcom-iop-sci.2019.00062
Mancuso D, Castagnolo G, Porto SMC. Cow Behavioural Activities in ExtensiveFarms: Challenges of Adopting Automatic Monitoring Systems. Sensors. 2023;23(8):3828. DOI: 10.3390/s23083828
Li Y, Shu H, Bindelle J, Xu B, Zhang W, Jin Z, Guo L, Wang W. Classification andAnalysis of Multiple Cattle Unitary Behaviors and Movements Based on MachineLearning Methods. Animals (Basel). 2022 Apr 20;12(9):1060. DOI: 10.3390/ani12091060.
Crowe, M.A., Hostens, M. & Opsomer, G. Reproductive management in dairy cows- the future. Ir Vet J 71, 1, 2018. DOI: 10.1186/s13620-017-0112-y
Gusterer E., Kanz P., Krieger S., Schweinzer V., Suss D., Lidauer L., Kickinger F.,Ohlschuster M., Auer W., Drillich M., Iwersen M. Sensor technology to support herdhealth monitoring: Using rumination duration and activity measures as unspecificvariables for the early detection of dairy cows with health deviations. Theriogenology,157, 2020, pp. 61-69, DOI: 10.1016/j.theriogenology.2020.07.028
Dineva, K., Atanasova, T. Analysis of Dairy Cow Behavioral Patterns Using aCombination of IoT Data and Signal Processing Techniques. Proceedings of 23rd International Multidisciplinary Scientific GeoConference SGEM 2023, 23, 6.1, STEF92Technology, 2023, DOI: 10.5593/sgem2023/6.1/s25.14
Balabanov, T. Long Short-Term Memory in MLP Pair. Proceedings of theInternational Scientific Conference UniTech 2017, Gabrovo, 17-18.11.2017, Vol. II,University publishing house V. Aprilov, 2017, ISSN:1313-230X, 375-379.
Wu Y, Liu M, Peng Z, Liu M, Wang M, Peng Y. Recognising Cattle Behaviourwith Deep Residual Bidirectional LSTM Model Using a Wearable MovementMonitoring Collar. Agriculture. 2022; 12(8):1237.DOI: 10.3390/agriculture12081237
Blagoev, I., Keremedchiev, D., Zankinski, I. Population based algorithms forartificial neural networks training in perfect information games. Informationtechnologies and control, 4, 2019, 23-28
Roelofs R. Measuring Generalization and Overfitting in Machine Learning.University of California, Berkeley, Technical Report No. UCB/EECS-2019-102, June19, 2019, http://www2.eecs.berkeley.edu/Pubs/TechRpts/2019/EECS-2019-102.pdf
View or Download full articleAccess options
SWS access login
Login as SWS Scientific CommitteeLogin as SWS Scientific PartnerLogin as SWS AuthorAuthors and approved SWS contributors will read and export their own linked papers after identity matching by SWS profile, email and SGEM GlobalID.
For librarian assistance: [email protected]
Purchase Instant Access
- Article can be downloaded after successful payment.
- Article may be used according to SWS library access terms.
- Article cannot be redistributed.