• Journal of Broadcast Engineering
• /
• v.27 no.1
• /
• pp.133-145
• /
• 2022

Compared to the continuously increasing dog population and industry size in Korea, systematic analysis of related data and research on breed classification methods are very insufficient. In this paper, an automatic breed classification method is proposed using deep learning technology for 14 major dog breeds domestically raised. To do this, dog images are collected for deep learning training and a dataset is built, and a breed classification algorithm is created by performing transfer learning based on VGG-16 and Resnet-34 as backbone networks. In order to check the transfer learning effect of the two models on dog images, we compared the use of pre-trained weights and the experiment of updating the weights. When fine tuning was performed based on VGG-16 backbone network, in the final model, the accuracy of Top 1 was about 89% and that of Top 3 was about 94%, respectively. The domestic dog breed classification method and data construction proposed in this paper have the potential to be used for various application purposes, such as classification of abandoned and lost dog breeds in animal protection centers or utilization in pet-feed industry.

• Asian-Australasian Journal of Animal Sciences
• /
• v.30 no.11
• /
• pp.1540-1549
• /
• 2017

Objective: Increasing food safety demands in the animal product market have created a need for a system to trace the food distribution process, from the manufacturer to the retailer, and genetic traceability is an effective method to trace the origin of animal products. In this study, we successfully achieved the farm tracing of 6,018 multi-breed pigs, using single nucleotide polymorphism (SNP) markers strictly selected through least absolute shrinkage and selection operator (LASSO) feature selection. Methods: We performed farm tracing of domesticated pig (Sus scrofa) from SNP markers and selected the most relevant features for accurate prediction. Considering multi-breed composition of our data, we performed feature selection using LASSO penalization on 4,002 SNPs that are shared between breeds, which also includes 179 SNPs with small between-breed difference. The 100 highest-scored features were extracted from iterative simulations and then evaluated using machine-leaning based classifiers. Results: We selected 1,341 SNPs from over 45,000 SNPs through iterative LASSO feature selection, to minimize between-breed differences. We subsequently selected 100 highest-scored SNPs from iterative scoring, and observed high statistical measures in classification of breeding farms by cross-validation only using these SNPs. Conclusion: The study represents a successful application of LASSO feature selection on multi-breed pig SNP data to trace the farm information, which provides a valuable method and possibility for further researches on genetic traceability.

• Journal of Information Processing Systems
• /
• v.7 no.4
• /
• pp.717-732
• /
• 2011

Classification in biomedical applications is an important task that predicts or classifies an outcome based on a given set of input variables such as diagnostic tests or the symptoms of a patient. Traditionally the classification algorithms would have to digest a stationary set of historical data in order to train up a decision-tree model and the learned model could then be used for testing new samples. However, a new breed of classification called stream-based classification can handle continuous data streams, which are ever evolving, unbound, and unstructured, for instance--biosignal live feeds. These emerging algorithms can potentially be used for real-time classification over biosignal data streams like EEG and ECG, etc. This paper presents a pioneer effort that studies the feasibility of classification algorithms for analyzing biosignals in the forms of infinite data streams. First, a performance comparison is made between traditional and stream-based classification. The results show that accuracy declines intermittently for traditional classification due to the requirement of model re-learning as new data arrives. Second, we show by a simulation that biosignal data streams can be processed with a satisfactory level of performance in terms of accuracy, memory requirement, and speed, by using a collection of stream-mining algorithms called Optimized Very Fast Decision Trees. The algorithms can effectively serve as a corner-stone technology for real-time classification in future biomedical applications.

• Proceedings of the KIEE Conference
• /
• 1999.07a
• /
• pp.27-30
• /
• 1999

In this paper HEV's are newly classified and a new breed of HEV's, which is called series-parallel compensated configuration is also presented. In this configuration the engine can be operated on constant-speed and constant-torque mode, while the power converter can be small-sized.

• Asian-Australasian Journal of Animal Sciences
• /
• v.26 no.2
• /
• pp.163-170
• /
• 2013

In order to analyze the genetic diversity and phylogenetic status of the Korean Chikso breed, we determined sequences of mtDNA cytochrome b (cyt b) gene and performed phylogenetic analysis using 239 individuals from 5 Chikso populations. Five non-synonymous mutations of a total of 15 polymorphic sites were identified among 239 cyt b coding sequences. Thirteen haplotypes were defined, and haplotype diversity was 0.4709 ranging from 0.2577 to 0.6114. Thirty-five haplotypes (C1-C35) were classified among 9 Asia and 3 European breeds. C2 was a major haplotype that contained 206 sequences (64.6%) from all breeds used. C3-C13 haplotypes were Chikso-specific haplotypes. C1 and C2 haplotypes contained 80.5% of cyt b sequences of Hanwoo, Yanbian, Zaosheng and JB breeds. In phylogenetic analyses, the Chikso breed was contained into B. taurus lineage and was genetically more closely related to two Chinese breeds than to Korean brown cattle, Hanwoo. These results suggest that Chikso and Hanwoo have a genetic difference based on the mtDNA cyt b gene as well as their coat color, sufficient for classification as a separate breed.

• Journal of Veterinary Clinics
• /
• v.39 no.5
• /
• pp.217-225
• /
• 2022

The population of pet cats has increased significantly, from 0.3% in 2002 to 5.6% in 2017. Large-scale feline demographic and disease data from Korea are lacking. The aim of this study was to investigate the demographic data (breed, sex, and age) and disease distribution of cats who visited private veterinary practices in Korea. Data including breed, sex, age, and disease, were compiled from 32,728 electronic medical records from 30 selected private veterinary practices, between January 1, 2016, and December 31, 2017. Diseases were classified based on the International Classification of Diseases 11 by the World Health Organization, and then compared and cross-analyzed according to breed, sex, and age. Korean shorthair was the most common breed. There was a high distribution of young cats, with 77.6% of the cats under 4 years of age, and an average age of 2.5 years. Diagnoses related to preventative medicine were the most frequent and diagnoses common to young cats had higher incidence. This demographic data and information about disease distribution can be used as a basis for future research and may be helpful for determining priorities in the diagnosis of diseases and establishing strategies for health management in cats.

• Journal of Veterinary Science
• /
• v.19 no.6
• /
• pp.725-734
• /
• 2018

Ovaries of 21 bitches presented with gynecopathies were surgically removed and histologically examined. Standard histological, as well as immunohistochemical, classification of 193 cystic structures resulted in the classification of 72 cysts of subsurface epithelial structures (SES), 61 follicular cysts (FCs), 38 cystic rete ovarii (CRO), 13 lutein cysts (LCs), and 9 non-classifiable cysts (NCCs). In addition to the histological classification, results were interpreted according to subject medical history, clinical examination outcome, and macroscopic observations during ovariohysterectomy. Dogs with ovarian cysts (OCs) and associated reproductive perturbations were mostly nulliparous, of large breed, and had an average of $9.5{\pm}3$ years. Prolonged or shortened inter-estrus intervals of past heats, however, seemed to be relatively low-risk factors for the development of OCs in dogs. Furthermore, we provide histological observations of a rarely seen canine LC including a degenerated oocyte in the central cavity.

• Plant Resources
• /
• v.2 no.2
• /
• pp.113-126
• /
• 1999

Through the research of tracheophytes type around Mt. Daedun, we are aiming at figuring out the habitat condition of useful resource plants by the classification of vegetation units and communities using the Z-M phyto-sociological method in the basis of the traits of species composition and by the analysis of vegetation and environment by way of coincidence method. Tracheophytes in our research sites was classifid into 117 family, 475 genus 797, species 102 variety,18 breed, in total to 917 kinds. The forest around Mt. Daedun district was classified into 6 communities, 12 groups, 2 sub-groups according to feature species group, differential species group and differential. Judging the result from the examination of community classification factors by the coincidence method, vegetation unit was decided by altitude and topography.

• Food Science of Animal Resources
• /
• v.41 no.6
• /
• pp.936-949
• /
• 2021

This study discriminated fatty acid profile and flavor characteristics of Beijing You Chicken (BYC) as a precious local breed and Dwarf Beijing You Chicken (DBYC) eggs. Fatty acid profile and flavor characteristics were analyzed to identify differences between BYC and DBYC eggs. Four classification algorithms were used to build classification models. Arachidic acid, oleic acid (OA), eicosatrienoic acid, docosapentaenoic acid (DPA), hexadecenoic acid, monounsaturated fatty acids (MUFA), polyunsaturated fatty acids (PUFA), unsaturated fatty acids (UFA) and 35 volatile compounds had significant differences in fatty acids and volatile compounds by gas chromatography-mass spectrometry (GC-MS) (p<0.05). For fatty acid data, k-nearest neighbor (KNN) and support vector machine (SVM) got 91.7% classification accuracy. SPME-GC-MS data failed in classification models. For electronic nose data, classification accuracy of KNN, linear discriminant analysis (LDA), SVM and decision tree was all 100%. The overall results indicated that BYC and DBYC eggs could be discriminated based on electronic nose with suitable classification algorithms. This research compared the differentiation of the fatty acid profile and volatile compounds of various egg yolks. The results could be applied to evaluate egg nutrition and distinguish avian eggs.

• Asian-Australasian Journal of Animal Sciences
• /
• v.14 no.9
• /
• pp.1203-1208
• /
• 2001

Linzhi Native Pig is a unique local breed recently discovered in the hinterland of Tibet. Its geological distribution, natural environment and ecological conditions have been explored. Using random sampling in typical colony of classification and standard animal-scientific and biogenetic techniques, we examined its contour features, size and weight, reproductive performances, carcass characters, meat quality, fresh-keeping features and the frequency distribution in the 19 structural gene loci encoding enzymes and proteins; according to folklores and Tibetan, Chinese and English history books, the materials and literature of Tibetan Studies, we have analyzed its origin and affirmed the fact that its products have been consumed as Tibetan medicine resources. Our findings make certain that Linzhi Native Pig holds great potential value in economy and culture.