• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.4
• /
• pp.135-144
• /
• 2018

The domestic pigsty environment is highly vulnerable to the spread of respiratory diseases such as foot-and-mouth disease because of the small space. In order to manage this issue, a variety of studies have been conducted to automatically analyze behavior of individual pigs in a pig pen through a video surveillance system using a camera. Even though it is required to correctly segment touching pigs for tracking each pig in complex situations such as aggressive behavior, detecting the correct boundaries among touching pigs using Kinect's depth information of lower accuracy is a challenging issue. In this paper, we propose a segmentation method using motion information of the touching pigs. In addition, our proposed method can be applied for detecting tracking errors in case of tracking individual pigs in the complex environment. In the experimental results, we confirmed that the touching pigs in a pig farm were separated with the accuracy of 86%, and also confirmed that the tracking errors were detected accurately.

• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.10
• /
• pp.473-478
• /
• 2015

Recently, automatic video monitoring of individual pigs is emerging as an important issue in the management of group-housed pigs. Although a rich variety of studies have been reported on video monitoring techniques in intensive pig farming, it still requires further elaboration. In particular, when there exist adjoining pigs in a crowd pig room, it is necessary to have a way of separating adjoining pigs from the perspective of an image processing technique. In this paper, we propose an efficient image segmentation solution using both spatio-temporal information and region growing method for the identification of individual pigs in video surveillance systems. The experimental results with the videos obtained from a pig farm located in Sejong illustrated the efficiency of the proposed method.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.61 no.6
• /
• pp.21-30
• /
• 2019

Livestock odor is comprised of mixed type of odorous compounds. Among these, ammonia ($NH_3$) and hydrogen sulfide ($H_2S$) are the two known major odor causing substances. Because high odor concentration reduces productivity of livestock and causes damage to the surrounding communities, quantitative analysis is needed to manage the odor inside and outside the livestock facilities. It is also necessary to evaluate odor dispersion according to the distance between the receptors taking into account the influence of odor source and weather condition. Therefore, in this study, we tried to evaluate the internal environment and odor dispersion from experimental pig house considering weather conditions. An experimental farm was specifically selected to eliminate the interference of odors generated by adjacent farms. $NH_3$ and complex odor were quantitatively analyzed using a gas detector and air dilution sensory method. The concentration of $NH_3$ and complex odor in pig house showed a distinct concentration difference according to the cleaning and ventilation conditions. $NH_3$ concentration and complex odor was lower than emission standard in the pig house and at the site boundary. The average $NH_3$ concentration (P1~P3) and the $NH_3$ concentration at the site boundary (S1) were strongly correlated with R=0.77. While the correlation for complex odor inside and at the site boundary had R=0.52. The correlation coefficient between $NH_3$ and the complex odor was 0.80.

• Journal of Veterinary Science
• /
• v.22 no.3
• /
• pp.35.1-35.13
• /
• 2021

Background: African swine fever (ASF) is an infectious viral disease of domestic pigs that presents as a hemorrhagic fever, and for which no effective vaccine is available. The disease has a serious negative social and economic impact on pig keepers. There is limited information on the potential risk factors responsible for the spread of ASF in South Kivu. Objective: The aim of this study was to determine the potential risk factors associated with ASF infection in suspected ASF virus (ASFV)-infected pigs. Methods: We sampled whole blood from 391 pigs. Additionally, 300 pig farmers were interviewed using a structured questionnaire. Viral DNA was detected by using the real-time polymerase chain reaction technique. Results: The majority of pigs sampled, 78% (95% confidence interval [CI], 74.4-82.6), were of local breeds. Over half, 60.4% (95% CI, 55.5-65.2), were female, and most of them, 90.5% (95% CI, 87.6-93.4), were adult pigs (> 1 year old). Viral DNA was detected in 72 of the 391 sampled pigs, indicating an overall infection rate of 18.4% (95% CI, 14.5-22.4). Multivariable logistic regression analysis revealed several risk factors positively associated with ASFV infection: feeding with swill in pen (odds ratio [OR], 3.8; 95% CI, 2.12-6.77); mixed ages of pigs in the same pen (OR, 3.3; 95% CI, 1.99-5.57); introduction of new animals to the farm (OR, 5.4; 95% CI, 1.91-15.28). The risk factors that were negatively (protective) correlated with ASFV positivity were the presence of male animals and the use of an in-pen breeding system. Conclusion: Local pig farmers should be encouraged to adopt proper husbandry and feeding practices in order to increase the number of ASF-free farms.

• Animal Bioscience
• /
• v.37 no.4
• /
• pp.622-630
• /
• 2024

Objective: Pig breeders cannot obtain phenotypic information at the time of selection for sow lifetime productivity (SLP). They would benefit from obtaining genetic information of candidate sows. Genomic data interpreted using deep learning (DL) techniques could contribute to the genetic improvement of SLP to maximize farm profitability because DL models capture nonlinear genetic effects such as dominance and epistasis more efficiently than conventional genomic prediction methods based on linear models. This study aimed to investigate the usefulness of DL for the genomic prediction of two SLP-related traits; lifetime number of litters (LNL) and lifetime pig production (LPP). Methods: Two bivariate DL models, convolutional neural network (CNN) and local convolutional neural network (LCNN), were compared with conventional bivariate linear models (i.e., genomic best linear unbiased prediction, Bayesian ridge regression, Bayes A, and Bayes B). Phenotype and pedigree data were collected from 40,011 sows that had husbandry records. Among these, 3,652 pigs were genotyped using the PorcineSNP60K BeadChip. Results: The best predictive correlation for LNL was obtained with CNN (0.28), followed by LCNN (0.26) and conventional linear models (approximately 0.21). For LPP, the best predictive correlation was also obtained with CNN (0.29), followed by LCNN (0.27) and conventional linear models (approximately 0.25). A similar trend was observed with the mean squared error of prediction for the SLP traits. Conclusion: This study provides an example of a CNN that can outperform against the linear model-based genomic prediction approaches when the nonlinear interaction components are important because LNL and LPP exhibited strong epistatic interaction components. Additionally, our results suggest that applying bivariate DL models could also contribute to the prediction accuracy by utilizing the genetic correlation between LNL and LPP.

• Parasites, Hosts and Diseases
• /
• v.62 no.3
• /
• pp.294-301
• /
• 2024

Toxoplasma gondii, a common protozoan parasite, poses significant public health risks due to its potential to cause toxoplasmosis in humans and can be contracted from pigs, which are considered its critical intermediate host. The aim of this study is to evaluate the prevalence of T. gondii in slaughtered pigs for human consumption, emphasizing the zoonotic implications and the need for improved biosecurity and monitoring practices in pig farming. A total of 1,526 pig samples (1,051 whole blood samples and 384 lung tissue samples from the local slaughterhouse and 91 aborted fetus samples from local farms) were collected throughout the whole country of Korea in 2020. Among them, 6 (0.4%) were found to be infected with T. gondii by nested PCR. When compared by sample type, the prevalence of T. gondii was significantly higher in the aborted fetus samples (2.2%, 2/91) than in the blood (0.3%, 3/1,051) and lung tissue samples (0.3%, 1/384). The B1 gene sequence of T. gondii was similar (97.9-99.8%) to that of the other T. gondii isolates. This study represents the first molecular genotyping survey of T. gondii in the lung tissue of fattening pigs and aborted fetuses in Korea. Our findings indicated the importance of adopting preventive measures including the implementation of rigorous farm hygiene protocols and the promotion of public awareness about the risks of consuming undercooked pork. By addressing the gaps in current control strategies and encouraging the One Health approach, this study contributes to the development of more effective strategies to mitigate the transmission of T. gondii from pigs to humans, ultimately safeguarding public health.

• Journal of Animal Environmental Science
• /
• v.15 no.3
• /
• pp.231-240
• /
• 2009

In this research pig house facilities what are 3,029 houses hold over 1000 heads were surveyed by scale and province. Full-time farms hold over 1000 heads breed total 7,229,892 heads. And farms breed 2,386.9 heads averagely. Pig houses were constructed august 1995 averagely. Each of houses have $3,017.2\;m^2$ scale. The construction type of pig house was winch-curtain type 77.2% which was most popular, confined type 51.3%, litter type 7.4% and loft type 4.6%. The winch-curtain type was popular than windowless type in pig farms which have 1,000-1,999 heads. But pig house construction type which have more than over 10,000 heads was windowless type more than winch-curtain type. Manure removing type was slurry 72.3% and scraper 38.5% in farms which have 1,000-1,999 heads. Manure removing type was slurry 83.3% in farms which have over 10,000 heads. Proportion of roof type of pig house was slate 51.2%, panel 46.1%. But in middle or small farms, slate type was only 25.0%. Proportion of wall type of pig house was 41.9%, block 21.9%, concrete 7.6%, winch-curtain 6.3%, and bnck 5.9%. Ventilation type of pig house was natural winch 46.1%, mechanical windowless 69.8% and mixed type 53.1%. So, mechanical windowless type was popular than natural winch type. Especially the farm scale is bigger the mechanical widowless type was more. Utilization period of pig house was 8.1 years about automatic feeder, 8.3 years about waterer, 8.2 years about electric facilities and 9.0 years about floor material. Thus, almost of facilities were used at least 8 years.

• Food Science of Animal Resources
• /
• v.38 no.2
• /
• pp.403-416
• /
• 2018

In this study, the dietary effects of probiotics with a liquid application system on meat quality and physicochemical characteristics of pigs were evaluated. A total of 80 Landrace${\times}$Yorkshire${\times}$Duroc (LYD) 3-way crossbred pigs (average age $175{\pm}5d$) were assigned to a conventional farm and a probiotics farm equipped with a liquid probiotics application system (40 pigs in each farm). The two treatments were: CON (diet without probiotics) and PRO (diet with probiotics). Dietary probiotics decreased shear force in the longissimus muscle compared to the control group (p<0.05). The treatment diet did not affect backfat thickness, carcass weight, meat color, cooking loss, water holding capacity (WHC), and drip loss. Dietary probiotics significantly reduced ash, salinity, and pH (at 5 and 15 d) (p<0.05). There was no significant effect on thiobarbituric acid reactive substance (TBARS) values. Polyunsaturated fatty acid (PUFA) and omega fatty acids (${\omega}3$ and ${\omega}6$) were significantly (p<0.05) higher in the PRO group, whereas monounsaturated fatty acid (MUFA) was decreased. The free amino acid composition, serine, lysine, histidine, and arginine levels were significantly lower in the PRO than in the control group. The treatment group exhibited higher nucleotide compounds (hypoxanthine, inosine, GMP, IMP) than the controls. Also, levels of ascorbic acid and thiamin were significantly different (p<0.05), while minerals were not significantly different between the groups. In conclusion, feeding of probiotics had effects on shear force, ash, salinity, pH, PUFA, and some amino acids which related to taste and flavor without any negative effects on the pigs' carcass traits.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.59 no.3
• /
• pp.71-81
• /
• 2017

Organic dust generated inside livestock facilities includes toxic organic matters such as bacteria and endotoxin. Dust can cause respiratory disease for worker and livestock, and consequently, degradation of welfare and productivity. Influence of dust on livestock workers has been studied since the 1970s. However, exposure limit for cattle farmer has not been established, unlike exposure limit for pig and poultry farmer. Furthermore, study on air quality inside livestock facility, especially inside dairy farm has been rarely conducted in Korea. In this study, dust concentration of TSP, PM10, inhalable and respirable dust has been monitored in the commercial dairy house according to location and working activities. Bedding material inside the stall was one of the major sources of dust. The amount of dust was related to water content level of the bedding material. Dust concentration was relatively high in leeward location, and the highest concentration was measured during TMR mixing process. The maximum value of inhalable dust concentration was 29.1 times higher than the reference value as fine particles drop to the TMR mixer. Dust generated by TMR mixing was presumed to decrease by adjusting moisture and drop height of feed.

• Clinical and Experimental Vaccine Research
• /
• v.13 no.1
• /
• pp.54-62
• /
• 2024

Purpose: Accidental vaccination with a live attenuated low-virulence strain of Miyagi (LOM) vaccine led to the reemergence of classical swine fever virus (CSFV) in Jeju province, South Korea in 2014. To control the continual outbreaks of LOM-derived CSFV, the provincial government launched a provincial mass vaccination project using a CSF-E2 subunit vaccine. We conducted this study to assess the herd immunity level and outcomes of E2 vaccine-based immunization in breeding and growing herds on Jeju Island during 2020-2021. Materials and Methods: A large-scale vaccination trial using the Bayovac CSF-E2 vaccine investigated its efficacy in breeding and growing herds under farm application conditions (10 CSFV-affected and three CSFV-naïve swine farms). Results: The level of herd immunity in each farm was classified into three (S1-S3) and six (G1-G6) profiles in breeding and growing herds, respectively. Immunity monitoring revealed a remarkable improvement in the herd immunity status in all farms. The majority (10/13) of farms, including CSFV-free farms, showed the S1G1 immunity profile in 2021, indicating the appropriate implementation of the advised vaccination regime. Moreover, there were significant decreases in E^rns seropositivity from 100% to 50% and 25.9% to 4.3% at farm and pig levels, respectively. In particular, all farms were confirmed as CSFV free in the growing-finishing herds. Conclusion: Our large-scale trial demonstrated the effectiveness of the E2 subunit vaccine in establishing herd immunity stabilization and eliminating CSFV circulation in the affected farms and highlighted the need for a provincial vaccination policy to regain the CSF-free status on Jeju Island.