• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.603-605
• /
• 2022

추천시스템은 개개인의 성향에 따른 맞춤화 추천이 가능하기 때문에 음악, 영상, 뉴스 등 많은 분야에서 관심을 받고 있다. 일반적인 추천시스템 모델은 블랙박스 모델이기 때문에 추천 결과에 따른 원인 도출을 할 수 없다. 하지만 XAI 의 모델은 이러한 블랙박스 모델의 단점을 해결하고자 제안되었다. 그 중 KGAT 는 Attention Score 를 기반으로 추천 결과에 따른 원인을 알 수 있다. 이와 같은 AI, XAI 등의 딥 러닝 모델에서 각각의 활성화 함수는 상황에 따라 상이한 성능을 나타낸다. 이러한 이유로 인해 데이터에 맞는 활성화 함수를 적용해보는 다양한 시도가 필요하다. 따라서 본 논문은 XAI 추천시스템 모델인 KGAT 의 성능 개선을 위해 여러 활성화 함수를 적용해보고, 실험을 통해 수정한 모델의 성능이 개선됨을 보인다.

• Geomechanics and Engineering
• /
• v.37 no.1
• /
• pp.21-29
• /
• 2024

The effective management of damage in tunnels is crucial for ensuring their safety, longevity, and operational efficiency. In this paper, we propose an educational management model tailored specifically for addressing damage in tunnels, utilizing numerical solution techniques. By leveraging advanced computational methods, we aim to develop a comprehensive understanding of the factors contributing to tunnel damage and to establish proactive measures for mitigation and repair. The proposed model integrates principles of tunnel engineering, structural mechanics, and numerical analysis to facilitate a systematic approach to damage assessment, diagnosis, and management. Through the application of numerical solution techniques, such as finite element analysis, we demonstrate the efficacy of the proposed model in simulating various damage scenarios and predicting their impact on tunnel performance. Additionally, the educational component of the model provides valuable insights and training opportunities for tunnel management personnel, empowering them to make informed decisions and implement effective strategies for ensuring the structural integrity and safety of tunnel infrastructure. Overall, the proposed educational management model represents a significant advancement in tunnel management practices, offering a proactive and knowledge-driven approach to addressing damage and enhancing the resilience of tunnel systems.

• International Journal of Computer Science & Network Security
• /
• v.23 no.12
• /
• pp.123-128
• /
• 2023

The main purpose of the study is to analyze the features of the influence of Agile management on the competence of the personnel of the socio-economic system in the digital economy. The research methodology implies the use of modern methods of analysis. Improving the business processes of an organization is associated with improving activities, the formation of effective management systems and processes, especially the organization's policy in the field of quality, rational use of resources, increasing the responsibility of management, social responsibility of the organization, etc. The modern knowledge economy places high demands on the effectiveness of behavioral models of employees of the organization. The role of the human factor in the production system is becoming more and more obvious. Therefore, it is important to study the competence of the personnel of any socio-economic system. Based on the results of the study, the key features of the influence of Agile management on the competence of the personnel of the socio-economic system in the digital economy were identified.

• International Journal of Computer Science & Network Security
• /
• v.23 no.12
• /
• pp.161-166
• /
• 2023

The main purpose of the study is to analyze the features of the influence of Agile management on the competence of the personnel of the socio-economic system in the digital economy. The research methodology implies the use of modern methods of analysis. Improving the business processes of an organization is associated with improving activities, the formation of effective management systems and processes, especially the organization's policy in the field of quality, rational use of resources, increasing the responsibility of management, social responsibility of the organization, etc. The modern knowledge economy places high demands on the effectiveness of behavioral models of employees of the organization. The role of the human factor in the production system is becoming more and more obvious. Therefore, it is important to study the competence of the personnel of any socio-economic system. Based on the results of the study, the key features of the influence of Agile management on the competence of the personnel of the socio-economic system in the digital economy were identified.

• Nutrition Research and Practice
• /
• v.10 no.5
• /
• pp.555-562
• /
• 2016

BACKGROUND/OBJECTIVES: Childhood obesity has become a global epidemic. Development of effective and sustainable programs to promote healthy behaviors from a young age is important. This study developed and tested an intervention program designed to promote healthy eating and physical activity among young children in South Korea by adaptation of the US National Aeronautics and Space Administration (NASA) Mission X (MX) Program. SUBJECTS/METHODS: The intervention program consisted of 4 weeks of fitness and 2 weeks of nutrition education. A sample of 104 subjects completed pre- and post- surveys on the Children's Nutrition Acknowledgement Test (NAT). Parents were asked for their children's characteristics and two 24-hour dietary records, the Nutrition Quotient (NQ) at baseline and a 6-week follow-up. Child weight status was assessed using Korean body mass index (BMI) percentiles. RESULTS: At baseline, 16.4% (boy: 15.4%; girl: 19.2%) of subjects were overweight or obese (based on $BMI{\geq}85%tile$). Fat consumption significantly decreased in normal BMI children ($48.6{\pm}16.8g$ at baseline to $41.9{\pm}18.1g$ after intervention, P < 0.05); total NQ score significantly increased from 66.4 to 67.9 (P < 0.05); total NAT score significantly improved in normal BMI children (74.3 at baseline to 81.9 after the program), children being underweight (from 71.0 to 77.0), and overweight children (77.1 at baseline vs. 88.2 after intervention, P < 0.001). CONCLUSIONS: The 6-week South Korean NASA MX project is feasible and shows favorable changes in eating behaviors and nutritional knowledge among young children.

• Journal of Korea Technology Innovation Society
• /
• v.18 no.2
• /
• pp.292-317
• /
• 2015

As modern science and technology and warfare become to be advanced and precise, the weapon systems becomes more complex based on state-of-the-art technology. Therefore, firms in the defense industry continue to accelerate research and development for up-to-date weapon systems with high complexity which urge the firms to collaborate with the external organizations to obtain the knowledge required and eventually to reduce costs and risk. This study tries an empirical study about the effect of collaboration on the innovation performances from the network analysis perspective. By surveying collaboration relationships among 530 firms in the Korean defense industry, we analyzed the alliance network of the defense industry. Network centrality including degree, closeness, and betweenness centralities is investigated and then the relationship among the network centrality property, internal R&D capabilities and innovation is analysed. The results show that firms with high internal R&D capabilities place the firm at center of the network. On the other hand, except for the firms with highly connected centrality, no relationship was found between the internal R&D capabilities and its performance and in turn. these capabilities had both direct and indirect effects on innovation performances through mediated collaboration among firms. This study implied that Korean firms with a high internal R&D capabilities in the defense industry which utilize knowledge, information and resources within the network more frequently show more innovative performance. This result claims the policy makers to participate more firms in fostering open innovation for the defense industry.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.2
• /
• pp.750-762
• /
• 2019

The importance of the call center as a contact point for the enterprise is growing. However, call centers have difficulty with their operating agents due to the agents' lack of knowledge and owing to frequent agent turnover due to downturns in the business, which causes deterioration in the quality of customer service. Therefore, through an N-bank call center case study, we developed a system to reduce the burden of keeping up business knowledge and to improve customer service quality. It is a "real-time agent advisor" system that provides agents with answers to customer questions in real time by combining AI technology for speech recognition, natural language processing, and questions & answers for existing call center information systems, such as a private branch exchange (PBX) and computer telephony integration (CTI). As a result of the case study, we confirmed that the speech recognition system for real-time call analysis and the corpus construction method improves the natural speech processing performance of the query response system. Especially with name entity recognition (NER), the accuracy of the corpus learning improved by 31%. Also, after applying the agent advisor system, the positive feedback rate of agents about the answers from the agent advisor was 93.1%, which proved the system is helpful to the agents.

• Knowledge Management Research
• /
• v.23 no.3
• /
• pp.129-152
• /
• 2022

As a key infrastructure for digital transformation, the spread of data, network, artificial intelligence (D.N.A.) fields and the emergence of promising industries are laying the groundwork for active digital innovation throughout the economy. In this study, by applying the text mining methodology, major topics were derived by using the abstract, publication year, and research field of the study corresponding to the SCIE, SSCI, and A&HCI indexes of the WoS database as input variables. First, main keywords were identified through TF and TF-IDF analysis based on word appearance frequency, and then topic modeling was performed using g-DMR. With the advantage of the topic model that can utilize various types of variables as meta information, it was possible to properly explore the meaning beyond simply deriving a topic. According to the analysis results, topics such as business intelligence, manufacturing production systems, service value creation, telemedicine, and digital education were identified as major research topics in digital transformation. To summarize the results of topic modeling, 1) research on business intelligence has been actively conducted in all areas after COVID-19, and 2) issues such as intelligent manufacturing solutions and metaverses have emerged in the manufacturing field. It has been confirmed that the topic of production systems is receiving attention once again. Finally, 3) Although the topic itself can be viewed separately in terms of technology and service, it was found that it is undesirable to interpret it separately because a number of studies comprehensively deal with various services applied by combining the relevant technologies.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.12A
• /
• pp.991-997
• /
• 2009

Transmit beamforming is simple method to achieve the full diversity gain that is available in multiple antenna(MIMO) wireless systems. Unfortunately, the prior condition to achieve this gain requires perfect channel knowledge at both transmitter and receiver, which is impractical on account of limited feedback link. Therefore, for the practical system, codebook based feedback scheme is often employed, where the beamforming vector is selected from the codebook to maximize the output signal-to-noise ratio (SNR) at receiver, and the receiver only sends back the index of the best beamforming vector to the transmitter. In this paper we derive analytical expression of average bit error rate (BER) for the codebook based transmit beamforming MISO system over the feedback error channel. Using this analytical result, we present optimum codebook indexing scheme to improve the performance of this system. From some selected numerical examples we show that our proposed codebook indexing scheme can provide nonnegligible performance improvements in terms of average BER over the severe feedback error channel.

• Korean Journal of Artificial Intelligence
• /
• v.7 no.1
• /
• pp.23-59
• /
• 2019

The purpose of this study is to develop a measure of service quality in the traditional market by examining previous research on the service quality of the traditional market studied so far. After defining basic concepts through definition of traditional market and existing studies, 5 categories of configuration items for SERVQUAL measurement in traditional market were made up based on existing researches related to definition of service quality and service quality of traditional market. A survey was conducted on the items that fit the intention of this study and various statistical analyzes were conducted. Statistical analysis was performed using SPSS 22.0 and AMOS 22.0. The reliability of the items was measured by the reliability test, and the predictability and accuracy of the items were examined. The validity of the measured variables was verified through confirmatory factor analysis. Reliability, empathy, responsiveness, certainty, and tangibility were the most important factors in this study. Responsiveness factors include communication, time reduction, real time, promptness. Assurance factors include the assurance of delivery, prompt answers, product knowledge items. Tangibility factors include, convenient device systems, location information, presence as a fact, and as a result, the latest modern items are adopted. The quality of service in the traditional market developed in this study was found to be good in reliability and validity test. Confirmatory factor analysis result using structural equation model also met the conformity index standard. If service satisfaction is measured based on this research, basic data can be presented to policy makers who implement policies on traditional markets to make the right decisions. In addition, it will be able to provide traditional market operators with operational strategy and marketing data. In the future, based on the traditional market service quality scale developed in this study, it is necessary to grasp the factors to be continuously managed to improve the service quality of the traditional market, user satisfaction, and intention to use.