• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.1
• /
• pp.114-123
• /
• 2018

This paper concerns a design and learning method of softmax function neural networks based on K-means clustering. The partial discharge data Information is preliminarily processed through simulation using an Epoxy Mica Coupling sensor and an internal Phase Resolved Partial Discharge Analysis algorithm. The obtained information is processed according to the characteristics of the pattern using a Motor Insulation Monitoring System program. At this time, the processed data are total 4 types that void discharge, corona discharge, surface discharge and slot discharge. The partial discharge data with high dimensional input variables are secondarily processed by principal component analysis method and reduced with keeping the characteristics of pattern as low dimensional input variables. And therefore, the pattern classifier processing speed exhibits improved effects. In addition, in the process of extracting the partial discharge data through the MIMS program, the magnitude of amplitude is divided into the maximum value and the average value, and two pattern characteristics are set and compared and analyzed. In the first half of the proposed partial discharge pattern classifier, the input and hidden layers are classified by using the K-means clustering method and the output of the hidden layer is obtained. In the latter part, the cross entropy error function is used for parameter learning between the hidden layer and the output layer. The final output layer is output as a normalized probability value between 0 and 1 using the softmax function. The advantage of using the softmax function is that it allows access and application of multiple class problems and stochastic interpretation. First of all, there is an advantage that one output value affects the remaining output value and its accompanying learning is accelerated. Also, to solve the overfitting problem, L2-normalization is applied. To prove the superiority of the proposed pattern classifier, we compare and analyze the classification rate with conventional radial basis function neural networks.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.23 no.2
• /
• pp.325-330
• /
• 2009

In Korea, medical diagnostic equipments and biochemical examination can not be used in order for diagnosing sub-healthy state or ante-disease state in oriental medicine clinic. So morphic analogical method used in oriental medicine can be a good tool as a disease-predictable signs in order to enable preventive diagnosis and therapy. Therefore the four geometrical subjects; Essence, Pneuma, Spirit, Blood(四科;精氣紳血) and the four taxonomical species; Pisces, Quadruped, Aves, Carapaces(四類;魚走鳥甲) are chosen as morphic models in this paper. The differences of two classifying methods with four subjects and four species were as follows. The diagnostic category was meta-medical and synthetic against medical specific. The diagnostic object was body in contrast with face. They were able to be applicant in psychology and classification of characteristics against diagnostics and therapeutics directly in oriental medicine. The theoretical basis was basic diagrams of four unit-fluids of body and morphological analogy with four animal species respectively. And the therapeutic aims were systemic pathogenesis following five phase theory against congestion and deficiency of Essence, Pneuma, Spirit, Blood. The four subjects and four species are mixed each other practically in clinic. But it should be used limitedly because of the above reasons described and must divide the principal and secondary factors and follow the pathology of principal shape factor. In order to improve the diagnostic value of ante-disease state, the discriminable standards, measurement methods, limit of interrelating interpretation and the criteria of abnormal disproportion were needed to be defined more clearly in advance.

• The Journal of Internal Korean Medicine
• /
• v.28 no.3
• /
• pp.453-463
• /
• 2007

Backgrounds : Glutathione-s-transferase (GST) is a kind of phase II metabolism enzyme and plays an important role in the detoxification of various toxic chemicals. It was reported that the genetic polymorphism of GSTM1 and GSTT1 genes may be responsible for asthma development and susceptibility to allergy. Traditional oriental medicine uses a unique diagnostic technique. differentiation-syndrome. to analyze signs and symptoms of patients synthetically. Through differentiation-syndrome. asthma patients can be divided into two groups: the deficiency syndrome group (DSG) and the excess syndrome group (ESG). Objectives : The purpose of this study was to investigate the possible association of GST gene polymorphism with clinical phenotype by differentiation-syndrome of bronchial asthma patients. Materials and Methods : One hundred and ten participants were evaluated by pulmonary function test. Patients with 53 DSG and 31 ESG by differentiation-syndrome were assessed for genetic analysis. GSTM1 and GSTT1 deletion polymorphism was performed by polymerase chain reaction (PCR). Results : GSTM1 gene deletion was detected in 43.4% of individuals in the DSG and in 38.71 % in the ESG. The distribution of GSTM1 polymorphism between DSG and ESG was not significantly different [$x^2$=0.1767, p=0.6742; OR(95% CI)=1.2139(0.4915-2.9979)]. The proportion of GSTT1 null genotypes was 41.51% in the DGS and 45.16% in the ESG. The distribution of GSTT1 polymorphism between DSG and ESG was also not significantly different [$x^2$=0.1065, p=0.7442; OR(95% CI)=0.8618(0.3525-2.1065)]. In the combined analysis of GSTM1 and GSTT1 genes, the frequency of both null type of GSTM1/GSTT1 genes was not significantly different from both positive type of GSTM1/GSTT1 genes[$x^2$=0.0768, p=0.7817; OR(95% CI)=1.2000(0.3303-4.3602)] Conclusions : These results indicate that polymorphism of the GST gene might not be associated with the symptomatic classification of DSG and ESG by differentiation-syndrome in Korean asthmatics.

• Korean Journal of Animal Reproduction
• /
• v.21 no.3
• /
• pp.265-274
• /
• 1997

The purpose of this study was attempted to investigate the a, pp.arences of healthy or artretic follicles in ovaries following repeats of pregnant mare serum gonadotropin(PMSG) treatments for superovulation in nulliparous rats. Thirty two rats(Sprague-Dawely, about 200-250 gm) were randomized into 4 groups. Control group rats were sacrified at estrus phase confirmed by vaginal smear. PMSG-treated group 1 rats, PMSG-treated group 2 rats and PMSG-treated group 3 rats were sacrified at 48 hrs after injection once with PMSG 25 IU, after 2 repeated injection by a week interval, and 3 repeated injection, respectively. The ovaires of rats were removed and then sections by paraffin embedding were stained with H-E or immunohistochemical staining using proliferating cell nuclear antigen monoclonal antibody (PCNA m Ab) and apoptotic kit. The criteria of follicle classification was based as small follicles with preantral follicles with 2~4 layers of granulosa cells surrounding the oocyte, as secondary follicles with more than 5 layers of granulosa cells and early signs of antral cavity or with small clefts on either side of the oocytes, and as tirtiary follicles with a single medium sized antral cavity or large well-formed antral cavity, respectively. The proportions of atretic follicles from small and middle follicles in immunohistochemical staining using PCNA m Ab were 17.9% and 21.3% in control group, 15.5% and 23.5% in PMSG-treated group 1, 24.3% and 26.7% in PMSG-treated group 2, 18.1% and 30.2% in PMSG-treated group 3, respectively. Groups with atretic follicles of higher proportion were ordered as PMSG-treated group 3, PMSG-treated group 2, PMSG-treated group 1 and control group. The proportions of positive cells in small, middle and large follicles were 31.1%, 33.5% and 28.5% respectively. The follicles with positive cells of higher proportion were ordered middle, small and large follicles. In immunohischemical staining using apoptotic kits, small follicles in all 4 groups did not contain positive cells, and proportions of atretic follicles from middle and large follicles were 24.9, 30.7, 33.8 and 40.1% in control, PMSG-treated gruop 1, PMSG-treated group 2 and PMSG-treated group 3, respectively. These results suggested that repeats of PMSG treatment increased proportion of atretic follicles in ovaries, and middle follicles are more quickly developing than small or large follicles.

• Korean Journal of Radiology
• /
• v.22 no.11
• /
• pp.1786-1796
• /
• 2021

Objective: To evaluate the prognostic implications of preoperative magnetic resonance imaging (MRI) features of hepatocellular carcinoma (HCC) with a focus on those with targetoid appearance based on the Liver Imaging Reporting and Data System (LI-RADS), as well as known microvascular invasion (MVI) features. Materials and Methods: This retrospective study included 242 patients (190 male; mean age, 57.1 years) who underwent surgical resection of a single HCC (≤ 5 cm) as well as preoperative gadoxetic acid-enhanced MRI between January 2012 and March 2015. LI-RADS category was assigned, and the LR-M category was further classified into two groups according to rim arterial-phase hyperenhancement (APHE). The imaging features associated with MVI were also assessed. The overall survival (OS), recurrence-free survival (RFS), and their associated factors were evaluated. Results: Among the 242 HCCs, 190 (78.5%), 25 (10.3%), and 27 (11.2%) were classified as LR-4/5, LR-M with rim APHE, and LR-M without rim APHE, respectively. LR-M with rim APHE (vs. LR-4/5; hazard ratio [HR] for OS, 5.48 [p = 0.002]; HR for RFS, 2.09 [p = 0.042]) and tumor size (per cm increase; HR for OS, 6.04 [p = 0.009]; HR for RFS, 1.77 [p = 0.014]) but not MVI imaging features (p > 0.05) were independent factors associated with OS and RFS. Compared to the 5-year OS and RFS rates in the LR-4/5 group (93.9% and 66.8%, respectively), the LR-M with rim APHE group had significantly lower rates (68.0% and 45.8%, respectively, both p < 0.05), while the LR-M without rim APHE group did not significantly differ in the survival rates (91.3% and 80.2%, respectively, both p > 0.05). Conclusion: Further classification of LR-M according to the presence of rim APHE may help predict the postoperative prognosis of patients with a single HCC.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.9 no.1
• /
• pp.119-132
• /
• 2014

This study analyzed the failure prediction model of the firms listed on the KOSDAQ by considering whether there are embezzlement, malpractice and the largest shareholder changes or not. This study composed a total of 166 firms by using two-paired sampling method. For sample of failed firm, 83 manufacturing firms which delisted on KOSDAQ market for 4 years from 2009 to 2012 are selected. For sample of normal firm, 83 firms (with same item or same business as failed firm) that are listed on KOSDAQ market and perform normal business activities during the same period (from 2009 to 2012) are selected. This study selected 80 financial ratios for 5 years immediately preceding from delisting of sample firm above and conducted T-test to derive 19 of them which emerged for five consecutive years among significant variables and used forward selection to estimate logistic regression model. While the precedent studies only analyzed the data of three years immediately preceding the delisting, this study analyzes data of five years immediately preceding the delisting. This study is distinct from existing previous studies that it researches which significant financial characteristic influences the insolvency from the initial phase of insolvent firm with time lag and it also empirically analyzes the usefulness of data by building a firm's fail prediction model which considered embezzlement/malpractice and the largest shareholder changes as dummy variable(non-financial characteristics). The accuracy of classification of the prediction model with dummy variable appeared 95.2% in year T-1, 88.0% in year T-2, 81.3% in year T-3, 79.5% in year T-4, and 74.7% in year T-5. It increased as year of delisting approaches and showed generally higher the accuracy of classification than the results of existing previous studies. This study expects to reduce the damage of not only the firm but also investors, financial institutions and other stakeholders by finding the firm with high potential to fail in advance.

• Journal of Intelligence and Information Systems
• /
• v.17 no.4
• /
• pp.255-277
• /
• 2011

Product Service System(PSS), which is an integrated combination of product and service, provides new value to customer and makes companies sustainable as well. The objective of this paper draws Critical Successful Factors(CSF) of PSS through multiple case study. First, we review various concepts and types in PSS and Platform business literature currently available on this topic. Second, after investigating various cases with the characteristics of PSS and platform business, we select four cases of 'iPod of Apple', 'Kindle of Amazon', 'Zune of Microsoft', and 'e-book reader of Sony'. Then, the four cases are categorized as successful and failed cases according to criteria of case selection and PSS classification. We consider two methodologies for the case selection, i.e., 'Strategies for the Selection of Samples and Cases' proposed by Bent(2006) and the seven case selection procedures proposed by Jason and John(2008). For case selection, 'Stratified sample and Paradigmatic cases' is adopted as one of several options for sampling. Then, we use the seven case selection procedures such as 'typical', 'diverse', 'extreme', 'deviant', 'influential', 'most-similar', and 'mostdifferent' and among them only three procedures of 'diverse', 'most?similar', and 'most-different' are applied for the case selection. For PSS classification, the eight PSS types, suggested by Tukker(2004), of 'product related', 'advice and consulancy', 'product lease', 'product renting/sharing', 'product pooling', 'activity management', 'pay per service unit', 'functional result' are utilized. We categorize the four selected cases as a product oriented group because the cases not only sell a product, but also offer service needed during the use phase of the product. Then, we analyze the four cases by using cross-case pattern that Eisenhardt(1991) suggested. Eisenhardt(1991) argued that three processes are required for avoiding reaching premature or even false conclusion. The fist step includes selecting categories of dimensions and finding within-group similarities coupled with intergroup difference. In the second process, pairs of cases are selected and listed. The second step forces researchers to find the subtle similarities and differences between cases. The third process is to divide the data by data source. The result of cross-case pattern indicates that the similarities of iPod and Kindle as successful cases are convenient user interface, successful plarform strategy, and rich contents. The differences between the successful cases are that, wheares iPod has been recognized as the culture code, Kindle has implemented a low price as its main strategy. Meanwhile, the similarities of Zune and PRS series as failed cases are lack of sufficient applications and contents. The differences between the failed cases are that, wheares Zune adopted an undifferentiated strategy, PRS series conducted high-price strategy. From the analysis of the cases, we generate three hypotheses. The first hypothesis assumes that a successful PSS system requires convenient user interface. The second hypothesis assumes that a successful PSS system requires a reciprocal(win/win) business model. The third hypothesis assumes that a successful PSS system requires sufficient quantities of applications and contents. To verify the hypotheses, we uses the cross-matching (or pattern matching) methodology. The methodology matches three key words (user interface, reciprocal business model, contents) of the hypotheses to the previous papers related to PSS, digital contents, and Information System (IS). Finally, this paper suggests the three implications from analyzed results. A successful PSS system needs to provide differentiated value for customers such as convenient user interface, e.g., the simple design of iTunes (iPod) and the provision of connection to Kindle Store without any charge. A successful PSS system also requires a mutually benefitable business model as Apple and Amazon implement a policy that provides a reasonable proft sharing for third party. A successful PSS system requires sufficient quantities of applications and contents.

• 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.

• Korean Journal of Soil Science and Fertilizer
• /
• v.6 no.1
• /
• pp.35-52
• /
• 1973

Red Yellow Soils occur very commonly in Korea and constitute the important upland soils of the country which are either presently being cultivated or are suitable for reclaiming and cultivating. These soils are distributed on rolling, moutain foot slopes, and terraces in the southern and western parts of the central districts of Korea, and are derived from granite, granite gneiss, old alluvium and locally from limestone and shale. This report is a summary of the morphology, physical and chemical characteristics of Red Yellow Soils. The data obtained from detailed soil surveys since 1964 are summarized as follows. 1. Red-Yellows Soils have an A, Bt, C profile. The A horizon is dark colored coarse loamy or fine loamy with the thin layer of organic matter. The B horizon is dominantly strong brown, reddish brown or yellowish red, clayey or fine loamy with clay cutans on the soil peds. The C horizon varies with parent materials, and is coarser texture and has a less developed structure than the Bt horizon. Soil depth, varied with relief and parent materials, is predominantly around 100cm. 2. In the physical characteristics, the clay content of surface soil is 18 to 35 percent, and of subsoil is 30 to 90 percent nearly two times higher than the surface soil. Bulk density is 1.2 to 1.3 in the surface soil and 1.3 to 1.5 in the subsoil. The range of 3-phase is mostly narrow with 45 to 50 percent in solid phase, 30 to 45 percent in liquid one, and 5 to 25 percent in gaseous state in the surface soil; and 50 to 60 solid, 35 to 45 percent liquid and less than 15 percent gaseous in the subsoil. Available soil moisture capacity ranges from 10 to 23 percent in the surface soil, and 5 to 16 percent in the subsoil. 3. Chemically, soil reaction is neutral to alkaline in soils derived from limestone or old fluviomarine deposits, and acid to strong acid in other ones. The organic matter content of surface soil varying considerably with vegetation, erosion and cultivation, ranges from 1.0 to 5.0 percent. The cation exchange capacity is 5 to 40 me/100gr soil and closely related to the content of organic matter, clay and silt. Base saturation is low, on the whole, due to the leaching of extractable cations, but is high in soils derived from limestone with high content of lime and magnesium. 4. Most of these soils mainly contain halloysite (a part of kaolin minerals), vermiculite (weathered mica), and illite, including small amount of chlorite, gibbsite, hematite, quartz and feldspar. 5. Characteristically they are similar to Red Yellow Podzolic Soils and a part of Reddish Brown Lateritic Soils of the United States, and Red Yellow Soils of Japan. According to USDA 7th Approximation, they can be classified as Udu Its or Udalfs, and in FAO classification system to Acrisols, Luvisols, and Nitosols.

• Korean Journal of Environmental Agriculture
• /
• v.25 no.4
• /
• pp.306-315
• /
• 2006

Two different experiments, adsorption/desorption and runoff by rainfall simulation of four pesticides, such as alachlor, ethalfluralin, ethoprophos and pendimethalin were undertaken their runoff and erosion losses from sloped land and to assess the influence of their properties and environmental factors on them. The mobility of four pesticides and which phase they were transported by were examined in adsorption study, and the influence of rainfall pattern and sloping degree on the pesticide losses were evaluated in simulated rainfall study. Freundlich adsorption parameters (K) by the adsorption and desorption methods were 1.2 and 2.2 for ethoprophos, 1.5 and 2.6 for alachlor, respectively. And adsorption distribution coefficients (Kd) by the adsorption and desorption methods were 56 and 94 for ethalfluralin, and 104 and 189 for pendimethalin, respectively. K or Kd values of pesticides by the desorption method which were desorbed from the soil after thoroughly mixing, were higher than these ones by the adsorption method which pesticides dissolved in water were adsorbed to the soil. Another parameter (1/n), representing the linearity of adsorption, in Freundlich equation for the pesticides tested ranged from 0.96 to 1.02 by the desorption method and from 0.87 to 1.02 by the adsorption method. Therefore, the desorption method was more independent from pesticide concentration in soil solution than the adsorption method. By Soil Survey and Land Research Center (SSLRC)'s classification for pesticide mobility, alachlor and ethoprophos were classified into moderately mobile $(75{\leq}Koc<500)$, and ethalfluralin and pendimethalin were included to non-mobile class (Koc > 4000). Runoff and erosion loss of pesticides by three rainfall scenarios were from 1.0 to 6.4% and from 0.3 to 1.2% for alachlor, from 1.0 to 2.5% and from 1.7 to 10.1% for ethalfluralin, from 1.3 to 2.9% and from 3.9 to 10.8% for pendimethalin, and from 0.6 to 2.7% and from 0.1 % 0.3% for ethoprophos, respectively. Distribution of pesticides in soil profile were investigated after the simulated rainfall study. Alachlor and ethoprophos were leached to from 10 to 15 cm of soil layer, but ethalfluralin and pendimethalin were mostly remained at the top 5 cm of soil profile. The losses of the pesticides at 30% of sloping degree were from 0.2 to 1.9 times higher than those at 10%. The difference of their runoff loss was related with their concentration in runoff water while the difference of their erosion loss must be closely related with the quantity of soil eroded.