• Proceedings of the KOSOMBE Conference
• /
• v.1994 no.12
• /
• pp.165-168
• /
• 1994

We proposed a new model of neural network, called Time Delay Counter-Propagation Neural network (TDCPN). This model is combined properly by the merits of Time Delay Neural Network (TDNN) structure and those of Counter - Propagation Neural network (CPN) learning rule, so that increase recognition rate but decrease total teaming time. And we use this model to simulate classification of EMG signals, and compare the recognition rate and teaming time with those of another neural network model. As a result of simulation, the proposed model is proved to be very effective.

• 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.33B no.9
• /
• pp.124-134
• /
• 1996

Korean has a large set of characters, and has a two-dimensional formation: each character is composed of graphemes in two dimensions. Whereas connections between characters are rare, connections inside a grapheme and between graphemes happen frequently and these connections generate many cursive strokes. To deal with the large character set and the cursive strokes, using the graphemes as a recognition unit is an efffective approach, because it naturally accommodates the structural characteristics of the characters. In this paper, we propose a grapheme-based on-line recognition method for cursive korean characters. Our method uses a TDNN recognition engine to segment cursive strokes into graphemes and a graph-algorithmic postprocessor based on korean grapheme composition rule and viterbi search algorithm to find the best recognition score path. We experimented the method on freely hand-written charactes and obtained a recognition rate of 94.5%.

• Proceedings of the KIEE Conference
• /
• 1994.11a
• /
• pp.405-407
• /
• 1994

In order to provide reliable power service and to prevent a potentail hazard and damage, it is important to detect high impedance fault in power distribution line. This paper presents a neural network based approach for the detection of high impedance faults. A time delay neural network has been selected and trained for the fault currents obtained from field experiments. Detection experiments have been performed with the data from four different high impedance surfaces. Experimental results indicated the feasibility of using TDNN for the detection of high impedance faults.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2000.08a
• /
• pp.273-276
• /
• 2000

자동차 번호판은 조명과 카메라에 따라 영상에서 다양한 형태로 나타나고 영상내의 잡음으로 인해 알고리즘 방식으로 자동차 번호판을 인식하기가 쉽지 않다. 이러한 문제에 적합한 해결 방법으로 본 논문에서는 학습 기반의 자동차 번호판 인식 시스템을 제안한다. 제안한 시스템은 자동차 검출 모듈, 번호판 추출 모듈, 번호판 문자인식 모듈로 구성된다. 본 논문에서는 자동차 번호판 추출을 위해서 시간-지연 신경망(Time-Delay Neural Networks : TDNN)과 번호판 인식을 위해서 일반적인 신경망보다 일반화 성능이 뛰어난 서포트 벡터 머신(Support Vector Machines : SVMs)을 시스템에 적용한다. 주차장과 톨케이트에서 여러 시간대의 움직이는 자동차 영상들을 실험한 결과, 자동차 검출율은 100%, 번호판 추출율은 97.5%, 번호판 문자 인식율은 97.2%의 성능을 내었고, 전체 시스템 성능은 94.7%이며 처리 시간은 약 1초 미만이다. 따라서 본 논문에서 제안한 시스템은 실세계에서 유용하게 적용될 수 있다.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.38 no.5
• /
• pp.671-683
• /
• 2018

The flood damage caused by heavy rains in urban watershed is increasing, and, as evidenced by many previous studies, urban flooding usually exceeds the water capacity of drainage networks. The flood on the area which considerably urbanized and densely populated cause serious social and economic damage. To solve this problem, deterministic and probabilistic studies have been conducted for the prediction flooding in urban areas. However, it is insufficient to obtain lead times and to derive the prediction results for the flood volume in a short period of time. In this study, IDNN, TDNN and NARX were compared for real-time flood prediction based on urban runoff analysis to present the optimal real-time urban flood prediction technique. As a result of the flood prediction with rainfall event of 2010 and 2011 in Gangnam area, the Nash efficiency coefficient of the input delay artificial neural network, the time delay neural network and nonlinear autoregressive network with exogenous inputs are 0.86, 0.92, 0.99 and 0.53, 0.41, 0.98 respectively. Comparing with the result of the error analysis on the predicted result, it is revealed that the use of nonlinear autoregressive network with exogenous inputs must be appropriate for the establishment of urban flood response system in the future.

• Journal of Korean Port Research
• /
• v.14 no.3
• /
• pp.321-329
• /
• 2000

Welding is essential for the manufacture of a range of engineering components which may vary from very large structures such as ships and bridges to very complex structures such as aircraft engines, or miniature components for microelectronic applications. Especially, a domestic situation of the welding automation is still depend on the arc sensing system in comparison to the vision sensing system. Specially, the gap-detecting of workpiece using conventional arc sensor is proposed in this study. As a same principle, a welding current varies with the size of a welding gap. This study introduce to the fuzzy membership filter to cancel a high frequency noise of welding current, and ART2 which has the competitive learning network classifies the signal patterns the filtered welding signal. A welding current possesses a specific pattern according to the existence or the size of a welding gap. These specific patterns result in different classification in comparison with an occasion for no welding gap. The patterns in each case of 1mm, 2mm, 3mm and no welding gap are identified by the artificial neural network.

• Journal of Korea Multimedia Society
• /
• v.6 no.5
• /
• pp.778-787
• /
• 2003

Intrusion detection systems based on rules are not efficient for mutated attacks, because they need additional rules for the variations. In this paper, we propose an intrusion detection system using the time delay neural network. Packets on the network can be considered as gray images of which pixels represent bytes of them. Using this continuous packet images, we construct a neural network classifier that discriminates between normal and abnormal packet flows. The system deals well with various mutated attacks, as well as well known attacks.

• Journal of the Institute of Convergence Signal Processing
• /
• v.13 no.4
• /
• pp.233-237
• /
• 2012

In this paper, We propose a control system which compensate a output of a main Neual Network using a RTDNN(Recurrent Time Delayed Neural Network) with a FLC(Fuzzy Logic Controller)After a learn of main neural network, it can occur a Over shoot or Under shoot from a disturbance or a load variations. In order to adjust above case, we used the fuzzy compensator to get an expected results. And the weight of main neural network can be changed with the result of learning a inverse model neural network of plant, so a expected dynamic characteristics of plant can be got. We can confirm good response characteristics of proposed neural network controller by the results of simulation.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.11
• /
• pp.1527-1535
• /
• 1995

This paper introduces an isolated word recognition system realized on a neurocomputer called E-MIND II, which is a 2-D torus wavefront array processor consisting of 256 DNP IIs. The DNP II is an all digital VLSI unit processor for the EMIND II featuring the emulation capability of more than thousands of neurons, the 40 MHz clock speed, and the on-chip learning. Built by these PEs in 2-D toroidal mesh architecture, the E- MIND II can be accelerated over 2 Gcps computation speed. In this light, the advantages of the E-MIND II in its capability of computing speed, scalability, computer interface, and learning are especially suitable for real time application such as speech recognition. We show how to map a TDNN structure on this array and how to code the learning and recognition algorithms for a user independent isolated word recognition. Through hardware simulation, we show that recognition rate of this system is about 97% for 30 command words for a robot control.