• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.4B
• /
• pp.683-691
• /
• 2000

In this paper, we proposed the cell multiplexer using Hopfield neural network and the bandwidth predictor using the backpropagation neural network in order to make an accurate call setup decision. The cell multiplexer controls heterogeneous traffic and the bandwidth predictor estimates minimum bandwidth which satisfies traffic's QoS and maximizes throughput in network. Also, a novel connection admission controller decides on connection setup using the predicted bandwidth from bandwidth predictor and available bandwidth in networks. And then, we proposed a fuzzy traffic policer, when traffic sources violate the contract, takes an appropriate action and aim proved traffic shaper, which controls burstness which is one of key characteristics in multimedia traffic. We simulated the proposed controller. Simulation results show that the proposed controller outperforms existing controller.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.1
• /
• pp.149-160
• /
• 1997

This paper is concerned with the problem of speaker-adaptive speech synthes is method using a mapped codebook designed by fuzzy mapping on FLVQ (Fuzzy Learning Vector Quantization). The FLVQ is used to design both input and reference speaker's codebook. This algorithm is incorporated fuzzy membership function into the LVQ(learning vector quantization) networks. Unlike the LVQ algorithm, this algorithm minimizes the network output errors which are the differences of clas s membership target and actual membership values, and results to minimize the distances between training patterns and competing neurons. Speaker Adaptation in speech synthesis is performed as follow;input speaker's codebook is mapped a reference speaker's codebook in fuzzy concepts. The Fuzzy VQ mapping replaces a codevector preserving its fuzzy membership function. The codevector correspondence histogram is obtained by accumulating the vector correspondence along the DTW optimal path. We use the Fuzzy VQ mapping to design a mapped codebook. The mapped codebook is defined as a linear combination of reference speaker's vectors using each fuzzy histogram as a weighting function with membership values. In adaptive-speech synthesis stage, input speech is fuzzy vector-quantized by the mapped codcbook, and then FCM arithmetic is used to synthesize speech adapted to input speaker. The speaker adaption experiments are carried out using speech of males in their thirties as input speaker's speech, and a female in her twenties as reference speaker's speech. Speeches used in experiments are sentences /anyoung hasim nika/ and /good morning/. As a results of experiments, we obtained a synthesized speech adapted to input speaker.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2004.05b
• /
• pp.759-764
• /
• 2004

본 연구는 Deng(1989)이 제시한 Grey 모형을 이용하여 성진강댐의 월유입량을 예측하였고 그 방법을 제시하였다. Grey 모형은 시계열모형이나 다른 모형에 비해 비교적 적은 수의 자료를 이용하고, 간단할 수식으로 구성되어 있는 장점이 있으나, 적은 수의 자료로 인해 입력자료가 가지는 증감의 경향(trend)으로 오차가 발생하기 쉽다. 그러므로 예측오차를 극복하기 위해서 Fuzzy 시스템을 결합한 Fuzzy-Grey 모형을 구성하였고 Fuzzy 시스템에 필요한 매개변수를 추정하기 위해 최적화기법인 유전자 알고리즘(GA; Genetic Algorithm)을 이용하였다. Grey 모형과 결합된 Fuzzy 시스템은 현재의 입력자료가 가지는 패턴과 가장 유사한 패턴의 과거자료를 이용하여 현재의 입력자료의 예측오차를 추론해내는 기능을 가진다. 오차를 추론하기 위해서 과거 월유입량 자료중 현재 입력 자료와 유사한 패턴을 Grey 상관도를 이용하여 검색하고, 보다 높은 유사성을 가지는 패턴을 선별하고자 노름(norm)을 사용하였고, 유전자 알고리즘의 탐색공간을 제한하였다. 이렇게 구성한 Fuzzy-Grey 모형을 이용하여 전국적인 가뭄년도였던 1992년, 1988년, 2001년에 대해 섬진강댐의 월유입량을 예측하였다. 오차는 1982년, 2001년, 1988년 순으로 비슷한 크기의 오차가 발생하였는데 결과를 분석하여 보면, 급격한 월유입량의 변화가 있었던 경우에 오차가 크게 발생하였으나 가뭄년도에 대해 월유입량의 불확실성이 큼에도 불구하고 비교적 월유입량의 추세를 잘 예측한 것으로 판단된다. 본 연구에서 적용한 Fuzzy-Grey 모형은 적은 수의 자료를 이용하여 예측하고 예측결과를 다시 입력자료로 사용하는 업데이트 방식을 사용하기 때문에 예측결과의 오차가 완전하게 보정되지 않으면 다음 결과에 역시 오차를 주게 되어 오차보정이 상당히 중요하다는 것을 알 수 있었다. 오차를 보다 효과적으로 보정하기 위해서는 퍼지제어에 사용되는 퍼지규칙의 수를 늘리고, 유입량에 직접적인 영향을 주는 강우량과 연계한 2변수의 Fuzzy-Grey 모형을 이용한다면 보다 정확한 유입량 예측이 가능할 것으로 사료된다.

• Journal of Korea Water Resources Association
• /
• v.53 no.6
• /
• pp.395-408
• /
• 2020

This paper aims to develop and apply three different machine learning approaches (i.e., artificial neural networks (ANN), adaptive neuro-fuzzy inference systems (ANFIS), and wavelet-based neural networks (WNN)) combined with an evolutionary optimization algorithm and the k-fold cross validation for multi-step (days) streamflow forecasting at the catchment located in Algeria, North Africa. The ANN and ANFIS models yielded similar performances, based on four different statistical indices (i.e., root mean squared error (RMSE), Nash-Sutcliffe efficiency (NSE), correlation coefficient (R), and peak flow criteria (PFC)) for training and testing phases. The values of RMSE and PFC for the WNN model (e.g., RMSE = 8.590 ㎥/sec, PFC = 0.252 for (t+1) day, testing phase) were lower than those of ANN (e.g., RMSE = 19.120 ㎥/sec, PFC = 0.446 for (t+1) day, testing phase) and ANFIS (e.g., RMSE = 18.520 ㎥/sec, PFC = 0.444 for (t+1) day, testing phase) models, while the values of NSE and R for WNN model were higher than those of ANNs and ANFIS models. Therefore, the new approach can be a robust tool for multi-step (days) streamflow forecasting in the Seybous River, Algeria.

• Journal of the Korea Society of Computer and Information
• /
• v.5 no.2
• /
• pp.90-97
• /
• 2000

This paper describes an speaker-adaptive speech recognition system which make a reliable recognition of speech signal for new speakers. In the Proposed method, an speech spectrum of new speaker is adapted to the reference speech spectrum by using Parameters of a 1st linear transformation network at the front of phoneme classification neural network. And the recognition system is based on semicontinuous HMM(hidden markov model) which use the multilayer perceptron as a fuzzy vector quantizer. The experiments on the isolated word recognition are performed to show the recognition rate of the recognition system. In the case of speaker adaptation recognition, the recognition rate show significant improvement for the unadapted recognition system.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.2
• /
• pp.165-172
• /
• 2010

In clinical data minig, choosing the optimal subset of features is such important, not only to reduce the computational complexity but also to improve the usefulness of the model constructed from the given data. Moreover the threshold values (i.e., cut-off points) of selected features are used in a clinical decision criteria of experts for differential diagnosis of diseases. In this paper, we propose a fuzzy discretization approach, which is evaluated by measuring the degree of separation of redundant attribute values in overlapping region, based on spatial distribution of data with continuous attributes. The weighted average of the redundant attribute values is then used to determine the threshold value for each feature and rough set theory is utilized to select a subset of relevant features from the overall features. To verify the validity of the proposed method, we compared experimental results, which applied to classification problem using 668 patients with a chief complaint of dyspnea, based on three discretization methods (i.e., equal-width, equal-frequency, and entropy-based) and proposed discretization method. From the experimental results, we confirm that the discretization methods with fuzzy partition give better results in two evaluation measures, average classification accuracy and G-mean, than those with hard partition.