id	author	title	date	pages	extension	mime	words	sentence	flesch	summary	cache	txt
afs-111665	Koskela, Olli; Benitez Pereira, Leonardo Santiago; Pölönen, Ilpo; Aronen, Ilmo; Kunttu, Iivari; Koskela, Olli	Deep learning image recognition of cow behavior and an open data set acquired near an automatic milking robot	2022	15	.pdf	application/pdf	8638	421	57	Previously, aggression has been detected with an accuracy rate of 98% and a recall rate of 98% (Chen et al. 2019); interaction or non-interaction with an accuracy rate of approximately 60% and a recall rate of 100% (Ardo et al. 2017); feeding or non-feeding with an accuracy rate of 92% and a recall rate of 88% (Porto et al. 2015), accuracy rate of 97% (Achour et al. 2020) or 99.4% in a pig study (Alameer et al. 2020); and mounting or non-mounting with an accuracy rate of 91% and a recall rate of 95% (Li et al. 2019). Computer vision approaches employing video cam- eras are scalable and low-cost solutions (Banhazi and Tscharke 2016) and have been successfully used to monitor physiological and behavioral parameters related to pre-slaughter stress (Jorquera-Chavez et al. 2019); to detect hoof disease (Gu et al. 2017); to track gait and identify lameness (Gardenier et al. 2018, Jiang et al. 2019a, Kang et al. 2022), to analyze health problems through calculating body condition scores (Zin et al. 2018b, Huang et al. 2019), body structure (Jiang et al. 2019 b, Liu et al. 2020) and faecal monitoring (Atkinson et al. 2020); and to de- tect aggressive behaviors (Chen et al. 2019).	cache/afs-111665.pdf	txt/afs-111665.txt