• Journal of KIISE:Software and Applications
• /
• v.26 no.11
• /
• pp.1261-1269
• /
• 1999

다층 퍼셉트론은 다양한 응용 분야에 성공적으로 적용되고 있는 대표적인 신경회로망 모델이다. 그러나 다층 퍼셉트론의 학습에서 나타나는 플라토에 기인한 느린 학습 속도와 지역 극소는 실제 응용문제에 적용함에 있어서 가장 큰 문제로 지적되어왔다. 이 문제를 해결하기 위해 여러 가지 다양한 학습알고리즘들이 개발되어 왔으나, 계산의 비효율성으로 인해 실제 문제에는 적용하기 힘든 예가 많은 등, 현재까지 만족할 만한 해결책은 제시되지 못하고 있다. 본 논문에서는 다층퍼셉트론의 베이시스 함수로 사용되는 시그모이드 함수를 보다 일반화된 형태로 정의하여 사용함으로써 학습에 있어서의 플라토를 완화하고, 지역극소에 빠지는 것을 줄이는 접근방법을 소개한다. 본 방법은 기존의 변형된 가중치 수정식을 사용한 학습 속도 향상의 방법들과는 다른 접근 방법을 택함으로써 기존의 방법들과 함께 사용하는 것이 가능하다는 특징을 갖고 있다. 제안하는 방법의 성능을 확인하기 위하여 간단한 패턴 인식 문제들에의 적용 실험 및 기존의 학습 속도 향상 방법을 함께 사용하여 시계열 예측 문제에 적용한 실험을 수행하였고, 그 결과로부터 제안안 방법의 효율성을 확인할 수 있었다. Abstract A multilayer perceptron is the most well-known neural network model which has been successfully applied to various fields of application. Its slow learning caused by plateau and local minima of gradient descent learning, however, have been pointed as the biggest problems in its practical use. To solve such a problem, a number of researches on learning algorithms have been conducted, but it can be said that none of satisfying solutions have been presented so far because the problems such as computational inefficiency have still been existed in these algorithms. In this paper, we propose a new learning approach to minimize the effect of plateau and reduce the possibility of getting trapped in local minima by generalizing the sigmoidal function which is used as the basis function of a multilayer perceptron. Adapting a new approach that differs from the conventional methods with revised updating equation, the proposed method can be used together with the existing methods to improve the learning performance. We conducted some experiments to test the proposed method on simple problems of pattern recognition and a problem of time series prediction, compared our results with the results of the existing methods, and confirmed that the proposed method is efficient enough to apply to the real problems.

• Korean Journal of Social Welfare Studies
• /
• v.49 no.4
• /
• pp.65-100
• /
• 2018

Korean Youth are facing diverse problems. For-instance Korean youth are even called '7 given-up generation' which indicates that they gave up marriage, giving birth, social relationship, housing, dream and the hope. From this point, the study concludes that the influential factors of the alcohol problems of youth should be studied based on the eco social perspectives. And it adopted data-mining methods, using SAS-Enterprise Miner for the analysis, targeting 2538 youths. Specifically, the study analyzed and chose the most predictable model using decision tree analysis, artificial neural network and logistic analysis. As the result, the study found that gender, age, smoking, spouse, family-number, jobsearching and economic participation are statistically significant determinants of alcohol problems of youth. Precisely, those who are male, younger, have the spouse, have less family number, searching jobs, have more income and have the job were more prone to have the alcohol problems. Based on the result, this study proposed the addiction problems targeting youth and etc. and expect to have the contribution on implementing procedures for the alcohol problems.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2015.05a
• /
• pp.519-519
• /
• 2015

2007년 발간된 IPCC의 4차 평가보고서에서 자연재해, 환경, 해양, 농업, 생태계, 보건 등 다양한 부분에 미치는 기후변화의 영향에 대한 과학적 근거들이 제시되면서 기후변화는 현세기 범지구적인 화두로 대두되고 있다. 또한, 기후변화에 의한 지구 온난화는 대규모의 수문순환 과정에서의 변화들과 연관되어 담수자원은 기후변화에 대단히 취약하며 미래로 갈수록 악영향을 받을 것으로 6차 기술보고서에서 제시하고 있다. 특히 우리나라는 지구온난화가 전 지구적인 평균보다 급속하게 진행될 가능성이 높기 때문에 기후변화에 대한 담수자원 취약성이 더욱 클 것으로 예상된다. 따라서 지표수에 용수의존도가 높은 우리나라의 댐 저수지를 대상으로 기후변화에 따른 수환경 변화의 정확한 분석과 취약성 평가는 필수적이다. 본 연구에서는 SRES A1B 시나리오를 적용하여 기후변화가 주암호 저수지의 수환경 변화에 미치는 영향을 분석하였다. 지역스케일의 미래 기후시나리오 생산을 위해 인공신경망(Artificial Neural Network.,ANN)기법을 적용하여 예측인자(강우, 상대습도, 최고온도, 최저온도)에 대해 강우-유출모형에 적용이 가능한 지역스케일로 통계적 상세화를 수행하였으며, 이를 유역모델에 적용하여 저수지 유입부의 유출량 및 부하량을 예측하였다. 유역 모델의 결과를 토대로 저수지 운영모델에 저수지 유입부의 유출량을 적용하여 미래 기간의 방류량을 산정하였으며, 최종적으로 저수지 모델에 유입량, 유입부하량 및 방류량을 적용하여 저수지 내 오염 및 영양물질 순환 및 분포 예측을 통해서 기후변화가 저수지 수환경에 미치는 영향을 평가하였다. 기후변화 시나리오에 따른 상세기 후전망을 위해서 기후인자의 미래분석 기간은 (I)단계 구간(2011~2040년), (II)단계 구간(2041~2070년), (III) 단계 구간(2071~2100년)의 3개 구간으로 설정하여 수행하였으며, Baseline인 1991~2010년까지의 실측값과 모의 값을 비교하여 검증하였다. 강우량의 경우 Baseline 대비 미래로 갈수록 증가하는 것으로 전망되었으며, 2011년 대비 2100년에서 연강수량 6.4% 증가한 반면, 일최대강수량이 7.0% 증가하는 것으로 나타나 미래로 갈수록 집중호우의 발생가능성이 커질 것으로 예측되었다. 유역의 수문 수질변화 전망도 강수량 증가의 영향으로 주암댐으로 유입하는 총 유량이 Baseline 대비 증가 하였으며, 유사량 및 오염부하량도 증가하는 것으로 나타났다. 저수지 수환경 변화 예측결과 유입량이 증가함에 따라서 연평균 체류시간이 감소하였으며, 기온 및 유입수온 상승의 영향으로 (I)단계 구간대비 미래로 갈수록 상층 및 심층의 수온이 상승하는 것으로 나타났다. 연중 수온성층기간 역시 증가하는 것으로 나타났으며, 남조류는 (I)단계 구간 대비 (III)단계 구간으로 갈수록 출현시기가 빨라지며 농도 역시 증가하였다. 또한 풍수년, 평수년에 비해 갈수년에 남조류의 연평균농도 상승폭과 최고농도가 크게 나타나 미래로 갈수록 댐 유입량이 적은 해에 남조류로 인한 피해 발생 가능성이 높아질 것으로 예상된다.

• Journal of the Korean Solar Energy Society
• /
• v.36 no.1
• /
• pp.63-73
• /
• 2016

How effectively a wind farm captures high market prices can greatly influence a wind farm's viability. This research identifies and creates an understanding of the effects that result in various capture prices (average revenue earned per unit of generation) that can be seen among different wind farms, in the current and future competitive SMP (System Marginal Price) market in South Korea. Through the use of a neural network to simulate changes in SMP caused by increased renewables, based on the Korea Institute of Energy Research's extensive wind resource database for South Korea, the variances in current and future capture prices are modelled and analyzed for both onshore and offshore wind power generation. Simulation results shows a spread in capture price of 5.5% for the year 2035 that depends on both a locations wind characteristics and the generations' correlation with other wind power generation. Wind characteristics include the generations' correlation with SMP price, diurnal profile shape, and capacity factor. The wind revenue cannibalization effect reduces the capture price obtained by wind power generation that is located close to a substantial amount of other wind power generation. In onshore locations wind characteristics can differ significantly/ Hence it is recommended that possible wind development sites have suitable diurnal profiles that effectively capture high SMP prices. Also, as increasing wind power capacity becomes installed in South Korea, it is recommended that wind power generation be located in regions far from the expected wind power generation 'hotspots' in the future. Hence, a suitable site along the east mountain ridges of South Korea is predicted to be extremely effective in attaining high SMP capture prices. Attention to these factors will increase the revenues obtained by wind power generation in a competitive electricity market.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.63 no.6
• /
• pp.77-88
• /
• 2021

Duck industry had a rapid growth in recent years. Nevertheless, researches to improve duck house environment are still not sufficient enough. Moisture generation of duck house litter is an important factor because it may cause severe illness and low productivity. However, the measuring process is difficult because it could be disturbed with animal excrements and other factors. Therefore, it has to be calculated according to the environmental data around the duck house litter. To cut through all these procedures, we built several machine learning regression model forecasting moisture generation of litter by measured environment data (air temperature, relative humidity, wind velocity and water contents). 5 models (Multi Linear Regression, k-Nearest Neighbors, Support Vector Regression, Random Forest and Deep Neural Network). have been selected for regression. By using R-Square, RMSE and MAE as evaluation metrics, the best accurate model was estimated according to the variables for each machine learning model. In addition, to address the small amount of data acquired through lab experiments, bootstrapping method, a technique utilized in statistics, was used. As a result, the most accurate model selected was Random Forest, with parameters of n-estimator 200 by bootstrapping the original data nine times.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.3
• /
• pp.234-240
• /
• 2021

In this paper, the mask-based speech enhancement is improved for effective speech recognition in noise environments. In the mask-based speech enhancement, enhanced spectrum is obtained by multiplying the noisy speech spectrum by the mask. The VoiceFilter (VF) model is used as the mask estimation, and the Spectrogram Inpainting (SI) technique is used to remove residual noise of enhanced spectrum. In this paper, we propose a combined loss to further improve speech enhancement. In order to effectively remove the residual noise in the speech, the positive part of the Triplet loss is used with the component loss. For the experiment TIMIT database is re-constructed using NOISEX92 noise and background music samples with various Signal to Noise Ratio (SNR) conditions. Source to Distortion Ratio (SDR), Perceptual Evaluation of Speech Quality (PESQ), and Short-Time Objective Intelligibility (STOI) are used as the metrics of performance evaluation. When the VF was trained with the mean squared error and the SI model was trained with the combined loss, SDR, PESQ, and STOI were improved by 0.5, 0.06, and 0.002 respectively compared to the system trained only with the mean squared error.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.14 no.2
• /
• pp.134-139
• /
• 2021

Currently, the autonomous vehicle market is commercializing a level 3 autonomous vehicle, but it still requires the attention of the driver. After the level 3 autonomous driving, the most notable aspect of level 4 autonomous vehicles is vehicle stability. This is because, unlike Level 3, autonomous vehicles after level 4 must perform autonomous driving, including the driver's carelessness. Therefore, in this paper, we propose the Emergency-notification and Driver-response Confirmation System(EDCS) for an autonomousvehicle safety that notifies the driver of an emergency situation and recognizes the driver's reaction in a situation where the driver is careless. The EDCS uses the emergency situation delivery module to make the emergency situation to text and transmits it to the driver by voice, and the driver response confirmation module recognizes the driver's reaction to the emergency situation and gives the driver permission Decide whether to pass. As a result of the experiment, the HMM of the emergency delivery module learned speech at 25% faster than RNN and 42.86% faster than LSTM. The Tacotron2 of the driver's response confirmation module converted text to speech about 20ms faster than deep voice and 50ms faster than deep mind. Therefore, the emergency notification and driver response confirmation system can efficiently learn the neural network model and check the driver's response in real time.

• KIPS Transactions on Computer and Communication Systems
• /
• v.10 no.7
• /
• pp.191-198
• /
• 2021

Since the size of training dataset become large and the model is getting deeper to achieve high accuracy in deep learning, the deep neural network training requires a lot of computation and it takes too much time with a single node. Therefore, distributed deep learning is proposed to reduce the training time by distributing computation across multiple nodes. In this study, we propose hybrid allreduce strategy that considers the characteristics of each layer and communication and computational overlapping technique for synchronization of distributed deep learning. Since the convolution layer has fewer parameters than the fully-connected layer as well as it is located at the upper, only short overlapping time is allowed. Thus, butterfly allreduce is used to synchronize the convolution layer. On the other hand, fully-connecter layer is synchronized using ring all-reduce. The empirical experiment results on PyTorch with our proposed scheme shows that the proposed method reduced the training time by up to 33% compared to the baseline PyTorch.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.4
• /
• pp.611-620
• /
• 2021

The maintenance industry is mainly progressing based on condition-based maintenance after corrective maintenance and preventive maintenance. In condition-based maintenance, maintenance is performed at the optimum time based on the condition of equipment. In order to find the optimal maintenance point, it is important to accurately understand the condition of the equipment, especially the remaining useful life. Thus, using simulation data (C-MAPSS), a prediction model is proposed to predict the remaining useful life of a turbofan engine. For the modeling process, a C-MAPSS dataset was preprocessed, transformed, and predicted. Data pre-processing was performed through piecewise RUL, moving average filters, and standardization. The remaining useful life was predicted using principal component analysis and the k-NN method. In order to derive the optimal performance, the number of principal components and the number of neighbor data for the k-NN method were determined through 5-fold cross validation. The validity of the prediction results was analyzed through a scoring function while considering the usefulness of prior prediction and the incompatibility of post prediction. In addition, the usefulness of the RUL prediction model was proven through comparison with the prediction performance of other neural network-based algorithms.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.2
• /
• pp.95-111
• /
• 2021

As the population decreases in an aging society, the average age of drivers increases. Accordingly, the elderly at high risk of being in an accident need autonomous-driving vehicles. In order to secure driving safety on the road, several technologies to respond to various obstacles are required in those vehicles. Among them, technology is required to recognize static obstacles, such as poor road conditions, as well as dynamic obstacles, such as vehicles, bicycles, and people, that may be encountered while driving. In this study, we propose a deep neural network algorithm capable of simultaneously detecting these two types of obstacle. For this algorithm, we used 1,418 road images and produced annotation data that marks seven categories of dynamic obstacles and labels images to indicate road damage. As a result of training, dynamic obstacles were detected with an average accuracy of 46.22%, and road surface damage was detected with a mean intersection over union of 74.71%. In addition, the average elapsed time required to process a single image is 89ms, and this algorithm is suitable for personal mobility vehicles that are slower than ordinary vehicles. In the future, it is expected that driving safety with personal mobility vehicles will be improved by utilizing technology that detects road obstacles.