• Journal of Intelligence and Information Systems
• /
• v.19 no.3
• /
• pp.57-71
• /
• 2013

Over a billion people in the world generate new news minute by minute. People forecasts some news but most news are from unexpected events such as natural disasters, accidents, crimes. People spend much time to watch a huge amount of news delivered from many media because they want to understand what is happening now, to predict what might happen in the near future, and to share and discuss on the news. People make better daily decisions through watching and obtaining useful information from news they saw. However, it is difficult that people choose news suitable to them and obtain useful information from the news because there are so many news media such as portal sites, broadcasters, and most news articles consist of gossipy news and breaking news. User interest changes over time and many people have no interest in outdated news. From this fact, applying users' recent interest to personalized news service is also required in news service. It means that personalized news service should dynamically manage user profiles. In this paper, a content-based news recommendation system is proposed to provide the personalized news service. For a personalized service, user's personal information is requisitely required. Social network service is used to extract user information for personalization service. The proposed system constructs dynamic user profile based on recent user information of Facebook, which is one of social network services. User information contains personal information, recent articles, and Facebook Page information. Facebook Pages are used for businesses, organizations and brands to share their contents and connect with people. Facebook users can add Facebook Page to specify their interest in the Page. The proposed system uses this Page information to create user profile, and to match user preferences to news topics. However, some Pages are not directly matched to news topic because Page deals with individual objects and do not provide topic information suitable to news. Freebase, which is a large collaborative database of well-known people, places, things, is used to match Page to news topic by using hierarchy information of its objects. By using recent Page information and articles of Facebook users, the proposed systems can own dynamic user profile. The generated user profile is used to measure user preferences on news. To generate news profile, news category predefined by news media is used and keywords of news articles are extracted after analysis of news contents including title, category, and scripts. TF-IDF technique, which reflects how important a word is to a document in a corpus, is used to identify keywords of each news article. For user profile and news profile, same format is used to efficiently measure similarity between user preferences and news. The proposed system calculates all similarity values between user profiles and news profiles. Existing methods of similarity calculation in vector space model do not cover synonym, hypernym and hyponym because they only handle given words in vector space model. The proposed system applies WordNet to similarity calculation to overcome the limitation. Top-N news articles, which have high similarity value for a target user, are recommended to the user. To evaluate the proposed news recommendation system, user profiles are generated using Facebook account with participants consent, and we implement a Web crawler to extract news information from PBS, which is non-profit public broadcasting television network in the United States, and construct news profiles. We compare the performance of the proposed method with that of benchmark algorithms. One is a traditional method based on TF-IDF. Another is 6Sub-Vectors method that divides the points to get keywords into six parts. Experimental results demonstrate that the proposed system provide useful news to users by applying user's social network information and WordNet functions, in terms of prediction error of recommended news.

• Journal of Intelligence and Information Systems
• /
• v.19 no.3
• /
• pp.93-111
• /
• 2013

As Internet and information technology (IT) continues to develop and evolve, the issue of big data has emerged at the foreground of scholarly and industrial attention. Big data is generally defined as data that exceed the range that can be collected, stored, managed and analyzed by existing conventional information systems and it also refers to the new technologies designed to effectively extract values from such data. With the widespread dissemination of IT systems, continual efforts have been made in various fields of industry such as R&D, manufacturing, and finance to collect and analyze immense quantities of data in order to extract meaningful information and to use this information to solve various problems. Since IT has converged with various industries in many aspects, digital data are now being generated at a remarkably accelerating rate while developments in state-of-the-art technology have led to continual enhancements in system performance. The types of big data that are currently receiving the most attention include information available within companies, such as information on consumer characteristics, information on purchase records, logistics information and log information indicating the usage of products and services by consumers, as well as information accumulated outside companies, such as information on the web search traffic of online users, social network information, and patent information. Among these various types of big data, web searches performed by online users constitute one of the most effective and important sources of information for marketing purposes because consumers search for information on the internet in order to make efficient and rational choices. Recently, Google has provided public access to its information on the web search traffic of online users through a service named Google Trends. Research that uses this web search traffic information to analyze the information search behavior of online users is now receiving much attention in academia and in fields of industry. Studies using web search traffic information can be broadly classified into two fields. The first field consists of empirical demonstrations that show how web search information can be used to forecast social phenomena, the purchasing power of consumers, the outcomes of political elections, etc. The other field focuses on using web search traffic information to observe consumer behavior, identifying the attributes of a product that consumers regard as important or tracking changes on consumers' expectations, for example, but relatively less research has been completed in this field. In particular, to the extent of our knowledge, hardly any studies related to brands have yet attempted to use web search traffic information to analyze the factors that influence consumers' purchasing activities. This study aims to demonstrate that consumers' web search traffic information can be used to derive the relations among brands and the relations between an individual brand and product attributes. When consumers input their search words on the web, they may use a single keyword for the search, but they also often input multiple keywords to seek related information (this is referred to as simultaneous searching). A consumer performs a simultaneous search either to simultaneously compare two product brands to obtain information on their similarities and differences, or to acquire more in-depth information about a specific attribute in a specific brand. Web search traffic information shows that the quantity of simultaneous searches using certain keywords increases when the relation is closer in the consumer's mind and it will be possible to derive the relations between each of the keywords by collecting this relational data and subjecting it to network analysis. Accordingly, this study proposes a method of analyzing how brands are positioned by consumers and what relationships exist between product attributes and an individual brand, using simultaneous search traffic information. It also presents case studies demonstrating the actual application of this method, with a focus on tablets, belonging to innovative product groups.

• Journal of Intelligence and Information Systems
• /
• v.26 no.3
• /
• pp.71-90
• /
• 2020

Recently, the global insurance industry is rapidly developing digital transformation through the use of artificial intelligence technologies such as machine learning, natural language processing, and deep learning. As a result, more and more foreign insurers have achieved the success of artificial intelligence technology-based InsurTech and platform business, and Ping An Insurance Group Ltd., China's largest private company, is leading China's global fourth industrial revolution with remarkable achievements in InsurTech and Digital Platform as a result of its constant innovation, using 'finance and technology' and 'finance and ecosystem' as keywords for companies. In response, this study analyzed the InsurTech and platform business activities of Ping An Insurance Group Ltd. through the ser-M analysis model to provide strategic implications for revitalizing AI technology-based businesses of domestic insurers. The ser-M analysis model has been studied so that the vision and leadership of the CEO, the historical environment of the enterprise, the utilization of various resources, and the unique mechanism relationships can be interpreted in an integrated manner as a frame that can be interpreted in terms of the subject, environment, resource and mechanism. As a result of the case analysis, Ping An Insurance Group Ltd. has achieved cost reduction and customer service development by digitally innovating its entire business area such as sales, underwriting, claims, and loan service by utilizing core artificial intelligence technologies such as facial, voice, and facial expression recognition. In addition, "online data in China" and "the vast offline data and insights accumulated by the company" were combined with new technologies such as artificial intelligence and big data analysis to build a digital platform that integrates financial services and digital service businesses. Ping An Insurance Group Ltd. challenged constant innovation, and as of 2019, sales reached $155 billion, ranking seventh among all companies in the Global 2000 rankings selected by Forbes Magazine. Analyzing the background of the success of Ping An Insurance Group Ltd. from the perspective of ser-M, founder Mammingz quickly captured the development of digital technology, market competition and changes in population structure in the era of the fourth industrial revolution, and established a new vision and displayed an agile leadership of digital technology-focused. Based on the strong leadership led by the founder in response to environmental changes, the company has successfully led InsurTech and Platform Business through innovation of internal resources such as investment in artificial intelligence technology, securing excellent professionals, and strengthening big data capabilities, combining external absorption capabilities, and strategic alliances among various industries. Through this success story analysis of Ping An Insurance Group Ltd., the following implications can be given to domestic insurance companies that are preparing for digital transformation. First, CEOs of domestic companies also need to recognize the paradigm shift in industry due to the change in digital technology and quickly arm themselves with digital technology-oriented leadership to spearhead the digital transformation of enterprises. Second, the Korean government should urgently overhaul related laws and systems to further promote the use of data between different industries and provide drastic support such as deregulation, tax benefits and platform provision to help the domestic insurance industry secure global competitiveness. Third, Korean companies also need to make bolder investments in the development of artificial intelligence technology so that systematic securing of internal and external data, training of technical personnel, and patent applications can be expanded, and digital platforms should be quickly established so that diverse customer experiences can be integrated through learned artificial intelligence technology. Finally, since there may be limitations to generalization through a single case of an overseas insurance company, I hope that in the future, more extensive research will be conducted on various management strategies related to artificial intelligence technology by analyzing cases of multiple industries or multiple companies or conducting empirical research.

• Journal of Intelligence and Information Systems
• /
• v.26 no.3
• /
• pp.109-125
• /
• 2020

The Ministry of National Defense is pushing for the Defense Acquisition Program to build strong defense capabilities, and it spends more than 10 trillion won annually on defense improvement. As the Defense Acquisition Program is directly related to the security of the nation as well as the lives and property of the people, it must be carried out very transparently and efficiently by experts. However, the excessive diversification of laws and regulations related to the Defense Acquisition Program has made it challenging for many working-level officials to carry out the Defense Acquisition Program smoothly. It is even known that many people realize that there are related regulations that they were unaware of until they push ahead with their work. In addition, the statutory statements related to the Defense Acquisition Program have the tendency to cause serious issues even if only a single expression is wrong within the sentence. Despite this, efforts to establish a sentence comparison system to correct this issue in real time have been minimal. Therefore, this paper tries to propose a "Comparison System between the Statement of Military Reports and Related Laws" implementation plan that uses the Siamese Network-based artificial neural network, a model in the field of natural language processing (NLP), to observe the similarity between sentences that are likely to appear in the Defense Acquisition Program related documents and those from related statutory provisions to determine and classify the risk of illegality and to make users aware of the consequences. Various artificial neural network models (Bi-LSTM, Self-Attention, D_Bi-LSTM) were studied using 3,442 pairs of "Original Sentence"(described in actual statutes) and "Edited Sentence"(edited sentences derived from "Original Sentence"). Among many Defense Acquisition Program related statutes, DEFENSE ACQUISITION PROGRAM ACT, ENFORCEMENT RULE OF THE DEFENSE ACQUISITION PROGRAM ACT, and ENFORCEMENT DECREE OF THE DEFENSE ACQUISITION PROGRAM ACT were selected. Furthermore, "Original Sentence" has the 83 provisions that actually appear in the Act. "Original Sentence" has the main 83 clauses most accessible to working-level officials in their work. "Edited Sentence" is comprised of 30 to 50 similar sentences that are likely to appear modified in the county report for each clause("Original Sentence"). During the creation of the edited sentences, the original sentences were modified using 12 certain rules, and these sentences were produced in proportion to the number of such rules, as it was the case for the original sentences. After conducting 1 : 1 sentence similarity performance evaluation experiments, it was possible to classify each "Edited Sentence" as legal or illegal with considerable accuracy. In addition, the "Edited Sentence" dataset used to train the neural network models contains a variety of actual statutory statements("Original Sentence"), which are characterized by the 12 rules. On the other hand, the models are not able to effectively classify other sentences, which appear in actual military reports, when only the "Original Sentence" and "Edited Sentence" dataset have been fed to them. The dataset is not ample enough for the model to recognize other incoming new sentences. Hence, the performance of the model was reassessed by writing an additional 120 new sentences that have better resemblance to those in the actual military report and still have association with the original sentences. Thereafter, we were able to check that the models' performances surpassed a certain level even when they were trained merely with "Original Sentence" and "Edited Sentence" data. If sufficient model learning is achieved through the improvement and expansion of the full set of learning data with the addition of the actual report appearance sentences, the models will be able to better classify other sentences coming from military reports as legal or illegal. Based on the experimental results, this study confirms the possibility and value of building "Real-Time Automated Comparison System Between Military Documents and Related Laws". The research conducted in this experiment can verify which specific clause, of several that appear in related law clause is most similar to the sentence that appears in the Defense Acquisition Program-related military reports. This helps determine whether the contents in the military report sentences are at the risk of illegality when they are compared with those in the law clauses.

• Journal of Intelligence and Information Systems
• /
• v.20 no.1
• /
• pp.195-211
• /
• 2014

Cloud computing services provide IT resources as services on demand. This is considered a key concept, which will lead a shift from an ownership-based paradigm to a new pay-for-use paradigm, which can reduce the fixed cost for IT resources, and improve flexibility and scalability. As IT services, cloud services have evolved from early similar computing concepts such as network computing, utility computing, server-based computing, and grid computing. So research into cloud computing is highly related to and combined with various relevant computing research areas. To seek promising research issues and topics in cloud computing, it is necessary to understand the research trends in cloud computing more comprehensively. In this study, we collect bibliographic information and citation information for cloud computing related research papers published in major international journals from 1994 to 2012, and analyzes macroscopic trends and network changes to citation relationships among papers and the co-occurrence relationships of key words by utilizing social network analysis measures. Through the analysis, we can identify the relationships and connections among research topics in cloud computing related areas, and highlight new potential research topics. In addition, we visualize dynamic changes of research topics relating to cloud computing using a proposed cloud computing "research trend map." A research trend map visualizes positions of research topics in two-dimensional space. Frequencies of key words (X-axis) and the rates of increase in the degree centrality of key words (Y-axis) are used as the two dimensions of the research trend map. Based on the values of the two dimensions, the two dimensional space of a research map is divided into four areas: maturation, growth, promising, and decline. An area with high keyword frequency, but low rates of increase of degree centrality is defined as a mature technology area; the area where both keyword frequency and the increase rate of degree centrality are high is defined as a growth technology area; the area where the keyword frequency is low, but the rate of increase in the degree centrality is high is defined as a promising technology area; and the area where both keyword frequency and the rate of degree centrality are low is defined as a declining technology area. Based on this method, cloud computing research trend maps make it possible to easily grasp the main research trends in cloud computing, and to explain the evolution of research topics. According to the results of an analysis of citation relationships, research papers on security, distributed processing, and optical networking for cloud computing are on the top based on the page-rank measure. From the analysis of key words in research papers, cloud computing and grid computing showed high centrality in 2009, and key words dealing with main elemental technologies such as data outsourcing, error detection methods, and infrastructure construction showed high centrality in 2010~2011. In 2012, security, virtualization, and resource management showed high centrality. Moreover, it was found that the interest in the technical issues of cloud computing increases gradually. From annual cloud computing research trend maps, it was verified that security is located in the promising area, virtualization has moved from the promising area to the growth area, and grid computing and distributed system has moved to the declining area. The study results indicate that distributed systems and grid computing received a lot of attention as similar computing paradigms in the early stage of cloud computing research. The early stage of cloud computing was a period focused on understanding and investigating cloud computing as an emergent technology, linking to relevant established computing concepts. After the early stage, security and virtualization technologies became main issues in cloud computing, which is reflected in the movement of security and virtualization technologies from the promising area to the growth area in the cloud computing research trend maps. Moreover, this study revealed that current research in cloud computing has rapidly transferred from a focus on technical issues to for a focus on application issues, such as SLAs (Service Level Agreements).

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.8 no.1
• /
• pp.1-9
• /
• 2006

Regardless of the recent observed warmer winters in Korea, more freeze injuries and associated economic losses are reported in fruit industry than ever before. Existing freeze-frost forecasting systems employ only daily minimum temperature for judging the potential damage on dormant flowering buds but cannot accommodate potential biological responses such as short-term acclimation of plants to severe weather episodes as well as annual variation in climate. We introduce 'dormancy depth', in addition to daily minimum temperature, as a complementary criterion for judging the potential damage of freezing temperatures on dormant flowering buds of grape vines. Dormancy depth can be estimated by a phonology model driven by daily maximum and minimum temperature and is expected to make a reasonable proxy for physiological tolerance of buds to low temperature. Dormancy depth at a selected site was estimated for a climatological normal year by this model, and we found a close similarity in time course change pattern between the estimated dormancy depth and the known cold tolerance of fruit trees. Inter-annual and spatial variation in dormancy depth were identified by this method, showing the feasibility of using dormancy depth as a proxy indicator for tolerance to low temperature during the winter season. The model was applied to 10 vineyards which were recently damaged by a cold spell, and a temperature-dormancy depth-freeze injury relationship was formulated into an exponential-saturation model which can be used for judging freeze risk under a given set of temperature and dormancy depth. Based on this model and the expected lowest temperature with a 10-year recurrence interval, a freeze risk probability map was produced for Hwaseong County, Korea. The results seemed to explain why the vineyards in the warmer part of Hwaseong County have been hit by more freeBe damage than those in the cooler part of the county. A dormancy depth-minimum temperature dual engine freeze warning system was designed for vineyards in major production counties in Korea by combining the site-specific dormancy depth and minimum temperature forecasts with the freeze risk model. In this system, daily accumulation of thermal time since last fall leads to the dormancy state (depth) for today. The regional minimum temperature forecast for tomorrow by the Korea Meteorological Administration is converted to the site specific forecast at a 30m resolution. These data are input to the freeze risk model and the percent damage probability is calculated for each grid cell and mapped for the entire county. Similar approaches may be used to develop freeze warning systems for other deciduous fruit trees.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.105-129
• /
• 2020

This study uses corporate data from 2012 to 2018 when K-IFRS was applied in earnest to predict default risks. The data used in the analysis totaled 10,545 rows, consisting of 160 columns including 38 in the statement of financial position, 26 in the statement of comprehensive income, 11 in the statement of cash flows, and 76 in the index of financial ratios. Unlike most previous prior studies used the default event as the basis for learning about default risk, this study calculated default risk using the market capitalization and stock price volatility of each company based on the Merton model. Through this, it was able to solve the problem of data imbalance due to the scarcity of default events, which had been pointed out as the limitation of the existing methodology, and the problem of reflecting the difference in default risk that exists within ordinary companies. Because learning was conducted only by using corporate information available to unlisted companies, default risks of unlisted companies without stock price information can be appropriately derived. Through this, it can provide stable default risk assessment services to unlisted companies that are difficult to determine proper default risk with traditional credit rating models such as small and medium-sized companies and startups. Although there has been an active study of predicting corporate default risks using machine learning recently, model bias issues exist because most studies are making predictions based on a single model. Stable and reliable valuation methodology is required for the calculation of default risk, given that the entity's default risk information is very widely utilized in the market and the sensitivity to the difference in default risk is high. Also, Strict standards are also required for methods of calculation. The credit rating method stipulated by the Financial Services Commission in the Financial Investment Regulations calls for the preparation of evaluation methods, including verification of the adequacy of evaluation methods, in consideration of past statistical data and experiences on credit ratings and changes in future market conditions. This study allowed the reduction of individual models' bias by utilizing stacking ensemble techniques that synthesize various machine learning models. This allows us to capture complex nonlinear relationships between default risk and various corporate information and maximize the advantages of machine learning-based default risk prediction models that take less time to calculate. To calculate forecasts by sub model to be used as input data for the Stacking Ensemble model, training data were divided into seven pieces, and sub-models were trained in a divided set to produce forecasts. To compare the predictive power of the Stacking Ensemble model, Random Forest, MLP, and CNN models were trained with full training data, then the predictive power of each model was verified on the test set. The analysis showed that the Stacking Ensemble model exceeded the predictive power of the Random Forest model, which had the best performance on a single model. Next, to check for statistically significant differences between the Stacking Ensemble model and the forecasts for each individual model, the Pair between the Stacking Ensemble model and each individual model was constructed. Because the results of the Shapiro-wilk normality test also showed that all Pair did not follow normality, Using the nonparametric method wilcoxon rank sum test, we checked whether the two model forecasts that make up the Pair showed statistically significant differences. The analysis showed that the forecasts of the Staging Ensemble model showed statistically significant differences from those of the MLP model and CNN model. In addition, this study can provide a methodology that allows existing credit rating agencies to apply machine learning-based bankruptcy risk prediction methodologies, given that traditional credit rating models can also be reflected as sub-models to calculate the final default probability. Also, the Stacking Ensemble techniques proposed in this study can help design to meet the requirements of the Financial Investment Business Regulations through the combination of various sub-models. We hope that this research will be used as a resource to increase practical use by overcoming and improving the limitations of existing machine learning-based models.

• 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.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.79-104
• /
• 2020

Recently, as deep learning has attracted attention, the use of deep learning is being considered as a method for solving problems in various fields. In particular, deep learning is known to have excellent performance when applied to applying unstructured data such as text, sound and images, and many studies have proven its effectiveness. Owing to the remarkable development of text and image deep learning technology, interests in image captioning technology and its application is rapidly increasing. Image captioning is a technique that automatically generates relevant captions for a given image by handling both image comprehension and text generation simultaneously. In spite of the high entry barrier of image captioning that analysts should be able to process both image and text data, image captioning has established itself as one of the key fields in the A.I. research owing to its various applicability. In addition, many researches have been conducted to improve the performance of image captioning in various aspects. Recent researches attempt to create advanced captions that can not only describe an image accurately, but also convey the information contained in the image more sophisticatedly. Despite many recent efforts to improve the performance of image captioning, it is difficult to find any researches to interpret images from the perspective of domain experts in each field not from the perspective of the general public. Even for the same image, the part of interests may differ according to the professional field of the person who has encountered the image. Moreover, the way of interpreting and expressing the image also differs according to the level of expertise. The public tends to recognize the image from a holistic and general perspective, that is, from the perspective of identifying the image's constituent objects and their relationships. On the contrary, the domain experts tend to recognize the image by focusing on some specific elements necessary to interpret the given image based on their expertise. It implies that meaningful parts of an image are mutually different depending on viewers' perspective even for the same image. So, image captioning needs to implement this phenomenon. Therefore, in this study, we propose a method to generate captions specialized in each domain for the image by utilizing the expertise of experts in the corresponding domain. Specifically, after performing pre-training on a large amount of general data, the expertise in the field is transplanted through transfer-learning with a small amount of expertise data. However, simple adaption of transfer learning using expertise data may invoke another type of problems. Simultaneous learning with captions of various characteristics may invoke so-called 'inter-observation interference' problem, which make it difficult to perform pure learning of each characteristic point of view. For learning with vast amount of data, most of this interference is self-purified and has little impact on learning results. On the contrary, in the case of fine-tuning where learning is performed on a small amount of data, the impact of such interference on learning can be relatively large. To solve this problem, therefore, we propose a novel 'Character-Independent Transfer-learning' that performs transfer learning independently for each character. In order to confirm the feasibility of the proposed methodology, we performed experiments utilizing the results of pre-training on MSCOCO dataset which is comprised of 120,000 images and about 600,000 general captions. Additionally, according to the advice of an art therapist, about 300 pairs of 'image / expertise captions' were created, and the data was used for the experiments of expertise transplantation. As a result of the experiment, it was confirmed that the caption generated according to the proposed methodology generates captions from the perspective of implanted expertise whereas the caption generated through learning on general data contains a number of contents irrelevant to expertise interpretation. In this paper, we propose a novel approach of specialized image interpretation. To achieve this goal, we present a method to use transfer learning and generate captions specialized in the specific domain. In the future, by applying the proposed methodology to expertise transplant in various fields, we expected that many researches will be actively conducted to solve the problem of lack of expertise data and to improve performance of image captioning.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.30 no.1
• /
• pp.14-21
• /
• 2012

The object of the study, Yousang-Dae(流觴臺) and engraved Go broad text on the flat rock in Gangneung-si Yungok-myun Yoodung-ri Baemgol, reveals that the place was for appreciating arts like Yusang Goksu and Taoist hermit's games. three times of detail reconnaissance survey brought about the results as follows. There is a the text, Manwolsan(滿月山) Baegundongcheon(白雲洞天), engraved on the rock in Baegunsa(白雲寺) that had been built by Doun at the first year of King Hungang(in 875) of the United Shilla, became in ruins in the middle of Joseon, and then was rebuilt in 1954. The text is an invaluable evidence indicating that the tradition of Taoist hermit and Sunbee(classical scholars) culture has been generated in Baemgol Valley. According to the 2nd vol. of Donghoseungram(東湖勝覽), the chronicle of Gangneung published by Choi Baeksoon in 1934, there is a record saying that 'Baegunsa in Namjeonhyeon is the classroom where famous teachers like Yulgok Lee Yi or Seongje Choi Ok were teaching' that verifies the historic property of the place. In addition, the management of Nujeong(樓亭) and Dongcheon can be traced through Baegunjeong(白雲亭) constructed by Kim Yoonkyung(金潤卿) in Muo year, the 9th year of Cheoljong(1858) according to Donghoseungram and the completed version of Jeungboyimyoungji(增補臨瀛誌). Also, Baegundongdongcheon(白雲亭洞天), the text engraved on the standing stone across the stream from Yousang-Dae stone, was created 3 years after the Baegunjeong construction in the 12th year of Cheoljong(1861), which refers a symbolic sign closely related with Yousang-Dae. Based on this premise and circumstance, with careful studying the remains of 'Yusang-dae' Goksuro, we discovered that the Sebun-seok(細分石) controling the amount and the speed of moving water and the remains of furrows of Keumbae-soek(擒盃石) and Yubae-gong(留盃孔) containing water stream with cups through the mountain stream and rocks around Yusang-Dae. In addition, as 21 people's names engraved under the statement of 'Oh-Seong(午星)' were discovered on the bottom of the rock, this clearly confirms that the place was one of the main cultural footholds of tasting the arts which have characteristics of Yu-Sang-Gok-Su-Yeon(流觴曲水宴) until the middle of the 20th century. It implies that the arts tasting culture of Sunbees had been inherited centering on Yusang-dae in this particular place until the middle of the 20th century. It is necessary to be studied in depth because the place is a historic and unique cultural place where 'Confucianism, Buddhism, and Zen'were combined together. Based on the result of the study, the identification of 23 people as well as the writer of Yusang-Dae text should be carefully studied in depth in terms of the characteristics of the place through gathering data about appreciation of arts like Yusanggoksu. Likewise, we should make efforts to discover the chess board engraved on the rock described on the documents, thus we should consider to establish plans to recover the original shape of the place, for example, breaking the cement pavement of the road, additional excavation, changing the existing route, and so fourth.