• Annual Conference of KIPS
• /
• 2022.05a
• /
• pp.441-442
• /
• 2022

교통사고 예측은 차량의 블랙박스 동영상을 통해 사고 발생을 최대한 빨리 예측하는 것을 목표로 한다. 이는 안전한 자율주행 시스템을 보장하는 데 중요한 역할을 한다. 다양한 교통 상황과 카메라의 제한된 시야로 인해 프레임에서 사고 가능성을 조기에 관찰하는 것은 어려운 도전이다. 예측의 핵심 기술은 객체의 시공간 관계를 학습하는 것이다. 본 논문에서는 블랙박스 동영상에서 사고 예측을 위한 계산 모델을 제안한다. 이것을 사용하여 사고 예방을 강화한다. 이 모델은 사고 위험에 대한 운전자의 시각적 인식에서 영감을 받았다. 객체 탐지기는 동영상 프레임에서 다양한 객체를 탐지한다. 탐지한 객체는 노드 생성기와 특징 추출기 동시에 통과한다. 노드 생성기에서 생성한 노드는 GCN 실행기를 사용한다. GCN 실행기는 각 프레임에 대한 객체의 3D 위치 관계를 계산한 후 공간 특징을 취득한다. 동시에 공간 특징과 특징 추출기에서 얻은 객체의 특징은 GRU 실행기로 보내진다. GRU 실행기 안에 시공간 특징을 암기하고 분석하여 교통사고 확률을 예측한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.01a
• /
• pp.127-128
• /
• 2022

최근 많은 증권사 및 다양한 금융사기업에서 투자자의 주식투자를 돕는 투자자문 인공지능, 로보어드바이저를 제안하고 활용한다. 본 논문에서는 증권사 등에서 사용되고 있는 주식 시세예측 알고리즘의 성능을 상호 비교분석한다. 주식 시계열 데이터 예측에 용이한 4가지의 인공지능 알고리즘인 LSTM, GRU, 딥Q 네트워크강화학습, XGBoost 알고리즘의 성능을 분석하고 비교하는 시스템을 구현하였다. 본 연구에서는 구현된 성능 분석 시스템을 통해 어떤 알고리즘이 주식 시세를 예측하고 활용하기 위해 가장 좋은 성능을 가졌는지 비교분석하고 해당 시스템의 결과분석이 주식예측에 어떠한 영향을 주는지를 평가한다.

• Annual Conference of KIPS
• /
• 2023.11a
• /
• pp.406-409
• /
• 2023

With the explosion of information, recommendation algorithms are becoming increasingly important in providing people with appropriate content, enhancing their online experience. In this paper, we propose a recommender system using advanced deep reinforcement learning(DRL) techniques. This method is more adaptive and integrative than traditional methods. We selected the MovieLens dataset and employed the precision metric to assess the effectiveness of our algorithm. The result of our implementation outperforms other baseline techniques, delivering better results for Top-N item recommendations.

• Annual Conference of KIPS
• /
• 2023.11a
• /
• pp.920-921
• /
• 2023

미디어 공유 활성화에 따라 개인정보 노출의 위험성이 증가하고 있다. 본 논문에서는 YOLOv5를 통해 학습한 모델을 바탕으로 이미지에서 개인정보가 담긴 물체를 탐지하는 연구를 진행하였다. 모델로 탐지된 객체에는 광학 인식 기술(OCR)을 적용하여 객체 내의 텍스트 속 개인정보 영역을 마스킹한다. 설계된 알고리즘은 여러 분야에 활용되어 개인정보에 대한 서비스 강화를 제공해 줄 수 있을 것으로 기대된다.

• The Journal of Korea Robotics Society
• /
• v.19 no.1
• /
• pp.92-97
• /
• 2024

This paper provides a study of distributional perspective on reinforcement learning for application in mobile robot navigation. Mapless navigation algorithms based on deep reinforcement learning are proven to promising performance and high applicability. The trial-and-error simulations in virtual environments are encouraged to implement autonomous navigation due to expensive real-life interactions. Nevertheless, applying the deep reinforcement learning model in real tasks is challenging due to dissimilar data collection between virtual simulation and the physical world, leading to high-risk manners and high collision rate. In this paper, we present distributional reinforcement learning architecture for mapless navigation of mobile robot that adapt the uncertainty of environmental change. The experimental results indicate the superior performance of distributional soft actor critic compared to conventional methods.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.39-40
• /
• 2024

본 연구는 SHAP(SHapley Additive exPlanations)을 활용하여 신용카드 사용자의 연체 가능성을 예측하는 기계학습 모델의 해석 가능성을 강화하는 방법을 제안한다. 대규모 신용카드 데이터를 분석하여, 고객의 나이, 성별, 결혼 상태, 결제 이력 등이 연체 발생에 미치는 영향을 명확히 하는 것을 목표로 한다. 본 연구를 토대로 금융기관은 더 정확한 위험 관리를 수행하고, 고객에게 맞춤형 서비스를 제공할 수 있는 기반을 마련할 수 있다.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.3
• /
• pp.243-250
• /
• 2020

In this paper, we propose an effective software education scheme for universities. The key idea of this software education scheme is to analyze software curriculum of QS world university rankings Top 10, SW-oriented university, and regional main national university. And based on the results, we propose five improvements for the effective SW education method of universities. The first is to enhance the adaptability of the industry by developing courses based on the SW developer's job analysis in the curriculum development process. Second, it is necessary to strengthen the curriculum of the 4th industrial revolution core technologies(cloud computing, big data, virtual/augmented reality, Internet of things, etc.) and integrate them with various fields such as medical, bio, sensor, human, and cognitive science. Third, programming language education should be included in software convergence course after basic syntax education to implement projects in various fields. In addition, the curriculum for developing system programming developers and back-end developers should be strengthened rather than application program developers. Fourth, it offers opportunities to participate in industrial projects by reinforcing courses such as capstone design and comprehensive design, which enables product-based self-directed learning. Fifth, it is necessary to develop university-specific curriculum based on local industry by reinforcing internship or industry-academic program that can acquire skills in local industry field.

• Journal of the Economic Geographical Society of Korea
• /
• v.17 no.1
• /
• pp.45-68
• /
• 2014

This research addressed improvement directions and problems of regional science and technology(S&T) policies in Daegu and Gyungbuk regions in terms of 'Creative Economy' which was a new paradigm of Park Gunhye Government. Creative Economy stressed the construction of an ecosystem in regional research and development activities, and thus it was deeply associated with building a regional innovation system(RIS). There were several problems to strengthen RIS with regional S&T policies of the regions as follows: limits in meeting regional needs due to excessive attraction of central government's projects into regions; the high ratio of programs for future basic research potentials; the lack of programs assessing and coordinating the policies; and the lack of experiences and expenditure of research institutes and firm supporting organizations. Due to these problems, the role of the policies in building RIS did not seem to be effective. Therefore, the policies need to be improved through the following measures: the expansion of regional own policies focusing regional needs; the enhancement of policy coordination by shifting to systematic approach; the expansion of soft supporting programs for constructing innovation systems; and the enhancement of stability and ability of research institutes and firm supporting organizations.

• Korean Journal of Comparative Education
• /
• v.24 no.5
• /
• pp.53-70
• /
• 2014

This study was performed in order to suggest the future model of Asian universities that could be used in the planning of the global competitive strategy. Futurologists forecasted the future of higher education using Harman Fan Scenario as like this. First, most current universities will be 'the satellite university' until 2015. Second, they also will replace 'the bookless university' until 2020. Third, they will be 'no calendar university' until 2025. And then they may be 'all have access university' until 2030. After 2030, futurologists prospected that almost universities based on off-line campus will be disappeared into the history. The analysis method of Harman fan scenario and applied scenarios were also used to "A study on the future scenario of Korean university". The predictive model and the alternative models were explored in a view point of students, enterprise, and government. Individuality with educational excellence are standardized for learner, profit and effectiveness are applied for enterpriser, and equality with welfare are adapted for national leader. Asian universities need to focus on bringing up the practical ability based on conscious and emotional education instead of knowledge based on memory. Also they need to enforce the specialized education that can create new jobs through convergence of interdisciplinary. Especially, Asian nations need to explore, to find the strengthen area of their universities compared with USA. And these area should be specialized. The convergency strategy between oriental medicine and informatics is a meaningful sample. Based on this point, a predicted with 3 alternative scenarios in a view point of equality were suggested for the future of Asian universities.

• Journal of Korean Home Economics Education Association
• /
• v.31 no.3
• /
• pp.135-153
• /
• 2019

The purpose of this study was to develop teaching-learning plans applying ARCS strategies for food safety education, focusing on units related to the 'food selection and safe cooking'. To achieve this purpose, this study was conducted in the following order of analysis, design, development, assessment I, revision I, assessment II, revision II, and completion. In the analysis stage, 2015 revised curriculum and middle school technology-home economics textbooks(12 kinds) contents of 'food selection and safe cooking' among content elements of core concept 'safety' were analyzed. In the design and development stages, teaching-learning plans, teaching-learning materials, and evaluation rubric for teaching-learning outcomes using the ARCS motivation strategy were developed. In the phases of assessment I and revision I, evaluation items were selected as open-ended questions about food safety education factors and ARCS strategies, and their validities were verified by four experts. The teaching-learning plans for nine lessons were revised based on the feedbacks such as evaluation plans considering the correspondence between instruction and evaluation, strategy to reinforce intrinsic motivation, correction of improper contents composition, and so on. In the phases of assessment II and revision II, the validity of the three items, including relevance of each teaching-learning to food safety education, suitability of learning goals, and appropriateness of motivation strategy, was verified by seven experts. The final teaching-learning plans for 10 lessons were developed by revising and supplementing the data by compiling opinions of the assessment II. It is expected that this study can contribute to food safety education for middle school students, and that teaching-learning plans which apply ARCS strategies for food safety education will be used as good references for school teachers and curriculum developers.