• The Journal of the Korea Contents Association
• /
• v.15 no.5
• /
• pp.132-141
• /
• 2015

Smart television(TV) is replacing the traditional television model and the importance of user experience(UX) is rising. User experience evaluates the emotion state of users such as immersion, pleasure, and interest. User experience together with usability is a principle to be considered as for designing a smart television. It contributes to improve user satisfaction and lead to the long-term purchase. User experience is more difficult to measure than usability, because UX evaluation requires to biological and psychological techniques. However, the disadvantages of these physiological and psychological techniques require high experimental costs and the restriction of experimental environment. The objective of this paper is first to review conventional methods regarding UX evaluation and suggests a new method for measuring the UX of smart TV which detects keywords related emotional representation. The text is acquired from purchase postscripts of smart TV in the Internet shopping malls. This method costs less than the questionnaire survey to detect emotion.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.3
• /
• pp.721-739
• /
• 2023

Rating prediction is an important issue in recommender systems, and its accuracy affects the experience of the user and the revenue of the company. Traditional recommender systems use Factorization Machinesfor rating predictions and each feature is selected with the same weight. Thus, there are problems with inaccurate ratings and limited data representation. This study proposes a deep recommendation model based on self-attention Factorization (SAFMR) to solve these problems. This model uses Convolutional Neural Networks to extract features from user and item reviews. The obtained features are fed into self-attention mechanism Factorization Machines, where the self-attention network automatically learns the dependencies of the features and distinguishes the weights of the different features, thereby reducing the prediction error. The model was experimentally evaluated using six classes of dataset. We compared MSE, NDCG and time for several real datasets. The experiment demonstrated that the SAFMR model achieved excellent rating prediction results and recommendation correlations, thereby verifying the effectiveness of the model.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.624-626
• /
• 2023

Credit scoring is a technique used by financial institutions to assess the creditworthiness of potential borrowers. This involves evaluating a borrower's credit history to predict the likelihood of defaulting on a loan. This paper presents an ensemble of two Transformer based models within a framework for discriminating the default risk of loan applications in the field of credit scoring. The first model is FinBERT, a pretrained NLP model to analyze sentiment of financial text. The second model is FT-Transformer, a simple adaptation of the Transformer architecture for the tabular domain. Both models are trained on the same underlying data set, with the only difference being the representation of the data. This multi-modal approach allows us to leverage the unique capabilities of each model and potentially uncover insights that may not be apparent when using a single model alone. We compare our model with two famous ensemble-based models, Random Forest and Extreme Gradient Boosting.

• The KIPS Transactions:PartD
• /
• v.13D no.2 s.105
• /
• pp.235-240
• /
• 2006

Software architectures may be described using text-based architecture description language(ADL). The key goals of an ADL are to communicate alternate designs between different stakeholders, to detect reusable structures, and to record design decisions. This paper provided a solution to the representation problem by creating a tool for three-dimensional representation of architectural viewpoints. The tool consisted of an architecture description language(VTADL) to first describe the software architectures and viewpoints on the architectures; and a VTADL-to-VRML translator to translate each viewpoint into a separate virtual reality world The goal of the paper was to devise algorithms for translating an ADL into effective VRML representations based on the desired viewpoint. The VRML representations were intended to enhance comprehension on the overall design and to improve communications between diverse stakeholders.

• Journal of Fashion Business
• /
• v.25 no.1
• /
• pp.96-107
• /
• 2021

The purpose of this study was to determine how to visualize classic makeup through Korean visual language in old literature. It provides consumers with creativity to understand and communicate and proposes a new conceptual visualization model. The research method was carried out by drawing from old literature studies, previous reproduction records, examples, and international standard diagram text language expression. First, the visualization work expressed in visual language in old literature was an objective and efficient method of information delivery as a characteristic of information design. Second, visual language expressed in old documents could be divided into makeup materials and actions. Also, the diagrams were appropriate for visualizing materials and materials for storytelling. Third, in the visualization of Korean classic makeup in old literature, images were more appropriate than diagrams in the case of action. The researcher proposed a method of visualizing historical knowledge that went one step beyond the existing simple event timing method. Timeline, correlation diagram, image, and text were combined in various ways to find the most effective historical knowledge visualization method. The representation of Korean classic makeup goes beyond the meaning of language or text and is the cultural content of re-creation, which requires systematic globalization.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.25 no.5
• /
• pp.765-772
• /
• 2011

Knowledge which is represented by formal logic are widely used in many domains such like artificial intelligence, information retrieval, e-commerce and so on. And for medical field, medical documentary records retrieval, information systems in hospitals, medical data sharing, remote treatment and expert systems need knowledge representation technology. To retrieve information intellectually and provide advanced information services, systematically controlled mechanism is needed to represent and share knowledge. Importantly, medical expert's knowledge should be represented in a form that is understandable to computers and also to humans to be applied to the medical information system supporting decision making. And it should have a suitable and efficient structure for its own purposes including reasoning, extendability of knowledge, management of data, accuracy of expressions, diversity, and so on. we call it ontology which can be processed with machines. We can use the ontology to represent traditional medicine knowledge in structured and systematic way with visualization, then also it can also be used education materials. Hence, the authors developed an Shanghanlun ontology by way of showing an example, so that we suggested a methodology for ontology development and also a model to structure the traditional medical knowledge. And this result can be used for student to learn Shanghanlun by graphical representation of it's knowledge. We analyzed the text of Shanghanlun to construct relational database including it's original text, symptoms and herb formulars. And then we classified the terms following some criterion, confirmed the structure of the ontology to describe semantic relations between the terms, especially we developed the ontology considering visual representation. The ontology developed in this study provides database showing fomulas, herbs, symptoms, the name of diseases and the text written in Shanghanlun. It's easy to retrieve contents by their semantic relations so that it is convenient to search knowledge of Shanghanlun and to learn it. It can display the related concepts by searching terms and provides expanded information with a simple click. It has some limitations such as standardization problems, short coverage of pattern(證), and error in chinese characters input. But we believe this research can be used for basic foundation to make traditional medicine more structural and systematic, to develop application softwares, and also to applied it in Shanghanlun educations.

• The Journal of Society for e-Business Studies
• /
• v.21 no.4
• /
• pp.1-14
• /
• 2016

Semantic search is known as a series of activities and techniques to improve the search accuracy by clearly understanding users' search intent without big cognitive efforts. Usually, semantic search engines requires ontology and semantic metadata to analyze user queries. However, building a particular ontology and semantic metadata intended for large amounts of data is a very time-consuming and costly task. This is why commercialization practices of semantic search are insufficient. In order to resolve this problem, we propose a novel semantic search method which takes advantage of our previous semantic tensor space model. Since each term is represented as the 2nd-order 'document-by-concept' tensor (i.e., matrix), and each concept as the 2nd-order 'document-by-term' tensor in the model, our proposed semantic search method does not require to build ontology. Nevertheless, through extensive experiments using the OHSUMED document collection and SCOPUS journal abstract data, we show that our proposed method outperforms the vector space model-based search method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.6
• /
• pp.1973-1993
• /
• 2022

Model-driven engineering (MDE) and aspect-oriented software development (AOSD) contribute to the common goal of development of high-quality code in reduced time. To complement each approach with the benefits of the other, various methods of integration of the two approaches were proposed in the past. Aspect-oriented code generation, which targets obtaining aspect-oriented code directly from aspect models, offers some unique advantages over the other integration approaches. However, the existing aspect-oriented code generation approaches do not comprehensively address all aspects of a model-driven code generation system, such as a textual representation of graphical models, conceptual mapping, and incorporation of behavioral diagrams. These problems limit the worth of generated code, especially in practical use. Here, we propose AJFCode, an approach for aspect-oriented model-driven code generation, which comprehensively addresses the various aspects including the graphical models and their text-based representation, mapping between visual model elements and code, and the behavioral code generation. Experiments are conducted to compare the maintainability and reusability characteristics of the aspect-oriented code generated using the AJFCode with the most comprehensive object-oriented code generation approach. AJFCode performs well in terms of all metrics related to maintainability and reusability of code. However, the most significant improvement is noticed in the separation of concerns, coupling, and cohesion. For instance, AJFCode yields significant improvement in concern diffusion over operations (19 vs 51), coupling between components (0 vs 6), and lack of cohesion in operations (5 vs 9) for one of the experimented concerns.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.12
• /
• pp.4275-4291
• /
• 2021

With the unprecedented growth of textual information on the Internet, an efficient automatic summarization system has become an urgent need. Recently, the neural network models based on the encoder-decoder with an attention mechanism have demonstrated powerful capabilities in the sentence summarization task. However, for paragraphs or longer document summarization, these models fail to mine the core information in the input text, which leads to information loss and repetitions. In this paper, we propose an abstractive document summarization method by applying guidance signals of key sentences to the encoder based on the hierarchical encoder-decoder architecture, denoted as KI-HABS. Specifically, we first train an extractor to extract key sentences in the input document by the hierarchical bidirectional GRU. Then, we encode the key sentences to the key information representation in the sentence level. Finally, we adopt key information representation guided selective encoding strategies to filter source information, which establishes a connection between the key sentences and the document. We use the CNN/Daily Mail and Gigaword datasets to evaluate our model. The experimental results demonstrate that our method generates more informative and concise summaries, achieving better performance than the competitive models.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.8
• /
• pp.301-310
• /
• 2021

The TATI model is a Traffic Accident Text to RGB Image model, which is a methodology proposed in this paper for predicting the severity of traffic accidents. Traffic fatalities are decreasing every year, but they are among the low in the OECD members. Many studies have been conducted to reduce the death rate of traffic accidents, and among them, studies have been steadily conducted to reduce the incidence and mortality rate by predicting the severity of traffic accidents. In this regard, research has recently been active to predict the severity of traffic accidents by utilizing statistical models and deep learning models. In this paper, traffic accident dataset is converted to color images to predict the severity of traffic accidents, and this is done via CNN models. For performance comparison, we experiment that train the same data and compare the prediction results with the proposed model and other models. Through 10 experiments, we compare the accuracy and error range of four deep learning models. Experimental results show that the accuracy of the proposed model was the highest at 0.85, and the second lowest error range at 0.03 was shown to confirm the superiority of the performance.