• Journal of Intelligence and Information Systems
• /
• v.25 no.2
• /
• pp.25-38
• /
• 2019

Selecting high-quality information that meets the interests and needs of users among the overflowing contents is becoming more important as the generation continues. In the flood of information, efforts to reflect the intention of the user in the search result better are being tried, rather than recognizing the information request as a simple string. Also, large IT companies such as Google and Microsoft focus on developing knowledge-based technologies including search engines which provide users with satisfaction and convenience. Especially, the finance is one of the fields expected to have the usefulness and potential of text data analysis because it's constantly generating new information, and the earlier the information is, the more valuable it is. Automatic knowledge extraction can be effective in areas where information flow is vast, such as financial sector, and new information continues to emerge. However, there are several practical difficulties faced by automatic knowledge extraction. First, there are difficulties in making corpus from different fields with same algorithm, and it is difficult to extract good quality triple. Second, it becomes more difficult to produce labeled text data by people if the extent and scope of knowledge increases and patterns are constantly updated. Third, performance evaluation is difficult due to the characteristics of unsupervised learning. Finally, problem definition for automatic knowledge extraction is not easy because of ambiguous conceptual characteristics of knowledge. So, in order to overcome limits described above and improve the semantic performance of stock-related information searching, this study attempts to extract the knowledge entity by using neural tensor network and evaluate the performance of them. Different from other references, the purpose of this study is to extract knowledge entity which is related to individual stock items. Various but relatively simple data processing methods are applied in the presented model to solve the problems of previous researches and to enhance the effectiveness of the model. From these processes, this study has the following three significances. First, A practical and simple automatic knowledge extraction method that can be applied. Second, the possibility of performance evaluation is presented through simple problem definition. Finally, the expressiveness of the knowledge increased by generating input data on a sentence basis without complex morphological analysis. The results of the empirical analysis and objective performance evaluation method are also presented. The empirical study to confirm the usefulness of the presented model, experts' reports about individual 30 stocks which are top 30 items based on frequency of publication from May 30, 2017 to May 21, 2018 are used. the total number of reports are 5,600, and 3,074 reports, which accounts about 55% of the total, is designated as a training set, and other 45% of reports are designated as a testing set. Before constructing the model, all reports of a training set are classified by stocks, and their entities are extracted using named entity recognition tool which is the KKMA. for each stocks, top 100 entities based on appearance frequency are selected, and become vectorized using one-hot encoding. After that, by using neural tensor network, the same number of score functions as stocks are trained. Thus, if a new entity from a testing set appears, we can try to calculate the score by putting it into every single score function, and the stock of the function with the highest score is predicted as the related item with the entity. To evaluate presented models, we confirm prediction power and determining whether the score functions are well constructed by calculating hit ratio for all reports of testing set. As a result of the empirical study, the presented model shows 69.3% hit accuracy for testing set which consists of 2,526 reports. this hit ratio is meaningfully high despite of some constraints for conducting research. Looking at the prediction performance of the model for each stocks, only 3 stocks, which are LG ELECTRONICS, KiaMtr, and Mando, show extremely low performance than average. this result maybe due to the interference effect with other similar items and generation of new knowledge. In this paper, we propose a methodology to find out key entities or their combinations which are necessary to search related information in accordance with the user's investment intention. Graph data is generated by using only the named entity recognition tool and applied to the neural tensor network without learning corpus or word vectors for the field. From the empirical test, we confirm the effectiveness of the presented model as described above. However, there also exist some limits and things to complement. Representatively, the phenomenon that the model performance is especially bad for only some stocks shows the need for further researches. Finally, through the empirical study, we confirmed that the learning method presented in this study can be used for the purpose of matching the new text information semantically with the related stocks.

• The Journal of Korean Society for Radiation Therapy
• /
• v.31 no.1
• /
• pp.57-65
• /
• 2019

Purpose: The purpose is to clarify the effect of additional scattering ratio on the edge of the block according to the increasing block thickness with low melting point lead alloy and pure lead in electron beam therapy. Methods and materials: $10{\times}10cm^2$ Shielding blocks made of low melting point lead alloy and pure lead were fabricated to shield mold frame half of applicator. Block thickness was 3, 5, 10, 15, 20 (mm) for each material. The common irradiation conditions were set at 6 MeV energy, 300 MU / Min dose rate, gantry angle of $0^{\circ}$, and dose of 100 MU. The relative scattering ratio with increasing block thickness was measured with a parallel plate type ion chamber(Exradin P11) and phantom(RW3) by varying the position of the shielding block(cone and on the phantom), the position of the measuring point(surface ans depth of $D_{max}$), and the block material(lead alloy and pure lead). Results : When (depth of measurement / block position / block material) was (surface / applicator / pure lead), the relative value(scattering ratio) was 15.33 nC(+0.33 %), 15.28 nC(0 %), 15.08 nC(-1.31 %), 15.05 nC(-1.51 %), 15.07 nC(-1.37 %) as the block thickness increased in order of 3, 5, 10, 15, 20 (mm) respectively. When it was (surface / applicator / alloy lead), the relative value(scattering ratio) was 15.19 nC(-0.59 %), 15.25 nC(-0.20 %), 15.15 nC(-0.85 %), 14.96 nC(-2.09 %), 15.15 nC(-0.85 %) respectively. When it was (surface / phantom / pure lead), the relative value(scattering ratio) was 15.62 nC(+2.23 %), 15.59 nC(+2.03 %), 15.53 nC(+1.67 %), 15.48 nC(+1.31 %), 15.34 nC(+0.39 %) respectively. When it was (surface / phantom / alloy lead), the relative value(scattering ratio) was 15.56 nC(+1.83 %), 15.55 nC(+1.77 %), 15.51 nC(+1.51 %), 15.42 nC(+0.92 %), 15.39 nC(+0.72 %) respectively. When it was (depth of $D_{max}$ / applicator / pure lead), the relative value(scattering ratio) was 16.70 nC(-10.87 %), 16.84 nC(-10.12 %), 16.72 nC(-10.78 %), 16.88 nC(-9.93 %), 16.90 nC(-9.82 %) respectively. When it was (depth of $D_{max}$ / applicator / alloy lead), the relative value(scattering ratio) was 16.83 nC(-10.19 %), 17.12 nC(-8.64 %), 16.89 nC(-9.87 %), 16.77 nC(-10.51 %), 16.52 nC(-11.85 %) respectively. When it was (depth of $D_{max}$ / phantom / pure lead), the relative value(scattering ratio) was 17.41 nC(-7.10 %), 17.45 nC(-6.88 %), 17.34 nC(-7.47 %), 17.42 nC(-7.04 %), 17.25 nC(-7.95 %) respectively. When it was (depth of $D_{max}$ / phantom / alloy lead), the relative value(scattering ratio) was 17.45 nC(-6.88 %), 17.44 nC(-6.94 %), 17.47 nC(-6.78 %), 17.43 nC(-6.99 %), 17.35 nC(-7.42 %) respectively. Conclusions: When performing electron therapy using a shielding block, the block position should be inserted applicator rather than the patient's body surface. The block thickness should be made to the minimum appropriate shielding thickness of each corresponding using energy. Also it is useful that the treatment should be performed considering the influence of scattering dose varying with distance from the edge of block.

• The Journal of Korean Society for Radiation Therapy
• /
• v.31 no.1
• /
• pp.75-81
• /
• 2019

Purpose: Helmet type bolus for 3D printer is being manufactured because of the disadvantages of Bolus materials when photon beam is used for the treatment of scalp malignancy. However, PLA, which is a used material, has a higher density than a tissue equivalent material and inconveniences occur when the patient wears PLA. In this study, we try to treat malignant scalp tumors by using M3 wax helmet with 3D printer. Methods and materials: For the modeling of the helmet type M3 wax, the head phantom was photographed by CT, which was acquired with a DICOM file. The part for helmet on the scalp was made with Helmet contour. The M3 Wax helmet was made by dissolving paraffin wax, mixing magnesium oxide and calcium carbonate, solidifying it in a PLA 3D helmet, and then eliminated PLA 3D Helmet of the surface. The treatment plan was based on Intensity-Modulated Radiation Therapy (IMRT) of 10 Portals, and the therapeutic dose was 200 cGy, using Analytical Anisotropic Algorithm (AAA) of Eclipse. Then, the dose was verified by using EBT3 film and Mosfet (Metal Oxide Semiconductor Field Effect Transistor: USA), and the IMRT plan was measured 3 times in 3 parts by reproducing the phantom of the head human model under the same condition with the CT simulation room. Results: The Hounsfield unit (HU) of the bolus measured by CT was $52{\pm}37.1$. The dose of TPS was 186.6 cGy, 193.2 cGy and 190.6 cGy at the M3 Wax bolus measurement points of A, B and C, and the dose measured three times at Mostet was $179.66{\pm}2.62cGy$, $184.33{\pm}1.24cGy$ and $195.33{\pm}1.69cGy$. And the error rates were -3.71 %, -4.59 %, and 2.48 %. The dose measured with EBT3 film was $182.00{\pm}1.63cGy$, $193.66{\pm}2.05cGy$ and $196{\pm}2.16cGy$. The error rates were -2.46 %, 0.23 % and 2.83 %. Conclusions: The thickness of the M3 wax bolus was 2 cm, which could help the treatment plan to be established by easily lowering the dose of the brain part. The maximum error rate of the scalp surface dose was measured within 5 % and generally within 3 %, even in the A, B, C measurements of dosimeters of EBT3 film and Mosfet in the treatment dose verification. The making period of M3 wax bolus is shorter, cheaper than that of 3D printer, can be reused and is very useful for the treatment of scalp malignancies as human tissue equivalent material. Therefore, we think that the use of casting type M3 wax bolus, which will complement the making period and cost of high capacity Bolus and Compensator in 3D printer, will increase later.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.63-83
• /
• 2019

Investors prefer to look for trading points based on the graph shown in the chart rather than complex analysis, such as corporate intrinsic value analysis and technical auxiliary index analysis. However, the pattern analysis technique is difficult and computerized less than the needs of users. In recent years, there have been many cases of studying stock price patterns using various machine learning techniques including neural networks in the field of artificial intelligence(AI). In particular, the development of IT technology has made it easier to analyze a huge number of chart data to find patterns that can predict stock prices. Although short-term forecasting power of prices has increased in terms of performance so far, long-term forecasting power is limited and is used in short-term trading rather than long-term investment. Other studies have focused on mechanically and accurately identifying patterns that were not recognized by past technology, but it can be vulnerable in practical areas because it is a separate matter whether the patterns found are suitable for trading. When they find a meaningful pattern, they find a point that matches the pattern. They then measure their performance after n days, assuming that they have bought at that point in time. Since this approach is to calculate virtual revenues, there can be many disparities with reality. The existing research method tries to find a pattern with stock price prediction power, but this study proposes to define the patterns first and to trade when the pattern with high success probability appears. The M & W wave pattern published by Merrill(1980) is simple because we can distinguish it by five turning points. Despite the report that some patterns have price predictability, there were no performance reports used in the actual market. The simplicity of a pattern consisting of five turning points has the advantage of reducing the cost of increasing pattern recognition accuracy. In this study, 16 patterns of up conversion and 16 patterns of down conversion are reclassified into ten groups so that they can be easily implemented by the system. Only one pattern with high success rate per group is selected for trading. Patterns that had a high probability of success in the past are likely to succeed in the future. So we trade when such a pattern occurs. It is a real situation because it is measured assuming that both the buy and sell have been executed. We tested three ways to calculate the turning point. The first method, the minimum change rate zig-zag method, removes price movements below a certain percentage and calculates the vertex. In the second method, high-low line zig-zag, the high price that meets the n-day high price line is calculated at the peak price, and the low price that meets the n-day low price line is calculated at the valley price. In the third method, the swing wave method, the high price in the center higher than n high prices on the left and right is calculated as the peak price. If the central low price is lower than the n low price on the left and right, it is calculated as valley price. The swing wave method was superior to the other methods in the test results. It is interpreted that the transaction after checking the completion of the pattern is more effective than the transaction in the unfinished state of the pattern. Genetic algorithms(GA) were the most suitable solution, although it was virtually impossible to find patterns with high success rates because the number of cases was too large in this simulation. We also performed the simulation using the Walk-forward Analysis(WFA) method, which tests the test section and the application section separately. So we were able to respond appropriately to market changes. In this study, we optimize the stock portfolio because there is a risk of over-optimized if we implement the variable optimality for each individual stock. Therefore, we selected the number of constituent stocks as 20 to increase the effect of diversified investment while avoiding optimization. We tested the KOSPI market by dividing it into six categories. In the results, the portfolio of small cap stock was the most successful and the high vol stock portfolio was the second best. This shows that patterns need to have some price volatility in order for patterns to be shaped, but volatility is not the best.

• The Journal of Korean Society for Radiation Therapy
• /
• v.30 no.1_2
• /
• pp.27-34
• /
• 2018

Purpose : To evaluate the effect of carbon couch side rail and vacuum immobilization device in case of lung RPO irradiation. Materials and Methods : The 10, 20, 30 mm thickness of vac-lok's right side were obtained. To measure of doses, glass dosimeters were used and measured reference point is left lung center at the phantom. A, B, C, and D points are left, right, down, and up directions based on the center point. In the state of Side-Rail-Out, place the without vac-lok, with the thickness of 10, 20, and 30 mm vac-lok. After the glass dosimeters was inserted in center, A, B, C, and D points, 100 MU of 6 MV X-ray were irradiated to the referenced center point in the condition of $10{\times}10cm^2$ field size, SAD 100 cm, gantry angle 225, 300 MU/min dose rate. Five measurements were made for each point. In the state of Side-Rail-In, five measurement were made for each point under the same conditions. The average is measured on each of the five Side-Rail-Out and Side-Rail-In measurements. Results : In the presence of side rail, the dose reduction ratio was -11.8 %, -12.3 %, -4.1 %, -12.3 %, -7.3 % for each A, B, C, and D points. In the state of Side-Rail-Out, the dose reduction ratio for the using 10 mm thickness of vac-lok was -0.9 % than without vac-lok. The dose reduction ratio for the using 20 mm thickness of vac-lok was -2.0 %, for the using 30 mm thickness of the vac-lok was -3.0 % than without vac-lok. In the state of Side-Rail-In, the dose reduction ratio for the using 10 mm thickness of vac-lok was -1.0 % than without vac-lok. The dose reduction ratio for the using 20 mm vac-lok was -2.1 %, for the using 30 mm vac-lok was -3.0 % than without vac-lok. Based on the value of no vac-lok dose in the Side-Rail-In state, The dose reduction ratios for the using 10 mm, 20 mm and 30 mm thickness of vac-loks In the Side-Rail-Out that the center point were -12.7 %, -13.7 %, -14.2 % and -12.8 %, -13.8 %, -14.5 % respectively at point A. The dose reduction ratios for the same conditions to the B point were -4.9 %, -6.1 %, -7.1 % and -13.4 %, -14.4 %, -15.5 % respectively at point C. The dose reduction ratios for the same conditions to the D point were -8.4 %, -9.0 %, -10.4 % respectively. Conclusion : The attenuation was caused by presence of side rails and thickness of vac-lok. Pay attention to these attenuation factors, making it a more effective radiation therapy.

• The Journal of Korean Society for Radiation Therapy
• /
• v.32
• /
• pp.41-52
• /
• 2020

Purpose: To find out the dosimetric usefulness, setup reproducibility and efficiency of applying 3D Bolus by comparing two treatment plans in which Commercial Bolus and 3D Bolus produced by 3D Printing Technology were applied to the neck during VMAT treatment of Hypopahrynx Cancer to evaluate the clinical applicability. Materials and Methods: Based on the CT image of the RANDO phantom to which CB was applied, 3D Bolus were fabricated in the same form. 3D Bolus was printed with a polyurethane acrylate resin with a density of 1.2g/㎤ through the SLA technique using OMG SLA 660 Printer and MaterializeMagics software. Based on two CT images using CB and 3D Bolus, a treatment plan was established assuming VMAT treatment of Hypopharynx Cancer. CBCT images were obtained for each of the two established treatment plans 18 times, and the treatment efficiency was evaluated by measuring the setup time each time. Based on the obtained CBCT image, the adaptive plan was performed through Pinnacle, a computerized treatment planning system, to evaluate target, normal organ dose evaluation, and changes in bolus volume. Results: The setup time for each treatment plan was reduced by an average of 28 sec in the 3D Bolus treatment plan compared to the CB treatment plan. The Bolus Volume change during the pretreatment period was 86.1±2.70㎤ in 83.9㎤ of CB Initial Plan and 99.8±0.46㎤ in 92.2㎤ of 3D Bolus Initial Plan. The change in CTV Min Value was 167.4±19.38cGy in CB Initial Plan 191.6cGy and 149.5±18.27cGy in 3D Bolus Initial Plan 167.3cGy. The change in CTV Mean Value was 228.3±0.38cGy in CB Initial Plan 227.1cGy and 227.7±0.30cGy in 3D Bolus Initial Plan 225.9cGy. The change in PTV Min Value was 74.9±19.47cGy in CB Initial Plan 128.5cGy and 83.2±12.92cGy in 3D Bolus Initial Plan 139.9cGy. The change in PTV Mean Value was 226.2±0.83cGy in CB Initial Plan 225.4cGy and 225.8±0.33cGy in 3D Bolus Initial Plan 224.1cGy. The maximum value for the normal organ spinal cord was the same as 135.6cGy on average each time. Conclusion: From the experimental results of this paper, it was found that the application of 3D Bolus to the irregular body surface is more dosimetrically useful than the application of Commercial Bolus, and the setup reproducibility and efficiency are excellent. If further case studies along with research on the diversity of 3D printing materials are conducted in the future, the application of 3D Bolus in the field of radiation therapy is expected to proceed more actively.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.29 no.2
• /
• pp.81-89
• /
• 2011

The results of tracking the symbolism of plants in the introduction factors of Sokhwa(folk painting) are as the following. 1. The term Sokhwa(俗畵) is not only a type of painting with a strong local customs, but also carries a symbolic meaning and was discovered in "Donggukisanggukjip" of Lee, Gyu-Bo(1268~1241) in the Goryo era as well as the various usage in the "Sok Dongmunseon" in the early Chosun era, "Sasukjaejip" of Gang, Hee-mang(1424~1483), "Ilseongrok(1786)" in the late Chosun era, "Jajeo(自著)" of Yoo, Han-joon(1732~1811), and "Ojuyeonmunjangjeonsango(五洲衍文長箋散稿)" of Lee, Gyu-gyung(1788~?). Especially, according to the Jebyungjoksokhwa allegation〈題屛簇俗畵辯證說〉in the Seohwa of the Insa Edition of Ojuyeonmunjangjeonsango, there is a record that the "people called them Sokhwa." 2. Contemporarily, the Korean Sokhwa underwent the prehistoric age that primitively reflected the natural perspective on agricultural culture, the period of Three States that expressed the philosophy of the eternal spirits and reflected the view on the universe in colored pictures, the Goryo Era that religiously expressed the abstract shapes and supernatural patterns in spacein symbolism, and the Chosun Era that established the traditional Korean identity of natural perspective, aesthetic values and symbolism in a complex integration in the popular culture over time. 3. The materials that were analyzed in 1,009 pieces of Korean Sokhwa showed 35 species of plants, 37 species of animals, 6 types of natural objects and other 5 types with a total of 83 types. 4. The shape aesthetics according to the aesthetic analysis of the plants in Sokhwa reflect the primitive world view of Yin/yang and the Five Elements in the peony paintings and dynamic refinement and biological harmonies in the maehwado; the composition aesthetics show complex multi-perspective composition with a strong noteworthiness in the bookshelf paintings, a strong contrast of colors with reverse perspective drawing in the battlefield paintings, and the symmetric beauty of simple orderly patterns in nature and artificial objects with straight and oblique lines are shown in the leisurely reading paintings. In terms of color aesthetics, the five colors of directions - east, west, south, north and the center - or the five basic colors - red, blue, yellow, white and black - are often utilized in ritual or religious manners or symbolically substitute the relative relationships with natural laws. 5. The introduction methods in the Korean Sokhwa exceed the simple imitation of the natural shapes and have been sublimated to the symbolism that is related to nature based on the colloquial artistic characteristics with the suspicion of the essence in the universe. Therefore, the symbolism of the plants and animals in the Korean Sokhwas is a symbolic recognition system, not a scientific recognition system with a free and unique expression with a complex interaction among religious, philosophical, ecological and ideological aspects, as a identity of the group culture of Koreans where the past and the future coexist in the present. This is why the Koran Sokhwa or the folk paintings can be called a cultural identity and can also be interpreted as a natural and folk meaningful scenic factor that has naturally integrated into our cultural lifestyle. However, the Sokhwa(folk paintings) that had been closely related to our lifestyle drastically lost its meaning and emotions through the transitions over time. As the living lifestyle predominantly became the apartment culture and in the historical situations where the confusion of the identity has deepened, the aesthetic and the symbolic values of the Sokhwa folk paintings have the appropriateness to be transmitted as the symbolic assets that protect our spiritual affluence and establish our identity.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.29 no.4
• /
• pp.14-26
• /
• 2011

Imdaejeong Wonlim is located on the verge of Sangsa Village in Sapyeong-ri, Daepyeong-myeon, Hwasun-gun Gyeongsangnam-do toward Northwest. It was planned by Sa-ae, Minjuhyeon in 1862 on the basis of Gobanwon built by Nam Eongi in 16th century against the backdrop of Mt. Bongjeong and facing Sapyeong Stream. As water flows from west to east in the shape of crane, this area is a propitious site standing for prosperity and happiness. This area shows a distinct feature of Wonlim surrounding the Imdaejeong with multi layers as consisting of 5 districts - front yard where landmark stone with engraved letters of 'Janggujiso of Master Sa-ea' and junipers are harmoniously arranged, internal garden of upper pavilion ranging from a pavilion to square pond with a little island in the middle, Sugyeongwon of under pavilionu consisting of 2 ponds with a painting of three taoist hermits, forest of Mt. Bonggeong and external garden including Sapyeong Stream and farmland. According to documentation and the results of on-site investigation, it is certainly proved that Imdaejeong Wonlim was motivated by Byeoseo Wonlim which realized the idea of 'going back to hometown after resignation' following the motives of Janggujiso, a hideout aimed to accomplish the ideology, 'training mind and fostering innate nature,' on the peaceful site surrounded by water and mountain, as well as motives of Sesimcheo(洗心處) to be unified with morality of Mother Nature, etc. In addition, it implies various imaginary landscapes such as Pihangji, Eupcheongdang, square pond with an island and painting of three Taoist hermits based on a notion that 'the further scent flies away, the fresher it becomes,' which is originated from Aelyeonseol(愛蓮說). In terms of technique of natural landscape treatment, divers techniques are found in Imdaejeong Wonlim such as distant view of Mt. Bongjeong, pulling view with an intention of transparent beauty of moonlight, circle view of natural and cultural sceneries on every side, borrowed scenary of pastoral rural life adopted as an opposite view, looked view of Sulyundaero, over looked view of pond, static view in pavilion and paths, close view of water space such as stream and pond, mushroom-and-umbrella like view of Imdaejeong, vista of pond surrounded by willows, imaginary view of engraved letters meaning 'widen knowledge by studying objectives' and selected view to comprise sunrise and sunset at the same time. In the beginning of construction, various plants seemed to be planted, albeit different from now, such as Ginkgo biloba, Phyllostachys spp., Salix spp., Pinus densiflora, Abies holophylla, Morus bombycis, Juglans mandschurica, Paulownia coreana, Prunus mume, Nelumbo nucifera, etc. Generally, it reflected dignity of Confucianism or beared aspect of semantic landscape implying Taoist taste and idea of Phoenix wishing a prosperity in the future. Furthermore, a diversity of planting methods were pursued for such as liner planting for the periphery of pond, bosquet planting and circle planting adopted around the pavilion, spot planting using green trees, solitary planting of monumentally planted Paulownia coreana and opposite planting presenting the Abies holophylla into yin and yang.

• Journal of Intelligence and Information Systems
• /
• v.27 no.1
• /
• pp.83-102
• /
• 2021

The government recently announced various policies for developing big-data and artificial intelligence fields to provide a great opportunity to the public with respect to disclosure of high-quality data within public institutions. KSURE(Korea Trade Insurance Corporation) is a major public institution for financial policy in Korea, and thus the company is strongly committed to backing export companies with various systems. Nevertheless, there are still fewer cases of realized business model based on big-data analyses. In this situation, this paper aims to develop a new business model which can be applied to an ex-ante prediction for the likelihood of the insurance accident of credit guarantee. We utilize internal data from KSURE which supports export companies in Korea and apply machine learning models. Then, we conduct performance comparison among the predictive models including Logistic Regression, Random Forest, XGBoost, LightGBM, and DNN(Deep Neural Network). For decades, many researchers have tried to find better models which can help to predict bankruptcy since the ex-ante prediction is crucial for corporate managers, investors, creditors, and other stakeholders. The development of the prediction for financial distress or bankruptcy was originated from Smith(1930), Fitzpatrick(1932), or Merwin(1942). One of the most famous models is the Altman's Z-score model(Altman, 1968) which was based on the multiple discriminant analysis. This model is widely used in both research and practice by this time. The author suggests the score model that utilizes five key financial ratios to predict the probability of bankruptcy in the next two years. Ohlson(1980) introduces logit model to complement some limitations of previous models. Furthermore, Elmer and Borowski(1988) develop and examine a rule-based, automated system which conducts the financial analysis of savings and loans. Since the 1980s, researchers in Korea have started to examine analyses on the prediction of financial distress or bankruptcy. Kim(1987) analyzes financial ratios and develops the prediction model. Also, Han et al.(1995, 1996, 1997, 2003, 2005, 2006) construct the prediction model using various techniques including artificial neural network. Yang(1996) introduces multiple discriminant analysis and logit model. Besides, Kim and Kim(2001) utilize artificial neural network techniques for ex-ante prediction of insolvent enterprises. After that, many scholars have been trying to predict financial distress or bankruptcy more precisely based on diverse models such as Random Forest or SVM. One major distinction of our research from the previous research is that we focus on examining the predicted probability of default for each sample case, not only on investigating the classification accuracy of each model for the entire sample. Most predictive models in this paper show that the level of the accuracy of classification is about 70% based on the entire sample. To be specific, LightGBM model shows the highest accuracy of 71.1% and Logit model indicates the lowest accuracy of 69%. However, we confirm that there are open to multiple interpretations. In the context of the business, we have to put more emphasis on efforts to minimize type 2 error which causes more harmful operating losses for the guaranty company. Thus, we also compare the classification accuracy by splitting predicted probability of the default into ten equal intervals. When we examine the classification accuracy for each interval, Logit model has the highest accuracy of 100% for 0~10% of the predicted probability of the default, however, Logit model has a relatively lower accuracy of 61.5% for 90~100% of the predicted probability of the default. On the other hand, Random Forest, XGBoost, LightGBM, and DNN indicate more desirable results since they indicate a higher level of accuracy for both 0~10% and 90~100% of the predicted probability of the default but have a lower level of accuracy around 50% of the predicted probability of the default. When it comes to the distribution of samples for each predicted probability of the default, both LightGBM and XGBoost models have a relatively large number of samples for both 0~10% and 90~100% of the predicted probability of the default. Although Random Forest model has an advantage with regard to the perspective of classification accuracy with small number of cases, LightGBM or XGBoost could become a more desirable model since they classify large number of cases into the two extreme intervals of the predicted probability of the default, even allowing for their relatively low classification accuracy. Considering the importance of type 2 error and total prediction accuracy, XGBoost and DNN show superior performance. Next, Random Forest and LightGBM show good results, but logistic regression shows the worst performance. However, each predictive model has a comparative advantage in terms of various evaluation standards. For instance, Random Forest model shows almost 100% accuracy for samples which are expected to have a high level of the probability of default. Collectively, we can construct more comprehensive ensemble models which contain multiple classification machine learning models and conduct majority voting for maximizing its overall performance.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.23 no.4
• /
• pp.329-339
• /
• 2021

Soybeans (Glycine max), one of major upland crops, require precise management of environmental conditions, such as temperature, water, and soil, during cultivation since they are sensitive to environmental changes. Application of spectral technologies that measure the physiological state of crops remotely has great potential for improving quality and productivity of the soybean by estimating yields, physiological stresses, and diseases. In this study, we developed and validated a soybean growth prediction model using multispectral imagery. We conducted a linear regression analysis between vegetation indices and soybean growth data (fresh weight and LAI) obtained at Miryang fields. The linear regression model was validated at Goesan fields. It was found that the model based on green ratio vegetation index (GRVI) had the greatest performance in prediction of fresh weight at the calibration stage (R²=0.74, RMSE=246 g/m², RE=34.2%). In the validation stage, RMSE and RE of the model were 392 g/m² and 32%, respectively. The errors of the model differed by cropping system, For example, RMSE and RE of model in single crop fields were 315 g/m² and 26%, respectively. On the other hand, the model had greater values of RMSE (381 g/m²) and RE (31%) in double crop fields. As a result of developing models for predicting a fresh weight into two years (2018+2020) with similar accumulated temperature (AT) in three years and a single year (2019) that was different from that AT, the prediction performance of a single year model was better than a two years model. Consequently, compared with those models divided by AT and a three years model, RMSE of a single crop fields were improved by about 29.1%. However, those of double crop fields decreased by about 19.6%. When environmental factors are used along with, spectral data, the reliability of soybean growth prediction can be achieved various environmental conditions.