• Smart Media Journal
• /
• v.13 no.6
• /
• pp.16-23
• /
• 2024

Pigs express their reactions to their environment and health status through a variety of sounds, such as grunting, coughing, and screaming. Given the significance of pig vocalizations, their study has recently become a vital source of data for livestock industry workers. To facilitate this, we propose a lightweight deep learning model based on MobileNet that analyzes pig vocal patterns to distinguish pig voices from farm noise and differentiate between vocal sounds and coughing. This model was able to accurately identify pig vocalizations amidst a variety of background noises and cough sounds within the pigsty. Test results demonstrated that this model achieved a high accuracy of 98.2%. Based on these results, future research is expected to address issues such as analyzing pig emotions and identifying stress levels.

• Journal of Korean Society of Occupational and Environmental Hygiene
• /
• v.16 no.1
• /
• pp.36-43
• /
• 2006

The principal aim of this field study was to determine the concentrations and emissions of gaseous contaminants such as ammonia and hydrogen sulfide in the different types of pig buildings in Korea and allow objective comparison between Korea and the other countries in terms of pig housing types. This field study was performed from May to June and from September to October in 2002. Pig buildings investigated in this research were selected in terms of three criteria; manure removal system, ventilation mode and growth stage of pig. Measurements of concentration and emission of ammonia and hydrogen sulfide in the pig buildings were done in 5 housing types and the visited farms were 15 sites per each housing type. Concentrations of ammonia and hydrogen sulfide were measured at three locations of the central alley in the pig building and emission rates of them were estimated by multiplying the average concentration($mg/m^3$) measured near the air outlet by the mean ventilation rate($m^3/h$) and expressed either per pig of liveweight 75kg(mg/h/pig) or per area($mg/h/m^2$). Concentrations of ammonia and hydrogen sulfide in the pig buildings were averaged to 7.5 ppm and 286.5 ppb and ranged from 0.8 to 21.4 ppm and from 45.8 to 1,235 ppb, respectively. The highest concentrations of ammonia and hydrogen sulfide were found in the mechanically ventilated buildings with slats; 12.1 ppm and 612.8 ppb, while the lowest concentrations of ammonia and hydrogen sulfide were found in the pig buildings with deep-litter bed system(2.2 ppm) and the naturally ventilated pig buildings with manure removal system by scraper(115.2 ppb), respectively(p<0.05). All the pig buildings were investigated not to exceed the threshold limit values(TLVs) of ammonia(25 ppm) and hydrogen sulfide(10 ppm). The mean emissions of ammonia and hydrogen sulfide per pig(75kg in terms of liveweight) and area($m^2$) from pig buildings were 250.2 mg/h/pig and 37.8 mg/h/pig and $336.3mg/h/m^2$ and $50.9mg/h/m^2$, respectively. The pig buildings with deep-litter bed system showed the lowest emissions of ammonia and hydrogen sulfide(p<0.05). However, the emissions of ammonia and hydrogen sulfide from the other pig buildings were not significantly different(p>0.05). Concentrations and emissions of ammonia and hydrogen sulfide were relatively higher in the pig buildings managed with deep-pit manure system with slats and mechanical ventilation mode than the different pig housing types. In order to prevent pig farm workers from adverse health effect caused by exposure to ammonia and hydrogen sulfide in pig buildings, they should wear the respirators during shift and be educated sustainably for the guideline related to occupational safety.

• Korean Journal of Veterinary Service
• /
• v.44 no.4
• /
• pp.217-225
• /
• 2021

We investigated the effect of temperature and stock density on the collection efficiency of oral fluid in the pig farm in Korea. Three pig farms with similar breeding environmental conditions were selected and four pens of each farm (total 12 pens) were tested for the collection efficiency of oral fluid from pigs. Collection rate was considered as significant when oral fluid was collected from 70% of pigs within a pen. In the case of growing pigs, when internal temperature of pig barn increased by one designated degree (5℃), the oral fluid collection rate significantly decreased by 24.7% (P<0.05). The collection rate of oral fluid also decreased by 7.1% (P<0.05) as the density rate increase by one designated degree (12.5%). It was estimated that the collection efficiency of oral fluid decreased when the internal temperature of pig barn was 30℃ or higher, or barn density is higher 25% or high. On the other hand, in the case of stall-housing sows, unlike growing pigs, there was no significant differences according to the temperature, so oral fluid collection was considered to be efficient even in hot season.

• Asian-Australasian Journal of Animal Sciences
• /
• v.15 no.11
• /
• pp.1543-1545
• /
• 2002

A T$\longrightarrow$A mutation in the promoter region of porcine myostatin (MSTN) gene has been identified in our previous work. This study analyzed the associations of the myostatin genotypes (TT, TA) caused by this mutation with birth weigh in Yorkshire pigs. Data from 211 unrelated individuals were collected three times from one breeding farm. Detections of the mutation were carried out by PCR-RFLPs approach. The effects of MSTN genotypes (TT and TA) on birth weight were compared by least square means. The results showed that for birth weight of Yorkshire pigs, individuals with TA genotype were significantly higher than those with TT genotype (p<0.05), and the birth weight for pigs with TA genotype were 1.37 kg in average but only 1.25 kg for pigs with TT genotype, indicating a positive effect of birth weight for A allele.

• Korean Journal of Environmental Agriculture
• /
• v.15 no.3
• /
• pp.355-361
• /
• 1996

The Purpose of this study was to investigate the effect of the Change in the operating conditions on rotary turning compost plants. The major parameters investigated were moisture content and mixing of the sawdust and pig farm wastewater. Pig farm scale composting plants with mixing rotary were used in this study. Wastes used for the study were sawdust, pig manure, urine and wastewater. When the moisture content was 75%, the compost product obtained from the plants had better physical characteristics than that obtained from the plants with moisture contents of 70%, 80% and 85%.(two a day mixing). When the turning was twice a day, the compost product obtained from the plants had better characteristics than that obtained from non-mixing.(moisture content 75%). C/N ratio, pH value and coliform bacterial population were stable in the compost.

• Korean Journal of Veterinary Service
• /
• v.27 no.2
• /
• pp.121-131
• /
• 2004

This experiment was executed to control effectively endemic disease of swine farms in Incheon metropolitan city. Mainly using PigMon program which had been developed by the College of Veterinary Medicine in the University of Minnesota(USA), we examined lesions of gastric ulcer and interstitial nephritis additionally. 446 heads of pigs shipped from 5 farms in Incheon to a slaughterhouse from June in 2003 to May in 2004 were examined. Infection rates by farms were obtained as follows; 1. Pneumonia was varied from 34.6% to 74.1% and pneumonic score was 1.47∼7.06. As for atrophic rhinitis, four farms were 100% and one farm was 89.5% and rhinitis score was 1.3∼3.2. 2. The infection rate of pericarditis and peritonitis was 1.0∼3.9% and liver white spots, papular dermatitis were observed in pigs of 9.8∼29.7%, 16.7∼51.4% respectively. 3. The outbreak rates of interstitial nephritis, lesions of ileal thickening and gastric ulcer were 15.4∼24.1%, 7.7∼13.5%, and 62.7%∼86.2% respectively.

• Asian-Australasian Journal of Animal Sciences
• /
• v.29 no.12
• /
• pp.1805-1811
• /
• 2016

The goal of this study was to estimate the emissions of greenhouse gases (GHG), namely methane ($CH_4$), nitrous oxide ($N_2O$), and carbon dioxide ($CO_2$) from poultry and pig production in South Korea over the last 10 years (2005 through 2014). The calculations of GHG emissions were based on Intergovernmental Panel on Climate Change (IPCC) guidelines. Over the study period, the $CH_4$ emission from manure management decreased in layer chickens, nursery to finishing pigs and gestating to lactating sows, but there was a gradual increase in $CH_4$ emission from broiler chickens and male breeding pigs. Both sows and nursery to finishing pigs were associated with greater emissions from enteric fermentation than the boars, especially in 2009. Layer chickens produced lower direct and indirect $N_2O$ emissions from 2009 to 2014, whereas the average direct and indirect $N_2O$ emissions from manure management for broiler chickens were 12.48 and $4.93Gg\;CO_2-eq/yr$, respectively. Annual direct and indirect $N_2O$ emissions for broiler chickens tended to decrease in 2014. Average $CO_2$ emission from direct on-farm energy uses for broiler and layer chickens were 46.62 and $136.56Gg\;CO_2-eq/yr$, respectively. For pig sectors, the $N_2O$ emission from direct and indirect sources gradually increased, but they decreased for breeding pigs. Carbon dioxide emission from direct on-farm energy uses reached a maximum of $53.93Gg\;CO_2-eq/yr$ in 2009, but this total gradually declined in 2010 and 2011. For boars, the greatest $CO_2$ emission occurred in 2012 and was $9.44Gg\;CO_2-eq/yr$. Indirect $N_2O$ emission was the largest component of GHG emissions in broilers. In layer chickens, the largest contributing factor to GHG emissions was $CO_2$ from direct on-farm energy uses. For pig production, the largest component of GHG emissions was $CH_4$ from manure management, followed by $CO_2$ emission from direct on-farm energy use and $CH_4$ enteric fermentation emission, which accounted for 8.47, 2.85, and $2.82Gg-CO_2/yr$, respectively. The greatest GHG emission intensity occurred in female breeding sows relative to boars. Overall, it is an important issue for the poultry and pig industry of South Korea to reduce GHG emissions with the effective approaches for the sustainability of agricultural practices.

• Journal of Microbiology and Biotechnology
• /
• v.21 no.1
• /
• pp.50-54
• /
• 2011

This study's objective was to determine the prevalence of Salmonella spp. in pigs and their farm environments in Korea, and to investigate the relationship between the strains based on their phenotypic and genotypic characteristics. A total of 36 Salmonella spp. were isolated in this study: 18 isolates from 492 pigs (3.7%) and 18 isolates from 418 (4.3%) farmhouse environmental samples from 16 different pig farms. Of the Salmonella strains isolated from the numerous environmental samples, the highest prevalence was observed in slurry or manure, followed by partitions, farmer's hands, floors, water/nipples, ventilation sources, and feed, respectively. All the Salmonella isolates originating from different farms were genetically distinct. In three farms, however, identical phage types and pulse-field gel electrophoresis patterns were observed among Salmonella isolates from pig feces and environmental samples. This study suggests that environments contaminated with Salmonella could pose an infection risk to pigs on pig farms.

• Journal of Veterinary Clinics
• /
• v.32 no.4
• /
• pp.324-329
• /
• 2015

The primary aim of this study was to investigate biosecurity practices in pig farms and to determine the major risk factors associated with PCV2 infection for a sampled swine population in Korea. To this end, we analyzed data from a cross-sectional study of 296 farrow-to-finish farms, which was conducted between March and September 2014 to explore the prevalence of swine disease at farm level. Face-to-face interviews by on-site visit of trained veterinarians were conducted with the farm owners or managers using a standardized questionnaires with information about basic demographical data and management practices. Farms were classified as negative or positive through the use of infection profiles that combined data on serological testing including PCR antigen test result, antibody titer and sero-conversion pattern at each age category taking into account vaccination status. Data were analyzed using multivariate ordinal logistic regression. Results from this study indicated that biosecurity level of the farms was considered not good given low compliance of the biosecurity programs and facilities in the farm: off-site removal of dead stocks (7%), off-site location of storage facility for incoming feeds (12.6%), off-site pick-up location for finishers (19.3%), restrictions on feed supplier vehicles for farm entrance (19.6%), restriction of finisher trucks entering the farm (22.4%), and restriction on manure disposal trucks entering the farm (26.4%). In the final model (n = 255), allowance of finisher truck driver to the pig unit had increased risk of infection (OR = 2.4, 95% CI 1.22-4.67) whereas farms with a sign forbidding the entrance had decreased risk of infection (OR = 0.19, 95% CI 0.10-0.58). Further comprehensive research with larger sample size is required to better understand the multifactorial characteristic that some predisposing risk factors that were not available in this study. To the best knowledge of the authors, this was the first study to use empirical data to report risk factors associated with PCV2 infection in the Korean pig farms. Results from the current study could be used to decide optimal biosecurity measures to reduce the impact of PCV2 infection to farmers and policy makers.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.12
• /
• pp.2348-2354
• /
• 2016

In recent days, IoT (Internet of Things) technology has been widely used in the field of agriculture, which enables the collection of environmental data and biometric data into the database. The availability of big data on agriculture results in the increase of the machine learning based analysis. Through the analysis, it is possible to forecast agricultural production and the diseases of livestock, thus helping the efficient decision making in the management of smart farm. Herein, we use the environmental and biometric data of Smart Pig farm to derive the accurate relationship model between the environmental information and the daily weight increase of swine and verify the accuracy of the derived model. To this end, we applied the M5P tree algorithm of machine learning which reveals that the wind speed is the major factor which affects the daily weight increase of swine.