• Journal of Electrical Engineering and information Science
• /
• v.3 no.3
• /
• pp.355-365
• /
• 1998

The purposes of this study are to propose a network for the characterizing of the input data and to show how to design predictive neural net재가 expert system which doesn't need previous knowledge base. We derived this network from the radial basis function networks(RBFN), and named it as a statistical EBFN. The proposed network can replace the statistical methods for analyzing dynamic relations between target disease and other parameters in medical studies. We compared statistical RBFN with the probabilistic neural network(PNN) and fuzzy logic(FL). And we testified our method in the diabetes prediction and compared our method with the well-known multilayer perceptron(MLP) neural network one, and showed good performance of our network. At last, we developed the diabetes prediction expert system based on the proposed statistical RBFN without previous knowledge base. Not only the applicability of the characterizing of parameters related to diabetes and construction of the diabetes prediction expert system but also wide applicabilities has the proposed statistical RBFN to other similar problems.

• Journal of Ocean Engineering and Technology
• /
• v.35 no.4
• /
• pp.287-295
• /
• 2021

This paper describes a recurrent neural network (RNN) for the fault classification of a blade pitch system of a spar-type floating wind turbine. An artificial neural network (ANN) can effectively recognize multiple faults of a system and build a training model with training data for decision-making. The ANN comprises an encoder and a decoder. The encoder uses a gated recurrent unit, which is a recurrent neural network, for dimensionality reduction of the input data. The decoder uses a multilayer perceptron (MLP) for diagnosis decision-making. To create data, we use a wind turbine simulator that enables fully coupled nonlinear time-domain numerical simulations of offshore wind turbines considering six fault types including biases and fixed outputs in pitch sensors and excessive friction, slit lock, incorrect voltage, and short circuits in actuators. The input data are time-series data collected by two sensors and two control inputs under the condition that of one fault of the six types occurs. A gated recurrent unit (GRU) that is one of the RNNs classifies the suggested faults of the blade pitch system. The performance of fault classification based on the gate recurrent unit is evaluated by a test procedure, and the results indicate that the proposed scheme works effectively. The proposed ANN shows a 1.4% improvement in its performance compared to an MLP-based approach.

• Nuclear Engineering and Technology
• /
• v.50 no.7
• /
• pp.1154-1159
• /
• 2018

Precise prediction of the radiation interaction position in scintillators plays an important role in medical and industrial imaging systems. In this research, the incident position of the gamma rays was predicted precisely in a plastic rod scintillator by using attenuation technique and multilayer perceptron (MLP) neural network, for the first time. Also, this procedure was performed using nonlinear regression (NLR) method. The experimental setup is comprised of a plastic rod scintillator (BC400) coupled with two PMTs at two sides, a $^{60}Co$ gamma source and two counters that record count rates. Using two proposed techniques (ANN and NLR), the radiation interaction position was predicted in a plastic rod scintillator with a mean relative error percentage less than 4.6% and 14.6%, respectively. The mean absolute error was measured less than 2.5 and 5.5. The correlation coefficient was calculated 0.998 and 0.984, respectively. Also, the ANN technique was confirmed by leave-one-out (LOO) method with 1% error. These results presented the superiority of the ANN method in comparison with NLR and the other methods. The technique and set up used are simpler and faster than other the previous position sensitive detectors. Thus, the time, cost and shielding and electronics requirements are minimized and optimized.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.44 no.1
• /
• pp.40-48
• /
• 2007

This paper presents a novel texture segmentation method using multilayer perceptron (MLP) networks and Markov random fields in multiscale Bayesian framework. Multiscale wavelet coefficients are used as input for the neural networks. The output of the neural network is modeled as a posterior probability. Texture classification at each scale is performed by the posterior probabilities from MLP networks and MAP (maximum a posterior) classification. Then, in order to obtain the more improved segmentation result at the finest scale, our proposed method fuses the multiscale MAP classifications sequentially from coarse to fine scales. This process is done by computing the MAP classification given the classification at one scale and a priori knowledge regarding contextual information which is extracted from the adjacent coarser scale classification. In this fusion process, the MRF (Markov random field) prior distribution and Gibbs sampler are used, where the MRF model serves as the smoothness constraint and the Gibbs sampler acts as the MAP classifier. The proposed segmentation method shows better performance than texture segmentation using the HMT (Hidden Markov trees) model and HMTseg.

• Journal of Bio-Environment Control
• /
• v.28 no.2
• /
• pp.95-103
• /
• 2019

Temperature and relative humidity are important factors in crop cultivation and should be properly controlled for improving crop yield and quality. In order to control the environment accurately, we need to predict how the environment will change in the future. The objective of this study was to predict air temperature and relative humidity at a future time by using a multilayer perceptron (MLP). The data required to train MLP was collected every 10 min from Oct. 1, 2016 to Feb. 28, 2018 in an eight-span greenhouse ($1,032m^2$) cultivating mango (Mangifera indica cv. Irwin). The inputs for the MLP were greenhouse inside and outside environment data, and set-up and operating values of environment control devices. By using these data, the MLP was trained to predict the air temperature and relative humidity at a future time of 10 to 120 min. Considering typical four seasons in Korea, three-day data of the each season were compared as test data. The MLP was optimized with four hidden layers and 128 nodes for air temperature ($R^2=0.988$) and with four hidden layers and 64 nodes for relative humidity ($R^2=0.990$). Due to the characteristics of MLP, the accuracy decreased as the prediction time became longer. However, air temperature and relative humidity were properly predicted regardless of the environmental changes varied from season to season. For specific data such as spray irrigation, however, the numbers of trained data were too small, resulting in poor predictive accuracy. In this study, air temperature and relative humidity were appropriately predicted through optimization of MLP, but were limited to the experimental greenhouse. Therefore, it is necessary to collect more data from greenhouses at various places and modify the structure of neural network for generalization.

• The KIPS Transactions:PartB
• /
• v.12B no.1 s.97
• /
• pp.25-30
• /
• 2005

In this paper, we analyzed and compared the performances of modular FFMLP(feedforward multilayer perceptron) and SVUT(Support Vector Machine) for the large-set classification problems. Overall, SVM dominated modular FFMLP in the correct recognition rate and other aspects Additionally, the recognition rate of SVM degraded more slowly than neural network as the number of classes increases. The trend of the recognition rates depending on the rejection rate has been analyzed. The parameter set of SVM(kernel functions and related variables) has been identified for the large-set classification problems.

• International Journal of Computer Science & Network Security
• /
• v.22 no.10
• /
• pp.406-412
• /
• 2022

Scene classification of very high-resolution (VHR) imagery can attribute semantics to land cover in a variety of domains. Real-world application requirements have not been addressed by conventional techniques for remote sensing image classification. Recent research has demonstrated that deep convolutional neural networks (CNNs) are effective at extracting features due to their strong feature extraction capabilities. In order to improve classification performance, these approaches rely primarily on semantic information. Since the abstract and global semantic information makes it difficult for the network to correctly classify scene images with similar structures and high interclass similarity, it achieves a low classification accuracy. We propose a VHR remote sensing image classification model that uses extracts the global feature from the original VHR image using an EfficientNet-V2L CNN pre-trained to detect similar classes. The image is then classified using a multilayer perceptron (MLP). This method was evaluated using two benchmark remote sensing datasets: the 21-class UC Merced, and the 38-class PatternNet. As compared to other state-of-the-art models, the proposed model significantly improves performance.

• Steel and Composite Structures
• /
• v.50 no.1
• /
• pp.77-87
• /
• 2024

In this study, the two-dimensional crack problem was investigated by using the finite element method (FEM)-based ANSYS package program and the artificial neural network (ANN)-based multilayer perceptron (MLP) method. For this purpose, a half-infinite functionally graded (FG) layer with a crack pressed through two rigid blocks was analyzed using FEM and ANN. Mass forces and friction were neglected in the solution. To control the validity of the crack problem model exercised, the acquired results were compared with a study in the literature. In addition, FEM and ANN results were checked using Root Mean Square Error (RMSE) and coefficient of determination (R²), and a well agreement was found. Numerical solutions were made considering different geometric parameters and material properties. The stress intensity factor (SIF) was examined for these values, and the results were presented. Consequently, it is concluded that the considered non-dimensional quantities have a noteworthy influence on the SIF. Also FEM and ANN can be logical alternative methods to time-consuming analytical solutions if used correctly.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.27 no.2
• /
• pp.65-72
• /
• 1990

The potential of neural networks for the recognition of the printed Korean characters is examined. In spite of good classification capability of neural networks, it is difficult to train a neural network to recognize Korean characters. The difficulty is due to a large number of Korean characters, the similarities among the characters, and the large number of data from the character images. To reduce the input image data, DC components are extracted from each input images. These preprocessed data are used as input to the neural network. The output nodes are composed to represent the characteristics of Korean characters. A MLP (multilayer perceptron) with one hidden layer was trained with a modified BEP algorithm, This method gives good recognition rate for the standard positioned characters of more than 2,300. The result shows that neural networks are well suited for the recognition of printed Korean characters.

• Journal of KIISE:Software and Applications
• /
• v.26 no.12
• /
• pp.1383-1392
• /
• 1999

이미 학습된 다층퍼셉트론 신경망을 디지털 VLSI 기술을 사용하여 하드웨어로 구현할 경우 신경망의 가중치 및 뉴런 출력들을 양자화해야 하는 문제가 발생한다. 이러한 신경망 변수들의 양자화는 결과적으로 주어진 입력에 대한 신경망의 최종 출력에서의 왜곡을 초래한다. 본 논문에서는 먼저 이러한 양자화로 인한 신경망 출력에서의 왜곡을 통계적으로 분석하였다. 분석 결과에 의하면 입력패턴 각 성분의 제곱들의 합과 가중치의 크기들이 양자화 영향에 주로 기여하는 것으로 나타났다. 이러한 분석 결과를 이용하여 양자화를 위한 정밀도가 주어졌을 때, 양자화 영향이 최소화된 다층퍼셉트론 신경망을 설계하는 방법을 제시하였다. 그리고 제안된 방법에 의해 얻은 신경망과 오류역전파 학습방법에 의하여 얻은 신경망의 성능을 비교함으로써 제안된 방법의 효율성을 입증하였다. 실험결과는 낮은 양자화 정밀도에서도 제안된 방법이 더 좋은 성능을 보였다.Abstract When we implement a multilayer perceptron with the digital VLSI technology, we generally have to quantize the weights and the neuron outputs. These quantizations eventually cause distortion in the output of the network for a given input. In this paper first we made a statistical analysis about the effect caused by the quantization on the output of the network. The analysis revealed that the sum of the squared input components and the sizes of the weights are the major factors which contribute to the quantization effect. We present a design method for an MLP which minimizes the quantization effect when the precision of the quantization is given. In order to show the effectiveness of the proposed method, we developed a network by our method and compared it with the one developed by the regular backpropagation. We could confirm that the network developed by our method performs better even with a low precision of the quantization.