• 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.

• Journal of Korea Water Resources Association
• /
• v.44 no.4
• /
• pp.275-283
• /
• 2011

A local or site-specific water temperature is downscaled from the nation-wide air temperature that represents simulation by General Circulation Model (GCM). Both two-step and one-step method are tested and compared in three sites: Masan Bay, Lake Sihwa, and Nakdong River Estuary. Two-step method uses a linear regression model as the first step that converts nation-wide air temperature into local air temperature, and the corresponding coefficient of determination is in the range of 0.98~0.99. The second step that converts air temperature into water temperature uses a nonlinear curve, so called S-curve, and the corresponding root mean squared error (RMSE) is 2.07 for rising limb in Masan Bay, 1.93 for falling limb in Masan Bay, 2.59 for Lake Sihwa, and 1.58 for Nakdong River Estuary. In a similar way, one-step method is performed to directly convert nation-wade air temperature into local water temperature, and the corresponding RMSE is 2.28 for rising limb in Masan Bay, 1.89 for falling limb in Masan Bay, 2.55 for Lake Sihwa, and 1.52 for Nakdong River Estuary. Consequently both methods show a similar level of performance, and one-step method is recommendable in that it is simple and practical in relative terms.

• Asian-Australasian Journal of Animal Sciences
• /
• v.27 no.10
• /
• pp.1406-1410
• /
• 2014

Age at first calving is an important trait for achieving earlier reproductive performance. To detect quantitative trait loci (QTL) for reproductive traits, a genome wide association study was conducted on the 96 Hanwoo cows that were born between 2008 and 2010 from 13 sires in a local farm (Juk-Am Hanwoo farm, Suncheon, Korea) and genotyped with the Illumina 50K bovine single nucleotide polymorphism (SNP) chips. Phenotypes were regressed on additive and dominance effects for each SNP using a simple linear regression model after the effects of birth-year-month and polygenes were considered. A forward regression procedure was applied to determine the best set of SNPs for age at first calving. A total of 15 QTL were detected at the comparison-wise 0.001 level. Two QTL with strong statistical evidence were found at 128.9 Mb and 111.1 Mb on bovine chromosomes (BTA) 2 and 7, respectively, each of which accounted for 22% of the phenotypic variance. Also, five significant SNPs were detected on BTAs 10, 16, 20, 26, and 29. Multiple QTL were found on BTAs 1, 2, 7, and 14. The significant QTLs may be applied via marker assisted selection to increase rate of genetic gain for the trait, after validation tests in other Hanwoo cow populations.

• Physical Therapy Korea
• /
• v.24 no.2
• /
• pp.76-91
• /
• 2017

Background: Agricultural work is physically demanding and is associated with a high frequency of musculoskeletal disorders. It is challenging to comprehensively understand the present status of work-related diseases and injuries among farmers in underdeveloped countries. Objects: This study aimed to elucidate the current status of work-related musculoskeletal disorders in local farmers in Tigray, Ethiopia, and identify the agricultural factors associated work-related musculoskeletal pain (AFWMP) and healthy living and healthy behavior factors associated work-related musculoskeletal pain (HFWMP). Methods: The Institute for Poverty Alleviation and International Development at Yonsei University conducted a survey of 126 households in Tigray, Ethiopia in 2014. A total of 116 individuals (73 men, 43 women) representing each household answered the questionnaires. Results: 1) Work-related musculoskeletal pain (WMSP) most commonly occurred when performing heavy lifting and most frequently occurred in the lower back. 2) Age, self-perceived labor intensity, and months of farming work were significantly higher in the pain group than those in the non-pain group. 3) Overall work-related musculoskeletal pain intensity (WPI) showed positive and negative correlations with years of farming experience and self-perceived health status, respectively. 4) In binary logistic regression, the occurrence of WMSP showed significant associations with self-perceived labor intensity. 5) On multiple linear regression analysis, age, months of farming work, and self-perceived health status had a significant impact on overall WPI. Conclusion: The WMSP of farmers in Tigray, Ethiopia was related to the characteristics of farm working and health status. Furthermore, HFWMP and AFWMP were the chief factors affecting the occurrence of WMSP in farmers in Tigray. Therefore, both HFWMP and AFWMP should be considered for clinical health assessments of farmers with WMSP in underdeveloped African countries.

• Journal of Medicine and Life Science
• /
• v.20 no.3
• /
• pp.107-114
• /
• 2023

Epidemiological control of coronavirus disease 2019 (COVID-19) is needed to estimate the infection period of confirmed cases and identify potential cases. The present study, targeting confirmed cases for which the time of COVID-19 symptom onset was disclosed, aimed to investigate the relationship between intervals (day) from symptom onset to testing the cycle threshold (CT) values of real-time reverse transcription-polymerase chain reaction. Of the COVID-19 confirmed cases, those for which the date of suspected symptom onset in the epidemiological investigation was specifically disclosed were included in this study. Interval was defined as the number of days from symptom onset (as disclosed by the patient) to specimen collection for testing. A locally weighted regression smoothing (LOWESS) curve was applied, with intervals as explanatory variables and CT values (CTR for RdRp gene and CTE for E gene) as outcome variables. After finding its non-linear relationship, a polynomial regression model was applied to estimate the 95% confidence interval values of CTR and CTE by interval. The application of LOWESS in 331 patients identified a U-shaped curve relationship between the CTR and CTE values according to the number of interval days, and both CTR and CTE satisfied the quadratic model for interval days. Active application of these results to epidemiological investigations would minimize the chance of failing to identify individuals who are in contact with COVID-19 confirmed cases, thereby reducing the potential transmission of the virus to local communities.

• Proceedings of the KSRS Conference
• /
• v.1
• /
• pp.305-307
• /
• 2006

A multi-spectral photometer was set up as an NASA/AERONET site at Kinki University campus in Higashi-Osaka in 2002 for measuring urban aerosols. In addition, the SPM-613D (Kimoto Electric) commenced measurement of suspended particles matter (SPM) as $PM_{10}$ and $PM_{2.5}$ on March 15, 2004 at the same AERONET site. The obtained results revealed that the poor air quality of the Higashi-Osaka site is due not only to anthropogenic particles from local emissions, such as diesel vehicles and chemical industries, but also to dust particles brought from continental desert areas by large scale climatic conditions. To understand the characteristics of background atmosphere over Higashi-Osaka, we examined the relationship between $PM_{2.5}$ concentration and aerosol optical thickness (AOT) at a wavelength of 0.87 μm based on AERONET data for background atmosphere (AOT<0.2). We obtained a linear regression line between AOT and $PM_{2.5}$ concentration. Using the linear relationships between AOT and $PM_{2.5}$, we show ground-level concentrations of $PM_{2.5}$ of background atmosphere from Terra/MODIS satellite measurements.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.24 no.6
• /
• pp.206-216
• /
• 2020

As the number of aging railway bridges in Korea increases, maintenance costs due to aging are increasing and continuous management is becoming more important. However, while the number of old facilities to be managed increases, there is a shortage of professional personnel capable of inspecting and diagnosing these old facilities. To solve these problems, this study presents an improved model that can detect Local damage to structures using machine learning techniques of AI technology. To construct a damage detection machine learning model, an analysis model of the bridge was set by referring to the design drawing of a non-ballasted plate-girder railroad bridge. Static strain data according to the damage scenario was extracted with the analysis model, and the Local damage index based on the reliability of the bridge was presented using statistical techniques. Damage was performed in a three-step process of identifying the damage existence, the damage location, and the damage severity. In the estimation of the damage severity, a linear regression model was additionally considered to detect random damage. Finally, the random damage location was estimated and verified using a machine learning-based damage detection classification learning model and a regression model.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.20 no.1
• /
• pp.34-41
• /
• 2008

Future impact of anthropogenic climate-induced change on ecological regime has been an issue and information on water temperature is required for estimating coastal aquatic environment. One way to induce water temperature is to relate water temperature to air temperature and GCM is able to provide future air temperature data to do this. However, GCM data of low spatial resolution doesn't incorporate local or sitespecific air temperature in need of application, and downscaling processes are essential. In this study, a linear regression is used to relate nationally averaged air temperature to local area for the time period of 2000-2005. The RMSE for calibration (2000-2005) is 1.584, while the RMSE for validation is 1.675 for the year 2006 and 1.448 for the year 2007. The NSC for calibration (2000-2005) is 0.962, while the NSC for validation is 0.955 for the year 2006 and 0.963 for the year 2007. The results show that the linear regression is a good tool to relate local air temperature to nationally averaged air temperature with $1.0{\sim}2.0^{\circ}C$ of RMSE. The study will contribute to estimate future impact of climate-induced change on aquatic environment in Korean coastal zone.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.24 no.1
• /
• pp.92-111
• /
• 2021

As fine dust negatively affects disease, industry and economy, the people are sensitive to fine dust. Therefore, if the occurrence of fine dust can be predicted, countermeasures can be prepared in advance, which can be helpful for life and economy. Fine dust is affected by the weather and the degree of concentration of fine dust emission sources. The industrial sector has the largest amount of fine dust emissions, and in industrial complexes, factories emit a lot of fine dust as fine dust emission sources. This study targets regions with old industrial complexes in local cities. The purpose of this study is to explore the factors that cause fine dust and develop a predictive model that can predict the occurrence of fine dust. weather data and fine dust data were used, and variables that influence the generation of fine dust were extracted through multiple regression analysis. Based on the results of multiple regression analysis, a model with high predictive power was extracted by learning with a machine learning regression learner model. The performance of the model was confirmed using test data. As a result, the models with high predictive power were linear regression model, Gaussian process regression model, and support vector machine. The proportion of training data and predictive power were not proportional. In addition, the average value of the difference between the predicted value and the measured value was not large, but when the measured value was high, the predictive power was decreased. The results of this study can be developed as a more systematic and precise fine dust prediction service by combining meteorological data and urban big data through local government data hubs. Lastly, it will be an opportunity to promote the development of smart industrial complexes.

• Journal of Agricultural Extension & Community Development
• /
• v.28 no.1
• /
• pp.41-52
• /
• 2021

It is important to understand the factors that affect the business performance of insect farm for continuous insect farm management. The purpose of this study is to investigate factors influencing the business performance of insect farm. For this study, 1,577 questionnaires were collected through a telephone survey targeting insect farm owner. As a result of analysis using linear multiple regression analysis, the factors affecting total sales were gender, age, business experience, number of workers, and national and local government support projects. The factors affecting the net profit rate were age, business experience, number of workers, national and local government support projects, and education. When the gender of the business operator is male, it only affected the increase in total sales, and it was found that both the total sales amount and the net profit margin increased with the younger the business operator's age.