• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.57-73
• /
• 2021

Maintenance and prevention of failure through anomaly detection of ICT infrastructure is becoming important. System monitoring data is multidimensional time series data. When we deal with multidimensional time series data, we have difficulty in considering both characteristics of multidimensional data and characteristics of time series data. When dealing with multidimensional data, correlation between variables should be considered. Existing methods such as probability and linear base, distance base, etc. are degraded due to limitations called the curse of dimensions. In addition, time series data is preprocessed by applying sliding window technique and time series decomposition for self-correlation analysis. These techniques are the cause of increasing the dimension of data, so it is necessary to supplement them. The anomaly detection field is an old research field, and statistical methods and regression analysis were used in the early days. Currently, there are active studies to apply machine learning and artificial neural network technology to this field. Statistically based methods are difficult to apply when data is non-homogeneous, and do not detect local outliers well. The regression analysis method compares the predictive value and the actual value after learning the regression formula based on the parametric statistics and it detects abnormality. Anomaly detection using regression analysis has the disadvantage that the performance is lowered when the model is not solid and the noise or outliers of the data are included. There is a restriction that learning data with noise or outliers should be used. The autoencoder using artificial neural networks is learned to output as similar as possible to input data. It has many advantages compared to existing probability and linear model, cluster analysis, and map learning. It can be applied to data that does not satisfy probability distribution or linear assumption. In addition, it is possible to learn non-mapping without label data for teaching. However, there is a limitation of local outlier identification of multidimensional data in anomaly detection, and there is a problem that the dimension of data is greatly increased due to the characteristics of time series data. In this study, we propose a CMAE (Conditional Multimodal Autoencoder) that enhances the performance of anomaly detection by considering local outliers and time series characteristics. First, we applied Multimodal Autoencoder (MAE) to improve the limitations of local outlier identification of multidimensional data. Multimodals are commonly used to learn different types of inputs, such as voice and image. The different modal shares the bottleneck effect of Autoencoder and it learns correlation. In addition, CAE (Conditional Autoencoder) was used to learn the characteristics of time series data effectively without increasing the dimension of data. In general, conditional input mainly uses category variables, but in this study, time was used as a condition to learn periodicity. The CMAE model proposed in this paper was verified by comparing with the Unimodal Autoencoder (UAE) and Multi-modal Autoencoder (MAE). The restoration performance of Autoencoder for 41 variables was confirmed in the proposed model and the comparison model. The restoration performance is different by variables, and the restoration is normally well operated because the loss value is small for Memory, Disk, and Network modals in all three Autoencoder models. The process modal did not show a significant difference in all three models, and the CPU modal showed excellent performance in CMAE. ROC curve was prepared for the evaluation of anomaly detection performance in the proposed model and the comparison model, and AUC, accuracy, precision, recall, and F1-score were compared. In all indicators, the performance was shown in the order of CMAE, MAE, and AE. Especially, the reproduction rate was 0.9828 for CMAE, which can be confirmed to detect almost most of the abnormalities. The accuracy of the model was also improved and 87.12%, and the F1-score was 0.8883, which is considered to be suitable for anomaly detection. In practical aspect, the proposed model has an additional advantage in addition to performance improvement. The use of techniques such as time series decomposition and sliding windows has the disadvantage of managing unnecessary procedures; and their dimensional increase can cause a decrease in the computational speed in inference.The proposed model has characteristics that are easy to apply to practical tasks such as inference speed and model management.

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

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

• Korean Journal of Heritage: History & Science
• /
• v.53 no.4
• /
• pp.2-31
• /
• 2020

CheomSeongDae (瞻星臺) is a stone structure built in Gyeongju, the former Silla Dynasty capital, during the reign of Queen Seondeok (632~647AD). There exist dozens of hypotheses regarding its original purpose. Depending on to whom you ask, the answer could be a celestial observatory, a religious altar, a Buddhist stupa, a monumental tower symbolizing scientific knowledge, and so on. The most common perception of the structure among lay people is a stargazing tower. Historians, however, have suggested that it was intended as "a gateway to the heavens", specifically the Trāyastriṃśa or the second of the six heavens of Kāmadhātu located on the top of Mountain Sumeru. The name "Cheom-seong-dae" could be interpreted in many different ways. 'Cheom (瞻)' could refer to looking up, staring, or admiring, etc.; 'Seong (星)' could mean a star, heaven, night, etc.; and 'heaven' in that context can be a physical or religious reference. 'Dae (臺)' usually refers to a high platform on which people stand or things are placed. Researchers from the science fields often read 'cheom-seong' as 'looking at stars'; while historians read it as 'admiring the Trāyastriṃśa' or 'adoring Śakra'. Śakra is said to be the ruler of Trāyastriṃśa' who governs the Four Heavenly Kings in the Cāturmahārājika heaven, the first of the six heavens of Kāmadhātu. Śakra is the highest authority of the heavenly kings in direct contact with humankind. This paper examined the usages of 'cheom-seong' in Chinese literature dated prior to the publication of 『Samguk Yusa』, a late 13th century Korean Buddhist historical book that contains the oldest record of the structure among all extant historical texts. I found the oldest usage of cheom-seong (瞻星臺) in 『Ekottara Āgama』, a Buddhist script translated into Chinese in the late 4th century, and was surprised to learn that its meaning was 'looking up at the brightness left by Śakra'. I also found that 'cheom-seong' had been incorporated in various religious contexts, such as Hinduism, Confucianism, Buddhist, Christianism, and Taoism. In Buddhism, there was good, bad, and neutral cheom-seong. Good cheom-seong meant to look up to heaven in the practice of asceticism, reading the heavenly god's intentions, and achieving the mindfulness of Buddhism. Bad cheom-seong included all astrological fortunetelling activities performed outside the boundaries of Buddhism. Neutral cheom-seong is secular. It may help people to understand the nature of the physical world, but was considered to have little meaning unless relating to the spiritual world of Buddhism. Cheom-seong had been performed repetitively in the processes of constructing Buddhist temples in China. According to Buddhist scripts, Queen Māyā of Sakya, the birth mother of Gautama Buddha, died seven days after the birth of Buddha, and was reborn in the Trāyastriṃśa heaven. Buddha, before reaching nirvana, ascended from Jetavana to Trāyastriṃśa and spent three months together with his mother. Gautama Buddha then returned to the human world, stepping upon the stairs built by Viśvakarman, the deity of the creative power in Trāyastriṃśa. In later years, King Asoka built a stupa at the site where Buddha descended. Since then, people have believed that the stairway to the heavens appears at a Buddhist stupa. Carefully examining the paragraphic structure of 『Samguk Yusa』's records on Cheomseongdae, plus other historical records, the fact that the alignment between the tomb of Queen Seondeok and Cheomseongdae perfectly matches the sunrise direction at the winter solstice supports this paper's position that Chemseongdae, built in the early years of Queen SeonDeok's reign (632~647AD), was a gateway to the Trāyastriṃśa heaven, just like the stupa at the Daci Temple (慈恩寺) in China built in 654. The meaning of 'Cheom-seong-dae' thus turns out to be 'adoring Trāyastriṃśa stupa', not 'stargazing platform'.

• Korean Journal of Heritage: History & Science
• /
• v.53 no.4
• /
• pp.32-59
• /
• 2020

South Korea's area-based heritage preservation system originates from the "Preservation of Traditional Buildings Act" enacted in 1984. However, this system was abolished in 1996. As there was a need for protection of ancient cities in the 1960s, Japan enacted the Historic City Preservation Act in 1966, and 'Preservation Areas for Historic Landscapes' and 'Special Preservation Districts for Historic Landscapes' were introduced. For the preservation of area-based heritage sites, the 'Important Preservation Districts for Groups of Traditional Buildings' system introduced as part of the revision of the Cultural Heritage Protection Act in 1975 was the beginning. Then, in the early-2000s, discussions on the preservation of area-based heritage sites began in earnest, and the 'Important Cultural Landscape' system was introduced for protection of the space and context between heritage sites. Also, '33 Groups of Modernization Industry Heritage Sites' were designated in 2007, covering various material and immaterial resources related to the modernization of Japan, and '100 Beautiful Historic Landscapes of Japan' were selected for protection of local landscapes with historic value in the same year. In 2015, the "Japanese Heritage" system was established for the integrated preservation and management of tangible and intangible heritage aspects located in specific areas; in 2016, the "Japanese Agricultural Heritage" system was established for the succession and fostering of the disappearing agriculture and fishery industries; and in 2017, "the 20th Century Heritage," was established, representing evidence of modern and contemporary Japanese technologies in the 20th century. As a result, presently (in September 2020), 30 'Historic Landscape Preservation Areas', 60 'Historic Landscape Special Districts,' 120 'Important Preservation Districts for Groups of Traditional Buildings," 65 'Important Cultural Landscapes,' 66 'Groups of Modernization Industry Heritage Sites,' 264 "100 Beautiful Historic Landscapes of Japan,' 104 'Japanese Heritage Sites,' and 15 'Japanese Agricultural Heritage Sites' have been designated. According to this perception of situations, the research process for this study with its basic purpose of extracting the general characteristics of Japan's area-based heritage preservation system, has sequentially spread since 1976 as follows. First, this study investigates Japan's area-based heritage site preservation system and sets the scope of research through discussions of literature and preceding studies. Second, this study investigates the process of the spread of the area-based heritage site preservation system and analyzes the relationship between the systems according to their development, in order to draw upon their characteristics. Third, to concretize content related to relationships and characteristics, this study involves in-depth analysis of three representative examples and sums them up to identify the characteristics of Japan's area-based heritage system. A noticeable characteristic of Japan's area-based heritage site preservation system drawn from this is that new heritage sites are born each year. Consequently, an overlapping phenomenon takes place between heritage sites, and such phenomena occur alongside revitalization of related industries, traditional industry, and cultural tourism and the improvement of localities as well as the preservation of area-based heritage. These characteristics can be applied as suggestions for the revitalization of the 'modern historical and cultural space' system implemented by South Korea.

• (The)Study of the Eastern Classic
• /
• no.62
• /
• pp.145-176
• /
• 2016

This paper aims to define the leadership of Gunja (君子, translated into prince, gentleman, or ideal man) based on Confucian Classics which offer the general values and norms of individuals' virtue and social virtuous acts. Thus, humanitarianism is regarded as true value, and the values of a virtuous person who properly practices social human relationships are discussed. The real worth of Gunja image is discussed as a true human image of "self-completion and completion of all things" (成己成物) which involves the convergence of truth, good and beauty where there is a sense of harmony and balance, where there is stern self discipline and self cultivation and where win-win values of human relationships are created. Confucian saint (聖人), wise man (賢人), great man (大人), and gentleman (君子) mean social leaders. They practice human morals, enlighten and beautify society with teachings, and are indicated as equipped with mental and material harmony, good character and competence, and economic power and morality. People today pursue their own personal growth according to their material preferences rather than pure intellectual cultural values, and are engrossed in visually beautiful external unlimited competition. In this digital age, we are supposed to demonstrate our individuality, but many people are obsessed with appearance, go on severe diet, and lose their health beauty, and consequently suffer mental stress. This trend fuels obsession with appearance and the sick practice of valuing appearance. As an alternative method to overcome this phenomenon, we need a leader image with the convergence of truth, good and beauty, which is characterized by internal self cultivation, external professionalism, and handsome and solid character. Confucian thoughts consist in practicing the Way of disciplining oneself for governing others (修己治人). Self discipline involves developing personal virtuous ability for cultivating a virtuous character, and governing others involves interacting to work together in society and to have right human relationships. Thus, leaders should impress not only themselves but also others. Self discipline for governing others means cultivating virtue for oneself and leading others. A true leader has self introspection and establishes himself through self discipline so that he can govern others or reach the realm of settling others where people live together. As all things have a value and a virtue, humans endeavor to cultivate character and virtue by learning and studying for securing their professionalism, reliability, character and ability, so as to create their own brand value. Personal character does not come from a high position, wealth and power. Character is a personal virtue, and is cultivated as immaculate and fresh through self discipline. As such, it well matches with a clean and clear spirit. This offers the ideal leader as the Guja image who has an extremely humane character, as well as being equipped with inherent virtues of intellect, benevolence and courage. Self development can foster virtue and self management through self leadership and self discipline. The leader in the relationship area can practice his virtue through virtuous acts, in other words, even think from another person's perspective. Such leader is mentioned as the principle of measuring square in the Great Learning. In our viewpoint, the beauty of character can breed the seed of virtue through intellect, benevolence and courage, the beauty of win-win can realize the right virtue by showing exemplary acts to others through considerateness, and the beauty of harmony can love and care for others like me through the principle of measuring square, thereby realizing the universal principle of virtue and harmony, which is like my mind. As such, the ideal leader, when his virtue and mind of being considerate of others all blending well, can exercise his ability to the full, can live together and coexist with many people, and can grow again into a triumphant relationship.

• 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.2
• /
• pp.55-78
• /
• 2021

Tosolve complex and diverse social problems and ensure the quality of life of individuals, social robots that can interact with humans are attracting attention. In the past, robots were recognized as beings that provide labor force as they put into industrial sites on behalf of humans. However, the concept of today's robot has been extended to social robots that coexist with humans and enable social interaction with the advent of Smart technology, which is considered an important driver in most industries. Specifically, there are service robots that respond to customers, the robots that have the purpose of edutainment, and the emotionalrobots that can interact with humans intimately. However, popularization of robots is not felt despite the current information environment in the modern ICT service environment and the 4th industrial revolution. Considering social interaction with users which is an important function of social robots, not only the technology of the robots but also other factors should be considered. The design elements of the robot are more important than other factors tomake consumers purchase essentially a social robot. In fact, existing studies on social robots are at the level of proposing "robot development methodology" or testing the effects provided by social robots to users in pieces. On the other hand, consumer emotions felt from the robot's appearance has an important influence in the process of forming user's perception, reasoning, evaluation and expectation. Furthermore, it can affect attitude toward robots and good feeling and performance reasoning, etc. Therefore, this study aims to verify the effect of appearance of social robot and consumer emotions on consumer's attitude toward social robot. At this time, a social robot design evaluation model is constructed by combining heterogeneous data from different sources. Specifically, the three quantitative indicator data for the appearance of social robots from the ABOT Database is included in the model. The consumer emotions of social robot design has been collected through (1) the existing design evaluation literature and (2) online buzzsuch as product reviews and blogs, (3) qualitative interviews for social robot design. Later, we collected the score of consumer emotions and attitudes toward various social robots through a large-scale consumer survey. First, we have derived the six major dimensions of consumer emotions for 23 pieces of detailed emotions through dimension reduction methodology. Then, statistical analysis was performed to verify the effect of derived consumer emotionson attitude toward social robots. Finally, the moderated regression analysis was performed to verify the effect of quantitatively collected indicators of social robot appearance on the relationship between consumer emotions and attitudes toward social robots. Interestingly, several significant moderation effects were identified, these effects are visualized with two-way interaction effect to interpret them from multidisciplinary perspectives. This study has theoretical contributions from the perspective of empirically verifying all stages from technical properties to consumer's emotion and attitudes toward social robots by linking the data from heterogeneous sources. It has practical significance that the result helps to develop the design guidelines based on consumer emotions in the design stage of social robot development.

• 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.

• 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.