• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 1999.05a
• /
• pp.370-374
• /
• 1999

The proposed algorithm used the Hybrid teaming rule in the input and hidden layer, and Back-Propagation teaming rule in the hidden and output layer. From the results of simulation of tracking control with one link manipulator as a plant, we verify the usefulness of the proposed control method to compare with common direct adaptive neural network control method; proposed hybrid teaming rule showed faster loaming time faster settling time than the direct adaptive neural network using Back-propagation algorithm. Usefulness of the proposed control method is that it is faster the learning time and settling time than common direct adaptive neural network control method.

• Journal of IKEEE
• /
• v.22 no.3
• /
• pp.816-821
• /
• 2018

Recently, machine learning algorithms based on artificial neural networks started to be used widely as classifiers in the field of EEG research for emotion analysis and disease diagnosis. When a machine learning model is used to classify EEG data, if training data is composed of only data having similar characteristics, classification performance may be deteriorated when applied to data of another group. In this paper, we propose a method to construct training data set by selecting several groups of data using semi-supervised learning algorithm to improve these problems. We then compared the performance of the two models by training the model with a training data set consisting of data with similar characteristics to the training data set constructed using the proposed method.

• Proceedings of the KIEE Conference
• /
• 2002.07d
• /
• pp.2407-2409
• /
• 2002

강화학습이란 에이전트가 알려지지 않은 미지의 환경에서 행위와 보답을 주고받으며, 임의의 상태에서 가장 적절한 행위를 학습하는 방법이다. 만약 강화학습 중에 에이전트가 과거 문제들을 해결하면서 학습한 환경에 대한 지식을 이용할 수 있는 능력이 있다면 새로운 문제를 빠르게 해결할 수 있다. 이런 문제를 풀기 위한 방법으로 에이전트가 과거에 학습한 여러 문제들에 대한 환경 지식(Domain Knowledge)을 Local state feature라는 기억공간에 학습한 후 행위함수론 학습할 때 지식을 활용하는 방법이 연구되었다. 그러나 기존의 연구들은 주로 2차원 공간에 대한 연구가 진행되어 왔다. 본 논문에서는 환경 지식을 이용한 강화학습 알고리즘을 3차원 공간에 대해서도 수행 할 수 있도록하는 개선된 알고리즘을 제안하였으며, 제안된 알고리즘의 유효성을 검증하기 위해 초소형 비행체의 항공운항 학습에 대해 모의실험을 수행하였다.

• Journal of The Korean Association of Information Education
• /
• v.12 no.3
• /
• pp.303-312
• /
• 2008

In correspondence to the educational demand on study of computer principles that is recently being focused, this study promotes basic understanding on data structure and algorithm at the elementary student level through the process of simple numerical expressions and proposes effective education contents and methods. For this, an unplugged type computer education material was produced to understand the method of the computers for receiving data through activities. Also, we proposed students to create animation data to learn numerical expressions and algorithm through arrangements and linked lists. To examine educational effectiveness of this study, an experiment study was conducted through the education content and method to the subject of one class in the fifth-grade of elementary school located in OO metropolitan city. As a result, the student learned that there is a difference in calculation method between computers and people; and this enabled basic understanding on algorithm and data structure and presented positive responses to algorithm and data structure. In conclusion, it is confirmed that it is possible to provide effective education for students if the principle study of algorithm is proposed to proper levels.

• Journal of IKEEE
• /
• v.23 no.4
• /
• pp.1381-1386
• /
• 2019

As traffic congestion in cities becomes more serious, intelligent traffic control is actively being researched. Reinforcement learning is the most actively used algorithm for traffic signal control, and recently Deep reinforcement learning has attracted attention of researchers. Extended versions of deep reinforcement learning have been emerged as deep reinforcement learning algorithm showed high performance in various fields. However, most of the existing traffic signal control were studied in a single intersection environment, and there is a limitation that the method at a single intersection does not consider the traffic conditions of the entire city. In this paper, we propose a cooperative traffic control at multi-intersection environment. The traffic signal control algorithm is based on a combination of extended versions of deep reinforcement learning and we considers traffic conditions of adjacent intersections. In the experiment, we compare the proposed algorithm with the existing deep reinforcement learning algorithm, and further demonstrate the high performance of our model with and without cooperative method.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.05a
• /
• pp.27-30
• /
• 2000

본 논문에서는 선형 이진 신경회로망(Linear Binary Neural Network)을 이용하여 이진 영상으로부터 골격(skeleton)을 추출하는 병렬 구조를 제안하였다. 기존의 골격 추출 알고리즘으로부터 이진함수를 추출하고 이를 MSP Term Grouping Algorithm을 이용하여 학습시켰다. 결과에서는 기존의 역전파(Back-propagation) 학습알고리즘을 사용한 신경회로망보다 더 쉽게 하드웨어로 구현할 수 있음을 보여준다.

• Journal of IKEEE
• /
• v.25 no.2
• /
• pp.273-279
• /
• 2021

In this paper, we propose an algorithm that shortens the learning time by performing individual learning using partitioning the deep learning structure. The proposed algorithm consists of four processes: network classification origin setting process, feature vector extraction process, feature noise removal process, and class classification process. First, in the process of setting the network classification starting point, the division starting point of the network structure for effective feature vector extraction is set. Second, in the feature vector extraction process, feature vectors are extracted without additional learning using the weights previously learned. Third, in the feature noise removal process, the extracted feature vector is received and the output value of each class is learned to remove noise from the data. Fourth, in the class classification process, the noise-removed feature vector is input to the multi-layer perceptron structure, and the result is output and learned. To evaluate the performance of the proposed algorithm, we experimented with the Extended Yale B face database. As a result of the experiment, in the case of the time required for one-time learning, the proposed algorithm reduced 40.7% based on the existing algorithm. In addition, the number of learning up to the target recognition rate was shortened compared with the existing algorithm. Through the experimental results, it was confirmed that the one-time learning time and the total learning time were reduced and improved over the existing algorithm.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.2
• /
• pp.164-170
• /
• 2004

This paper proposes a Distributed Autonomous Robotic System(AIS) based on Artificial Immune System(AIS) and Distributed Genetic Algorithm(DGA). The behaviors of robots in the system are divided into global behaviors and local behaviors. The global behaviors are actions to search tasks in environment. These actions are composed of two types: dispersion and aggregation. AIS decides one among above two actions, which robot should select and act on in the global. The local behaviors are actions to execute searched tasks. The robots learn the cooperative actions in these behaviors by the DGA in the local. The proposed system is more adaptive than the existing system at the viewpoint that the robots learn and adapt the changing of tasks.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.10 no.3
• /
• pp.270-279
• /
• 2000

This paper describes the on-chip learning algorithm of neural networks using the stochastic pulse arithmetic. Stochastic pulse arithmetic is the computation using the numbers represented by the probability of 1' and 0's occurrences in a random pulse stream. This stochastic arithmetic has the merits when applied to neural network ; reduction of the area of the implemented hardware and getting a global solution escaping from local minima by virtue of the stochastic characteristics. And in this study, the on-chip learning algorithm is derived from the backpropagation algorithm for effective hardware implementation. We simulate the nonlinear separation problem of the some character patterns to verify the proposed learning algorithm. We also had good results after applying this algorithm to recognize printed and handwritten numbers.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2022.06a
• /
• pp.167-168
• /
• 2022

선박을 운항함에 있어 최적항로를 결정하는 것은 항해시간과 연료 소모를 줄이는 중요한 요인 중의 하나이다. 기존에는 항로를 결정하기 위해 항해사의 전문적인 지식이 요구되지만 이러한 방법은 최적의 항로라고 판단하기 어렵다. 따라서 연료비 절감과 선박의 안전을 고려한 최적의 항로를 생성할 필요가 있다. 연료 소모량 혹은 항해시간을 최소화하기 위해서 에이스타 알고리즘, Dijkstra 알고리즘을 적용한 연구가 있다. 하지만 이러한 연구들은 최단거리만 구할 뿐 선박의 안전, 해상상태 등을 고려하지 못한다. 이를 보완하기 위해 본 연구에서는 강화학습 알고리즘을 적용하고자한다. 강화학습 알고리즘은 앞으로 누적 될 보상을 최대화 하는 행동으로 정책을 찾는 방법으로, 본 연구에서는 강화학습 알고리즘의 하나인 Q-learning을 사용하여 선박의 안전을 고려한 최적의 항로를 생성하는 기법을 제안 하고자 한다.