• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.8
• /
• pp.1560-1566
• /
• 2017

Recently, accumulation of data on pig farm is enabled through the wide spread of smart pig farm equipped with Internet-of-Things based sensors, and various machine learning algorithms are applied on the data in order to improve the productivity of pig farm. Herein, multiple machine learning schemes are used to predict the water usage in pig farm which is known to be one of the most important element in pig farm management. Especially, regression algorithms, which are linear regression, regression tree and AdaBoost regression, and classification algorithms which are logistic classification, decision tree and support vector machine, are applied to derive a prediction scheme which forecast the water usage based on the temperature and humidity of pig farm. Through performance evaluation, we find that the water usage can be predicted with high accuracy. The proposed scheme can be used to detect the malfunction of water system which prevents the death of pigs and reduces the loss of pig farm.

• Journal of Environmental Health Sciences
• /
• v.47 no.5
• /
• pp.462-471
• /
• 2021

Background: The number of synthesized chemicals has rapidly increased over the past decade. For many chemicals, there is a lack of information on toxicity. With the current movement toward reducing animal testing, the use of toxicity big data and deep learning could be a promising tool to screen potential toxicants. Objectives: This study identified potential chemicals related to reproductive and estrogen receptor (ER)-mediated toxicities for 1135 cleaning products and 886 laundry products. Methods: We listed chemicals contained in cleaning and laundry products from a publicly available database. Then, chemicals that potentially exhibited reproductive and ER-mediated toxicities were identified using the European Union Classification, Labeling and Packaging classification and ToxCast database, respectively. For chemicals absent from the ToxCast database, ER activity was predicted using deep learning models. Results: Among the 783 listed chemicals, there were 53 with potential reproductive toxicity and 310 with potential ER-mediated toxicity. Among the 473 chemicals not tested with ToxCast assays, deep learning models indicated that 42 chemicals exhibited ER-mediated toxicity. A total of 13 chemicals were identified as causing reproductive toxicity by reacting with the ER. Conclusions: We demonstrated a screening method to identify potential chemicals related to reproductive and ER-mediated toxicities utilizing chemical toxicity big data and deep learning. Integrating toxicity data from in vivo, in vitro, and deep learning models may contribute to screening chemicals in consumer products.

• Korean Journal of Agricultural Science
• /
• v.47 no.4
• /
• pp.1109-1122
• /
• 2020

The aim of this study was to develop a marbling classification and prediction model using small parts of sirloin images based on a deep learning algorithm, namely, a convolutional neural network (CNN). Samples were purchased from a commercial slaughterhouse in Korea, images for each grade were acquired, and the total images (n = 500) were assigned according to their grade number: 1++, 1+, 1, and both 2 & 3. The image acquisition system consists of a DSLR camera with a polarization filter to remove diffusive reflectance and two light sources (55 W). To correct the distorted original images, a radial correction algorithm was implemented. Color images of sirloins of Hanwoo (mixed with feeder cattle, steer, and calf) were divided and sub-images with image sizes of 161 × 161 were made to train the marbling prediction model. In this study, the convolutional neural network (CNN) has four convolution layers and yields prediction results in accordance with marbling grades (1++, 1+, 1, and 2&3). Every single layer uses a rectified linear unit (ReLU) function as an activation function and max-pooling is used for extracting the edge between fat and muscle and reducing the variance of the data. Prediction accuracy was measured using an accuracy and kappa coefficient from a confusion matrix. We summed the prediction of sub-images and determined the total average prediction accuracy. Training accuracy was 100% and the test accuracy was 86%, indicating comparably good performance using the CNN. This study provides classification potential for predicting the marbling grade using color images and a convolutional neural network algorithm.

• Journal of Multimedia Information System
• /
• v.9 no.2
• /
• pp.113-120
• /
• 2022

Mongolian folk songs are inspired by Mongolian labor songs and are classified into long and short songs. Mongolian long songs have ancient origins, are rich in legends, and are a great source of folklore. So it was inscribed by UNESCO in 2008. Mongolian written literature is formed under the direct influence of oral literature. Mongolian long song has 3 classes: ayzam, suman, and besreg by their lyrics and structure. In ayzam long song, the world perfectly embodies the philosophical nature of world phenomena and the nature of human life. Suman long song has a wide range of topics such as the common way of life, respect for ancestors, respect for fathers, respect for mountains and water, livestock and animal husbandry, as well as the history of Mongolia. Besreg long songs are dominated by commanded and trained characters. In this paper, we proposed a method to classify their 3 types of long songs using machine learning, based on their lyrics structures without semantic information. We collected lyrics of over 80 long songs and extracted 11 features from every single song. The features are the name of a song, number of the verse, number of lines, number of words, general value, double value, elapsed time of verse, elapsed time of 5 words, and the longest elapsed time of 1 word, full text, and type label. In experimental results, our proposed features show on average 78% recognition rates in function type machine learning methods, to classify the ayzam, suman, and besreg classes.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.701-702
• /
• 2021

The purpose of the study was to identify fiber changes induced by electrical stimulation of a certain neural substrate in the rat brain. In the stimulation group, the peripheral nerve was injured and the brain area associated to inhibit sensory information was electrically stimulated. There were sham and sham stimulation groups as controls. Then high-field diffusion tensor imaging (DTI) was acquired. 35 features were taken from the DTI measures from 7 different brain pathways. To compare the efficacy of the classification for 3 animal groups, the linear regression analysis (LDA) and the machine learning technique (MLP) were applied. It was found that the testing accuracy by MLP was about 77%, but that of accuracy by LDA was much higher than MLP. In conclusion, machine learning algorithm could be used to identify and predict the changes of the brain white matter in some situations. The limits of this study will be discussed.

• Journal of Life Science
• /
• v.27 no.3
• /
• pp.283-288
• /
• 2017

Porcine circovirus type 2 (PCV2) is a notorious and ubiquitous virus in the swine industry. The susceptibility of the host to PCV2 infection is considered to be one factor associated with the dynamics of PCV2. The objective of this study was to verify the criteria for host susceptibility to PCV2, using blood parameters of post-weaned pigs naturally infected with the virus. The PCV2 DNA viral load, antibody titer, and leukopenia characteristics were measured in the serum extracted from the pigs at the 10th week. We classified the pigs into high (>5.0), intermediate (3.0 to 5.0), and low (<3.0) groups on the basis of the PCV2 viral load (log copies/ml), or as positive (${\leq}0.50$) and negative (>0.50) groups on the basis of antibody titer (sample-to-negative corrected ratio). Moreover, using these two categorized parameters, we suggested the criteria for classification into the susceptible and resistant groups. Statistical analyses revealed that pigs in the susceptible group had a significantly higher viral load (p<0.001) and negative antibody titer (p<0.001), as well as significantly lower leukocyte counts (p=0.018) and lower amounts of several leukocyte components (p<0.05), than pigs in the resistant group. We concluded that the susceptible group could be considered to have PCV2-induced leukopenia. Therefore, we suggest that the combined classifications of viral loads and anti-PCV2 antibodies can be used to determine PCV2-induced leukopenia in the subclinical PCV2 infection of post-weaned pig populations.

• Journal of Animal Science and Technology
• /
• v.59 no.8
• /
• pp.17.1-17.13
• /
• 2017

Background: Omega-3 long-chain (${\geq}C_{20}$) polyunsaturated fatty acids (${\omega}3$ LC-PUFA) confer important attributes to health-conscious meat consumers due to the significant role they play in brain development, prevention of coronary heart disease, obesity and hypertension. In this study, the ${\omega}3$ LC-PUFA content of raw and cooked Longissimus thoracis et lumborum (LTL) muscle from genetically divergent Australian prime lambs supplemented with dietary degummed crude canola oil (DCCO) was evaluated. Methods: Samples of LTL muscle were sourced from 24 first cross ewe and wether lambs sired by Dorset, White Suffolk and Merino rams joined to Merino dams that were assigned to supplemental regimes of degummed crude canola oil (DCCO): a control diet at 0 mL/kg DM of DCCO (DCCOC); 25 mL/kg DM of DCCO (DCCOM) and 50 mL/kg DCCO (DCCOH). Lambs were individually housed and offered 1 kg/day/head for 42 days before being slaughtered. Samples for cooked analysis were prepared to a core temperature of $70^{\circ}C$ using conductive dry-heat. Results: Within raw meats: DCCOH supplemented lambs had significantly (P < 0.05) higher concentrations of eicosapentaenoic (EPA, $20:5{\omega}3$) and EPA + docosahexaenoic (DHA, $22:6{\omega}3$) acids than those supplemented with DCCOM or DCCOC; Dorset sired lambs contained significantly (P < 0.05) more EPA and EPA + DHA than other sire breeds; diet and sire breed interactions were significant (P < 0.05) in affecting EPA and EPA + DHA concentrations. In cooked meat, ${\omega}3$ LC-PUFA concentrations in DCCOM (32 mg/100 g), DCCOH (38 mg/100 g), Dorset (36 mg/100 g), White Suffolk (32 mg/100 g), ewes (32 mg/100 g) and wethers (33 mg/100 g), all exceeded the minimum content of 30 mg/100 g of edible cooked portion of EPA + DHA for Australian defined 'source' level ${\omega}3$ LC-PUFA classification. Conclusion: These results present that combinations of dietary degummed crude canola oil, sheep genetics and culinary preparation method can be used as effective management tools to deliver nutritionally improved ${\omega}3$ LC-PUFA lamb to meat consumers.

• Journal of the Korean Chemical Society
• /
• v.63 no.5
• /
• pp.342-345
• /
• 2019

The standards for the contents of glyphosate and glufosinate in foods are specific and well categorized. However, the standard of content in animal feeds is relatively inadequate and the classification is insufficient. There is also constant debate about the risk of glyphosate and glufosinate to human health, but the risk to animals has not been well studied. In this study, we established an analytical method in feeds that is estimated to be the path for animals to ingest glyphosate. The solvent extraction was carried out using 25% methanol. After centrifugation, samples were purified using solid phase extraction (SPE) and quantitatively analysed using LC-MS/MS after concentrated. Assessment of validation was conducted through detection limits, accuracy, and precision tests. The detection limits for the established method were 1.8 of ${\mu}g/kg$ of glufosinate and $2.4{\mu}g/kg$ of glyphosate. Accuracy was ranged from 94.4% to 103.4% and precision was range from 1.5% to 7.2%. Glufosinate was detected in one sample ($ND{\sim}8.8{\mu}g/kg$) and glyphosate was detected in all but one sample ($ND{\sim}337.0{\mu}g/kg$) by applying the analytical method to animal feeds (n=13).

• Journal of Life Science
• /
• v.30 no.12
• /
• pp.1063-1069
• /
• 2020

Two crucian carp species (Carassius auratus and C. cuvieri) inhabit Lake Yedang in South Korea, and C. auratus is known to be native to Korea. Classification of these two freshwater fish species is often confused because of their morphological similarity. To distinguish the two species, we conducted phylogenetic and population genetic analyses of C. auratus and C. cuvieri based on their mitochondrial DNA sequences of the cytochrome b gene (CYTB). We also compared our partial CYTB sequence (<1,056 bp) with 10 Chinese, nine Japanese, and two Russian crucian carp fishes. The results of our phylogenetic analysis showed that C. auratus and C. cuvieri were clearly divided into two phylogroups. The nucleotide diversity (π) of C. auratus from Korea, China, and Japan showed a range of 0.146%~0.421%, while the range of π of C. cuvieri from Korea and Japan was lower than those of C. auratus (0.0%~0.054%). Moreover, the comparison of CYTB divergence among crucian carp fishes in China, Japan, and Korea indicated that Korean Carassius fishes were distantly related to those from China and Japan, with two exceptions: the pairwise Fst value between Korean C. auratus and northern Chinese C. auratus was not significantly different. In addition, no significant genetic divergence between Korean and Japanese C. cuvieri was detected. We conclude that, despite the morphological similarities, C. auratus and C. cuvieri should be considered as separate freshwater fish resources in conservation efforts for genetic diversity.

• Cartoon and Animation Studies
• /
• s.9
• /
• pp.266-282
• /
• 2005

Cartoon & Animated cartoon is consists of imaginal attributes and linguistic attributes, and it is closely connected with humor and satirical contents. And then various expressions using animals as matter communicate satirical attributes of a satire strongly and easily. On this article, techniques of satirical expression using animals in Cartoon & Animated cartoon media are studied and analyzed. By the method, it looks around briefly beginning from primitive cave paintings of the prehistoric age to various contemporary Cartoon & Animated cartoon character industries as historical background of Cartoon & Animated cartoon, and also arranges various types that literary expression and representation for visual expression techniques - metaphorical expressions, emblematic expressions, figure of speech and so forth - on literature. This attempt aims for presenting a basic analysis method that connecting and combining Cartoon & Animated cartoon media with humanistic classification and making database of existing data. These accumulated data will indicate cartoon and the action of meaning.