• Journal of Animal Science and Technology
• /
• v.61 no.3
• /
• pp.147-153
• /
• 2019

A goal for swine farming is the improvement in the number of live-born and weaned piglets per sow. Hence, the effect of parities should consider the correlation between the component traits of reproductive performance, weaning, and duration. Sows were housed in farrowing pens (W 2.2 ${\times}$ D 1.8 ${\times}$ H 1.2 m) on a partially slatted plastic floor. Twenty sows used in this study were between the first and sixth parity in gilts (P1), parity 2-5 (P3), and parity 6-9 (P6). Data collection by parity was classified into three categories: (1) reproduction performance (gestation length, total number of piglets born, number of piglets live born, number of piglets stillborn, total piglet birth weight; (2) weaning traits (weaning period, number of piglets weaning, total piglets weaning weight); (3) duration traits (farrowing duration, placenta expulsion duration, time from last piglet to first placenta, average birth interval, and tail wagging behavior). Gestation length was higher in P6 than P1 and P3 of different parity sows. The maximum value in P1 and P3 was 117 days, but the median value in P6 was 117 days (p < 0.05). The total number of piglets born (p = 0.113), number of piglets live born (p = 0.118), number of still piglets born (p = 0.151), and total piglet birth weight (p = 0.117) were not affected by parity. The number of live piglets was higher than the other parities by an average of $15.6{\pm}2.1$ in P1. The duration of farrowing was the lowest at 22.2 min in P6, but the maximum value was 42.2 min more than other parities (p = 0.355). Weaning traits of sows also did not differ significantly (p > 0.05), but the weaning period from P1 was lower than that of the other parities (p = 0.170). The number of piglets weaned was 10 heads on average in P1, P3, and P6 (p < 0.05). However, the mean values of the total piglet weaning weight (p = 0.377) of P6 (62.0 10.4 kg) were higher than those of P1 (54.9 10.2 kg) and P3 (58.4 13.6 kg). The placenta expulsion duration was higher in P6 than that in P1 and P3 (p = 0.447). The time from the last piglet to first placenta was be lower in P3 than that of the other parities (p = 0.206). The average birth interval was higher in P3 than that of the other parities (p = 0.156). Tail wagging (count) behavior was higher in P6 than in the other parities (p = 0.065). The data showed that the reproduction performance, total piglets born, and weight were higher in the gilts group, and higher in the weaning trait than that in the P6 group. This study examined the relationship between reproductive performance, birth interval and tail motion according to sow parity. Regarding duration, farrowing duration was lower in P6 than that in the other parities, but placenta expulsion and tail wagging were higher in P6 than in the other parities. Therefore, it is possible that the results from these sows could be used as basic data for effective farm management.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.4
• /
• pp.2148-2161
• /
• 2019

In this paper, we present a real-time cattle action recognition algorithm to detect the estrus phase of cattle from a live video stream. In order to classify cattle movement, specifically, to detect the mounting action, the most observable sign of the estrus phase, a simple yet effective feature description exploiting motion history images (MHI) is designed. By learning the proposed features using the support vector machine framework, various representative cattle actions, such as mounting, walking, tail wagging, and foot stamping, can be recognized robustly in complex scenes. Thanks to low complexity of the proposed action recognition algorithm, multiple cattle in three enclosures can be monitored simultaneously using a single fisheye camera. Through extensive experiments with real video streams, we confirmed that the proposed algorithm outperforms a conventional human action recognition algorithm by 18% in terms of recognition accuracy even with much smaller dimensional feature description.

• Korean Journal of Veterinary Research
• /
• v.42 no.3
• /
• pp.403-410
• /
• 2002

This study was performed to investigate the general prepartum behavioral ethogram of Bos taurus coreanae (Hanwoo cow). In this study, 4 pregnant cows were placed in a separate area. We recorded the behaviors of the cows using time lapse VCR for 48 hours and analyzed behaviors with the scan point sampling method. We observed maintenance behaviors, social behaviors and ingestion behaviors. During the observation period, the time budgets of behaviors in order of frequency were LD(lying down, 38.2%), ST(standing, 24.7%), EA(eating, 10.7%), WA(walking, 7.2%), LR(lying down rumination, 5.6%), SR(standing rumination, 3.3%), TW(tail wagging, 3.1%) and SG(self grooming, 1.8%). The time budgets of the other behaviors such as PG(pairwise grooming), FC(fly catching) were negligible (<1%).