• Asian-Australasian Journal of Animal Sciences
• /
• v.13 no.7
• /
• pp.1017-1025
• /
• 2000

The traditional methods for determining the quality of milk, cheese and meat are tedious and expensive, with a significant wastage of chemicals which pollute the environment. To overcome these disadvantages, the potential of near infrared spectrophotometry (NIR) for monitoring the quality of milk and meat has been evaluated by a number of researchers. While most studies indicate that NIR can be used to predict chemical composition of milk and meat, and to monitor the cutting-point during cheese manufacturing, one study demonstrated the potential of NIR to predict sensory characteristics (e.g. hardness and tenderness) of beef. These calibrations were developed on a small number of samples, limiting their value for adoption by the industries. Now that the sophisticated computer software is available, more robust calibrations need to be developed to monitor both chemical and physical characteristics of meat and meat products simultaneously.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.11
• /
• pp.457-464
• /
• 2019

The weight of pig is one of the main factors in determining the health and growth state of pigs, their shipment, the breeding environment, and the ration of feed, and thus measuring the pig's weight is an important issue in productivity perspective. In order to estimate the pig's weight by using the number of pig's pixels from images, acquired from a Top-view camera, the posture determining and the head removal from images are necessary to measure the accurate number of pixels. In this research, we propose the fast and accurate method to determine the pig's posture by using a fast image processing technique, find the head location by using a fast deep learning technique, and remove pig's head by using light weighted image processing technique. First, we determine the pig's posture by comparing the length from the center of the pig's body to the outline of the pig in the binary image. Then, we train the location of pig's head, body, and hip in images using YOLO(one of the fast deep learning based object detector), and then we obtain the location of pig's head and remove an outside area of head by using head location. Finally, we find the boundary of head and body by using Convex-hull, and we remove pig's head. In the Experiment result, we confirmed that the pig's posture was determined with an accuracy of 0.98 and a processing speed of 250.00fps, and the pig's head was removed with an accuracy of 0.96 and a processing speed of 48.97fps.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.05a
• /
• pp.701-702
• /
• 2013

전국 50여개의 AI(Artificial Insemination)센터는 국내 양돈산업 인공수정 기술을 개발하고 보급하는 중추적인 역할을 수행하고 있다. 이에 반해 AI센터의 숫자 규모는 전국적으로 매우 제한되어 있어, AI센터의 운영 및 AI 기술에 대한 정보관리는 각 센터별 독자적인 운영시스템으로 관리되어 상호 정보융합을 통한 양돈산업 발전에 활용되는 사례가 매우 적다. 또한 개별 AI센터에서 관리하고 있는 소비자들의 지역분포도가 매우 폭넓어 실시간으로 수요자에 대한 판매 관리정보를 제공함에 있어 그 한계를 가지고 있다. 이에 본 논문에서는 전국의 AI센터 관리운영에 통합적이고 효율성을 지원할 수 있는 모바일 웹기반 개선된 AI PigMoS(Pig Monitoring System, PigMoS) 시스템을 제안하고 구현하였다. 본 논문에서 제안한 모바일 웹기반 개선된 AI PigMoS 시스템은 이동성, 실시간 정보서비스 등에 해당되는 시스템 모듈을 모바일 웹을 기반으로 구현하여 개별 AI센터에서 운영할 수 있게 하였다. 이에 본 논문에서는 기존의 AI PigMoS 시스템을 개선하여 재구축하였으며, 이동성, 실시간 정보서비스 등이 필요한 모듈을 중심으로 모바일 기능을 설계하고 구현하여, 원거리 소비자들에게 실시간으로 생성된 AI정보를 제공하여 AI센터의 정보관리 효율성과 경쟁력 향상을 높일 것으로 기대한다.

• KIPS Transactions on Computer and Communication Systems
• /
• v.6 no.10
• /
• pp.407-414
• /
• 2017

Pig monitoring applications consisting of many tasks can take advantage of inherent data parallelism and enable parallel processing using performance accelerators. In this paper, we propose a task distribution method for pig monitoring applications into a heterogenous computing platform consisting of a multicore-CPU and a manycore-GPU. That is, a parallel program written in OpenCL is developed, and then the most suitable processor is determined based on the measured execution time of each task. The proposed method is simple but very effective, and can be applied to parallelize other applications consisting of many tasks on a heterogeneous computing platform consisting of a CPU and a GPU. Experimental results show that the performance of the proposed task distribution method on three different heterogeneous computing platforms can improve the performance of the typical GPU-only method where every tasks are executed on a deviceGPU by a factor of 1.5, 8.7 and 2.7, respectively.

• The Plant Pathology Journal
• /
• v.15 no.3
• /
• pp.137-143
• /
• 1999

A novel chromosomal gene tagging technique using a specific fragment of the fatty acid desaturase-like open reading frame (des-like ORF) from the tox-argK gene cluster of Pseudomonas syringae pv. phaseolicola was developed to identify Xanthomonas spp.released into the environment as biocontrol agents. X. campestris pv. convolvuli FB-635, a pathogen of Convolvulus arvensis L., (bindweed), was chosen as the organism in which to develop and test the system. A 0.52 kb DES fragment amplified from P. syringae pv. phaseolicola C-199 was inserted into pGX15, a cosmid clone containing a 10.3 kb Eco RI-HindIII fragment derived from the xanthomonadin biosynthetic gene cluster contained in plasmid pIG102, to create a pigG::DES insertion. The 10.8 kb EcoRI-BamHI fragment carrying the pigG:: DES insertion was cloned into pLAFR3 to generate pLXP22. pLXP22 was then conjugated into X. campestris pv. convolvuli FB-635 and the pigG::DES insertion integrated into the bacterial chromosome by marker exchange. Rifampicin resistant, tetracycline sensitive, starch hydrolyzing, white colonies were used to differentiate the marked strain from yellow pigmented wild-type ones. PCR primers specific for the unique DES fragment were used for direct detection of the marked strain. Result showed the marked strain could be detected at very low levels even in the presence of high levels of other closely related or competitive bacteria. This PCR-based DES-tagging system provides a rapid and specific tool for directly monitoring the dispersal and persistence of Xanthomonas spp.released into the environment.

• Journal of Soil and Groundwater Environment
• /
• v.23 no.1
• /
• pp.30-40
• /
• 2018

To evaluate potential impacts of shallow groundwater by the leachate from buried carcass, we investigated hydrochemical characteristics of both leachate and shallow groundwater from monitoring wells and surrounding shallow groundwater wells in an area potentially affected by pig carcass burial. The hydrochemical survey was conducted before and after the relocation of a burial pit. The leachate samples and the groundwater affected by leachate showed the hydrochemistry of $Ca-HCO_3$ type with high $NH_4{^+}$ concentrations, while unaffected groundwater was mostly the $Ca(Na)-Cl+NO_3$ type due to pervasive impacts from agrochemicals. The results of factor analysis on hydrochemical data showed the followings: 1) contamination of groundwater from agro-livestock farming and livestock burial are coexisting in the study area, 2) among ionic species, $HCO_3{^-}$, $NH_4{^+}$, $NO_3{^-}$ and Mn are very useful to differentiate the groundwater contamination from leachate, and 3) groundwater contamination by leachate has been recognized around the monitoring wells even after the relocation of a burial pit, likely due to residual contaminants in surrounding soils. Therefore, it is suggested that continued monitoring of groundwater contamination should be conducted after the relocation of carcass burial pits.

• KIPS Transactions on Computer and Communication Systems
• /
• v.5 no.10
• /
• pp.319-326
• /
• 2016

Abnormal situation caused by aggressive behavior of pigs adversely affects the growth of pigs, and comes with an economic loss in intensive pigsties. Therefore, IT-based video surveillance system is needed to monitor the abnormal situations in pigsty continuously in order to minimize the economic demage. In this paper, we propose a new Kinect camera-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 moving-pigs are labeled as regions of interest. 3) A contour method is proposed and applied to solve the touching-pigs problem in the Kinect-depth image. The experimental results with the depth videos obtained from a pig farm located in Sejong illustrate the efficiency of the proposed method.

• Reproductive and Developmental Biology
• /
• v.33 no.3
• /
• pp.139-146
• /
• 2009

This study tried to develop the system (device) that automatically notify a manager of condition just before and after farrowing to extend ubiquitous-based technology and to increase efficiency of delivery care and productivity by reducing human labor and time on standby when farrowing management is done in the difficult and hard working environment of farrowing such as night or holidays in field sand especially in pig industry. In this test, selected 10 gilts were executed timed artificial insemination and were set up each temperature sensor and load sensor to them 3 days before the estimated farrowing day and were observed the farrowing situation. This study was embodied the NESPOT-based (KT Corporation) monitoring system, the system to transmit data in real time by utilization of wireless LAN and the sensor module to apply the ubiquitous environment to them. And this study was observed the situation to automatically notify situations of 10 gilts that first bore just before and after farrowing. The result obtained the farrowing situations of them in real time by setup of the NESPOT-based monitoring system to check farrowing situation directly is as follow. The average time of the automatic notice about situation just before farrowing by the temperature sensor was 27.5 minutes before the beginning of farrowing (the expulsion time of a piglet). 6 of 8 pregnant gilts that first bore automatically were notified situations just before farrowing and the temperature sensors inserted into 2 ones before farrowing were omitted. (The automatic notice rate 75%) The average time of the automatic notice of situation just after farrowing by the load sensor was taken 46.5 minutes after the beginning of farrowing (the expulsion time of a first piglet). The average gestation period of 8 ones that first bore and were tested by the automatic notice of farrowing situation was 115.6 days. This result found that the automatic farrowing notice system by the temperature sensor is more efficient than the load sensor as the automatic farrowing alarm device and sanitary treatment and improvement of the omission rate were required.

• 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.

• Korean Journal of Veterinary Service
• /
• v.45 no.3
• /
• pp.191-199
• /
• 2022

We investigated the virulence genes, O-serotypes, antimicrobial resistance of pathogenic E. coli isolated from carcasses (n=455) and environmental (n=372) samples of 11 cattle and 12 pig slaughterhouses from December 2020 to December 2021. E. coli were isolated from nine carcasses (2.0%), three slaughter facilities (1.4%), two utensils (2.7%) and three abattoir workers (3.5%) from four cattle and four pig slaughterhouses. Among all isolates, 13 STEC (76.5%) were identified, followed by four EPEC (23.5%). As a result of the antibiotic susceptibility test, all isolates were resistant to at least one antimicrobial, of which 70.6% isolates showed multidrug resistance patterns. The serotypes were diverse in pigs compared to cattle, with serotypes O18, O66, O109 in cattle and O9, O76, O85, O100, O153, and O159 in pigs. In a single cattle slaughterhouse, eight STEC O66 were isolated from various types of sample (4 slaughter animal surfaces, 3 gloves, and 1 knife) with two antimicrobial resistance patterns (CHL-FIS-STR and CHL-FIS). Those two types of strain were suspected cross-contamination from utensils to slaughter animal surfaces. These results showed that pathogenic E. coli were detected in carcasses and various environmental samples in cattle and pig slaughterhouses. Nationwide monitoring and hygiene management are required to prevent cross-contamination of STEC isolate slaughterhouses.