• Journal of the Korean Institute of Intelligent Systems
• /
• v.3 no.3
• /
• pp.38-54
• /
• 1993

퍼지 제어기(FLC)는 Max-Min CRI 방법을 이용하여 추론하는 시스템이다. 그러나 이 방법은 주관적인 멤버쉽 함수의 결정, 오류 발생 가중치 전략, 비합리적인 추론 규칙들의 조합이라는 세가지 문제점 때문에 원하는 추론 결과와 실제 추론 결과 사이에 상당한 오류 영역을 발생시킨다. 본 논문에서는 이를 해결하기 위해 퍼지 이론에 신경 회로망의 학습 기능이 융합되어 지능적으로 작동하는 뉴로-퍼지 시스템(INFS)을 제안한다. INFS는 이상의 문제 해결 방안이 지식 획득 단계, 적응 조절단계를 통해 작동함으로써 임의의 입력에 대해서도 추론이 가능한 시스템이다. 제안된 INFS를직류 계열 모니터에 적용한 결과 신경 회로망을 사용하지 않았을때 보다 오류 영역을 상당히 줄여주었다. 또한 학습 시간을 고려해 볼 때, INFS에서 사용하는 추론 방법(NCRI 방법)이 지금까지 다른 방법에 비해 휠씬 효율적이었다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2010.05a
• /
• pp.1439-1442
• /
• 2010

Time-lag recurrent neural networks model (Time-Lag RNNM) is used to estimate daily pan evaporation (PE) using limited climatic variables such as max temperature ($T_{max}$), min temperature ($T_{min}$), mean wind speed ($W_{mean}$) and mean relative humidity ($RH_{mean}$). And, for the performances of Time-Lag RNNM, it is composed of training and test performances, respectively. The training and test performances are carried out using daily time series data, respectively. From this research, we evaluate the impact of Time-Lag RNNM for the modeling of the nonlinear time series data. We should, thus, construct the credible data of the daily PE using Time-Lag RNNM, and can suggest the methodology for the irrigation and drainage networks system. Furthermore, this research represents that the strong nonlinear relationship such as pan evaporation modeling can be generalized using Time-Lag RNNM.

• KIISE Transactions on Computing Practices
• /
• v.22 no.11
• /
• pp.614-618
• /
• 2016

As information on the internet and the data from smart devices are growing, the amount of stream data is also increasing in the real world. The stream data, which is a potentially large data, requires online learnable models and algorithms. In this paper, we propose a novel class of models: predictive convolutional neural networks to be able to perform online learning. These models are designed to deal with longer patterns as the layers become higher due to layering convolutional operations: detection and max-pooling on the time axis. As a preliminary check of the concept, we chose two-month gathered GPS data sequence as an observation sequence. On learning them with the proposed method, we compared the original sequence and the regenerated sequence from the abstract information of the models. The result shows that the models can encode long-range patterns, and can generate a raw observation sequence within a low error.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.6
• /
• pp.374-382
• /
• 2020

The purpose of this study is to improve the learning speed of an ammunition stockpile reliability classification artificial neural network model by proposing a normalization method that reduces the number of input variables based on the characteristic of Ammunition Stockpile Reliability Program (ASRP) data without loss of classification performance. Ammunition's performance requirements are specified in the Korea Defense Specification (KDS) and Ammunition Stockpile reliability Test Procedure (ASTP). Based on the characteristic of the ASRP data, input variables can be normalized to estimate the lot percent nonconforming or failure rate. To maintain the unitary hypercube condition of the input variables, min-max normalization method is also used. Area Under the ROC Curve (AUC) of general min-max normalization and proposed 2-step normalization is over 0.95 and speed-up for marching learning based on ASRP field data is improved 1.74 ~ 1.99 times depending on the numbers of training data and of hidden layer's node.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.7
• /
• pp.199-210
• /
• 1994

Most of clustering methods usually employ a center or predefined shape of a cluster to assign the input data into the cluster. When there is no information about data set, it is impossible to predict how many clusters are to be or what shape clusters take. (the shape of clusters could not be easily represented by the center or predefined shape of clusters) Therefore, it is difficult to assign input data into a proper cluster using previous methods. In this paper, to overcome such a difficulty a cluster is to be represented as a collection of several subclusters representing boundary of the cluster. And membership functions are used to represent how much input data bllongs to subclusters. Then the position of the nearest subcluster is adaptively corrected for expansion of cluster, which the subcluster belongs to by use of a competitive learning neural network. To show the validity of the proposed method a numerical example is illustrated where FMMC(Fuzzy Min-Max Clustering) algorithm is compared with the proposed method.

• 제어로봇시스템학회:학술대회논문집
• /
• 1993.10a
• /
• pp.724-730
• /
• 1993

Most of clustering methods usually employ the center of a cluster to assign the input data into a cluster. When the shape of a cluster could not be easily represented by the center of cluster, however, it is difficult to assign input data into a proper cluster using previous methods. In this paper, to overcome such a difficulty, a cluster is to be represented as a collection of several subclusters. And membership functions are used to represent how much input data belong to subclusters. Then the position of each subcluster is adoptively corrected by use of a competitive learning neural network. To show the validity of the proposed method, a numerical example is illustrated, where FMMC(Fuzzy Min-Max Clustering) algorithm is compared with the proposed method.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.11b
• /
• pp.778-780
• /
• 2005

최근 인공지능의 기법을 도입한 게임에 관한 연구가 활발히 진행되고 있다. 특히 신경망의 역 전파 알고리즘을 적용한 게임은 구현이 용이하고 학습이 완료되면 비교적 실행이 빨라서 많은 연구가 진행되고 있지만 기본적인 학습시간이 길고 최적화에 관한 문제점이 존재하고 있다. 이러한 문제점을 개선하고자 본 논문에서는 기존의 역 전파 알고리즘과 강화학습의 Q-learning알고리즘을 모델로 게임에 적용하여 비교 분석 하였다. 실험은 단순한 min-max 알고리즘과 각각 대결하여 승수 와 승율을 중심으로 비교하였고 실험의 결과는 강화학습의 알고리즘이 역 전파 알고리즘에 비하여 비교적 우수한 결과를 제시하였다.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.40 no.4
• /
• pp.193-205
• /
• 2003

There has been so many research activities about robot soccer system in the many research fields, for example, intelligent control, communication, computer technology, sensor technology, image processing, mechatronics. Especially researchers research strategy for attacking in the field of strategy, and develop intelligent strategy. Then, soccer robots cannot defense completely and efficiently by using simple defense strategy. Therefore, intention extraction of attacker is needed for efficient defense. In this thesis, intention extractor of soccer robots is designed and developed based on FMMNN(Fuzzy Min-Max Neural networks ). First, intention for soccer robot system is defined, and intention extraction for soccer robot system is explained.. Next, FMMNN based intention extractor for soccer robot system is determined. FMMNN is one of the pattern classification method and have several advantages: on-line adaptation, short training time, soft decision. Therefore, FMMNN is suitable for soccer robot system having dynamic environment. Observer extracts attack intention of opponents by using this intention exactor, and this intention extractor is also used for analyzing strategy of opponent team. The capability of developed intention extractor is verified by simulation of 3 vs. 3 robot succor simulator. It was confirmed that the rates of intention extraction each experiment increase.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.37 no.6
• /
• pp.50-63
• /
• 2000

In this paper, a new EMG pattern classification method based on soft computing techniques is proposed to help the disabled and the elderly handle rehabilitation robotic arm systems. First, it is shown that EMG is more useful than existing input devices such as voice, a laser pointer and a keypad in view of naturality, extensibility, and applicability. Then, a new procedure is proposed to select the minimal feature set. As methods of classifying the pre-defined motions, a fuzzy pattern classification and fuzzy min-max neural networks (FMMNN) are designed using the selected features. As results, the motions are recognized with success rates of 83 percent and 90 Percent using fuzzy pattern classification and FMMNN, respectively.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.5
• /
• pp.341-346
• /
• 2013

In this paper, we propose a rule extraction method using a modified Fuzzy Min-Max (FMM) neural network. The suggested method supplements the hyperbox definition with a frequency factor of feature values in the learning data set. We have defined a relevance factor between features and pattern classes. The proposed model can solve the ambiguity problem without using the overlapping test process and the contraction process. The hyperbox membership function based on the fuzzy partitions is defined for each dimension of a pattern class. The weight values are trained by the feature range and the frequency of feature values. The excitatory features and the inhibitory features can be classified by the proposed method and they can be used for the rule generation process. From the experiments of sign language recognition, the proposed method is evaluated empirically.