• 한국공간구조학회논문집
• /
• 제23권3호
• /
• pp.87-94
• /
• 2023

Chloride is one of the most common threats to reinforced concrete (RC) durability. Alkaline environment of concrete makes a passive layer on the surface of reinforcement bars that prevents the bar from corrosion. However, when the chloride concentration amount at the reinforcement bar reaches a certain level, deterioration of the passive protection layer occurs, causing corrosion and ultimately reducing the structure's safety and durability. Therefore, understanding the chloride diffusion and its prediction are important to evaluate the safety and durability of RC structure. In this study, the chloride diffusion coefficient is predicted by machine learning techniques. Various machine learning techniques such as multiple linear regression, decision tree, random forest, support vector machine, artificial neural networks, extreme gradient boosting annd k-nearest neighbor were used and accuracy of there models were compared. In order to evaluate the accuracy, root mean square error (RMSE), mean square error (MSE), mean absolute error (MAE) and coefficient of determination (R2) were used as prediction performance indices. The k-fold cross-validation procedure was used to estimate the performance of machine learning models when making predictions on data not used during training. Grid search was applied to hyperparameter optimization. It has been shown from numerical simulation that ensemble learning methods such as random forest and extreme gradient boosting successfully predicted the chloride diffusion coefficient and artificial neural networks also provided accurate result.

• 대한원격탐사학회지
• /
• 제35권2호
• /
• pp.229-239
• /
• 2019

모든 식생 군락은 각자 층위구조를 가지고 있다. 이를 '식생층위구조'라 부른다. 요즈음은 이 층위구조가 산림의 활력도, 다양성, 그리고 환경영향을 평가하는데 중요한 식별자로 작용하기 때문에 산림조사에 있어서 식생층위구조는 필수적으로 조사되어야한다. 그런데, 식생층위구조는 일종의 내부구조이므로 일반적으로 산림조사는 현장조사를 통해 이루어지는데, 이는 전통적인 방식으로 시간과 예산이 많이 든다. 따라서 본 연구에서는 산림의 층위구조를 조사하는데 드는 시간과 예산을 줄이기 위해 넓은 지역 탐사에 효과적인 원격탐사기법 중 항공촬영 사진과 대량의 데이터 마이닝(Data Mining)이 가능한 머신러닝(Machine Learning)기법 이용한 층위구조의 분류 방법을 제시한다. 칼라 항공사진, LiDAR(Light Detection and Ranging) DSM(Digital Surface Model)과 DTM(Digital Terrain Model)을 이용하여 Support Vector Machine(SVM) 머신러닝 기법을 이용하여 층위분류 연구를 진행하였다. 현장조사 자료를 참조하여 SVM기법 분류 결과와 비교했을 때 픽셀수에 기반한 정확도는 66.22%로 확인 되었다. 층위 분류 정확도는 단층과 다층의 구분은 비교적 높게 나타났으나, 다층끼리의 분류는 어렵다는 결론이 나타났다. 이러한 연구결과는 향후 다양한 식생데이터와 영상자료를 수집한다면 식생구조에 대한 머신러닝 연구분야에 더욱 발전이 가능할 것으로 기대된다.

• 한국정보시스템학회지:정보시스템연구
• /
• 제9권1호
• /
• pp.27-44
• /
• 2000

The structure of neural networks is represented by a weighted directed graph with nodes representing units and links representing connections. Each link is assigned a numerical value representing the weight of the connection. In learning process, the values of weights are adjusted by errors. Following experiment results, the interval of adjusting weights, that is, epoch size influenced neural networks＇ performance. As epoch size is larger than a certain size, neural networks＇performance decreased drastically. And the number of hidden layer＇s node also influenced neural networks＇performance. The networks＇performance decreased as hidden layers have more nodes and then increased at some number of hidden layer＇s node. So, in implementing of neural networks the epoch size and the number of hidden layer＇s node should be decided by systematic methods, not empirical or heuristic methods.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제30권7_8호
• /
• pp.649-658
• /
• 2003

본 연구에서는 ART2 신경회로망의 성능을 개선하기 위한 계층적 구조를 제안하고, 구성된 클러스터에 대하여 적합도(fitness) 선택을 통한 빠르고 효과적인 패턴 분류 모델(HART2)을 제안한다. 본 논문에서 제안하는 신경회로망은 비지도 학습을 통하여 대략적으로 1차 클러스터를 형성하고, 이 각각의 1차 클러스터로 분류된 패턴에 대해 지도학습을 통한 2군 클러스터를 생성하여 패턴을 분류하는 계층적 신경회로망이다. 이 신경회로망을 이용한 패턴분류 과정은 먼저 입력패턴을 1차 클러스터와 비교하여 유사한 몇 개의 1차 클러스터를 적합도에 따라 선택한다. 이때, 입력패턴과 클러스터들간의 상대 측정 거리비에 기반한 적합도 함수를 도입하여 1차 클러스터에 연결된 클러스터들을 Pruning 함으로써 계층적인 네트워크에서의 속도 향상과 정확성을 추구하였다. 마지막으로 입력패턴과 선택된 1차 클러스터에 연결된 2차 클러스터와의 비교를 통해 최종적으로 패턴을 분류하게 된다. 본 논문의 효율성을 검증하기 위하여 22종의 한글 및 영어 글꼴에 대한 숫자 데이타를 다양한 형태로 변형시켜 확장된 테스트 패턴에 대하여 실험해 본 결과 제안된 신경회로망의 패턴 분류 능력의 우수함을 증명하였다

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1998년도 추계학술대회 학술발표 논문집
• /
• pp.560-567
• /
• 1998

This paper concerned about a imputed color printed material image in camera to decrease noise and distortion by processing median filtering with input image to identical condition. Also this paper proposed the way of compares a normal printed material with an abnormal printed material color tone with trained a learning of the error back-propagation to block classification by extracting five place from identical block(3${\times}$3) of color printed material R, G, B value. As a representative algorithm of multi-layer perceptron the error Back-propagation technique used to solve complex problems. However, the Error Back-propagation is algorithm which basically used a gradient descent method which can be converged to local minimum and the Back Propagation train include problems, and that may converge in a local minimum rather than get a global minimum. The network structure appropriate for a given problem. In this paper, a good result is obtained by improve initial condition and adjust th number of hidden layer to solve the problem of real time process, learning and train.

• 한국멀티미디어학회논문지
• /
• 제24권2호
• /
• pp.274-284
• /
• 2021

Customized services to a sleep induction for better sleepcare are more effective because of different satisfaction levels to users. The EOG data measured at the frontal lobe when a person blinks his eyes can be used as biometric data because it has different values for each person. The accuracy of measurement is degraded by a noise source, such as toss and turn. Therefore, it is necessary to analyze the noisy data and remove them from normal EOG by filtering. There are low-pass filtering and high-pass filtering as filtering using a frequency band. However, since filtering within a frequency band range is also required for more effective performance, we propose a machine learning model for the filtering of EOG data in this paper as the second filtering method. In addition, optimal values of parameters such as the depth of the hidden layer, the number of nodes of the hidden layer, the activation function, and the dropout were found through experiments, to improve the performance of the machine learning filtering model, and the filtering performance of 95.7% was obtained. Eventually, it is expected that it can be used for effective user identification services by using filtering model for EOG data.

• 지능정보연구
• /
• 제22권2호
• /
• pp.127-142
• /
• 2016

딥러닝은 인공신경망(neural network)이라는 인공지능분야의 모형이 발전된 형태로서, 계층구조로 이루어진 인공신경망의 내부계층(hidden layer)이 여러 단계로 이루어진 구조이다. 딥러닝에서의 주요 모형은 합성곱신경망(convolutional neural network), 순환신경망(recurrent neural network), 그리고 심층신뢰신경망(deep belief network)의 세가지라고 할 수 있다. 그 중에서 현재 흥미로운 연구가 많이 발표되어서 관심이 집중되고 있는 모형은 지도학습(supervised learning)모형인 처음 두 개의 모형이다. 따라서 본 논문에서는 지도학습모형의 가중치를 최적화하는 기본적인 방법인 오류역전파 알고리즘을 살펴본 뒤에 합성곱신경망과 순환신경망의 구조와 응용사례 등을 살펴보고자 한다. 본문에서 다루지 않은 모형인 심층신뢰신경망은 아직까지는 합성곱신경망 이나 순환신경망보다는 상대적으로 주목을 덜 받고 있다. 그러나 심층신뢰신경망은 CNN이나 RNN과는 달리 비지도학습(unsupervised learning)모형이며, 사람이나 동물은 관찰을 통해서 스스로 학습한다는 점에서 궁극적으로는 비지도학습모형이 더 많이 연구되어야 할 주제가 될 것이다.

• 환경영향평가
• /
• 제12권4호
• /
• pp.271-279
• /
• 2003

Temperature and humidity forecasting have been performed using artificial neural networks model(ANN). We composed ANN with multi-layer perceptron which is 2 input layers, 2 hidden layers and 1 output layer. Back propagation algorithm was used to train the ANN. 6 nodes and 12 nodes in the middle layers were appropriate to the temperature model for training. And 9 nodes and 6 nodes were also appropriate to the humidity model respectively. 90% of the all data was used learning set, and the extra 10% was used to model verification. In the case of temperature, average temperature before 15 minute and humidity at present constituted input layer, and temperature at present constituted out-layer and humidity model was vice versa. The sensitivity analysis revealed that previous value data contributed to forecasting target value than the other variable. Temperature was pseudo-linearly related to the previous 15 minute average value. We confirmed that ANN with multi-layer perceptron could support pollutant dispersion model by computing meterological data at real time.

• 한국도로학회논문집
• /
• 제20권2호
• /
• pp.57-65
• /
• 2018

PURPOSES : The study aims to predict the service life of national highway asphalt pavements through deep learning methods by using maintenance history data of the National Highway Pavement Management System. METHODS : For the configuration of a deep learning network, this study used Tensorflow 1.5, an open source program which has excellent usability among deep learning frameworks. For the analysis, nine variables of cumulative annual average daily traffic, cumulative equivalent single axle loads, maintenance layer, surface, base, subbase, anti-frost layer, structural number of pavement, and region were selected as input data, while service life was chosen to construct the input layer and output layers as output data. Additionally, for scenario analysis, in this study, a model was formed with four different numbers of 1, 2, 4, and 8 hidden layers and a simulation analysis was performed according to the applicability of the over fitting resolution algorithm. RESULTS : The results of the analysis have shown that regardless of the number of hidden layers, when an over fitting resolution algorithm, such as dropout, is applied, the prediction capability is improved as the coefficient of determination ($R^2$) of the test data increases. Furthermore, the result of the sensitivity analysis of the applicability of region variables demonstrates that estimating service life requires sufficient consideration of regional characteristics as $R^2$ had a maximum of between 0.73 and 0.84, when regional variables where taken into consideration. CONCLUSIONS : As a result, this study proposes that it is possible to precisely predict the service life of national highway pavement sections with the consideration of traffic, pavement thickness, and regional factors and concludes that the use of the prediction of service life is fundamental data in decision making within pavement management systems.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2017년도 춘계학술대회
• /
• pp.335-338
• /
• 2017

현재 인공지능과 딥 러닝이 사회적인 이슈로 떠오르고 있는 추세이며, 다양한 분야에 이 기술들을 응용하고 있다. 인공지능 분야의 여러 알고리즘들 중에서 각광받는 방법 중 하나는 Convolutional Neural Network이다. Convolutional Neural Network는 일반적인 Neural Network 방법에 Convolution 연산을 하여 Feature를 추출하는 Convolution Layer를 추가한 형태이다. Convolutional Neural Network를 적은 양의 데이터에서 이용하거나, Layer의 구조가 복잡하지 않은 경우에는 학습시간이 길지 않아 속도에 크게 신경 쓰지 않아도 되지만, 학습 데이터의 크기가 크고, Layer의 구조가 복잡할수록 학습 시간이 상당히 오래 걸린다. 이로 인해 GPU를 이용하여 병렬처리를 하는 방법을 많이 사용하는데, 본 논문에서는 CUDA를 이용한 Convolutional Neural Network를 구현하였으며, CPU를 이용한 방법보다 학습 속도가 빨라지고 큰 데이터를 학습 시키는데 더욱 효율적으로 진행하도록 한다.