• Proceedings of the Korea Multimedia Society Conference
• /
• 2001.11a
• /
• pp.662-665
• /
• 2001

기존의 규칙기반 침입탐지 시스템은 사후처리시 규칙 추가로 인하여 새로운 변종의 공격을 탐지하지 못한다. 본 논문에서는 규칙기반 시스템의 한계점을 극복하기 위하여, 시간지연 신경망(Time Delay Neural Network; 이하 TDNN) 침입탐지 시스템을 제안한다. 네트워크강의 패킷은 바이트 단위를 하나의 픽셀로 하는 0에서 255사이 값으로 이루어진 그레이 이미지로 볼 수 있다. 이러한 연속된 패킷이미지를 시간지연 신경망의 학습패턴으로 사용한다. 정상적인 흐름과 비정상적인 흐름에 대한 패킷 이미지를 학습하여 두 가지 클래스에 대한 신경망 분류기를 구현한다. 개발하는 침입탐지 시스템은 알려진 다양한 침입유형뿐만 아니라, 새로운 변종에 대해서도 분류기의 유연한 반응을 통하여 효과적으로 탐지할 수 있다.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.1
• /
• pp.171-179
• /
• 1995

In many continuous speech recognition systems, phoneme is used as a basic recognition unit However, the coarticulation generated among neighboring phonemes makes difficult to recognize phonemes consistently. This paper proposes allophone as an alternative recognition unit. We have classified each phoneme into three different allophone groups by the location of phoneme within a syllable. For a recognition algorithm, time-delay neural network(TDNN) has been designed. To recognize all Korean allophones, TDNNs are constructed in modular fashion according to acoustic-phonetic features (e.g. voiced/unvoiced, the location of phoneme within a word). Each TDNN is trained independently, and then they are integrated hierarchically into a whole speech recognition system. In this study, we have experimented Korean plosives with phoneme-based recognition system and allophone-based recognition system. Experimental results show that allophone-based recognition is much less affected by the coarticulation.

• Phonetics and Speech Sciences
• /
• v.9 no.2
• /
• pp.85-94
• /
• 2017

Conventional speaker verification systems using time delay neural network, identity vector and probabilistic linear discriminant analysis (TDNN-Ivector-PLDA) are known to be very effective for verifying long-duration speech utterances. However, when test utterances are of short duration, duration mismatch between enrollment and test utterances significantly degrades the performance of TDNN-Ivector-PLDA systems. To compensate for the I-vector mismatch between long and short utterances, this paper proposes to use probabilistic linear discriminant analysis (PLDA) model adaptation with augmented data. A PLDA model is trained on vast amount of speech data, most of which have long duration. Then, the PLDA model is adapted with the I-vectors obtained from short-utterance data which are augmented by using vocal tract length perturbation (VTLP). In computer experiments using the NIST SRE 2008 database, the proposed method is shown to achieve significantly better performance than the conventional TDNN-Ivector-PLDA systems when there exists duration mismatch between enrollment and test utterances.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2003.05a
• /
• pp.285-288
• /
• 2003

기존의 침입탐지 시스템은 오용탐지모델이 널리 사용되고 있다. 이 모델은 낮은 오판율(False Alarm rates)을 가지고 있으나 새로운 공격에 대해 전문가시스템(Expert Systems)에 의한 규칙추가를 필요로 하고, 그 규칙과 완전히 매칭되는 시그너처만 공격으로 탐지하므로 변형된 공격을 탐지하지 못한다는 문제점을 가지고 있다. 본 논문에서는 이러한 문제점을 보완하기 위해 주성분분석(Principle Component Analysis ; 이하 PCA)과 시간지연신경망(Time Delay Neural Network ; 이하 TDNN)을 이용한 침입탐지 시스템을 제안한다. 패킷은 PCA를 이용하여 주성분을 결정하고 패킷이미지패턴으로 만든다. 이 연속된 패킷이미지패턴을 시간지연신경망의 학습패턴으로 사용한다.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.17 no.7 s.124
• /
• pp.662-667
• /
• 2007

A new neuro-control scheme for active control of structures is proposed. It utilizes lattice pattern of state vector as training data of probabilistic neural network(PNN). Therefore. it is the so-called lattice probabilistic neural network(LPNN). PNN makes control forces by using all the training patterns. Therefore, it takes much time to obtain a control force in application. This inevitably may delay the control action. However. control force of LPNN is calculated by using only the adjacent information of LPNN input. So, the response of LPNN is greatly faster than PNN. The proposed control algorithm is applied for three story building under California and El Centro earthquakes. Also, control results of the LPNN are compared with those of the conventional PNN. The structural responses have been suppressed effectively by the proposed algorithm.

• Journal of the Korean Society for Precision Engineering
• /
• v.12 no.5
• /
• pp.25-32
• /
• 1995

In highly automated milling process, in-process monitoring of the malfunction is indispensable to ensure efficient cutting operation. Among many malfunctions in milling process, chatter vibration deteriorates surface finish, tool life and productivity. In this study, the monitoring system of chatter vibration for face milling process is proposed and experimentally estimated. The monitoring system employs two types of sensor such as cutting force and acceleration in sensory detection state. The RMS value and band frequency energy of the sensor signals are extracted in time domain for the input patterns of neural network to reduce time delay in signal processing state. The resultes of experimental evaluation show that the system works well over a wide range of cutting conditions.

• Proceedings of the KIEE Conference
• /
• 1993.11a
• /
• pp.293-295
• /
• 1993

In this paper, Neural-Network Identifier that has time-delay element, error limit and small weighting factor is proposed. A proposed identifier has good performance to identify non-linear system with noise. To test the effectiveness of the algorithm presented above, the simulation for output tracking of non-linear system is implemented.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.13 no.2
• /
• pp.63-70
• /
• 1999

This paper is proposed a new method to deal with the optimized auto-tuning for the Pill controller which is used to the process-control in various fields. First of all, in this method, 1st order delay system with dead time which is modelled from the unit step response of the system is Pade-approximated, then initial values are determined by the Ziegler-Nichols method. So we can find the parameters of Pill controller so as to minimize the fuzzy criterion function which includes the maximum overshoot, damping ratio, rising time and settling time. Finally, after studying the parameters of Pill controller by Backpropagation of Neural-Network, when we give new K, L, T values to Neural-Network, the optimized parameter of Pill controller is found by Neural-Network Program.rogram.

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.5
• /
• pp.1037-1045
• /
• 1996

In this paper, the parallel model for stereo camera is employed to find the heralding angle and the distance between a leading vehicle and the following vehicle, BART(Binocular Autonomous Research Team vehicle). Two TDNNs (Time Delay Neural Network) such as S-TDNN and A-TDNN are introduced to control BART. S-TDNN controls the speed of the following vehicle while A-TDNN controls the steering angle of BATR. A human drives BART to collect data which are used for training the said neural networks. The trained networks performed the vehicle tracking function satisfactorily under the same driving conditions performed by the human driver. The neural network approach has good portability which decreases costs and saves development time for the different types of vehicles.

• Journal of Industrial Technology
• /
• v.21 no.B
• /
• pp.91-98
• /
• 2001

In this paper, center detection and motion analysis of a moving object are studied. Kohonen's self-organizing neural network models are used for the moving objects tracking and time delay neural networks are used for dynamic characteristic analysis. Instead of objects brightness, neuron projections by Kohonen Networks are used. The motion of target objects can be analyzed by using the differential neuron image between the two projections. The differential neuron image which is made by two consecutive neuron projections is used for center detection and moving objects tracking. The two differential neuron images which are made by three consecutive neuron projections are used for the moving trajectory estimation. It is possible to distinguish 8 directions of a moving trajectory with two frames and 16 directions with three frames.