• Journal of Internet Computing and Services
• /
• v.21 no.3
• /
• pp.123-131
• /
• 2020

Along with the rapid development of artificial intelligence technology, natural language processing, which deals with human language, is also actively studied. In particular, BERT, a language model recently proposed by Google, has been performing well in many areas of natural language processing by providing pre-trained model using a large number of corpus. Although BERT supports multilingual model, we should use the pre-trained model using large amounts of Korean corpus because there are limitations when we apply the original pre-trained BERT model directly to Korean. Also, text contains not only vocabulary, grammar, but contextual meanings such as the relation between the front and the rear, and situation. In the existing natural language processing field, research has been conducted mainly on vocabulary or grammatical meaning. Accurate identification of contextual information embedded in text plays an important role in understanding context. Knowledge graphs, which are linked using the relationship of words, have the advantage of being able to learn context easily from computer. In this paper, we propose a system to extract Korean contextual information using pre-trained BERT model with Korean language corpus and knowledge graph. We build models that can extract person, relationship, emotion, space, and time information that is important in the text and validate the proposed system through experiments.

• Journal of the Korean Society for Library and Information Science
• /
• v.51 no.4
• /
• pp.99-120
• /
• 2017

In order to develop a semiautomatic support system that allows researchers concerned to efficiently analyze the technical trends for the ever-growing industry and market. This paper introduces a couple of Korean sentence generation models that can automatically generate definitional statements as well as descriptions of technical terms and concepts. The proposed models are based on a deep learning model called LSTM (Long Sort-Term Memory) capable of effectively labeling textual sequences by taking into account the contextual relations of each item in the sequences. Our models take technical terms as inputs and can generate a broad range of heterogeneous textual descriptions that explain the concept of the terms. In the experiments using large-scale training collections, we confirmed that more accurate and reasonable sentences can be generated by CHAR-CNN-LSTM model that is a word-based LSTM exploiting character embeddings based on convolutional neural networks (CNN). The results of this study can be a force for developing an extension model that can generate a set of sentences covering the same subjects, and furthermore, we can implement an artificial intelligence model that automatically creates technical literature.

• 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.

• Korean Journal of Remote Sensing
• /
• v.33 no.6_2
• /
• pp.1061-1073
• /
• 2017

In this study, images were classified using convolutional neural network (CNN) - a deep learning technique - to investigate the feasibility of information production through a combination of artificial intelligence and spatial data. CNN determines kernel attributes based on a classification criterion and extracts information from feature maps to classify each pixel. In this study, a CNN network was constructed to classify materials with similar spectral characteristics and attribute information; this is difficult to achieve by conventional image processing techniques. A Compact Airborne Spectrographic Imager(CASI) and an Airborne Imaging Spectrometer for Application (AISA) were used on the following three study sites to test this method: Site 1, Site 2, and Site 3. Site 1 and Site 2 were agricultural lands covered in various crops,such as potato, onion, and rice. Site 3 included different buildings,such as single and joint residential facilities. Results indicated that the classification of crop species at Site 1 and Site 2 using this method yielded accuracies of 96% and 99%, respectively. At Site 3, the designation of buildings according to their purpose yielded an accuracy of 96%. Using a combination of existing land cover maps and spatial data, we propose a thematic environmental map that provides seasonal crop types and facilitates the creation of a land cover map.

• Journal of Korean Neurosurgical Society
• /
• v.63 no.3
• /
• pp.386-396
• /
• 2020

Objective : To generate synthetic spine magnetic resonance (MR) images from spine computed tomography (CT) using generative adversarial networks (GANs), as well as to determine the similarities between synthesized and real MR images. Methods : GANs were trained to transform spine CT image slices into spine magnetic resonance T2 weighted (MRT2) axial image slices by combining adversarial loss and voxel-wise loss. Experiments were performed using 280 pairs of lumbar spine CT scans and MRT2 images. The MRT2 images were then synthesized from 15 other spine CT scans. To evaluate whether the synthetic MR images were realistic, two radiologists, two spine surgeons, and two residents blindly classified the real and synthetic MRT2 images. Two experienced radiologists then evaluated the similarities between subdivisions of the real and synthetic MRT2 images. Quantitative analysis of the synthetic MRT2 images was performed using the mean absolute error (MAE) and peak signal-to-noise ratio (PSNR). Results : The mean overall similarity of the synthetic MRT2 images evaluated by radiologists was 80.2%. In the blind classification of the real MRT2 images, the failure rate ranged from 0% to 40%. The MAE value of each image ranged from 13.75 to 34.24 pixels (mean, 21.19 pixels), and the PSNR of each image ranged from 61.96 to 68.16 dB (mean, 64.92 dB). Conclusion : This was the first study to apply GANs to synthesize spine MR images from CT images. Despite the small dataset of 280 pairs, the synthetic MR images were relatively well implemented. Synthesis of medical images using GANs is a new paradigm of artificial intelligence application in medical imaging. We expect that synthesis of MR images from spine CT images using GANs will improve the diagnostic usefulness of CT. To better inform the clinical applications of this technique, further studies are needed involving a large dataset, a variety of pathologies, and other MR sequence of the lumbar spine.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.11
• /
• pp.208-216
• /
• 2019

Construction projects generate a massive amount of diverse information. It takes at least five years to more than 10 years to complete, so it is important to manage the information on a project's history, including processes and costs. Furthermore, it is necessary to determine if construction projects have been carried out according to the planned goals, and to convert a construction information management system (CALS) into a virtuous cycle. It is easy to ensure integrated information management in private construction projects because constructors can take care of the whole process (from planning to completion), whereas it is difficult for public construction projects because various agencies are involved in the projects. A CALS manages the project information of public road construction, but that information is managed according to CALS subsystems, resulting in disconnected information among the subsystems, and making it impossible to monitor integrated information. Thus, this study proposes integrated information management measures to ensure comprehensive management of the information generated during the construction life cycle. To that end, a CALS is improved by standardizing and integrating the system database, integrating the individually managed user information, and connecting the system with the Dbrain tool, which collectively builds artificial intelligence, to ensure information management based on the project budget.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.11
• /
• pp.519-531
• /
• 2020

Global warming is accelerating as greenhouse gas emissions increase owing to the increase in population and urbanization rates worldwide. As an alternative to this solution, smart cities are being promoted. The purpose of this paper is to suggest a plan for developing energy service modules for the Sejong 5-1 living area, which has been selected as a test-bed for smart cities in Korea. Based on the smart city plans announced by the government for this study, a survey questionnaire on 12 energy services was composed by collecting the opinions of experts. The survey was conducted with 1,000 citizens, the degree of necessity of energy service that citizens think of was identified. Principal Component Analysis and Association Rule Mining were conducted to describe 12 energy service items in a reduced manner and analyze the correlation and relationship of each energy service. Finally, three modules were suggested using the analyzed results so that 12 energy services could be implemented in an efficient platform. These results are expected to contribute to the realization of a smart city to make them easily accessible for those who want to promote platform services in the energy field and envision energy service items.

• Journal of Broadcast Engineering
• /
• v.23 no.3
• /
• pp.351-360
• /
• 2018

Human emotion recognition is a research topic that is receiving continuous attention in computer vision and artificial intelligence domains. This paper proposes a method for classifying human emotions through multiple neural networks based on multi-modal signals which consist of image, landmark, and audio in a wild environment. The proposed method has the following features. First, the learning performance of the image-based network is greatly improved by employing both multi-task learning and semi-supervised learning using the spatio-temporal characteristic of videos. Second, a model for converting 1-dimensional (1D) landmark information of face into two-dimensional (2D) images, is newly proposed, and a CNN-LSTM network based on the model is proposed for better emotion recognition. Third, based on an observation that audio signals are often very effective for specific emotions, we propose an audio deep learning mechanism robust to the specific emotions. Finally, so-called emotion adaptive fusion is applied to enable synergy of multiple networks. The proposed network improves emotion classification performance by appropriately integrating existing supervised learning and semi-supervised learning networks. In the fifth attempt on the given test set in the EmotiW2017 challenge, the proposed method achieved a classification accuracy of 57.12%.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.13 no.1
• /
• pp.145-155
• /
• 2018

The matter of cultivating entrepreneurship and will to start a business of university students majoring in agriculture and life sciences and college students majoring in agriculture as a future leader in the sector is a very important object of study. However, the discussion on entrepreneurship, establishment of a business and venture based on creative technology and innovative management have been scarcely had, because traditionally the majority of agricultural business has been a small-sized and simple business run by a small farmer. Education for starting an agricultural business in agriculture industry has been ignored even in the developed countries. ICT and AI(artificial intelligence)-based smart agriculture in the 4th Industrial Revolution Age is emerging as a new growth potential of our agriculture industry. Thus, the interest in farmers to start a business and venture agriculture is growing in the agriculture industry. Accordingly, the study draws the influence factors regarding the effect of the planned behavior of the university students who take part in the education course for starting an agricultural business and an agricultural venture business on entrepreneurship and will to start the business and conducts the empirical analysis. The businessmen who newly join the agriculture industry should perform the technical innovation and the creative business activities to be able to compete in the agriculture industry.

• Journal of Technology Innovation
• /
• v.27 no.4
• /
• pp.111-144
• /
• 2019

As virtual assistants rapidly diffused into the market, the voice shopping market is expected to expand. The purpose of this study is to identify the factors that determine the consumers' intention to adopt voice shopping by using the unified theory of acceptance and use of technology(UTAUT). In this study, we set variables that influence the intention to adoption of voice shopping with performance expectation and effort expectations as the variables of UTAUT and playfulness expectations as an extended variable. In addition, we also include four voice secretary attributes such as response accuracy, compatibility, social presence, and safety in our research model to investigate the source of motivation of voice shopping adoption. The result of this analysis shows that variables such as performance expectation, effort expectation, and amusement expectation have a positive effect on the intention to adoption of voice shopping. With respect to the four voice shopping attributes, compatibility had a positive effect on performance expectancy, effort expectancy, and playfulness expectancy. Social presence has a positive effect on playfulness expectancy. Safety has a positive effect on effort expectancy and playfulness expectancy. On the other hand, response accuracy is not significant for performance expectancy, effort expectancy, and playfulness expectancy. This study reveals the determinants of intention to adopt the new purchasing method called voice shopping, and suggests the important factors for the innovation of commerce business.