• Journal of the Korean Society of Safety
• /
• v.38 no.1
• /
• pp.70-77
• /
• 2023

Gas has replaced coal or petroleum as primary fuel because of its convenience. However, gas has risk of fire, explosion, or poisoning. To reduce gas-related accidents, many strategic projects have been being carried based on 'Gas Safety Management Basic Plans' on a domestic scale. In spite of those projects, the gas-related accident rate did not decrease over past decades. Thus, this study was conducted to analyze the effectiveness of ongoing projects, and to find out ways to make improvements. Conventional statistical analyses on accident data published by gas-related institutions were not useful to determine meaningful attributes to predict future. Whereas, accident case analyses adopted in the present study discovered differences in the type of people and their unsafe acts for each gas type. Meanwhile, the overall average priority of projects was not high in the aspect of System Safety Precedence. If the current trend is maintained, with sigmoid functions, it can be estimated that mean annual accident rate will decrease by only 2.0% in the next two decades. To improve the current trend, the present study made conclusions as followings: (1) safety projects should be designed with careful consideration of accident traits including gas type, unsafe acts, and persons involved and (2) alternative strategies should include system considerations such as minimum hazard design and safety devices prior to mere education or training. To summarize briefly, the present state related with gas accidents highlights the necessity of a system-based multidisciplinary approach.

• The Korean Journal of Financial Management
• /
• v.19 no.2
• /
• pp.211-231
• /
• 2002

본 연구의 목적은 VECM(Vector Error Correction Model)과 인공지능모형(Artificial Neural Networks)을 이용하여 우리나라 증권시장과 거시경제 변수들과의 장기적 관계에 대한 설명력을 비교해보고자 함에 있다. VECM이 APT(Arbitrage Pricing Theory)에 기초를 둔 선형동학모형이라고 한다면, 인공지능모형은 비모수적 비선형모형이라는 점에서, 두 방법론의 분석결과를 직접 비판하는 것은 의미있는 연구라고 할 수 있다. 인공지능모형을 주로 활용하는 선행연구들에 의하면, 증권시장은 시장의 특이패턴들로 인해 계량경제학적 접근인 선형 모형보다는 인공지능모형을 통해 증권시장의 움직임을 설명하고 예측하는 것이 더 바람직할 수도 있다는 것이다. 따라서, 본 연구에서는 VECM분석에서 자료의 안정성을 검증하고, 공적분 백터를 발견한 이후, 장기적 균형관계의 실증적 분석을 하였다. 그리고, 인공지능모형에서는 delta rule과 Sigmoid 함수를 이용한 GRNN(General Regression Neural Net)과 Back-Propagation등의 방법들을 활용하였다. 이러한 분석결과, Back-Propagation 모형이 다른 모든 모형들보다도 더 우수한 설명력을 보여주고 있었다. 이러한 결과들은 인공지능모형이 동태적인 선형 모형보다도 더 우수한 설명력을 제공할 수 있는 가능성을 보여주고 있었다.

• Journal of Korean Society for Geospatial Information Science
• /
• v.3 no.2 s.6
• /
• pp.91-100
• /
• 1995

The aim of this study is to classify mixed information in a pixel of a remote sensing image data (in the case of SPOT HRV's band $1{\sim}3,\;20m{\times}20m$). First, the loss of information and the uncertainty of mixed pixel are examined. To solve the problems, methods by fuzzy sigmoid function and back-propagation neural network are suggested. Then. the study simulates and comparatively analyzes the two methods.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.03a
• /
• pp.53-56
• /
• 1998

본 논문에서의 공학적인 체계성을 갖고 초기 연결 가중치 및 임계치를 결정해 주면서, 학습까지 가능한 신경망을 제안한다. 기존의 오류 역전파 신경망을 적용할 때 경험에 의하여 은닉층 노드수를 결정하거나 임의의 실수 값으로 초기 연결 가중치 및 임계값을 주었을 때 자주 발생하는 학습 마비 현상을 피할 수 있고, Bose가 제안된 Voronoi 공간 분류에 의한 신경망 구성에서 학습이 불가능하다는 제안적인 단점을 보안하였다. 초기 가중치는 Voronoi 공간 분류가 이루어져 있다고 할 때 Bose가 제안한 초기 가중치 결정법을 개선하여 사용하고, Bose의 경우 신경망 노드가 Step function을 이용하여 정보를 전달하였으나 본 연구에서는 학습이 가능한 함수인 Sigmoid function을 이용하였다. 제안된 새로운 신경망의 성능 및 효율성을 비교하기 위하여 선형분리가 불가능한 XOR문제를 실험한 결과, 기존의 학습 가능한 EBP에서 허용오차 0.05 수준일 때 80%정도 학습마비 현상이 발생하였던 심각한 문제점을 보완할 수 있었고, 또한 학습 속도면에서 8~9배 정도 빠른 성능을 나타내었다.

• The Journal of the Acoustical Society of Korea
• /
• v.25 no.8
• /
• pp.383-388
• /
• 2006

This Paper presents a novel approach to single channel microphone speech enhancement in noisy environments. Widely used noise reduction techniques based on the spectral subtraction are generally expressed as a spectral gam depending on the signal-to-noise ratio (SNR). The well-known decision-directed(DD) estimator of Ephraim and Malah efficiently reduces musical noise under the background noise conditions, but generates the delay of the a prioiri SNR because the DD weights the speech spectrum component of the Previous frame in the speech signal. Therefore, the noise suppression gain which is affected by the delay of the a priori SNR, which is estimated by the DD matches the previous frame rather than the current one, so after noise suppression. this degrades the noise reduction performance during speech transient periods. We propose a computationally simple but effective speech enhancement technique based on the sigmoid type function for the weight Parameter of the DD. The proposed approach solves the delay problem about the main parameter, the a priori SNR of the DD while maintaining the benefits of the DD. Performances of the proposed enhancement algorithm are evaluated by ITU-T p.862 Perceptual Evaluation of Speech duality (PESQ). the Mean Opinion Score (MOS) and the speech spectrogram under various noise environments and yields better results compared with the fixed weight parameter of the DD.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.1
• /
• pp.87-91
• /
• 2005

The cascade-correlation (CC) learning algorithm of Fahlman and Lebiere is one of the most influential constructive algorithm in a neural network. Cascading the hidden neurons results in a network that can represent very strong nonlinearities. Although this power is in principle useful, it can be a disadvantage if such strong nonlinearity is not required to solve the problem. 3 models are presented and compared empirically. All of them are based on valiants of the cascade architecture and output neurons weights training of the CC algorithm. Empirical results indicate the followings： (1) In the pattern classification, the model that train only new hidden neuron to output layer connection weights shows the best predictive ability; (2) In the function approximation, the model that removed input-output connection and used sigmoid-linear activation function is better predictability than CasCor algorithm.

• Journal of the Korea Concrete Institute
• /
• v.27 no.4
• /
• pp.331-341
• /
• 2015

The main purpose of this study is reducing the cost and effort for characterization of tensile strength of fiber reinforced concrete, in order to use in structural design. For this purpose, in this study, test for fiber reinforced concrete was carried out. Because fiber reinforced concrete is consisted of diverse material, it is hard to define the correlation between mix proportions and strength. Therefore, compressive strength test and tensile strength test were carried out for the range of smaller than 100 MPa of compressive strength and 0.25~1% of steel fiber volume fraction. as a results of test, two types of tensile strength were highly affected by compressive strength of concrete. However, increase rate of tensile strength was decreased with increase of compressive strength. Increase rate of tensile strength was decreased with increase of fiber volume fraction. Database was constructed using previous research data. Because estimation equations for tensile strength of fiber reinforced concrete should be multiple variable function, linear regression is hard to apply. Therefore, in this study, we decided to use the ANN(Artificial Neural Network). ANN was constructed using multiple layer perceptron architecture. Sigmoid function was used as transfer function and back propagation training method was used. As a results of prediction using artificial neural network, predicted values of test data and previous research which was randomly selected were well agreed with each other. And the main effective parameters are water-cement ratio and fiber volume fraction.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.26 no.5
• /
• pp.437-444
• /
• 2020

This study was focused on the stabilization of surge motions of a moored vessel under irregular head seas. A two-point moored vessel shows strong non-linearity even in regular sea, owing to its inherent non-linear restoring force. A long-crested irregular wave is subjected to the vessel system, resulting in more complex nonlinear behavior of the displacement and velocities than in the case of regular waves. Sliding mode control (SMC) is implemented in the moored vessel to control both surge displacement and surge velocity. The SMC can provide a closed-loop system with performance and robustness against parameter uncertainties and disturbances; however, chattering is the main drawback for implementing SMC. The goal of minimizing the chattering and state convergence with accuracy is achieved using a quasi-sliding mode that approximates the discontinuous function via a continuous sigmoid function. Numerical simulations were conducted to validate the effectiveness of the proposed control algorithm.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.246-246
• /
• 2021

본 연구는 강우 발생시 유량을 추정하는 것에 목적이 있다. 이를 위해 본 연구는 선행연구의 모형 개발방법론에서 벗어나 딥러닝 알고리즘 중 하나인 합성곱 신경망 (convolution neural network)과 수문학적 이미지 (hydrological image)를 이용하여 강우 발생시 유량을 추정하였다. 합성곱 신경망은 일반적으로 분류 문제 (classification)을 해결하기 위한 목적으로 개발되었기 때문에 불특정 연속변수인 유량을 모의하기에는 적합하지 않다. 이를 위해 본 연구에서는 합성곱 신경망의 완전 연결층 (Fully connected layer)를 개선하여 연속변수를 모의할 수 있도록 개선하였다. 대부분 합성곱 신경망은 RGB (red, green, blue) 사진 (photograph)을 이용하여 해당 사진이 나타내는 것을 예측하는 목적으로 사용하지만, 본 연구의 경우 일반 RGB 사진을 이용하여 유출량을 예측하는 것은 경험적 모형의 전제(독립변수와 종속변수의 관계)를 무너뜨리는 결과를 초래할 수 있다. 이를 위해 본 연구에서는 임의의 유역에 대해 2차원 공간에서 무차원의 수문학적 속성을 갖는 grid의 집합으로 정의되는 수문학적 이미지는 입력자료로 활용했다. 합성곱 신경망의 구조는 Convolution Layer와 Pulling Layer가 5회 반복하는 구조로 설정하고, 이후 Flatten Layer, 2개의 Dense Layer, 1개의 Batch Normalization Layer를 배열하고, 다시 1개의 Dense Layer가 이어지는 구조로 설계하였다. 마지막 Dense Layer의 활성화 함수는 분류모형에 이용되는 softmax 또는 sigmoid 함수를 대신하여 회귀모형에서 자주 사용되는 Linear 함수로 설정하였다. 이와 함께 각 층의 활성화 함수는 정규화 선형함수 (ReLu)를 이용하였으며, 모형의 학습 평가 및 검정을 판단하기 위해 MSE 및 MAE를 사용했다. 또한, 모형평가는 NSE와 RMSE를 이용하였다. 그 결과, 모형의 학습 평가에 대한 MSE는 11.629.8 m3/s에서 118.6 m3/s로, MAE는 25.4 m3/s에서 4.7 m3/s로 감소하였으며, 모형의 검정에 대한 MSE는 1,997.9 m3/s에서 527.9 m3/s로, MAE는 21.5 m3/s에서 9.4 m3/s로 감소한 것으로 나타났다. 또한, 모형평가를 위한 NSE는 0.7, RMSE는 27.0 m3/s로 나타나, 본 연구의 모형은 양호(moderate)한 것으로 판단하였다. 이에, 본 연구를 통해 제시된 방법론에 기반을 두어 CNN 모형 구조의 확장과 수문학적 이미지의 개선 또는 새로운 이미지 개발 등을 추진할 경우 모형의 예측 성능이 향상될 수 있는 여지가 있으며, 원격탐사 분야나, 위성 영상을 이용한 전 지구적 또는 광역 단위의 실시간 유량 모의 분야 등으로의 응용이 가능할 것으로 기대된다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.3 no.2
• /
• pp.313-319
• /
• 1999

We devise the 3 models of Multilayered Recurrent Prediction Neural Network(MLRPNN), which are obtained by modifying the Multilayered Perceptron(MLP) with 4 layers. We experimentally study the speech recognition performance of 3 models by a comparative method, according to the variation of the prediction order, the number of neurons in two hidden layers, initial values of connecting weights and transfer function, respectively. By the experiment, the recognition performance of each MLRPNN is better than that of MLP. At the model that returns the output of the upper hidden layer to the lower hidden layer, the recognition performance shows the best value. All MLRPNNs, which have 10 or 15 neurons in the upper and lower hidden layer and is predicted by 3rd or 4th order, show the improved speech recognition rate. On learning, these MLRPNNs have a better recognition rate when we set the initial weights between -0.5 and 0.5, and use the unipolar sigmoid transfer function in the lower hidden layer.