• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.61-64
• /
• 2020

현재까지 심층 학습을 이용하여 텍스트를 자동으로 분류해주는 연구가 활발히 진행되었으며, 특히 소프트웨어 카테고리를 자동으로 분류해주는 연구가 이루어지고 있다. 최근 심층 신경망의 적절한 구조를 효율적으로 탐색할 수 있는 가중치 공유 기법이 연구되었다. 우리는 이를 응용하여 본 논문에서 가중치 공유를 이용한 소프트웨어 카테고리 분류 방법을 제안하며, 여러 실험을 통해 해당 기법의 성능을 측정하고 논의한다.

• Proceedings of the Korean Institute of Communication Sciences Conference
• /
• 2004.07a
• /
• pp.396-396
• /
• 2004

• 제어로봇시스템학회:학술대회논문집
• /
• 1998.10a
• /
• pp.26-29
• /
• 1998

This paper proposes a novel method to efficiently develop GUI based control software for a legged mobile robot. Although GUI is convenient it is a very burden to both a computer and its developer. In case of the mobile robot, these problems are more serious. The proposed method solves these problems by separating GUI from control software. An implementation based upon the proposed method demonstrates its effectiveness.

• Journal of Engineering Education Research
• /
• v.19 no.2
• /
• pp.60-69
• /
• 2016

This paper deals with the selection method of effective engineering design problem based on LEGO Mindstorm NXT for basic design education. By YouTube case study of various LEGO-based engineering designs for olympic sports, performance criteria have been developed including programming complexity, structural complexity, sensor/actuator complexity and variety of game operation. Programming complexity includes range of programming code length and possible program variety. Structural complexity includes variety of structural elements such as length, shape, weight, and volume to overcome design restrictions. Sensor/actuator complexity includes variety of sensor used and number of possible actuator assemblies. Variety of game operation includes game complexity and required creativity to make LEGO robots. Based on these performance criteria, four representative sports were selected as the candidates for effective engineering design problem. Finally, feasibility and attributes of each candidate were verified by real implementation examples.

• Journal of information and communication convergence engineering
• /
• v.17 no.4
• /
• pp.246-254
• /
• 2019

This paper proposes a solution to the problem of finding a subgraph for a given instance of many terminals on a Euclidean plane. The subgraph is a tree, whose nodes represent the chosen terminals from the problem instance, and whose edges are line segments that connect two corresponding terminals. The tree is required to have the maximum number of nodes while the length is limited and is not sufficient to interconnect all the given terminals. The problem is shown to be NP-hard, and therefore a genetic algorithm is designed as an efficient practical approach. The method is suitable to various probable applications in layout optimization in areas such as communication network construction, industrial construction, and a variety of machine and electronics design problems. The proposed heuristic can be used as a general-purpose practical solver to reduce industrial costs by determining feasible interconnections among many types of components over different types of physical planes.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2017.07a
• /
• pp.311-313
• /
• 2017

우리 팀은 이미지 인식, 나아가서 실시간 이미지의 분석에 대해 연구하기로 했다. 본 논문에서는 카메라에서 비추어지는 이미지를 인식하는 기술과 기술을 활용한 예시를 보여준다. 결과 자료는 최종 사용자가 아닌, 개발자나 디자이너가 2차 가공을 할 수 있는 형태로 제공된다. 이 방식은 이미지의 종류나 위치 등 다양한 종류의 결과 값을 도출할 수 있다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06a
• /
• pp.253-255
• /
• 2006

무선 센서 네트워크는 수백 혹은 수천 개의 무선 센서 노드들로 이루어지고 센서 노드의 플랫폼은 비용 효율성 때문에 매우 제한적인 메모리 공간을 지닌다. 이러한 센서 노드들은 자연의 정보를 수집하고, 이웃 노드들끼리 통신하며, 정보를 가공하여 사용자에게 실시간으로 전달하는 기능을 담당한다. 따라서 무선 센서 네트워크를 위한 센서 운영체제는 공간 효율적이고 다수의 작업들을 실시간으로 처리할 수 있는 멀티 쓰레드 기법이 필요하다. 본 논문에서는 공간 제약적인 센서 운영체제를 위한 스택리스 쓰레드 기법을 제안한다. 제안한 기법을 사용하면, 기존의 스택기반 쓰레드를 사용하는 것보다 메모리 공간의 사용량을 절감지킬 수 있다. 본 논문의 비교 실험 결과를 통하여, 제안한 기법을 사용하는 것이 기존의 방법보다 메모리 사용량을 상당히 줄일 수 있음을 보인다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2010.06b
• /
• pp.107-111
• /
• 2010

급변화하는 비즈니스 환경에 가장 빠르게 대응할 수 있고, IT 자원의 상호운용성 및 재활용성을 증대할 수 있는 SOA 기반 소프트웨어 시장이 급격히 증가함에 따라 SOA 기반 시스템 품질 평가 방법들이 연구되고 있다. 그러나, SOA에 융합된 BI 관점의 평가 방법은 연구가 부족하다. 본 연구에서는 ISO/IEC 9126국제 표준을 참조하여 SOA와 융합된 BI의 품질 평가 특성을 제시하고, 사례 연구를 통해 품질 평가 방법을 제안 및 검증한다. 본 연구를 통해, BI를 SOA와 융합하는 과정에 품질 특성을 고려하여 구현 및 융합함으로써 소프트웨어의 품질 향상을 유도하고 완성된 소프트웨어의 품질 평가에 활용될 것으로 기대한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.5
• /
• pp.2381-2399
• /
• 2019

Traditional recommendation algorithms on Collaborative Filtering (CF) mainly focus on the rating prediction with explicit ratings, and cannot be applied to the top-N recommendation with implicit feedbacks. To tackle this problem, we propose a new collaborative filtering approach namely Maximize MAP with Matrix Factorization (MFMAP). In addition, in order to solve the problem of non-smoothing loss function in learning to rank (LTR) algorithm based on pairwise, we also propose a smooth MAP measure which can be easily implemented by standard optimization approaches. We perform experiments on three different datasets, and the experimental results show that the performance of MFMAP is significantly better than other recommendation approaches.

• Journal of Engineering Education Research
• /
• v.17 no.4
• /
• pp.95-101
• /
• 2014

As other major, students have difficulties to be successfully adapted to computer science major without some interest and skill to computer programming. In this paper, we try to find successful factors for computer science major freshmen students to computer programming. The factors we focused are programming experience before college entrance, taking liberal arts/natural science courses at high school, application motivations to computer major, existence of mentors, satisfaction to his/her computer department, student's holland job aptitude code. After analysis, taking liberal arts/natural science courses at high school, satisfaction to computer department, some holland job aptitude code are significant to their successful adaptation to computer major. Also, we found the holland job apptitude code is closely related to student's satisfaction to their major for engineering students including computer science students. Our analysis results will be a suggestion for designing computer science education program with students who enters college without some aptitude or preparation to his major.