• Journal of Intelligence and Information Systems
• /
• v.26 no.4
• /
• pp.111-126
• /
• 2020

Most industries have recently become aware of the importance of customer lifetime value as they are exposed to a competitive environment. As a result, preventing customers from churn is becoming a more important business issue than securing new customers. This is because maintaining churn customers is far more economical than securing new customers, and in fact, the acquisition cost of new customers is known to be five to six times higher than the maintenance cost of churn customers. Also, Companies that effectively prevent customer churn and improve customer retention rates are known to have a positive effect on not only increasing the company's profitability but also improving its brand image by improving customer satisfaction. Predicting customer churn, which had been conducted as a sub-research area for CRM, has recently become more important as a big data-based performance marketing theme due to the development of business machine learning technology. Until now, research on customer churn prediction has been carried out actively in such sectors as the mobile telecommunication industry, the financial industry, the distribution industry, and the game industry, which are highly competitive and urgent to manage churn. In addition, These churn prediction studies were focused on improving the performance of the churn prediction model itself, such as simply comparing the performance of various models, exploring features that are effective in forecasting departures, or developing new ensemble techniques, and were limited in terms of practical utilization because most studies considered the entire customer group as a group and developed a predictive model. As such, the main purpose of the existing related research was to improve the performance of the predictive model itself, and there was a relatively lack of research to improve the overall customer churn prediction process. In fact, customers in the business have different behavior characteristics due to heterogeneous transaction patterns, and the resulting churn rate is different, so it is unreasonable to assume the entire customer as a single customer group. Therefore, it is desirable to segment customers according to customer classification criteria, such as loyalty, and to operate an appropriate churn prediction model individually, in order to carry out effective customer churn predictions in heterogeneous industries. Of course, in some studies, there are studies in which customers are subdivided using clustering techniques and applied a churn prediction model for individual customer groups. Although this process of predicting churn can produce better predictions than a single predict model for the entire customer population, there is still room for improvement in that clustering is a mechanical, exploratory grouping technique that calculates distances based on inputs and does not reflect the strategic intent of an entity such as loyalties. This study proposes a segment-based customer departure prediction process (CCP/2DL: Customer Churn Prediction based on Two-Dimensional Loyalty segmentation) based on two-dimensional customer loyalty, assuming that successful customer churn management can be better done through improvements in the overall process than through the performance of the model itself. CCP/2DL is a series of churn prediction processes that segment two-way, quantitative and qualitative loyalty-based customer, conduct secondary grouping of customer segments according to churn patterns, and then independently apply heterogeneous churn prediction models for each churn pattern group. Performance comparisons were performed with the most commonly applied the General churn prediction process and the Clustering-based churn prediction process to assess the relative excellence of the proposed churn prediction process. The General churn prediction process used in this study refers to the process of predicting a single group of customers simply intended to be predicted as a machine learning model, using the most commonly used churn predicting method. And the Clustering-based churn prediction process is a method of first using clustering techniques to segment customers and implement a churn prediction model for each individual group. In cooperation with a global NGO, the proposed CCP/2DL performance showed better performance than other methodologies for predicting churn. This churn prediction process is not only effective in predicting churn, but can also be a strategic basis for obtaining a variety of customer observations and carrying out other related performance marketing activities.

• MISULJARYO - National Museum of Korea Art Journal
• /
• v.98
• /
• pp.104-129
• /
• 2020

Designated as a national treasure of Korea and inscribed on the UNESCO World Heritage List, the Tripitaka Koreana at Haeinsa Temple is the world's oldest and most comprehensive extant version of the Tripitaka in Hanja script (i.e., Chinese characters). The set consists of 81,352 carved woodblocks, some of which have two or more copies, which are known as "duplicate woodblocks." These duplicates are supplementary woodblocks (bogakpan) that were carved some time after the original production, likely to replace blocks that had been eroded or damaged by repeated printings. According to the most recent survey, the number of supplementary woodblocks is 118, or approximately 0.14% of the total set, which attests to the outstanding preservation of the original woodblocks. Research on the supplementary woodblocks can reveal important details about the preservation and management of the Tripitaka Koreana woodblocks. Most of the supplementary woodblocks were carved during the Joseon period (1392-1910) or Japanese colonial period (1910-1945). Although the details of the woodblocks from the Japanese colonial period have been recorded and organized to a certain extent, no such efforts have been made with regards to the woodblocks from the Joseon period. This paper analyzes the characteristics and production date of the supplementary woodblocks of the Tripitaka Koreana. The sutra with the most supplementary woodblocks is the Maha Prajnaparamita Sutra (Perfection of Transcendental Wisdom), often known as the Heart Sutra. In fact, 76 of the total 118 supplementary woodblocks (64.4%) are for this sutra. Hence, analyses of printed versions of the Maha Prajnaparamita Sutra should illuminate trends in the carving of supplementary woodblocks for the Tripitaka Koreana, including the representative characteristics of different periods. According to analysis of the 76 supplementary woodblocks of the Maha Prajnaparamita Sutra, 23 were carved during the Japanese colonial period: 12 in 1915 and 11 in 1937. The remaining 53 were carved during the Joseon period at three separate times. First, 14 of the woodblocks bear the inscription "carved in the mujin year by Haeji" ("戊辰年更刻海志"). Here, the "mujin year" is estimated to correspond to 1448, or the thirtieth year of the reign of King Sejong. On many of these 14 woodblocks, the name of the person who did the carving is engraved outside the border. One of these names is Seonggyeong, an artisan who is known to have been active in 1446, thus supporting the conclusion that the mujin year corresponds to 1448. The vertical length of these woodblocks (inside the border) is 21 cm, which is about 1 cm shorter than the original woodblocks. Some of these blocks were carved in the Zhao Mengfu script. Distinguishing features include the appearance of faint lines on some plates, and the rough finish of the bottoms. The second group of supplementary woodblocks was carved shortly after 1865, when the monks Namho Yeonggi and Haemyeong Jangung had two copies of the Tripitaka Koreana printed. At the time, some of the pages could not be printed because the original woodblocks were damaged. This is confirmed by the missing pages of the extant copy that is now preserved at Woljeongsa Temple. As a result, the supplementary woodblocks are estimated to have been produced immediately after the printing. Evidently, however, not all of the damaged woodblocks could be replaced at this time, as only six woodblocks (comprising eight pages) were carved. On the 1865 woodblocks, lines can be seen between the columns, no red paint was applied, and the prayers of patrons were also carved into the plates. The third carving of supplementary woodblocks occurred just before 1899, when the imperial court of the Korean Empire sponsored a new printing of the Tripitaka Koreana. Government officials who were dispatched to supervise the printing likely inspected the existing blocks and ordered supplementary woodblocks to be carved to replace those that were damaged. A total of 33 supplementary woodblocks (comprising 56 pages) were carved at this time, accounting for the largest number of supplementary woodblocks for the Maha Prajnaparamita Sutra. On the 1899 supplementary woodblocks, red paint was applied to each plate and one line was left blank at both ends.

• 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.

• The Journal of Korean Society for Radiation Therapy
• /
• v.32
• /
• pp.17-29
• /
• 2020

Purpose: The purpose of this work was to investigate the dosimetric impact of mixed energy partial arc technique on prostate cancer VMAT. Materials and Methods: This study involved prostate only patients planned with 70Gy in 30 fractions to the planning target volume (PTV). Femoral heads, Bladder and Rectum were considered as oragan at risk (OARs). For this study, mixed energy partial arcs (MEPA) were generated with gantry angle set to 180°~230°, 310°~50° for 6MV arc and 130°~50°, 310°~230° for 15MV arc. Each arc set the avoidance sector which is gantry angle 230°~310°, 50°~130° at first arc and 50°~310° at second arc. After that, two plans were summed and were analyzed the dosimetry parameter of each structure such as Maximum dose, Mean dose, D2%, Homogeneity index (HI) and Conformity Index (CI) for PTV and Maximum dose, Mean dose, V70Gy, V50Gy, V30Gy, and V20Gy for OARs and Monitor Unit (MU) with 6MV 1 ARC, 6MV, 10MV, 15MV 2 ARC plan. Results: In MEPA, the maximum dose, mean dose and D2% were lower than 6MV 1 ARC plan(p<0.0005). However, the average difference of maximum dose was 0.24%, 0.39%, 0.60% (p<0.450, 0.321, 0.139) higher than 6MV, 10MV, 15MV 2 ARC plan, respectively and D2% was 0.42%, 0.49%, 0.59% (p<0.073, 0.087, 0.033) higher than compared plans. The average difference of mean dose was 0.09% lower than 10MV 2 ARC plan, but it is 0.27%, 0.12% (p<0.184, 0.521) higher than 6MV 2 ARC, 15MV 2 ARC plan, respectively. HI was 0.064±0.006 which is the lowest value (p<0.005, 0.357, 0.273, 0.801) among the all plans. For CI, there was no significant differences which were 1.12±0.038 in MEPA, 1.12±0.036, 1.11±0.024, 1.11±0.030, 1.12±0.027 in 6MV 1 ARC, 6MV, 10MV, 15MV 2 ARC, respectively. MEPA produced significantly lower rectum dose. Especially, V70Gy, V50Gy, V30Gy, V20Gy were 3.40, 16.79, 37.86, 48.09 that were lower than other plans. For bladder dose, V30Gy, V20Gy were lower than other plans. However, the mean dose of both femoral head were 9.69±2.93, 9.88±2.5 which were 2.8Gy~3.28Gy higher than other plans. The mean MU of MEPA were 19.53% lower than 6MV 1 ARC, 5.7% lower than 10MV 2 ARC respectively. Conclusion: This study for prostate radiotherapy demonstrated that a choice of MEPA VMAT has the potential to minimize doses to OARs and improve homogeneity to PTV at the expense of a moderate increase in maximum and mean dose to the femoral heads.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.25 no.2
• /
• pp.15-24
• /
• 2021

Purpose SPECT/CT was noted for its excellent correction method and qualitative functions based on fusion images in the early stages of dissemination, and interest in and utilization of quantitative functions has been increasing with the recent introduction of companion diagnostic therapy(Theranostics). Unlike PET/CT, various conditions like the type of collimator and detector rotation are a challenging factor for image acquisition and reconstruction methods at absolute quantification of SPECT/CT. Therefore, in this study, We want to find out the effect on the radioactivity concentration estimate by the increase or decrease of the total acquisition time according to the number of projections and the acquisition time per projection among SPECT/CT imaging conditions. Materials and Methods After filling the 9,293 ml cylindrical phantom with sterile water and diluting 99mTc 91.76 MBq, the standard image was taken with a total acquisition time of 600 sec (10 sec/frame × 120 frames, matrix size 128 × 128) and also volume sensitivity and the calibration factor was verified. Based on the standard image, the comparative images were obtained by increasing or decreasing the total acquisition time. namely 60 (-90%), 150 (-75%), 300 (-50%), 450 (-25%), 900 (+50%), and 1200 (+100%) sec. For each image detail, the acquisition time(sec/frame) per projection was set to 1.0, 2.5, 5.0, 7.5, 15.0 and 20.0 sec (fixed number of projections: 120 frame) and the number of projection images was set to 12, 30, 60, 90, 180 and 240 frames(fixed time per projection:10 sec). Based on the coefficients measured through the volume of interest in each acquired image, the percentage of variation about the contrast to noise ratio (CNR) was determined as a qualitative assessment, and the quantitative assessment was conducted through the percentage of variation of the radioactivity concentration estimate. At this time, the relationship between the radioactivity concentration estimate (cps/ml) and the actual radioactivity concentration (Bq/ml) was compared and analyzed using the recovery coefficient (RC_Recovery Coefficients) as an indicator. Results The results [CNR, radioactivity Concentration, RC] by the change in the number of projections for each increase or decrease rate (-90%, -75%, -50%, -25%, +50%, +100%) of total acquisition time are as follows. [-89.5%, +3.90%, 1.04] at -90%, [-77.9%, +2.71%, 1.03] at -75%, [-55.6%, +1.85%, 1.02] at -50%, [-33.6%, +1.37%, 1.01] at -25%, [-33.7%, +0.71%, 1.01] at +50%, [+93.2%, +0.32%, 1.00] at +100%. and also The results [CNR, radioactivity Concentration, RC] by the acquisition time change for each increase or decrease rate (-90%, -75%, -50%, -25%, +50%, +100%) of total acquisition time are as follows. [-89.3%, -3.55%, 0.96] at - 90%, [-73.4%, -0.17%, 1.00] at -75%, [-49.6%, -0.34%, 1.00] at -50%, [-24.9%, 0.03%, 1.00] at -25%, [+49.3%, -0.04%, 1.00] at +50%, [+99.0%, +0.11%, 1.00] at +100%. Conclusion In SPECT/CT, the total coefficient obtained according to the increase or decrease of the total acquisition time and the resulting image quality (CNR) showed a pattern that changed proportionally. On the other hand, quantitative evaluations through absolute quantification showed a change of less than 5% (-3.55 to +3.90%) under all experimental conditions, maintaining quantitative accuracy (RC 0.96 to 1.04). Considering the reduction of the total acquisition time rather than the increasing of the image acquiring time, The reduction in total acquisition time is applicable to quantitative analysis without significant loss and is judged to be clinically effective. This study shows that when increasing or decreasing of total acquisition time, changes in acquisition time per projection have fewer fluctuations that occur in qualitative and quantitative condition changes than the change in the number of projections under the same scanning time conditions.

• Journal of the Daesoon Academy of Sciences
• /
• v.36
• /
• pp.227-266
• /
• 2020

The purpose of this paper is to review the representative Buddhist policies enforced during the reign of Gwanghaegun (光海君), the 15th king of the Joseon Dynasty, and the aspects of the Buddhist community affected by them. Through this, the influence and dynamism of Buddhism during the reign of Gwanghaegun will be revealed. Some of the findings will run contrary to what is popularly known about Joseon Buddhism and the policy of Sungyueokbul (崇儒抑佛), 'Revering Confucianism and Supressing Buddhism.' During the Joseon Dynasty, Neo-Confucianism was taken as an ideological background, and consequently, Buddhism was ostracized by the ruling class who advocated the exclusion of heretical views. This also characterized King Gwanghaegun's reign during the Mid-Joseon Dynasty. In reality though, the ruling class held mixed opinions about Buddhism, and this influenced the Buddhist community in the Gwanghaegun Period. The military might of Japan demonstrated during the Japanese Invasion of Korea in 1592, led the ruling class to recognize Buddhism, and as a result, the status of Buddhism rose to a certain extent. Based on its elevated status and the aftermath of the Japanese Invasion of Korea, the Buddhist community engaged in social welfare activities inspired by the notion of requiting favors, and the Buddhist community gained recognition for providing relief services. As a result, the number of monks increased, and the economic situation improved as land ownership was granted to temples and monks. This is the means by which the Japanese Invasion of Korea influenced the Buddhist policies of the Gwanghaegun Period and changed the religious topography of Buddhism. During the reign of King Gwanghaegun, the ruling class regarded Buddhism as heretical, but offered posthumous titles to monks who engaged in meritorious services during the Japanese invasions of 1592~1598. Favorable and/or preferential treatment was also granted to some Buddhist monks. In addition, monks began to perform labor projects that demanded organizational and physical strength, such as those which related to national defense and architecture. However, throughout the Gwanghaegun Period, the monks were paid a certain amount of compensation for their labor, and the monks' responsibility for labor increased. This can be understood as a partial reconciliation with Buddhism or an acceptance of Buddhism rather than the suppression of Buddhism often presented by historians. As for policies which affected Buddhism, the Buddhist community showed signs of cooperation with the ruling class, the creation and reconstruction of temples, and the production of Buddhist art. Through close ties with the ruling class, Buddhism during the Gwanghaegun Period saw the Buddhist community actively responded policies that impacted Buddhism, and this allowed their religious orders to be maintained. In this way, it was also confirmed that the monk, Buhyu Seonsu (浮休 善修) and his disciple Byeogam Gakseong (碧巖 覺性), took up leadership roles in their Buddhist community. The Buddhist-aimed policies of Gwanghaegun were implemented against the backdrop of the Buddhist community, wherein the ruling class held mixed opinions regarding Buddhism. As such, both improvements and set backs for Buddhism could be observed during that time period. The ruling class actively utilized the organizational power of Buddhism for national defense and civil engineering after the Japanese invasions of 1592~1598. Out of gratitude, they implemented appropriate compensation for the Buddhists involved. The Buddhist community also responded to policies that affected them through exchanges with the ruling class. They succeeded in securing funds and support to repair and produce Buddhist temples and artworks. A thoughtful inspection of the policies towards and responses to Buddhism during the Gwanghaegun Period, shows that Buddhism actually enjoyed considerable organizational power and influence. This flies in the face of the general description of Joseon Buddhism as "Sungyueokbul (revering Confucianism and supressing Buddhism)."

• Journal of the Daesoon Academy of Sciences
• /
• v.36
• /
• pp.1-34
• /
• 2020

It has been suggested that Jeungsan's prophetic poem that starts with the verse "For about seven or eight years, there will be a castle in the ancient country [七八年間古國城] ⋯" originally comes from Prophecies of Jeong Gam (鄭鑑錄). Despite Jeungsan, himself, obviously having been critical of that text, this claim has become the basic grounds for discourse suggesting that Jeungsan was not only interested in Prophecies of Jeong Gam but also considerably influenced by the text. However, the claim itself was formulated due to misunderstandings of the Chinese poems that had been included in A Compilation of Secret Prophecies Hidden in the Family-clan of Seogye (西溪家臧訣). These poems pursue a different ideological orientation than the poem from Prophecies of Jeong Gam. Ultimately, the Chinese poem in the verse 84 the chapter titled, Prophetic Elucidations in The Canonical Scripture of Daesoon Jinrihoe cannot provide a basis for the claim that Jeungsan was strongly influenced by Prophecies of Jeong Gam. This claim that Prophecies of Jeong Gam made a deep impact on Jeungsan and Daesoon Thought was based on three other texts outside of those that appear within verse 84 of Prophetic Elucidations. The first supposedly-related line is: "Heaven opens at the period of the Rat (Ja 子), Earth opens at the period of the Ox (Chuk 丑), humankind starts at the period of the Tiger (Ihn 寅)." This line comes from from Shao Kangjie's Book of Supreme World Ordering Principles (皇極經世), and the line could be quoted idiomatically as an expression in the Joseon Dynasty. Accordingly, attempts to relate Daesoon Thought to Prophecies of Jeong Gam are a distortion that arise from the assumption that Jeungsan had a significant interest in Prophecies of Jeong Gam. The second related line is "At the foot of Mount Mother (母岳山), a golden icon of Buddha has the ability to speak [母岳山下 金佛能言]." That line is nearly identical to the verse "On the summit of Mount Mother, a golden icon of Buddha has the ability to speak [母岳山頭 金佛能言]." Yet, Jeungsan changed '頭 (du, the summit)' to '下 (ha, the foot or under)' and express his own unique religious prophecy. This allusion to the prophecies of Jeong Gam is actually a criticism designed to disprove the earlier prophecy. Third, is the verse, "The form of Buddhism, creation of daoism, and propriety of Confucianism [佛之形體仙之造化儒之凡節]," which is characteristically related to Daesoon Thought. This verse can only be found in the prophetic text, Prophecies of Chochang (蕉蒼訣), and it is provided a main source when alleging that Prophecies of Jeong Gam was an influence on Daesoon Thought. However, considering the context of Prophecies of Chochang and the year of its publication (it is assumed to be compiled after 1950s), this does not hold water as Jeungsan had already passed into Heaven several decades before that time. This disqualifies the verse from being a basis for asserting Prophecies of Jeong Gam as an influence on Daesoon Thought. Contrary to the original assertion, there is a considerable amount of evidence that Prophecies of Chochang absorbed aspects of Daesoon Thought, which were simply revised in a novel way. There is no truly compelling evidence underpinning the argument that Prophecies of Jeong Gam had a unilateral impact on Daesoon Thought. There seems to be a great deal of confusion and numerous misinterpretations on this matter. Therefore, the claim that Daesoon Thought, as developed by Jeungsan, was influenced by the discourse on dynastic revolution and feng shui contained in Prophecies of Jeong Gam should be re-examined at the level of its very premise.

• Journal of Intelligence and Information Systems
• /
• v.27 no.4
• /
• pp.1-22
• /
• 2021

Aspect Based Sentiment Analysis (ABSA), which analyzes sentiment based on aspects that appear in the text, is drawing attention because it can be used in various business industries. ABSA is a study that analyzes sentiment by aspects for multiple aspects that a text has. It is being studied in various forms depending on the purpose, such as analyzing all targets or just aspects and sentiments. Here, the aspect refers to the property of a target, and the target refers to the text that causes the sentiment. For example, for restaurant reviews, you could set the aspect into food taste, food price, quality of service, mood of the restaurant, etc. Also, if there is a review that says, "The pasta was delicious, but the salad was not," the words "steak" and "salad," which are directly mentioned in the sentence, become the "target." So far, in ABSA, most studies have analyzed sentiment only based on aspects or targets. However, even with the same aspects or targets, sentiment analysis may be inaccurate. Instances would be when aspects or sentiment are divided or when sentiment exists without a target. For example, sentences like, "Pizza and the salad were good, but the steak was disappointing." Although the aspect of this sentence is limited to "food," conflicting sentiments coexist. In addition, in the case of sentences such as "Shrimp was delicious, but the price was extravagant," although the target here is "shrimp," there are opposite sentiments coexisting that are dependent on the aspect. Finally, in sentences like "The food arrived too late and is cold now." there is no target (NULL), but it transmits a negative sentiment toward the aspect "service." Like this, failure to consider both aspects and targets - when sentiment or aspect is divided or when sentiment exists without a target - creates a dual dependency problem. To address this problem, this research analyzes sentiment by considering both aspects and targets (Target-Aspect-Sentiment Detection, hereby TASD). This study detected the limitations of existing research in the field of TASD: local contexts are not fully captured, and the number of epochs and batch size dramatically lowers the F1-score. The current model excels in spotting overall context and relations between each word. However, it struggles with phrases in the local context and is relatively slow when learning. Therefore, this study tries to improve the model's performance. To achieve the objective of this research, we additionally used auxiliary loss in aspect-sentiment classification by constructing CNN(Convolutional Neural Network) layers parallel to existing models. If existing models have analyzed aspect-sentiment through BERT encoding, Pooler, and Linear layers, this research added CNN layer-adaptive average pooling to existing models, and learning was progressed by adding additional loss values for aspect-sentiment to existing loss. In other words, when learning, the auxiliary loss, computed through CNN layers, allowed the local context to be captured more fitted. After learning, the model is designed to do aspect-sentiment analysis through the existing method. To evaluate the performance of this model, two datasets, SemEval-2015 task 12 and SemEval-2016 task 5, were used and the f1-score increased compared to the existing models. When the batch was 8 and epoch was 5, the difference was largest between the F1-score of existing models and this study with 29 and 45, respectively. Even when batch and epoch were adjusted, the F1-scores were higher than the existing models. It can be said that even when the batch and epoch numbers were small, they can be learned effectively compared to the existing models. Therefore, it can be useful in situations where resources are limited. Through this study, aspect-based sentiments can be more accurately analyzed. Through various uses in business, such as development or establishing marketing strategies, both consumers and sellers will be able to make efficient decisions. In addition, it is believed that the model can be fully learned and utilized by small businesses, those that do not have much data, given that they use a pre-training model and recorded a relatively high F1-score even with limited resources.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.67 no.1
• /
• pp.1-8
• /
• 2022

In order to manufacture feed suitable for consumer use and provide feed value information, we analyzed the feed components of the four main forage rice varieties by plant parts harvested 30 days after heading. The contents of the six feed ingredients were significantly different (p<0.05) among harvested parts. In the panicle, the crude protein (CP) (6.97%) and lignin (3.11%) were the highest, while the crude ash (CA) and neutral detergent fiber (NDF) contents were significantly lower, resulting in a total digestible nutrient (TDN) content of 77.29%, which is higher than that of the stem (64.82%) and leaf blade and sheath (LBS) (63.57%) (p<0.05). In contrast, the content of crude fat (CF) did not differ significantly among parts (p<0.05). In panicles from 'Jonong', 'Nokyang' and 'Yeongwoo', the TDN content of each cultivar was 78.48-79.07%, with no significant difference among the varieties. In 'Mogwoo' (Mw), the CP content was 8.70%, which was much higher than that of other varieties (p<0.05). In particular, the Mw TDN content was slightly lower in the panicle (72.95%) but higher in the stem (75.37%) and LBS (66.49%) than in the other varieties. The CA, NDF, acid detergent fiber (ADF), and lignin contents were also very low compared to other varieties; therefore, the feed value of the stem and LBS was excellent. In addition, the total dry matter weight (DMW) was 123 g per hill, which was much higher than 82-105 g per hill for other varieties. The distribution of DMW by part was LBS (56.9 g), stem (36.8 g), and panicle (29.3 g), and because the parts, except the panicles, were much higher than the 43-57% of other varieties (grain straw ratio: 76%), rice straw is advantageous in terms of quantity and feed value when used as forage on farms. The relative feed value (RFV) of the four cultivars ranged from 86.79-403.74 across all parts, and hay of grade 3 or higher with an RFV of 100 or more increased with delayed heading in both stems and LBS. This is due to the accumulation of starch into grains during ripening, which supports the observation that the RFV of the early flowering 'Jonong' and 'Nokyang' panicles increased.

• Trans-
• /
• v.12
• /
• pp.51-79
• /
• 2022

This study investigates the methods for deriving colors which can serve as a reference to users such as designers and or contents creators who search for online images from the web portal sites using specific words for color planning and more. Two experiments were conducted in order to accomplish this. Digital scenery photos within the geographic scope of Korea were downloaded from web portal sites, and those photos were studied to find out what colors were used to describe daytime and nighttime. Machine learning was used as the study methodology to classify colors in daytime and nighttime, and KSCA was used to derive the color frequency of daytime and nighttime photos and to compare and analyze the two results. The results of classifying the colors of daytime and nighttime photos using machine learning show that, when classifying the colors by 51~100%, the area of daytime colors was approximately 2.45 times greater than that of nighttime colors. The colors of the daytime class were distributed by brightness with white as its center, while that of the nighttime class was distributed with black as its center. Colors that accounted for over 70% of the daytime class were 647, those over 70% of the nighttime class were 252, and the rest (31-69%) were 101. The number of colors in the middle area was low, while other colors were classified relatively clearly into day and night. The resulting color distributions in the daytime and nighttime classes were able to provide the borderline color values of the two classes that are classified by brightness. As a result of analyzing the frequency of digital photos using KSCA, colors around yellow were expressed in generally bright daytime photos, while colors around blue value were expressed in dark night photos. For frequency of daytime photos, colors on the upper 40% had low chroma, almost being achromatic. Also, colors that are close to white and black showed the highest frequency, indicating a large difference in brightness. Meanwhile, for colors with frequency from top 5 to 10, yellow green was expressed darkly, and navy blue was expressed brightly, partially composing a complex harmony. When examining the color band, various colors, brightness, and chroma including light blue, achromatic colors, and warm colors were shown, failing to compose a generally harmonious arrangement of colors. For the frequency of nighttime photos, colors in approximately the upper 50% are dark colors with a brightness value of 2 (Munsell signal). In comparison, the brightness of middle frequency (50-80%) is relatively higher (brightness values of 3-4), and the brightness difference of various colors was large in the lower 20%. Colors that are not cool colors could be found intermittently in the lower 8% of frequency. When examining the color band, there was a general harmonious arrangement of colors centered on navy blue. As the results of conducting the experiment using two methods in this study, machine learning could classify colors into two or more classes, and could evaluate how close an image was with certain colors to a certain class. This method cannot be used if an image cannot be classified into a certain class. The result of such color distribution would serve as a reference when determining how close a certain color is to one of the two classes when the color is used as a dominant color in the base or background color of a certain design. Also, when dividing the analyzed images into several classes, even colors that have not been used in the analyzed image can be determined to find out how close they are to a certain class according to the color distribution properties of each class. Nevertheless, the results cannot be used to find out whether a specific color was used in the class and by how much it was used. To investigate such an issue, frequency analysis was conducted using KSCA. The color frequency could be measured within the range of images used in the experiment. The resulting values of color distribution and frequency from this study would serve as references for color planning of digital design regarding natural scenery in the geographic scope of Korea. Also, the two experiments are meaningful attempts for searching the methods for deriving colors that can be a useful reference among numerous images for content creator users of the relevant field.