• Journal of Bio-Environment Control
• /
• v.18 no.1
• /
• pp.15-22
• /
• 2009

Adequate environment conditions with growth stage of potato were decided in a photoautotrophic micropropagation system using models. Total 20 day-period of growth were divided into three growth periods such as 6 (stage 1), 7(stage 2), and 7(stage 3) days. At the 1st stage, no significant differences were observed in the growth of potato plantlets at various photosynthetic photon flux density (PPFD) and $CO_2$ conditions. Considering damaged leaves, $80\;mmol{\cdot}m^{-2}{\cdot}s^{-1}$ PPFD and ambient $CO_2$ level were adequate in this stage. At the 2nd stage, significant differences were partly observed in several growth characteristics including dry weight. Based on the dry matter model, over $240\;mol{\cdot}m^{-2}{\cdot}s^{-1}$ PPFD was too high to cultivate potato plantlets at this stage due to the occurrence of damaged leaves. Considering both plant growth and energy efficiency, $160\;mol{\cdot}m^{-2}{\cdot}s^{-1}$ PPFD and $700\;mol{\cdot}mol^{-1}\;CO_2$ were selected for the adequate combination. At the 3rd stage, the biomass accumulation was significantly induced in potato plantlets under higher levels of PPFD and $CO_2$ concentration as suggested by increased fresh and dry weights. However, we could not find the saturated point with regard to dry matter due to continuous increase of dry mater even under maximum PPFD ($320\;mmol{\cdot}m^{-2}{\cdot}s^{-1})$. Thus, $320\;mol{\cdot}m^{-2}{\cdot}s^{-1}$ PPFD and $1800\;mol{\cdot}mol^{-1}\;CO_2$ were considered as the best choice at final stage in this study. In conclusion, even though the growth period of micropropagated potato plantlets was quite a short, favorable environmental conditions required at each growth stage were different. This technique could improve the growth of micropropagated plantlets compared to the conventional micropropagation and apply to other agriculturally important crops as well as potato in the future.

• Journal of Life Science
• /
• v.21 no.2
• /
• pp.322-327
• /
• 2011

The effects of green tea consumption and/or exercise for 12weeks on body weight and select biochemical markers in plasma were evaluated in obese adolescents with a fat ratio of greater than 25%. The subjects were randomly divided into a control group (n=9), green tea consumption group (n=9), exercise group (n=9) and green tea consumption with exercise group (n=9). Subjects in both green tea consumption group and green tea consumption with exercise group were given more than five cups of green tea extract in hot water ($90^{\circ}C$) daily, equivalent to 1.5-1.7 g dry green tea, for 12 weeks. Subjects in both the exercise group and green tea consumption with exercise group participated in a training program (HRmax 60-70%, 60 min/day) for 12 weeks. Control subjects were only given water equal to the quantity of green tea being given to the subjects of green tea consumption. No significant changes body weights were seen in any of these treatments, but the waist to hip ratio was reduced with treatments of both green tea and exercise. The control group showed no significant changes in TNF-$\alpha$, IL-6 and leptin levels. Green tea consumption reduced leptin (p<0.05), TNF-$\alpha$, and leptin levels. Exercise lowered TNF-$\alpha$ (p<0.05), IL-6 (p<0.01), and leptin (p<0.05) concentrations. Meanwhile, a combination of green tea consumption and exercise lowered TNF-$\alpha$, IL-6 (p<0.05) and leptin (p<0.05) levels. These results indicate that green tea consumption and exercise both had a positive effect on the reduction of inflammatory cytokines, TNF-$\alpha$, IL-6 and leptin, in obese adolescents, but no synergistic effect on the reduction of these cytokines.

• Journal of Practical Agriculture & Fisheries Research
• /
• v.23 no.1
• /
• pp.89-104
• /
• 2021

Based on the TF-IDF weighted value that evaluates the importance of words that play a key role, the semantic network analysis(SNA) was conducted on the self-introduction letter of freshman at Korea National College of Agriculture and Fisheries(KNCAF) in 2020. The top three words calculated by TF-IDF weights were agriculture, mathematics, study (Q. 1), clubs, plants, friends (Q. 2), friends, clubs, opinions, (Q. 3), mushrooms, insects, and fathers (Q. 4). In the relationship between words, the words with high betweenness centrality are reason, high school, attending (Q. 1), garbage, high school, school (Q. 2), importance, misunderstanding, completion (Q.3), processing, feed, and farmhouse (Q. 4). The words with high degree centrality are high school, inquiry, grades (Q. 1), garbage, cleanup, class time (Q. 2), opinion, meetings, volunteer activities (Q.3), processing, space, and practice (Q. 4). The combination of words with high frequency of simultaneous appearances, that is, high correlation, appeared as 'certification - acquisition', 'problem - solution', 'science - life', and 'misunderstanding - concession'. In cluster analysis, the number of clusters obtained by the height of cluster dendrogram was 2(Q.1), 4(Q.2, 4) and 5(Q. 3). At this time, the cohesion in Cluster was high and the heterogeneity between Clusters was clearly shown.

• Korean Journal of Poultry Science
• /
• v.39 no.2
• /
• pp.87-95
• /
• 2012

This experiment was conducted to investigate the effects of varying levels of metabolizable energy (ME) and crude protein (CP) on growth performance and carcass characteristics in layer-type growing male chicks. Nine hundred 1-d-old Hy-Line Brown male chicks were randomly allocated to 30 pens in a $2{\times}3$ factorial design. The experimental diets contained 2 levels of ME (2,800 kcal/kg and 2,950 kcal/kg) in combination with 3 levels of CP (17%, 18.5%, and, 20%). A significant interaction of ME and CP on feed intake was observed (p<0.05). No interaction was observed between ME and CP for 53 d BW gain or FCR, which improved linearly with dietary CP levels (p<0.05). A significant interaction or tendency was observed between ME and CP levels. The intake of ME for 1 g BW gain was linearly decreased with increasing CP levels (p<0.001). The intake of CP per bird was significantly increased in low ME (2,800 kcal/kg) treatment than that of the high ME treatment (2,950 kcal/kg) (p<0.05), and dietary CP level had more influence on CP intake for gram BW gain than level of ME. The relative weights of liver, spleen, breast meat and, leg were not influenced by the dietary treatments. Serum BUN, albumin, creatinine, and the activities of GOT and GPT were not influenced significantly by the diet treatment. In conclusion, the growth performance in layer-type male chicks was linearly increased when the level of dietary CP increased. The ME and CP did not affect the carcass characteristics and blood profiles. Therefore, the optimum levels of dietary ME and CP to improve the growth were 2,800 kcal/kg and above 18.5% in layer-type growing male chicks, respectively.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.139-156
• /
• 2021

The biggest reason for using a deep learning model in image classification is that it is possible to consider the relationship between each region by extracting each region's features from the overall information of the image. However, the CNN model may not be suitable for emotional image data without the image's regional features. To solve the difficulty of classifying emotion images, many researchers each year propose a CNN-based architecture suitable for emotion images. Studies on the relationship between color and human emotion were also conducted, and results were derived that different emotions are induced according to color. In studies using deep learning, there have been studies that apply color information to image subtraction classification. The case where the image's color information is additionally used than the case where the classification model is trained with only the image improves the accuracy of classifying image emotions. This study proposes two ways to increase the accuracy by incorporating the result value after the model classifies an image's emotion. Both methods improve accuracy by modifying the result value based on statistics using the color of the picture. When performing the test by finding the two-color combinations most distributed for all training data, the two-color combinations most distributed for each test data image were found. The result values were corrected according to the color combination distribution. This method weights the result value obtained after the model classifies an image's emotion by creating an expression based on the log function and the exponential function. Emotion6, classified into six emotions, and Artphoto classified into eight categories were used for the image data. Densenet169, Mnasnet, Resnet101, Resnet152, and Vgg19 architectures were used for the CNN model, and the performance evaluation was compared before and after applying the two-stage learning to the CNN model. Inspired by color psychology, which deals with the relationship between colors and emotions, when creating a model that classifies an image's sentiment, we studied how to improve accuracy by modifying the result values based on color. Sixteen colors were used: red, orange, yellow, green, blue, indigo, purple, turquoise, pink, magenta, brown, gray, silver, gold, white, and black. It has meaning. Using Scikit-learn's Clustering, the seven colors that are primarily distributed in the image are checked. Then, the RGB coordinate values of the colors from the image are compared with the RGB coordinate values of the 16 colors presented in the above data. That is, it was converted to the closest color. Suppose three or more color combinations are selected. In that case, too many color combinations occur, resulting in a problem in which the distribution is scattered, so a situation fewer influences the result value. Therefore, to solve this problem, two-color combinations were found and weighted to the model. Before training, the most distributed color combinations were found for all training data images. The distribution of color combinations for each class was stored in a Python dictionary format to be used during testing. During the test, the two-color combinations that are most distributed for each test data image are found. After that, we checked how the color combinations were distributed in the training data and corrected the result. We devised several equations to weight the result value from the model based on the extracted color as described above. The data set was randomly divided by 80:20, and the model was verified using 20% of the data as a test set. After splitting the remaining 80% of the data into five divisions to perform 5-fold cross-validation, the model was trained five times using different verification datasets. Finally, the performance was checked using the test dataset that was previously separated. Adam was used as the activation function, and the learning rate was set to 0.01. The training was performed as much as 20 epochs, and if the validation loss value did not decrease during five epochs of learning, the experiment was stopped. Early tapping was set to load the model with the best validation loss value. The classification accuracy was better when the extracted information using color properties was used together than the case using only the CNN architecture.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.205-225
• /
• 2018

Convolutional Neural Network (ConvNet) is one class of the powerful Deep Neural Network that can analyze and learn hierarchies of visual features. Originally, first neural network (Neocognitron) was introduced in the 80s. At that time, the neural network was not broadly used in both industry and academic field by cause of large-scale dataset shortage and low computational power. However, after a few decades later in 2012, Krizhevsky made a breakthrough on ILSVRC-12 visual recognition competition using Convolutional Neural Network. That breakthrough revived people interest in the neural network. The success of Convolutional Neural Network is achieved with two main factors. First of them is the emergence of advanced hardware (GPUs) for sufficient parallel computation. Second is the availability of large-scale datasets such as ImageNet (ILSVRC) dataset for training. Unfortunately, many new domains are bottlenecked by these factors. For most domains, it is difficult and requires lots of effort to gather large-scale dataset to train a ConvNet. Moreover, even if we have a large-scale dataset, training ConvNet from scratch is required expensive resource and time-consuming. These two obstacles can be solved by using transfer learning. Transfer learning is a method for transferring the knowledge from a source domain to new domain. There are two major Transfer learning cases. First one is ConvNet as fixed feature extractor, and the second one is Fine-tune the ConvNet on a new dataset. In the first case, using pre-trained ConvNet (such as on ImageNet) to compute feed-forward activations of the image into the ConvNet and extract activation features from specific layers. In the second case, replacing and retraining the ConvNet classifier on the new dataset, then fine-tune the weights of the pre-trained network with the backpropagation. In this paper, we focus on using multiple ConvNet layers as a fixed feature extractor only. However, applying features with high dimensional complexity that is directly extracted from multiple ConvNet layers is still a challenging problem. We observe that features extracted from multiple ConvNet layers address the different characteristics of the image which means better representation could be obtained by finding the optimal combination of multiple ConvNet layers. Based on that observation, we propose to employ multiple ConvNet layer representations for transfer learning instead of a single ConvNet layer representation. Overall, our primary pipeline has three steps. Firstly, images from target task are given as input to ConvNet, then that image will be feed-forwarded into pre-trained AlexNet, and the activation features from three fully connected convolutional layers are extracted. Secondly, activation features of three ConvNet layers are concatenated to obtain multiple ConvNet layers representation because it will gain more information about an image. When three fully connected layer features concatenated, the occurring image representation would have 9192 (4096+4096+1000) dimension features. However, features extracted from multiple ConvNet layers are redundant and noisy since they are extracted from the same ConvNet. Thus, a third step, we will use Principal Component Analysis (PCA) to select salient features before the training phase. When salient features are obtained, the classifier can classify image more accurately, and the performance of transfer learning can be improved. To evaluate proposed method, experiments are conducted in three standard datasets (Caltech-256, VOC07, and SUN397) to compare multiple ConvNet layer representations against single ConvNet layer representation by using PCA for feature selection and dimension reduction. Our experiments demonstrated the importance of feature selection for multiple ConvNet layer representation. Moreover, our proposed approach achieved 75.6% accuracy compared to 73.9% accuracy achieved by FC7 layer on the Caltech-256 dataset, 73.1% accuracy compared to 69.2% accuracy achieved by FC8 layer on the VOC07 dataset, 52.2% accuracy compared to 48.7% accuracy achieved by FC7 layer on the SUN397 dataset. We also showed that our proposed approach achieved superior performance, 2.8%, 2.1% and 3.1% accuracy improvement on Caltech-256, VOC07, and SUN397 dataset respectively compare to existing work.