• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.10a
• /
• pp.289-295
• /
• 1998

본 논문은 빠른 학습과 정확한 근사 능력을 갖는 새로운 CMAC 신경망 기반 퍼지 제어기르 제안한다. 제안한 CMAC 신경망 기반 퍼지 제어기(CBFLC)는 한 학습 주기 동안 전향 및 역전파 연산시 신경망내 유닛중 극히 일부분만이 활성화되어 학습에 참가하므로 학습 시간이 매우 빠르고, 비퍼지화 연산시 소속 함수의 중심값 뿐 아니라 폭을 동시에 고려하여 정확한 근사화를 얻는다. 제안한 퍼지 제어기내 입？출력 소속 함수의 중심값 및 폭 등의 구조적 파라메터들은 역전파 알고리즘에 의해 갱신된다. 제안한 CMAC 신경망 기반 퍼지 제어기를 트럭 후진 주차문제에 적용하여 근사화 능력 및 제어 성능면에서 여러 다른 퍼지 제어기들과 비교한다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1993.06a
• /
• pp.1118-1120
• /
• 1993

Fuzzy logic places a considerable burden on an inference engine for applications such as control or approximate reasoning. Various neural network architectures have been proposed to deal with the computational task, and yet, maintain flexibility in the desired traits of the final system. Recently, we introduced a trainable network architecture whose nodes implement weighted Yager additive hybrid operators for fuzzy logic inference in an approximate reasoning setting. In this paper we examine the utility of such networks for control situations. We show that they are capable of learning control functions which are piece-wise monotonic in each of the variables. The learning ability is demonstrated through an example.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.6 no.4
• /
• pp.271-276
• /
• 2006

To implement a generalization of value functions in Adaptive Search Element (ASE)-reinforcement learning, CMAC (Cerebellar Model Articulation Controller) is integrated into ASE controller. ASE-reinforcement learning scheme is briefly studied to discuss how CMAC is integrated into ASE controller. Neighbourhood Sequential Training for CMAC is utilized to establish the look-up table and to produce discrete control outputs. In computer simulation, an ASE controller and a couple of ASE-CMAC neural network are trained to balance the inverted pendulum on a cart. The number of trials until the controllers are established and the learning performance of the controllers are evaluated to find that generalization ability of the CMAC improves the speed of the ASE-reinforcement learning enough to realize the cartpole control system.

• Journal of information and communication convergence engineering
• /
• v.2 no.1
• /
• pp.32-35
• /
• 2004

Human ability to perceive colors is a very subjective matter. The task of measuring and analyzing appropriate colors from colored images, which matches human sensitivity for perceiving colors, has been a challenge to the research community. In this paper we propose a novel approach, which involves the use of fuzzy logic and reasoning to analyze the RGB color intensities extracted from sensory inputs to understand human sensitivity for various colors. Based on this approach, an intelligent system has been built to predict the subject's personality. The results of experiments conducted with this system are discussed in the paper.

• Journal of the Korean Society for Precision Engineering
• /
• v.21 no.7
• /
• pp.7-14
• /
• 2004

In an upcoming ubiquitous era, humankind will live in a ubiquitous space, where everything is connected through communication network. In this ubiquitous space, a ubiquitous robot, which can be used by anyone for any service through any device and any network at anytime and anywhere in a u-space, is expected to be required to serve seamless and context-aware services to humankind. In this paper, we introduce the ubiquitous robot, and define three components of the ubiquitous robot. The first one is "SoBot" which can be connected through the network in anywhere with environment recognition function and communication ability with human. The second one is "EmBot" which is embedded into environments and mobile robots and has localization and certification function with sensor fusion. The last one is "Mobile Robot" which serves overall physical services. This paper also introduces KAIST ITRC-Intelligent Robot Research Center that pursues the implementation of the ubiquitous robot.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2006.11a
• /
• pp.310-313
• /
• 2006

본 논문은 스마트 무인항공기를 개발하거나 획득시에 요구되는 전투실험 수행 중 지능화 정도에 대한 평가 및 실험방향을 제시를 위한 지능화 성숙도 모델을 제안한다. 먼저 표적탐색 소요검증 전투실험 절차를 제시하고, 지능화 정도를 4단계로 나누어 단계별 요구되는 지능수준을 제시한다. 분류된 지능수준별로 기술수준, 동작수준, 상호운용성 수준 영역의 4단계 각 수준별 요구 능력을 분석, 제시하여 지능화 정도를 측정할 수 있는 지능화 성숙도 모델을 설계한다. 마지막으로 표적탐색 소요판단을 위한 전투실험시 활용 가능한 중점분야를 지능화 성숙도 모델 영역별로 식별하고, 단계별 식별된 중점분야를 실험할 수 있는 전투실험 평가요소를 제시한다.

• ETRI Journal
• /
• v.44 no.2
• /
• pp.194-207
• /
• 2022

In the last decade, substantial progress has been achieved in intelligent traffic control technologies to overcome consistent difficulties of traffic congestion and its adverse effect on smart cities. Edge computing is one such advanced progress facilitating real-time data transmission among vehicles and roadside units to mitigate congestion. An edge computing-based deep reinforcement learning system is demonstrated in this study that appropriately designs a multiobjective reward function for optimizing different objectives. The system seeks to overcome the challenge of evaluating actions with a simple numerical reward. The selection of reward functions has a significant impact on agents' ability to acquire the ideal behavior for managing multiple traffic signals in a large-scale road network. To ascertain effective reward functions, the agent is trained withusing the proximal policy optimization method in several deep neural network models, including the state-of-the-art transformer network. The system is verified using both hypothetical scenarios and real-world traffic maps. The comprehensive simulation outcomes demonstrate the potency of the suggested reward functions.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.1
• /
• pp.9-14
• /
• 2004

Rational sense is affected by emotion. If we add the factor of estimated emotion by environment information into robots, we may get more intelligent and human-friendly robots. However, various sensory information and pattern classification are prescribed for robots to learn emotion so that the networks are suitable for the necessity of robots. Neural network has superior ability to extract character of system but neural network has defect of temporal cross talk and local minimum convergence. To solve the defects, many kinds of modular neural networks have been proposed because they divide a complex problem into simple several subproblems. The modular neural network, introduced by Jacobs and Jordan, shows an excellent ability of recomposition and recombination of complex work. On the other hand, the recurrent network acquires state representations and representations of state make the recurrent neural network suitable for diverse applications such as nonlinear prediction and modeling. In this paper, we applied recurrent network for the expert network in the modular neural network structure to learn data pattern based on emotional assessment. To show the performance of the proposed network, simulation of learning the environment and behavior pattern is proceeded with the real time implementation. The given problem is very complex and has too many cases to learn. The result will show the performance and good ability of the proposed network and will be compared with the result of other method, general modular neural network.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.3
• /
• pp.735-748
• /
• 2014

The fault-tolerance routing problem is one of the most important issues in the application of the Internet of Things, and has been attracting growing research interests. In order to maintain the communication paths from source sensors to the macronodes, we present a hybrid routing scheme and model, in which alternate paths are created once the previous routing is broken. Then, we propose an improved efficient and intelligent fault-tolerance algorithm (IEIFTA) to provide the fast routing recovery and reconstruct the network topology for path failure in the Internet of Things. In the IEIFTA, mutation direction of the particle is determined by multi-swarm evolution equation, and its diversity is improved by the immune mechanism, which can improve the ability of global search and improve the converging rate of the algorithm. The simulation results indicate that the IEIFTA-based fault-tolerance algorithm outperforms the EARQ algorithm and the SPSOA algorithm due to its ability of fast routing recovery mechanism and prolonging the lifetime of the Internet of Things.

• Communications of Mathematical Education
• /
• v.21 no.2 s.30
• /
• pp.271-282
• /
• 2007

Producing tools for actively meeting social needs in a radical changing society due to the development of modern technology has been shifted from physical ability to intelligent ability. The prominence of educating creativity is perceived as a good preparation in order to deal with them. Considered that assessment which is systematic activity to collect, analyze, diagnose, and judge information of a series of instruction practices is means to impart evidence and feedback of teaching learning practices, education and assessment is placed on reciprocal relationship. Nevertheless, there has been some tendency of neglect of assessment, comparing education for upbringing creativity. In this paper model of pencil and paper problem is discussed focusing on the sub-components of creativity and problem solving as one of the variety of means to extend mathematical creativity.