• Journal of Electrical Engineering and Technology
• /
• 제12권2호
• /
• pp.911-917
• /
• 2017

There are generally three folds when developing neural network classifiers. They are as follows: 1) discriminant function; 2) lots of parameters in the design of classifier; and 3) high dimensional training data. Along with this viewpoint, we propose space search optimized polynomial neural network classifier (PNNC) with the aid of data preprocessing technique and simultaneous tuning strategy, which is a balance optimization strategy used in the design of PNNC when running space search optimization. Unlike the conventional probabilistic neural network classifier, the proposed neural network classifier adopts two type of polynomials for developing discriminant functions. The overall optimization of PNNC is realized with the aid of so-called structure optimization and parameter optimization with the use of simultaneous tuning strategy. Space search optimization algorithm is considered as a optimize vehicle to help the implement both structure and parameter optimization in the construction of PNNC. Furthermore, principal component analysis and linear discriminate analysis are selected as the data preprocessing techniques for PNNC. Experimental results show that the proposed neural network classifier obtains better performance in comparison with some other well-known classifiers in terms of accuracy classification rate.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2009년도 학술발표회 초록집
• /
• pp.125-128
• /
• 2009

The research of climate change impact in hydrometeorology often relies on climate change information. In this paper, neural networks models such as generalized regression neural networks model (GRNNM) and multilayer perceptron neural networks model (MLP-NNM) are proposed statistical downscaling of the daily precipitation. The input nodes of neural networks models consist of the atmospheric meteorology and the atmospheric pressure data for 4 grid points including $127.5^{\circ}E/37.5^{\circ}N$, $127.5^{\circ}E/35^{\circ}N$, $125^{\circ}E/37.5^{\circ}N$ and $125^{\circ}E/35^{\circ}N$, respectively. The output node of neural networks models consist of the daily precipitation data for Seoul station. For the performances of the neural networks models, they are composed of training and test performances, respectively. From this research, we evaluate the impact of GRNNM and MLP-NNM performances for the downscaling of the daily precipitation data. We should, therefore, construct the credible daily precipitation data for Seoul station using statistical downscaling method. The proposed methods can be applied to future climate prediction/projection using the various climate change scenarios such as GCMs and RCMs.

• 대한전기학회논문지:전력기술부문A
• /
• 제48권1호
• /
• pp.8-14
• /
• 1999

This paper presents the methods of short-term load forecasting Kohonen neural networks and back-propagation neural networks. First, historical load data is divided into 5 patterns for the each seasonal data using Kohonen neural networks and using these results, load forecasting neural network is used for next day hourly load forecasting. Next day hourly load of weekdays and weekend except holidays are forecasted. For load forecasting in summer, max-temperature and min-temperature data as well as historical hourly load date are used as inputs of load forecasting neural networks for a better forecasting accuracy. To show the possibility of the proposed method, it was tested with hourly load data of Korea Electric Power Corporation(1994-95).

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1997년도 한국자동제어학술회의논문집; 한국전력공사 서울연수원; 17-18 Oct. 1997
• /
• pp.708-711
• /
• 1997

This paper proposes the hybrid algorithm for the optimization of the structure and parameters of the fuzzy neural networks by genetic algorithms (GA) to improve the behaviour and the design of fuzzy neural networks. Fuzzy neural networks have a distinguishing feature in that they can possess the advantage of both neural networks and fuzzy systems. In this way, we can bring the low-level learning and computational power of neural networks into fuzzy systems and also high-level, human like IF-THEN rule thinking and reasoning of fuzzy systems into neural networks. As a result, there are many research works concerning the optimization of the structure and parameters of fuzzy neural networks. In this paper, we propose the hybrid algorithm that can optimize both the structure and parameters of fuzzy neural networks. Numerical example is provided to show the advantages of the proposed method.

• 한국농업기계학회:학술대회논문집
• /
• 한국농업기계학회 1993년도 Proceedings of International Conference for Agricultural Machinery and Process Engineering
• /
• pp.1273-1281
• /
• 1993

Estimation of daily and seasonal evaportranspiration is essential for water resource planning irrigation feasibility study, and real-time irrigation water management . This paper is to evaluate the applicability of neural networks to the estimation of evapotranspiration . A neural network was developed to forecast daily evapotranspiration of the rice crop. It is a three-layer network with input, hidden , and output layers. Back-propagation algorithm with delta learning rule was used to train the neural network. Training neural network wasconducted usign daily actural evapotranspiration of rice crop and daily climatic data such as mean temperature, sunshine hours, solar radiation, relative humidity , and pan evaporation . During the training, neural network parameters were calibrated. The trained network was applied to a set of field data not used in the training . The created response of the neural network was in good agreement with desired values. Evaluating the neural networ performance indicates that neural network may be applied to the estimation of evapotranspiration of the rice crop.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제7권8호
• /
• pp.307-324
• /
• 2018

최근 순환 신경 망(Recurrent Neural Networks)은 시간에 대한 의존성을 고려한 구조를 통해 순차 데이터(Sequential data)의 예측 문제 해결에서 각광받고 있다. 하지만 순차 데이터의 시간 스텝이 늘어남에 따라 발생하는 그라디언트 소실(Gradients vanishing)이 문제로 대두되었다. 이를 해결하기 위해 장단기 기억 모델(Long Short-Term Memory)이 제안되었지만, 많은 데이터를 저장하고 장기간 보존하는 데에 한계가 있다. 따라서 순환 신경망과 메모리 요소(Memory component)를 활용한 학습 모델인 메모리-증대 신경망(Memory-Augmented Neural Networks)에 대한 연구가 최근 활발히 진행되고 있다. 본 논문에서는 딥 러닝(Deep Learning) 분야의 화두로 떠오른 메모리-증대 신경망 주요 모델들의 구조와 특징을 열거하고, 이를 활용한 최신 기법들과 향후 연구 방향을 제시한다.

• Asian Journal of Atmospheric Environment
• /
• 제10권2호
• /
• pp.67-79
• /
• 2016

The forecasting of air pollution is an important and popular topic in environmental engineering. Due to health impacts caused by unacceptable particulate matter (PM) levels, it has become one of the greatest concerns in metropolitan cities like Karaj City in Iran. In this study, the concentration of $PM_{2.5}$ was predicted by applying a multilayer percepteron (MLP) neural network, a radial basis function (RBF) neural network and a Markov chain model. Two months of hourly data including temperature, NO, $NO_2$, $NO_x$, CO, $SO_2$ and $PM_{10}$ were used as inputs to the artificial neural networks. From 1,488 data, 1,300 of data was used to train the models and the rest of the data were applied to test the models. The results of using artificial neural networks indicated that the models performed well in predicting $PM_{2.5}$ concentrations. The application of a Markov chain described the probable occurrences of unhealthy hours. The MLP neural network with two hidden layers including 19 neurons in the first layer and 16 neurons in the second layer provided the best results. The coefficient of determination ($R^2$), Index of Agreement (IA) and Efficiency (E) between the observed and the predicted data using an MLP neural network were 0.92, 0.93 and 0.981, respectively. In the MLP neural network, the MBE was 0.0546 which indicates the adequacy of the model. In the RBF neural network, increasing the number of neurons to 1,488 caused the RMSE to decline from 7.88 to 0.00 and caused $R^2$ to reach 0.93. In the Markov chain model the absolute error was 0.014 which indicated an acceptable accuracy and precision. We concluded the probability of occurrence state duration and transition of $PM_{2.5}$ pollution is predictable using a Markov chain method.

• 한국정보통신학회논문지
• /
• 제26권1호
• /
• pp.49-57
• /
• 2022

최근 인공지능의 다양한 활용은 기계학습의 딥 인공신경망 구조를 통해 가능해졌으며 인간과 같은 능력을 보여주고 있다. 불행하게도 딥 구조의 인공신경망은 아직 정확한 해석이 이루어지고 있지 못하고 있다. 이러한 부분은 인공지능에 대한 불안감과 거부감으로 작용하고 있다. 우리는 이러한 문제 중에서 인공신경망의 능력 부분을 해결한다. 인공신경망 구조의 크기를 계산하고, 그 인공신경망이 처리할 수 있는 데이터의 크기를 계산해 본다. 계산의 방법은 수학에서 쓰이는 군의 방법을 사용하여 데이터와 인공신경망의 크기를 군의 구조와 크기를 알 수 있는 Order를 이용하여 계산한다. 이를 통하여 인공신경망의 능력을 알 수 있으며, 인공지능에 대한 불안감을 해소할 수 있다. 수치적 실험을 통하여 데이터의 크기와 딥 인공신경망을 계산하고 이를 검증한다.

• 전기학회논문지
• /
• 제60권3호
• /
• pp.639-647
• /
• 2011

In this paper, we introduce a design methodology of data-centroid Radial Basis Function neural networks with extended polynomial function. The two underlying design mechanisms of such networks involve K-means clustering method and Particle Swarm Optimization(PSO). The proposed algorithm is based on K-means clustering method for efficient processing of data and the optimization of model was carried out using PSO. In this paper, as the connection weight of RBF neural networks, we are able to use four types of polynomials such as simplified, linear, quadratic, and modified quadratic. Using K-means clustering, the center values of Gaussian function as activation function are selected. And the PSO-based RBF neural networks results in a structurally optimized structure and comes with a higher level of flexibility than the one encountered in the conventional RBF neural networks. The PSO-based design procedure being applied at each node of RBF neural networks leads to the selection of preferred parameters with specific local characteristics (such as the number of input variables, a specific set of input variables, and the distribution constant value in activation function) available within the RBF neural networks. To evaluate the performance of the proposed data-centroid RBF neural network with extended polynomial function, the model is experimented with using the nonlinear process data(2-Dimensional synthetic data and Mackey-Glass time series process data) and the Machine Learning dataset(NOx emission process data in gas turbine plant, Automobile Miles per Gallon(MPG) data, and Boston housing data). For the characteristic analysis of the given entire dataset with non-linearity as well as the efficient construction and evaluation of the dynamic network model, the partition of the given entire dataset distinguishes between two cases of Division I(training dataset and testing dataset) and Division II(training dataset, validation dataset, and testing dataset). A comparative analysis shows that the proposed RBF neural networks produces model with higher accuracy as well as more superb predictive capability than other intelligent models presented previously.

• 융합신호처리학회논문지
• /
• 제24권2호
• /
• pp.90-96
• /
• 2023

합성곱 신경망을 비롯하여 딥러닝 신경망의 학습에서 많은 양의 훈련데이터의 확보는 과적합 현상을 피하고 우수한 성능을 가지기 위해서 매우 중요하다. 하지만, 딥러닝 신경망에서의 레이블화된 훈련데이터의 확보는 실제로는 매우 제한적이다. 이를 극복하기 위해, 이미 획득한 훈련데이터를 변형, 조작 등으로 추가로 훈련데이터를 생성하는 여러 증강 방법이 제안되었다. 하지만, 이미지, 문자 등의 훈련데이터와 달리, 인간 동작 인식을 행하는 합성곱 신경망의 생체신호 훈련데이터를 추가로 생성하는 증강 방법은 연구 문헌에서 찾아보기 어렵다. 본 연구에서는 합성곱 신경망에 기반한 인간 동작 인식을 위한 생체신호 훈련데이터를 생성하는 간편하지만, 효과적인 증강 방법을 제안한다. 본 연구의 제안된 증강 방법의 유용성은 추가로 생성된 생체신호 훈련데이터로 학습하여 합성곱 신경망이 인간 동작을 높은 정확도로 인식하는 것을 보임으로써 검증하였다.