• Journal of Gifted/Talented Education
• /
• v.13 no.4
• /
• pp.95-117
• /
• 2003

This study is to suggest the alternative to limits of intelligence focused on Psychometric tests. Through this study, it was found that triarchic theory of intelligence and thinking styles, which were suggested by Sternberg, were useful. The subjects are 122 student who are at three science-high-schools. The results show that the subjects preferred judicial, executive, and hierarchical rather than conservative styles of thinking, and they had strong analytical, creative, and practical ability. The correlation between academic achievement and triarchic intelligence except automation was significant. The difference of academic achievements was not significant by styles of thinking related to creativity and pattern of triarchic intelligence. There was no interaction between two variables as we expected. The practical ability illustrated the total academic performance very well. And executive, judicial thinking styles were prediction variable in case of considering with triarchic intelligence. Through the results, it could be suggested that triarchic intelligence and thinking styles of non cognitive concept could be important standard referred to selection for the science-gifted, and argued that the reform of the science-high-school was needed to produce the creative-productive science-gifted student.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.358-360
• /
• 2023

뱀장어는 내수면 양식어종으로 뱀장어 양식에서 널리 쓰이는 지수식 양식에 있어서 가장 중요하고 가장 어려운 것은 수질관리다. 수질을 구성하는 요소와 공급된 사료량은 서로 상관관계를 가지며, 이 상관관계에 이상 현상이 발생하면 먹이 섭취 불량과 폐사로 이어질 수 있다. 그래서 본 연구에서는 센서로 측정한 양식장 데이터와 인공지능 모델을 이용하여 수조 속 DO 를 예측하는 모델을 새롭게 제안하여, 적절한 사료 공급 시점과 적절한 공급량을 결정하는 방안에 적절히 사용할 수 있다는 것을 검증하였다. 사료 공급과 공급량에 따른 변화를 가미한 3 시간 후의 DO 를 합당한 이벤트 처리를 통해 예측하였다. 이를 활용하면 사료로 인해 떨어지는 DO 수치를 예측하고, DO 수치가 낮아 회복이 필요한 시점에 투입하는 사료량을 조절하여 질식으로 인해 발생하는 폐사로부터 양식어를 지키며 보다 안정적으로 양식을 위해 활용할 수 있다는 점을 확인할 수 있었다.

• Journal of Internet Computing and Services
• /
• v.24 no.4
• /
• pp.93-105
• /
• 2023

In order to transform the traditional aquaculture industry, which is dependent on experience, labor-intensive and natural environment, into future intelligent smart aquaculture, digital aquaculture improves aquaculture reproducibility and efficiency of production process through digitization of the aquaculture industry based on ICT equipments, Data analysis and utilization for promoted to increase the acceptability of aquaculturist. Europe's advanced fisheries countries have achieved rapid growth not only in aquaculture technology but also in the aquaculture equipment industry through digitization that combines information and communication technology with aquaculture farms. However, it is not possible to collect aquacultural data in Korea because it has not secured a Korean aquaculture industry for multi-variety, small-scale production and aquaculturists' refusal of reception for digital transformation. Therefore, this study intends to suggest the development direction of digital aquaculture to convert to intelligent smart aquaculture in the future by analyzing trends and critical technology.

• Journal of The Korean Association For Science Education
• /
• v.23 no.1
• /
• pp.21-34
• /
• 2003

This study aims to show how scientifically gifted students think in terms of Thinking Style Inventory based on Sternberg's theory of mental self-government and to examine the relationships between their thinking styles, intelligence and creativity. Two hundred and sixty-six middle school students (169 boys, 97 girls) who enrolled in a gifted education program participated in this study. Results indicated that scientifically gifted students prefer legislative, liberal, judical thinking styles, in comparison to general students, known to be related to creative and critical thinking rather than executive and conventional styles. There was no significant correlation between any of thinking style sub measures and Raven' Matrices and Scientific Aptitude Test, but some correlations were found among the sub measures of thinking style and TTCT. Whereas liberal students gained high originality scores, conventional students gained low fluency scores. Also, judical thinking style showed significant correlations with originality and flexibility TTCT sub scores. In sum, this study showed the characteristics of thinking styles of scientifically gifted students and provided implications for gifted education based on the findings presented.

• The Journal of Bigdata
• /
• v.8 no.2
• /
• pp.73-82
• /
• 2023

With 78% of current fisheries workers being elderly, there's a pressing need to address labor shortages. Consequently, active research on smart aquaculture technologies, centered on object detection and tracking algorithms, is underway. These technologies allow for fish size analysis and behavior pattern forecasting, facilitating the development of real-time monitoring and automated systems. Our study utilized video data from cameras outside aquaculture facilities and implemented fish detection and tracking algorithms. We aimed to tackle high maintenance costs due to underwater conditions and camera corrosion from ammonia and pH levels. We evaluated the performance of a real-time system using YOLOv7 for fish detection and the SORT algorithm for movement tracking. YOLOv7 results demonstrated a trade-off between Recall and Precision, minimizing false detections from lighting, water currents, and shadows. Effective tracking was ascertained through re-identification. This research holds promise for enhancing smart aquaculture's operational efficiency and improving fishery facility management.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.10a
• /
• pp.869-870
• /
• 2013

본 논문은 Ubiquitous Networking 기술을 기반으로 한 IT와 수산업과의 융합 서비스 기술을 지원하기 위해서 양식장의 지능형 유비쿼터스 시스템의 구축을 제안한다. 이 시스템은 어장의 원격 모니터링 및 관리, 스마트폰을 기반으로 어장의 이상 변화를 감지하고 SMS 등을 통해서 알림을 제공한다. 그리고 양식장 관리 정보 모니터링 및 제어 등을 통한 수산물 양식의 양식장 미생물 유지 및 최적 관리를 위한 유비쿼터스 기술과 양식장의 양식 관리 정보 공유 플랫폼을 개발한다. 따라서 양어장 내의 정보를 무선 센서를 통해 자동으로 수집하고, 수산물의 종류, 성장 단계, 기후 및 환경에 따라 각종 생장 조건을 최적으로 관리함으로써 각 수산물 재배에 최적화된 파라미터를 바탕으로 생장 및 품질을 예측하여 수산물의 생장 및 생산력을 극대화한다.

• The Journal of the Korea Contents Association
• /
• v.20 no.10
• /
• pp.167-176
• /
• 2020

The automated fish feed system currently used in Korea supplies a certain amounts of feed to water tanks at a certain time. This automated system can reduce the labor cost of managing aqua farms, but it is very difficult to control intelligently and appropriately the amount of expensive feed that is critical to aqua farm productivity. In this paper, we propose the FIIFF Inference Model( Fuzzy Inference-based Intelligent Fish Feeding Model) that can solves the problems of these existing automatic fish feeding devices and maximizes the efficiency of feed supply while properly maintaining the growth rate of fish in aqua farms. The proposed FIIFF inference model has the advantage of being able to control feed amounts appropriately since it computes the amount of feed using the current water environments and fish activity state of the aqua farms. The result of the feed amount yield experiment with the proposed FIIFF Inference Model represents the effect of saving 14.8% over the eight months of actual feed amount in the aqua farm.

• KIPS Transactions on Computer and Communication Systems
• /
• v.9 no.7
• /
• pp.157-164
• /
• 2020

As the consumption of fishery products continues to increase, aquaculture industry has emerged instead of fishing industry facing limitations of fish stock resources. Recently, smart fish farming industry has rapidly developed through convergence with 4th Industrial Revolution technology. Accordingly, it is important to derive a future model of smart fish farming platforms in order to secure the superiority of the aquaculture industry and the technology standard hegemony. In this study, the future direction of smart fish farm platform was derived through the analysis of environment related to politics, economy, society, and technology related to smart fish farming by applying PEST methodology of macro-environment analysis. It is expected that it will help the public and industrial circles in planning and implementing related projects by including the entire process of value chain of aquaculture industry of breeding, production, management and distribution, and by presenting advanced models based on artificial intelligence and digital twin.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.496-497
• /
• 2021

감정 분류는 사람의 사고방식이나 행동양식을 구분하기 위한 중요한 열쇠로, 지난 수십 년간 감정 분석과 관련된 다양한 연구가 진행되었다. 감정 분류의 품질과 정확도를 높이기 위한 방법 중 하나로 단일 레이블링 대신 다중 레이블링된 데이터 세트를 감정 분석에 활용하는 연구가 제안되었고, 본 논문에서는 T5 모델을 한국어와 영어 코퍼스로 학습한 KE-T5 모델을 기반으로 한국어 발화 데이터를 단일 레이블링한 경우와 다중 레이블링한 경우의 감정 분류 성능을 비교한 결과 다중 레이블 데이터 세트가 단일 레이블 데이터 세트보다 23.3% 더 높은 정확도를 보임을 확인했다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.04a
• /
• pp.241-244
• /
• 2007

본 논문에서는 박테리아의 주화성에 기초한 Bacteria Cooperative Optimization(BCO) 알고리즘을 소개한다. BCO는 Ant Colony Optimization (ACO)처럼 자연계에 존재하는 생명체의 행동양식을 모방하여 만든 최적화 알고리즘으로 크게 초기화, 측정, 행동결정, 이동으로 구성된다. 우리는 먼저 BCO 알고리즘을 설명하고 2차원 함수 최적화 문제를 이용하여 BCO알고리즘과 Genetic Algorithm(GA) 그리고 Bacterial Foraging for Distributed Optimization(BFO)의 성능 측정 결과를 기술한다. 실험 결과 BCO의 성능이 GA나 BFO보다 우수함을 보였다.