• The Journal of the Korea Contents Association
• /
• v.18 no.2
• /
• pp.1-10
• /
• 2018

Aggression among pigs adversely affects economic returns and animal welfare in intensive pigsties. Recently, some studies have applied information technology to a livestock management system to minimize the damage resulting from such anomalies. Nonetheless, detecting each pig in a crowed pigsty is still challenging problem. In this paper, we propose a new Kinect camera and deep learning-based monitoring system for the detection of the individual pigs. The proposed system is characterized as follows. 1) The background subtraction method and depth-threshold are used to detect only standing-pigs in the Kinect-depth image. 2) The standing-pigs are detected by using YOLO (You Only Look Once) which is the fastest and most accurate model in deep learning algorithms. Our experimental results show that this method is effective for detecting individual pigs in real time in terms of both cost-effectiveness (using a low-cost Kinect depth sensor) and accuracy (average 99.40% detection accuracies).

• Asian-Australasian Journal of Animal Sciences
• /
• v.13 no.10
• /
• pp.1394-1398
• /
• 2000

This experiment was carried out to examine the seasonal changes in feed intake and feeding behavior in Korean spotted deer under farmed condition to obtain basic information for efficient feeding management. The seasonal daily gain was the highest (p<0.05) in summer and the lowest (p<0.05) in winter. Dry matter intake (DMI) was the highest (p<0.05) in spring (2,685 g/day) and the lowest in winter (1,929 g/day). Intake of roughage in the DMI was the greatest in spring and that in winter was significantly lower (p<0.05) than in spring. Also DMI, expressed in terms of metabolic body weight ($kgW^{0.75}$), was 85.5 g, 70.6 g, 70.9 g and 65.1 g for spring, summer, autumn and winter, respectively, and thus was the highest in spring and the lowest in winter (p<0.05). Deer exhibited similar eating patterns, comparatively short and frequent periods, in all seasons. They showed comparatively intensive patterns of rumination during midnight for autumn and winter and relatively continuous patterns of chewing activity during spring and summer. There were no significant differences in seasonal eating time and ruminating time. However, exercise time was the greatest for winter and the lowest for summer and there was a significant difference (p<0.05) between summer and winter. Although not significant, eating time per 100 gDM ingested tended to be short in spring and summer and long in autumn and winter. Ruminating time per 100 gDM ingested was the shortest (p<0.05) in spring compared with in other seasons. The conclusion can be drawn that since deer have seasonal differences in feed intake and feeding habits, it is necessary to establish and develop an efficient feeding system for deer.

• Asian-Australasian Journal of Animal Sciences
• /
• v.33 no.7
• /
• pp.1209-1216
• /
• 2020

Objective: The present study aimed to evaluate the performance of odor abatement by using two different ventilation-biofilter systems with recycled stablized swine wastewater. Methods: The performance of odor removal efficiency was evaluated using two different ventilation-biofilter-recycled wastewater arrangements. A recirculating air-flow ventilation system connected to a vertical biofilter (M1) and a plug-flow ventilation system connected to a horizontal biofilter (M2) were installed. Water dripping over the surface of the biofilter was recycled at a flow rate of 0.83 L/h in summer and 0.58 L/h in winter to reduce odorous compounds and particulate matter (PM). The experiments were performed for 64 days with M1 and M2 to investigate how these two ventilation-biofilter systems influenced the reduction of odor compounds in the model houses. Odorous compounds, NH₃ and volatile organic compounds (VOCs) were analyzed, and microclimatic variables such as temperature, humidity, and PM were monitored. Results: Ammonia concentration inside M1 was about 41% higher on average than that in M2. PM and total suspended particles (TSPs) inside M1 were about 62.2% and 69.9%, respectively, higher than those in M2. TSPs in the model house were positively correlated with the concentration of NH₃ and VOCs. Conclusion: M2 emitted lower concentration of odorous compounds than M1. Moreover, M2 could maintain the optimum temperature condition for a swine house during the cooler season. The plug-flow ventilation-horizontal biofilter system could be used for pig houses to minimize air pollution produced by swine farming activities and maintain optimum microclimate conditions for pigs.

• Asian-Australasian Journal of Animal Sciences
• /
• v.10 no.4
• /
• pp.435-438
• /
• 1997

Twelve newborn goat kids born of philippine does (3.5 and 5 years old) were used in this study. Four mother (candidate) doe goats were randomly allocated to each group. The mother does were infected orally with three levels (0, 15,000 and 30,000 larvae) of infective Haemonchus contortus larvae. Before infection all animals were housed in individual pens with concrete floors. They were provided with a uniform management. Estrus of does were synchronized using PGF2 alpha. All the animals were bred naturally by the same buck. Baby goat born of infected mother goats were divided into three groups. $T_1$, $T_2$ and $T_3$), respectively, from mother treatment groups. Birth weight and growth of goat kids born from H. contortus infected mother goats were determined. Birth weights of kids of $T_1$, $T_2$ and $T_3$ were 1.9, 1.5 and 1.2 kg, respectively. No significant (p > 0.05) differences in birth weight of kids for the 3 treatment groups were found. However, significant (p < 0.05) effects of stomach worm infection and duration of infection on liveweight gain of kids were observed. After second and third week of birth, respectively, the kids of groups 3 and 2 registered lover liveweight gains than the kids in control group. However, no significant (p > 0.05) difference in liveweight gain was found between the kids of infected mother does. Fecal egg counts of the infected mother does showed patent infections which also indicated by postmortem worm counts. However, no worm egg was found in the feces of the test kids.

• Asian-Australasian Journal of Animal Sciences
• /
• v.20 no.5
• /
• pp.661-668
• /
• 2007

Data on 1,037 Nili-Ravi buffaloes from four institutional herds were used to study lifetime milk yield, herd life, productive life and breeding efficiency. A general linear model was used to study the environmental effects while an animal model having herd, year of birth and age at first calving (as covariate) along with random animal effect was used to estimate breeding values. The lifetime milk yield, herd life, productive life and breeding efficiency averaged $7,723{\pm}164$ kg, $3,990{\pm}41$ days, $1,061{\pm}19$ days and 64 percent, respectively. All the traits were significantly (p<0.01) affected by the year of birth and herd of calving, while the herd life was also affected (p<0.01) by the age at first calving. The heritabilities for lifetime milk yield, herd life, productive life and breeding efficiency were $0.093{\pm}0.056$, $0.001{\pm}0.055$, $0.144{\pm}0.079$ and 0.001, respectively. The definition for productive life, where each lactation gets credit upto 10 months had slightly better heritability and may be preferred over the definition where no limit is placed on lactation length. The genetic correlation between productive life and lifetime milk yield was low but high between productive life and herd life. The selection for productive life will increase herd life while lifetime milk yield will also improve. The overall phenotypic trend during the period under the study was negative for lifetime milk yield (-280 kg/year), herd life (-93 days), productive life (-42 days/year) and breeding efficiency (-0.36 percent/year), whereas the genetic trend was positive for lifetime milk yield (+15 kg/year) and productive life (+4 days/year).

• 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.

• Journal of Veterinary Clinics
• /
• v.23 no.4
• /
• pp.453-457
• /
• 2006

This study determined the effects of several reproductive factors at prostaglandin $F_{2{\alpha}}\;(PGF_{2{\alpha}})$ administration on the subsequent estrous exhibition and conception. Three hundreds and twenty six dairy cows in seven dairy herds received a 25 mg $PGF_{2{\alpha}}$ after confirming the presence of corpus luteum (CL) by ultrasonography, and the cows exhibited estrus within 7 days following $PGF_{2{\alpha}}$ administration were artificially inseminated (AI). Two hundreds cows among the 326 cows received additional ultrasonography at $PGF_{2{\alpha}}$ administration to measure the diameters of the largest follicle and CL on ovaries, and blood samples collected from the cows were analyzed for serum progesterone (P4) level. Cow parity, days open, body condition score (BCS), season and herd variables were recorded. Of the treated 326 cows, 171 cows (52.5%) showed estrus within 7 days after treatment, and the conception rate following AI was 37.4% (64/171). There were significant differences on the estrous exhibition ($31.3{\sim}65.8%$, p<0.01) and conception rates ($23.1{\sim}66.7%$, p<0.05) among the herds, while cow parity, days open, BCS and season did not affect the subsequent estrous exhibition and conception rates. The diameters of the largest follicle and CL on ovaries, and serum P4 level at the $PGF_{2{\alpha}}$ administration were not related to the subsequent estrous exhibition and conception. The results indicate that the improved outcomes of synchronization of estrus using a single $PGF_{2{\alpha}}$ administration may be related to the appropriate management of the herd.

• Korean Journal of Agricultural Science
• /
• v.46 no.4
• /
• pp.907-914
• /
• 2019

Ammonia (NH₃) that reacts with nitric or sulfuric acid in the air is the major culprit contributing to the formation of fine particulate matter (PM_2.5). NH₃ volatilization mainly originates from nitrogen fertilizer and livestock manure applied to arable soil. Cation exchange capacity (CEC) of peat moss (PM) and zeolite (ZL) is high enough to adsorb ammonium (NH₄⁺) in soil. Therefore, they might inhibit volatilization of NH₃. The objective of this study was to compare the effect of PM and ZL on NH₃ volatilization from upland soil. For this, a laboratory experiment was carried out, and NH₃ volatilization from the soil was monitored for 12 days. PM and ZL were added at the rate of 0, 1, 2, and 4% (wt wt^-1) with 354 N g m^-2 of urea. Cumulative NH₃-N volatilization decreased with increasing addition rate of both materials. Mean value of cumulative NH₃-N volatilization across application rate with PM was lower than that with ZL. CEC increased with increasing addition rate of both materials. While the soil pH increased with ZL, it decreased with PM. Increase in CEC resulted in NH₄⁺ adsorption on the negative charge of the external surface of both materials. In addition, decrease in soil pH hinders the conversion of NH₄⁺ to NH₃. Based on the above results, the addition of PM or ZL could be an optimum management to reduce NH₃ volatilization from the soil. However, PM was more effective in decreasing NH₃ volatilization than ZL due to the combined effect of CEC and pH.

• Asian-Australasian Journal of Animal Sciences
• /
• v.13 no.3
• /
• pp.348-355
• /
• 2000

The study was conducted to determine physicochemical parameters in various physical fractions (linter, hull, kernel, oil and meal) of cottonseed of different varieties (MNH 147, CIM 240, NIAB 78, FH 87, CIM 109, MNH 93, FH 682, GOHAR 87, SLS 1 and B 557). Average components of linter, hull, and kernel in different varieties of cotton were 12.21, 28.24 and 70.42%, respectively. Average percentage of meal and oil was 48.97 and 22.09% in seed, and 69.28 and 30.72% in kernel, respectively. Maximum percentage of meal was recovered from variety CIM 240 and lowest in variety CIM 109. Statistical analysls revealed variety differences (p<0.05) in seed and it's components. Average contents of crude protein, crude fiber and ash was 22.31, 17.74 and 4.27% in seed, 2.85, 56.50 and 2.61% in hull; 32.62, 3.45 and 4.01 % in kernel; 47.15, 5.00 and 5.78% in meal, respectively. Average contents of Ca, p, Mg, K, Na and Cl were 0.09, 0.22, 0.26, 0.65, 0.009 and 0.035% in seed; 0.12, 0.07, 0.09, 0.51, 0.020 and 0.034% in hull and 0.16, 0.59, 0.32, 1.01, 0.03 and 0.07% in meal of different varieties of cotton, respectively. Fe, Zn, Cu and Mn were 141.35, 24.55, 186.50 and 27.12 mg/kg in seed; 158.48, 2.06, 74.60, and 22.17 mg/kg in hulls; and 167.62, 20.30, 185.83 and 20.67 mg/kg in meal, respectively. Significant varietal differences were observed in proximate composition and mineral contents of cottonseeds and derived products. Cottonseeds and their products of varieties FH 87, CIM 109 and MNH 93 showed higher nutrient density while lower was observed in varieties CIM 240, SLS I and FH 682.

• Food Science of Animal Resources
• /
• v.35 no.1
• /
• pp.108-113
• /
• 2015

The purpose of this study was to develop predictive models for the growth of Listeria monocytogenes in pork Bulgogi at various storage temperatures. A two-strain mixture of L. monocytogenes (ATCC 15313 and isolated from pork Bulgogi) was inoculated on pork Bulgogi at 3 Log CFU/g. L. monocytogenes strains were enumerated using general plating method on Listeria selective medium. The inoculated samples were stored at 5, 15, and $25^{\circ}C$ for primary models. Primary models were developed using the Baranyi model equations, and the maximum specific growth rate was shown to be dependent on storage temperature. A secondary model of growth rate as a function of storage temperature was also developed. As the storage temperature increased, the lag time (LT) values decreased dramatically and the specific growth rate of L. monocytogenes increased. The mathematically predicted growth parameters were evaluated based on the modified bias factor ($B_f$), accuracy factor ($A_f$), root mean square error (RMSE), coefficient of determination ($R^2$), and relative errors (RE). These values indicated that the developed models were reliably able to predict the growth of L. monocytogenes in pork Bulgogi. Hence, the predictive models may be used to assess microbiological hygiene in the meat supply chain as a function of storage temperature.