• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2005.04a
• /
• pp.161-165
• /
• 2005

In order to produce an optimal traffic cycle. We must first check how many waiting cars are at the lower intersection, because waiting queue is bigger than the length of upper traffic intersection. Start up delay time and vehicle waiting time occurs. To reduce vehicle waiting time, in this paper, we present an optimal green time algorithm using fuzzy neural network. Through computer simulation has been proven to be improved average vehicle speed than fixed traffic signal light which do not consider different intersection conditions.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.1
• /
• pp.11-22
• /
• 1994

For the conventional systme based on word, it is very difficult to enlarge the number of vocabulary. To cope with this problem, we must use more fundamental units of speech. For example, syllables and phonemes are such units, Korean speech consists of initial consonants, middle vowels and final consonants and has characteristic that we can obtain syllables from speech easily. In this paper, we show a speech recognition system with the advantage of the syllable characteristics peculiar to the Korean speech. The algorithm of recognition system is the Time Delay Neural Network. To recognize many recognition units, system consists of initial consonants, middle vowels, and final consonants recognition neural network. At first, our system recognizes initial consonants, middle vowels and final consonants. Then using this results, system recognizes isolated words. Through experiments, we got 85.12% recognition rate for 2735 data of initial consonants, 86.95% recognition rate for 3110 data of middle vowels, and 90.58% recognition rate for 1615 data of final consonants. And we got 71.2% recognition rate for 250 data of isolated words.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2001.11a
• /
• pp.85-90
• /
• 2001

본 논문에서는 한국어 숫자음 인식을 위한 시간 지연 신경망(Time delay neural network-TDNN)과 은닉 마르코프 모델(Midden Markov Model-HMM)의 결합 방법에 대해서 연구하였고 그 성능을 측정하였으며, 기존의 시스템과 비교 평가하였다. 이 알고리즘은 TDNN과 HMM의 구조적인 결합에 기반하고 있는데 TDNN의 두번째 은닉층의 출력이 HMM의 입력으로 들어가도록 구성되었다. 그러면 HMM은 TDNN의 출력으로 각 단어에 대해서 훈련과정을 거치게 된다. 이렇게 구성된 인식알고리즘은 TDNN의 뛰어난 단기간(Short-time)분류 기능과 HMM의 시간 정렬(time-warping) 능력을 동시에 갖게 된다. 위의 과정을 컴퓨터 시뮬레이션을 이용하여 구현하였으며, 한사람의 음성을 녹음하여 실험한 결과 기존의 TDNN만으로 만들어진 인식기보다는 3%, HMM만으로 구성된 인식기 보다는 5.7% 나은 성능을 얻을 수 있었다.

• The Journal of the Acoustical Society of Korea
• /
• v.13 no.2E
• /
• pp.26-31
• /
• 1994

A new feature extraction technique utilizing strange attractor and artificial neural network for speaker recognition is presented. Since many signals change their characteristics over long periods of time, simple time-domain processing techniques should e capable of providing useful information of signal features. In many cases, normal time series can be viewed as a dynamical system with a low-dimensional attractor that can be reconstructed from the time series using time delay. The reconstruction of strange attractor is described. In the technique, the raw signal will be reproduced into a geometric three dimensional attractor. Classification decision for speaker recognition is based upon the processing or sets of feature vectors that are derived from the attractor. Three different methods for feature extraction will be discussed. The methods include box-counting dimension, natural measure with regular hexahedron and plank-type box. An artificial neural network is designed for training the feature data generated by the method. The recognition rates are about 82%-96% depending on the extraction method.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.16 no.3
• /
• pp.197-207
• /
• 2016

It is very important to maintain a constant chlorine concentration in the post chlorination process, which is the final step in the water treatment process (hereafter WTP) before servicing water to citizens. Even though a flow meter between the filtration basin and clear well must be installed for the post chlorination process, it is not easy to install owing to poor installation conditions. In such a case, a raw water flow meter has been used as an alternative and has led to dosage errors due to detention time. Therefore, the inlet flow to the clear well is estimated by a time series neural network for the plant without a measurement value, a new residual chlorine meter is installed in the inlet of the clear well to decrease the control period, and the proposed modeling and controller to analyze the chlorine concentration change in the well is a neuro fuzzy algorithm and cascade method. The proposed algorithm led to post chlorination and chlorination improvements of 1.75 times and 1.96 times respectively when it was applied to an operating WTP. As a result, a hygienically safer drinking water is supplied with preemptive response for the time delay and inherent characteristics of the disinfection process.

• 제어로봇시스템학회:학술대회논문집
• /
• 1993.10b
• /
• pp.378-384
• /
• 1993

In this paper, an intelligent adaptive controller is proposed for the process with unmodelled dynamics. The intelligent adaptive controller consists of the numeric adaptive controller and the intelligent tuning part. The continuous scheme is used for the numeric adaptive controller to avoid the problems occurred in the discrete time schemes. The adaptive controller is adopted to the process with time delay. It is an implicit adaptive algorithm based on GMV using the emulator. The tuning part changes the design parameters in the control algorithm. It is a multilayer neural network trained by robustness analysis data. The proposed method can improve the robustness of the adaptive control system because the design parameters are tuned according to the operating points of the process. Through the simulation, robustnesses are shown for intelligent adaptive controller. Finally, the proposed algorithms are implemented on the electric furnace temperature control system. The effectiveness of the proposed algorithm is shown from experiments.

• Structural Engineering and Mechanics
• /
• v.85 no.3
• /
• pp.393-406
• /
• 2023

Smart structures are those structure that could adopt some behavior to prevent instability in their responses. The recognition of stability deterioration has been performed through rigid mathematical formulations in control theory and unpredicted results could not be addressed in control systems since they are able to only work under their predefined condition. On the other hand, incorporating all affecting parameters could result in high computational cost and delay time in the response of the systems. Artificial intelligence (AI) method has shown to be a promising methodology not only in the computer science by at everyday life and in engineering problems. In the present study, we exploit the capabilities of artificial intelligence method to obtain frequency response of a smart structure. In this regard, a comprehensive development of equations is presented using Hamilton' principle and first order shear deformation theory. The equations were solved by numerical methods and the results are used to train an artificial neural network (ANN). It is demonstrated that ANN modeling could provide accurate results in comparison to the numerical solutions and it take less time than numerical solution.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.4
• /
• pp.46-63
• /
• 1995

This thesis described an unlimited vocabulary connected speech recognition system using Time Delay Neural Network(TDNN). The recognition unit is the diphone unit which includes the transition section of two phonemes, and the number of diphone unit is 329. The recognition processing of korean connected speech is composed by three part; the feature extraction section of the input speech signal, the diphone recognition processing and post-processing. In the feature extraction section, the extraction of diphone interval in input speech signal is carried and then the feature vectors of 16th filter-bank coefficients are calculated for each frame in the diphone interval. The diphone recognition processing is comprised by the three stage hierachical structure and is carried using 30 Time Delay Neural Networks. particularly, the structure of TDNN is changed so as to increase the recognition rate. The post-processing section, mis-recognized diphone strings are corrected using the probability of phoneme transition and the probability o phoneme confusion and then the eojeols (Korean word or phrase) are formed by combining the recognized diphones.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.42 no.10
• /
• pp.884-892
• /
• 2014

In this paper, a meta model using neural network substituting for the simulator aerodynamic database is proposed to improve simulation fidelity near the critical flight area and real-time performance. It is shown that the accuracy of the meta model is relatively higher than the existing table lookup methods for arbitrary nonlinear database and the calculation speed is also improved for a specific F-16 maneuver simulation. The increase in the number of hidden nodes in the meta model for better accuracy of database representations causes a delay in function generation due to increased time required for computing exponential functions. In order to make up this drawback, we additionally study the fast exponential function method.

• The Journal of the Acoustical Society of Korea
• /
• v.13 no.1
• /
• pp.5-13
• /
• 1994

This paper presents a study on Neural Networks for Phoneme Recognition and performs the Phoneme Recognition using TDNN (Time Delay Neural Network). Also, this paper proposes training algorithm for speech recognition using neural nets that is a proper to large scale TDNN. Because Phoneme Recognition is indispensable for continuous speech recognition, this paper uses TDNN to get accurate recognition result of phonemes. And this paper proposes new training algorithm that can converge TDNN to an optimal state regardless of the number of phonemes to be recognized. The recognition experiment was performed with new training algorithm for TDNN that combines backpropagation and Cauchy algorithm using stochastic approach. The results of the recognition experiment for three phoneme classes for two speakers show the recognition rates of $98.1\%$. And this paper yielded that the proposed algorithm is an efficient method for higher performance recognition and more reduced convergence time than TDNN.