• 한국지능시스템학회논문지
• /
• 제15권7호
• /
• pp.852-857
• /
• 2005

본 논문은 지능형 로봇 시스템을 위한 인간 몸의 하이브리드 실루엣 추출 기법을 제안한다. 지능형 로봇은 내부적인 진동과 낮은 해상도로 인해 강인한 실루엣 추출을 필요로 한다. 이를 극복하기 위해서 본 논문에서는 하이브리드 실루엣 추출 기법을 제안하였다. 하이브리드 실루엣은 영상간의 공간차 및 시간차 정보를 고려 생성되며 움직임 영역 모델을 통해 두 정보간의 중요성에 가중치를 준다. 최종적으로 실험결과를 통해 제안된 기법의 우수성을 확인하였다.

• 한국지능시스템학회논문지
• /
• 제15권7호
• /
• pp.858-863
• /
• 2005

센서 네트워크는 다수의 센서 노드들이 싱크노드와 데이터 중심(Data centric) 기반으로 통신을 하게 되며 이때 사용되는 라우팅 알고리즘 중 하나가 Directed Diffusion 알고리즘이다. Directed Diffusion은 싱크노드의 named data 질의에 기반을 둔 라우팅 프로토콜로 다수의 소스 노드와 다수의 싱크 노드의 상황에서도 효율적으로 동작한다는 점과 각각의 질의에 의한 라우팅 경로 상에서 데이터 융합(aggregation) 과 caching을 수행할 수 있다는 장점을 갖는다. 그러나 강화된 gradient 경로를 얻기 위해 요구되는 부담이 크다는 단점을 갖는다. 따라서 본 연구에서는 interest 패킷에 hop-count를 도입함으로써 gradient가 과다하게 설정되는 것을 제한함으로써 에너지 사용 효율을 높일 수 있는 개선된 Directed Diffusion 알고리즘을 제시한다. 또한 시뮬레이션을 통해 제안된 알고리즘의 유용성을 확인하고자 한다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.96.3-96
• /
• 2001

In this paper the self-organized and fuzzy inference used stochastic gradient ascent method is proposed. Fuzzy rule and fuzzy set increase as occasion demands autonomously according to the observation information. And two rules(or two fuzzy sets)becoming to be similar each other as progress of learning are unified. This unification causes the reduction of a number of parameters and learning time. Using fuzzy inference and making a rule with an appropriate state division, our proposed method makes it possible to construct a robust reinforcement learning system.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1995년도 Proceedings of the Korea Automation Control Conference, 10th (KACC); Seoul, Korea; 23-25 Oct. 1995
• /
• pp.183-186
• /
• 1995

A method is presented for optimization of Universal Learning Networks (ULN), where, together with gradient method, Simulated Annealing (SA) is employed to elude local minima. The effectiveness of the method is shown by its application to control of a crane system.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1986년도 한국자동제어학술회의논문집; 한국과학기술대학, 충남; 17-18 Oct. 1986
• /
• pp.468-470
• /
• 1986

An optimal control in heat-up operation was formulated for minimizing the quadratic performance criterion which is a function of temperature, temperature gradient in the wall and fuel flow rate. For optimal control law computations mathematical model was simplified with assumptions and then linearized by use of orthogonal collocation in radial direction. Effects of weighting function assigned to temperature and temperature gradient and final time were compared with industrial data.

• Journal of the Optical Society of Korea
• /
• 제20권1호
• /
• pp.118-124
• /
• 2016

The shape and location of the cutoff shield in a projection-type headlight system were optimized by a ray-tracing technique. A shield based on a Petsval surface showed better cutoff characteristics than a flat or cylindrical shield, such as a sharp intensity gradient and less color separation at the cutoff line. Adjustment of the shield’s location between the reflector and the aspheric lens further improved its cutoff characteristics.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.373-373
• /
• 2000

In this paper, we propose a fuzzy modeling algorithm which divides the input space more efficiently than convention methods by taking into consideration correlations between components of sample data. The proposed fuzzy modeling algorithm consists of two steps: coarse tuning, which determines consequent parameters approximately using FCRM clustering method, and fine tuning, which adjusts the premise and consequent parameters more precisely by gradient descent algorithm. To evaluate the performance of the proposed fuzzy mode, we use the numerical data of nonlinear function.

• 대한조선학회논문집
• /
• 제56권1호
• /
• pp.58-65
• /
• 2019

The stability, reliability and efficiency of a smart ship are important issues as the interest in an autonomous ship has recently been high. An automatic collision avoidance system is an essential function of an autonomous ship. This system detects the possibility of collision and automatically takes avoidance actions in consideration of economy and safety. In order to construct an automatic collision avoidance system using reinforcement learning, in this work, the sequential decision problem of ship collision is mathematically formulated through a Markov Decision Process (MDP). A reinforcement learning environment is constructed based on the ship maneuvering equations, and then the three key components (state, action, and reward) of MDP are defined. The state uses parameters of the relationship between own-ship and target-ship, the action is the vertical distance away from the target course, and the reward is defined as a function considering safety and economics. In order to solve the sequential decision problem, the Deep Deterministic Policy Gradient (DDPG) algorithm which can express continuous action space and search an optimal action policy is utilized. The collision avoidance system is then tested assuming the $90^{\circ}$intersection encounter situation and yields a satisfactory result.

• 전기의세계
• /
• 제24권5호
• /
• pp.103-106
• /
• 1975

This Paper deals with an applicatoin of Luenberger Observer to the Linear Stochastic Systems. The basic technique is the use of a matrix version of the Maximum Principle of Pontryagin coupled with the use of gradient matrices to derive the gain matix for minimum error covariance. The optimal observer which is derived turns out to be identical to the well-known Kalman-Bucy Filter.

• IEIE Transactions on Smart Processing and Computing
• /
• 제3권5호
• /
• pp.259-266
• /
• 2014

In this paper, we propose a novel technique for noise robust automatic speech recognition (ASR). The development of ASR techniques has made it possible to recognize isolated words with a near perfect word recognition rate. However, in a highly noisy environment, a distinct mismatch between the trained speech and the test data results in a significantly degraded word recognition rate (WRA). Unlike conventional ASR systems employing Mel-frequency cepstral coefficients (MFCCs) and a hidden Markov model (HMM), this study employ histogram of oriented gradient (HOG) features and a Support Vector Machine (SVM) to ASR tasks to overcome this problem. Our proposed ASR system is less vulnerable to external interference noise, and achieves a higher WRA compared to a conventional ASR system equipped with MFCCs and an HMM. The performance of our proposed ASR system was evaluated using a phonetically balanced word (PBW) set mixed with artificially added noise.