|
RECOGNISING DAIRY COWS' BEHAVIOUR WITH LSTM MODEL TO IMPROVE FARM MANAGEMENT PRACTICES
|
|
|
Kristina Dineva; Tatiana Atanasova
|
|
|
||
|
10.5593/sgem2023v/6.2
|
|
|
1314-2704
|
|
|
||
|
English
|
|
|
23
|
|
|
6.2
|
|
|
• Prof. DSc. Oleksandr Trofymchuk, UKRAINE
• Prof. Dr. hab. oec. Baiba Rivza, LATVIA |
|
|
||
|
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.
|
|
|
||
|
||
|
conference
|
|
|
||
|
||
|
Proceedings of 23rd International Multidisciplinary Scientific GeoConference SGEM 2023
|
|
|
23rd International Multidisciplinary Scientific GeoConference SGEM 2023, 28-30 November, 2023
|
|
|
Proceedings Paper
|
|
|
STEF92 Technology
|
|
|
International Multidisciplinary Scientific GeoConference-SGEM
|
|
|
SWS Scholarly Society; Acad Sci Czech Republ; Latvian Acad Sci; Polish Acad Sci; Russian Acad Sci; Serbian Acad Sci and Arts; Natl Acad Sci Ukraine; Natl Acad Sci Armenia; Sci Council Japan; European Acad Sci, Arts and Letters; Acad Fine Arts Zagreb Croatia; Croatian Acad Sci and Arts; Acad Sci Moldova; Montenegrin Acad Sci and Arts; Georgian Acad Sci; Acad Fine Arts and Design Bratislava; Russian Acad Arts; Turkish Acad Sci.
|
|
|
353-360
|
|
|
28-30 November, 2023
|
|
|
website
|
|
|
|
|
|
9618
|
|
|
farm management, IoT (Internet of things), cow’s behavior recognition, LSTM (long short-term memory) neural networks, accelerometer and gyroscope data
|
|