• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.157-173
• /
• 2021

With the development of information technology, the amount of available information increases daily. However, having access to so much information makes it difficult for users to easily find the information they seek. Users want a visualized system that reduces information retrieval and learning time, saving them from personally reading and judging all available information. As a result, recommendation systems are an increasingly important technologies that are essential to the business. Collaborative filtering is used in various fields with excellent performance because recommendations are made based on similar user interests and preferences. However, limitations do exist. Sparsity occurs when user-item preference information is insufficient, and is the main limitation of collaborative filtering. The evaluation value of the user item matrix may be distorted by the data depending on the popularity of the product, or there may be new users who have not yet evaluated the value. The lack of historical data to identify consumer preferences is referred to as data sparsity, and various methods have been studied to address these problems. However, most attempts to solve the sparsity problem are not optimal because they can only be applied when additional data such as users' personal information, social networks, or characteristics of items are included. Another problem is that real-world score data are mostly biased to high scores, resulting in severe imbalances. One cause of this imbalance distribution is the purchasing bias, in which only users with high product ratings purchase products, so those with low ratings are less likely to purchase products and thus do not leave negative product reviews. Due to these characteristics, unlike most users' actual preferences, reviews by users who purchase products are more likely to be positive. Therefore, the actual rating data is over-learned in many classes with high incidence due to its biased characteristics, distorting the market. Applying collaborative filtering to these imbalanced data leads to poor recommendation performance due to excessive learning of biased classes. Traditional oversampling techniques to address this problem are likely to cause overfitting because they repeat the same data, which acts as noise in learning, reducing recommendation performance. In addition, pre-processing methods for most existing data imbalance problems are designed and used for binary classes. Binary class imbalance techniques are difficult to apply to multi-class problems because they cannot model multi-class problems, such as objects at cross-class boundaries or objects overlapping multiple classes. To solve this problem, research has been conducted to convert and apply multi-class problems to binary class problems. However, simplification of multi-class problems can cause potential classification errors when combined with the results of classifiers learned from other sub-problems, resulting in loss of important information about relationships beyond the selected items. Therefore, it is necessary to develop more effective methods to address multi-class imbalance problems. We propose a collaborative filtering model using CGAN to generate realistic virtual data to populate the empty user-item matrix. Conditional vector y identify distributions for minority classes and generate data reflecting their characteristics. Collaborative filtering then maximizes the performance of the recommendation system via hyperparameter tuning. This process should improve the accuracy of the model by addressing the sparsity problem of collaborative filtering implementations while mitigating data imbalances arising from real data. Our model has superior recommendation performance over existing oversampling techniques and existing real-world data with data sparsity. SMOTE, Borderline SMOTE, SVM-SMOTE, ADASYN, and GAN were used as comparative models and we demonstrate the highest prediction accuracy on the RMSE and MAE evaluation scales. Through this study, oversampling based on deep learning will be able to further refine the performance of recommendation systems using actual data and be used to build business recommendation systems.

• MISULJARYO - National Museum of Korea Art Journal
• /
• v.97
• /
• pp.87-104
• /
• 2020

Myogilsang on Diamond Mountain, signed and dated (2000) by Seon-u Yeong (1946-2009), is the first work by a North Korean artist to enter the collection of the National Museum of Korea (fig. 1a). The donor acquired the painting directly from the artist in Pyeongyang in 2006. In consequence, there are no issues with the painting's authenticity.This painting is the largest among all existing Korean paintings, whether contemporary or from the Joseon Dynasty, to depict this iconography (see chart 1. A Chronological List of Korean Myogilsang Paintings.) It is ink and color on paper, measures 130.2 × 56.2 centimeters, and is in a hanging scroll format. Since this essay is intended as a brief introduction of the painting and not in-depth research into it, I will simply examine the following four areas: 1. Seon-u Yeong's background; 2. The location and the traditional appellation of the rock-cut image known as Myogilsang; 3. The iconography of the image; and 4) A comparative analysis of Seon-u Yeong's painting in light of other paintings on the same theme. Finally, I will present two more of his works to broaden the understanding of Seon-u Yeong as a painter. 1. Seon-u Yeong: According to the donor, who met Seon-u at his workshop in the Cheollima Jejakso (Flying Horse Workshop) three years before the artist's death, he was an individual of few words but displayed a firm commitment to art. His preference for subjects such as Korean landscapes rather than motifs of socialist realism such as revolutionary leaders is demonstrated by the fact that, relative to his North Korean contemporaries, he seems to have produced more paintings of the former. In recent years, Seon-u Yeong has been well publicized in Korea through three special exhibitions (2012 through 2019). He graduated from Pyeongyang College of Fine Arts in 1969 and joined the Central Fine Arts Production Workshop focusing on oil painting. In 1973 he entered the Joseon Painting Production Workshop and began creating traditional Korean paintings in ink and color. His paintings are characterized by intense colors and fine details. The fact that his mother was an accomplished embroidery specialist may have influenced on Seon-u's choice to use intense colors in his paintings. By 1992, he had become a painter representing the Democratic People's Republic of Korea with several titles such as Artist of Merit, People's Artist, and more. About 60 of his paintings have been designated as National Treasures of the DPRK. 2. The Myogilsang rock-cut image is located in the Manpok-dong Valley in the inner Geumgangsan Mountain area. It is a high-relief image about 15 meters tall cut into a niche under 40 meters of a rock cliff. It is the largest of all the rock-cut images of the Goryeo period. This image is often known as "Mahayeon Myogilsang," Mahayeon (Mahayana) being the name of a small temple deep in the Manpokdong Valley (See fig. 3a & 3b). On the right side of the image, there is an intaglio inscription of three Chinese characters by the famous scholar-official and calligrapher Yun Sa-guk (1728-1709) reading "妙吉祥"myogilsang (fig. 4a, 4b). 3. The iconography: "Myogilsang" is another name for the Bhodhisattva Mañjuśrī. The Chinese pronunciation of Myogilsang is "miaojixiang," which is similar in pronunciation to Mañjuśrī. Therefore, we can suggest a 妙吉祥 ↔ Mañjuśrī formula for the translation and transliteration of the term. Even though the image was given a traditional name, the mudra presented by the two hands in the image calls for a closer examination. They show the making of a circle by joining the thumb with the ring finger (fig. 6). If the left land pointed downward, this mudra would conventionally be considered "lower class: lower life," one of the nine mudras of the Amitabha. However, in this image the left hand is placed across its abdomen at an almost 90-degree angle to the right hand (fig. 6). This can be interpreted as a combination of the "fear not" and the "preaching" mudras (see note 10, D. Saunders). I was also advised by the noted Buddhist art specialist Professor Kim Jeong-heui (of Won'gwang University) to presume that this is the "preaching" mudra. Therefore, I have tentatively concluded that this Myogilsang is an image of the Shakyamuni offering the preaching mudra. There is no such combination of hand gestures in any other Goryeo-period images. The closest I could identify is the Beopjusa Rock-cut Buddha (fig. 7) from around the same time. 4. Comparative analysis: As seen in , except for the two contemporary paintings, all others on this chart are in ink or ink and light color. Also, none of them included the fact that the image is under a 40-meter cliff. In addition, the Joseon-period paintings all depicted the rock-cut image as if it were a human figure, using soft brushstrokes and rounded forms. None of these paintings accurately rendered the mudra from the image as did Seon-u. Only his painting depicts the natural setting of the image under the cliff along with a realistic rendering of the image. However, by painting the tall cliff in dark green and by eliminating elements on either side of the rock-cut image, the artist was able to create an almost surreal atmosphere surrounding the image. Herein lies the uniqueness of Seon-u Yeong's version. The left side of Seon-u's 2007 work Mount Geumgang (fig. 8) lives up to his reputation as a painter who depicts forms (rocks in this case) in minute detail, but in the right half of the composition it also shows his skill at presenting a sense of space. In contrast, Wave (fig. 9), a work completed one year before his death, displays his faithfulness to the traditions of ink painting. Even based on only three paintings by Seon-u Yeong, it seems possible to assess his versatility in both traditional ink and color mediums.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.57-78
• /
• 2020

With the development of the Internet, consumers have had an opportunity to check product information easily through E-Commerce. Product reviews used in the process of purchasing goods are based on user experience, allowing consumers to engage as producers of information as well as refer to information. This can be a way to increase the efficiency of purchasing decisions from the perspective of consumers, and from the seller's point of view, it can help develop products and strengthen their competitiveness. However, it takes a lot of time and effort to understand the overall assessment and assessment dimensions of the products that I think are important in reading the vast amount of product reviews offered by E-Commerce for the products consumers want to compare. This is because product reviews are unstructured information and it is difficult to read sentiment of reviews and assessment dimension immediately. For example, consumers who want to purchase a laptop would like to check the assessment of comparative products at each dimension, such as performance, weight, delivery, speed, and design. Therefore, in this paper, we would like to propose a method to automatically generate multi-dimensional product assessment scores in product reviews that we would like to compare. The methods presented in this study consist largely of two phases. One is the pre-preparation phase and the second is the individual product scoring phase. In the pre-preparation phase, a dimensioned classification model and a sentiment analysis model are created based on a review of the large category product group review. By combining word embedding and association analysis, the dimensioned classification model complements the limitation that word embedding methods for finding relevance between dimensions and words in existing studies see only the distance of words in sentences. Sentiment analysis models generate CNN models by organizing learning data tagged with positives and negatives on a phrase unit for accurate polarity detection. Through this, the individual product scoring phase applies the models pre-prepared for the phrase unit review. Multi-dimensional assessment scores can be obtained by aggregating them by assessment dimension according to the proportion of reviews organized like this, which are grouped among those that are judged to describe a specific dimension for each phrase. In the experiment of this paper, approximately 260,000 reviews of the large category product group are collected to form a dimensioned classification model and a sentiment analysis model. In addition, reviews of the laptops of S and L companies selling at E-Commerce are collected and used as experimental data, respectively. The dimensioned classification model classified individual product reviews broken down into phrases into six assessment dimensions and combined the existing word embedding method with an association analysis indicating frequency between words and dimensions. As a result of combining word embedding and association analysis, the accuracy of the model increased by 13.7%. The sentiment analysis models could be seen to closely analyze the assessment when they were taught in a phrase unit rather than in sentences. As a result, it was confirmed that the accuracy was 29.4% higher than the sentence-based model. Through this study, both sellers and consumers can expect efficient decision making in purchasing and product development, given that they can make multi-dimensional comparisons of products. In addition, text reviews, which are unstructured data, were transformed into objective values such as frequency and morpheme, and they were analysed together using word embedding and association analysis to improve the objectivity aspects of more precise multi-dimensional analysis and research. This will be an attractive analysis model in terms of not only enabling more effective service deployment during the evolving E-Commerce market and fierce competition, but also satisfying both customers.