http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Evolvable Neural Networks for Time Series Prediction with Adaptive Learning Interval
서상욱,이동욱,심귀보 한국지능시스템학회 2008 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.8 No.1
This paper presents adaptive learning data of evolvable neural networks (ENNs) for time series prediction of nonlinear dynamic systems. ENNs are a special class of neural networks that adopt the concept of biological evolution as a mechanism of adaptation or learning. ENNs can adapt to an environment as well as changes in the environment. ENNs used in this paper are L-system and DNA coding based ENNs. The ENNs adopt the evolution of simultaneous network architecture and weights using indirect encoding. In general just previous data are used for training the predictor that predicts future data. However the characteristics of data and appropriate size of learning data are usually unknown. Therefore we propose adaptive change of learning data size to predict the future data effectively. In order to verify the effectiveness of our scheme, we apply it to chaotic time series predictions of Mackey-Glass data.
다각형 기반의 Q-Learning과 Cascade SVM을 이용한 군집로봇의 목표물 추적 알고리즘
서상욱,양현창,심귀보,Seo, Sang-Wook,Yang, Hyung-Chang,Sim, Kwee-Bo 대한임베디드공학회 2008 대한임베디드공학회논문지 Vol.3 No.2
This paper presents the polygon-based Q-leaning and Cascade Support Vector Machine algorithm for object search with multiple robots. We organized an experimental environment with ten mobile robots, twenty five obstacles, and an object, and then we sent the robots to a hallway, where some obstacles were lying about, to search for a hidden object. In experiment, we used four different control methods: a random search, a fusion model with Distance-based action making (DBAM) and Area-based action making (ABAM) process to determine the next action of the robots, and hexagon-based Q-learning and dodecagon-based Q-learning and Cascade SVM to enhance the fusion model with DBAM and ABAM process.
서상욱 한국해양경찰학회 2013 한국해양경찰학회보 Vol.3 No.1
2013년 박근혜 정부는 ‘안전한 사회 건설 및 국가재난관리시스템 강화’라는 국정 기조로 안전정책을 강력하게 추진하고 있다. 이에 국민의 생명과 안전을 지키는 것 을 주요임무로 하는 경찰기능의 역할이 어느 때보다 중요하게 부각되고 있으며, 특 히 해양에서의 경찰 및 오염방제 임무를 수행하고 있는 해양경찰은 해양사고 예방을 위한 ‘안전관리’에 보다 많은 관심을 기울이고 있다. 다만, 실제로 해양에서 발생하는 안전사고를 완벽하게 예방하기에는 물리적으로 한계가 있으며, 해양사고의 약 70%를 차지하고 있는 어선의 경우에는 개인 위주의 생계형 어업활동에 이용되고 있어 안전관리체계가 매우 미흡한 실정이다. 이런 이유 로 지금까지 다양한 연구가 이루어져 왔으나, 대부분이 어선 안전사고의 원인 분석 을 통한 제도 개선과 법적근거 마련 등의 중·장기적 대안 제시에 초점을 맞추었다. 따라서 본 연구는 기존의 연구와는 달리 해양경찰의 어선 안전관리체계에 대한 문제점 분석을 통해 단기간에 적용할 수 있는 해양경비체계 개선방안을 제시하는데 그 목적이 있다. 해양경찰은 이번 연구결과를 기반으로 경비활동과 연계한 종합적 해양 안전망을 구축하여 바다를 경영하는 국가의 중심축으로서 자리매김해야 할 것이다.
Behavior Learning of Swarm Robot System using Bluetooth Network
서상욱,양현찬,심귀보 한국지능시스템학회 2009 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.9 No.1
With the development of techniques, robots are getting smaller, and the number of robots needed for application is greater and greater. How to coordinate large number of autonomous robots through local interactions has becoming an important research issue in robot community. Swarm Robot Systems (SRS) is a system that independent autonomous robots in the restricted environments infer their status from preassigned conditions and operate their jobs through the cooperation with each other. In the SRS, a robot contains sensor part to percept the situation around them, communication part to exchange information, and actuator part to do a work. Especially, in order to cooperate with other robots, communicating with other robots is one of the essential elements. Because Bluetooth has many advantages such as low power consumption, small size module package, and various standard protocols, it is rated as one of the efficient communicating technologies which can apply to small-sized robot system. In this paper, we will develop Bluetooth communicating system for autonomous robots. And we will discuss how to construct and what kind of procedure to develop the communicating system for group behavior of the SRS under intelligent space.
서상욱,최은정,정현철,이종식,김건엽,이재석,소규호 한국환경생물학회 2015 환경생물 : 환경생물학회지 Vol.33 No.3
This study was conducted to find out the methodology of carbon budget assessment among soil, atmosphere and plant. Soil respiration, net ecosystem productivity of herbs and net ecosystem productivity of woody plants have been measured in 30 years old pear orchard at Naju. Closed Dynamic Chamber (CDC) method was used to measure soil respiration and net ecosystem productivity of herbs. Net ecosystem productivity of woody plant (pear) was determined by eddy covariance method using the EddyPro (5.2.1) program. As for soil respiration, 429.1 mg CO2 m-2 h-1 was released to atmosphere and sensitivity of soil temperature (Q10) was 2.3. In case of herbs, respiration was superior to photosynthesis during measurement period. From 20 to 24 Jun 2015, the sum of absorbed and released CO2 by herb’s photosynthesis and respiration was 156.1 mg CO2 m-2 h-1. Woody plants showed the 680.1 mg CO2 m-2 h-1 of absorption by photosynthesis. In a farm scale, the sum of soil respiration, and net ecosystem productivity of herbs and woody plants was 0.04 ton CO2 ha-1 during the measurement period, and it showed that pear orchard act as a CO2 sink. This study using various approaches is expected to present a methodology for evaluating the carbon budget of perennial woody crop plantations.