• 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.

• Annual Conference of KIPS
• /
• 2020.11a
• /
• pp.788-791
• /
• 2020

낙농업에서 경제적 손실을 불러일으키고 관찰 시간과 비용이 필요한 젖소의 유방염 관리는 중요하다. 그러나 지금까지의 연구는 유방염 진단에 초점을 맞추고 있고, 예측하려는 시도는 전무하다. 유방염에 걸린 개체는 며칠 동안 우유를 생산할 수 없기 때문에 낙농가에 막대한 피해를 준다. 따라서 젖소가 유방염에 걸려 증상이 나타나기 전에 미리 파악해 조처를 할 수 있도록 하는 것이 중요하다. 이에 본 연구는 유방염 예측을 위해 생체 데이터를 포함한 다중 센싱 데이터를 사용해 유방염 예측 모델을 개발하였다. 모델에 사용된 데이터는 충청남도의 농가에 설치된 로봇 착유기로 부터 수집하였으며, 일정 기간 동안의 다중 센싱 데이터를 바탕으로 다음 날의 유방염 여부를 예측한다. 많은 양의 비선형 데이터를 효과적으로 처리하기 위해 다층 퍼셉트론을 사용해 모델을 학습하였다. 그 결과, 81.6%의 예측 정확도를 보였으며 교차 검증을 통해 정확도뿐만 아니라 재현율까지 우수함을 확인할 수 있었다.

• The Journal of the Korea Contents Association
• /
• v.4 no.3
• /
• pp.99-105
• /
• 2004

This paper proposes optimal learning rates in the gradient descent training of multilayer perceptrons, which are a separate learning rate for weights associated with each neuron and a separate one for assigning virtual hidden targets associated with each training pattern Effectiveness of the proposed error function was demonstrated for a handwritten digit recognition and an isolated-word recognition tasks and very fast learning convergence was obtained.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.2
• /
• pp.319-328
• /
• 2021

In this paper, we perform prediction of amount of electric power plant for complex of wind plant using multi-layer perceptron in order to calculate exact calculation of capacity of ESS to maximize profit through generation and to minimize generation cost of wind generation. We acquire wind speed, direction of wind and air density as variables to predict the amount of generation of wind power. Then, we merge and normalize there variables. To train model, we divide merged variables into data as train and test data with ratio of 70% versus 30%. Then we train model by using training data, and we alsouate the prediction performance of model by using test data. Finally, we present the result of prediction in amount of wind power.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.36 no.6
• /
• pp.515-523
• /
• 2018

In order to obtain consistent change detection result for multi-temporal satellite images, preprocessing must be performed. In particular, the preprocessing related to the spectral values can be performed by the radiometric normalization, and relative radiometric normalization is generally utilized. However, most relative radiometric normalization methods assume a linear relationship between the two images, and nonlinear spectral characteristics such as phenological differences are not considered. Therefore, this study proposes a relative radiometric normalization which assumes nonlinear relationships that can perform compositive normalization of radiometric and phenological characteristics. The proposed method selects the subject and reference images, and then extracts the radiometric control set samples through the no-change method. In addition, spectral indexes as well as pixel values are extracted in order to consider sufficient information, and modeling of nonlinear relationships is performed through multilayer perceptron. Finally, the proposed method is compared with the conventional relative radiometric normalization methods, which shows that the proposed method is visually and quantitatively superior.

• Journal of Korea Multimedia Society
• /
• v.13 no.3
• /
• pp.438-456
• /
• 2010

Iris recognition uses a unique iris pattern of user to identify person. In order to enhance the performance of iris recognition, it is reported that the diameter of iris region should be greater than 200 pixels in the captured iris image. So, the previous iris system used zoom lens camera, which can increase the size and cost of system. To overcome these problems, we propose a new method of enhancing the accuracy of iris recognition on low-resolution iris images which are captured without a zoom lens. This research is novel in the following two ways compared to previous works. First, this research is the first one to analyze the performance degradation of iris recognition according to the decrease of the image resolution by excluding other factors such as image blurring and the occlusion of eyelid and eyelash. Second, in order to restore a high-resolution iris image from single low-resolution one, we propose a new method based on multiple multi-layered perceptrons (MLPs) which are trained according to the edge direction of iris patterns. From that, the accuracy of iris recognition with the restored images was much enhanced. Experimental results showed that when the iris images down-sampled by 6% compared to the original image were restored into the high resolution ones by using the proposed method, the EER of iris recognition was reduced as much as 0.133% (1.485% - 1.352%) in comparison with that by using bi-linear interpolation

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.40 no.4
• /
• pp.266-274
• /
• 2003

Distance Fourier descriptors of local target boundary and feature information fusion using multiple MLPs (Multilayer perceptrons) are proposed. They are used to identify nonoccluded and partially occluded targets in natural FLIR (forward-looking infrared) images. After segmenting a target, radial Fourier descriptors as global shape features are defined from the target boundary. A target boundary is partitioned into four local boundaries to extract local shape features. In a local boundary, a distance function is defined from boundary points and a line between two extreme points. Distance Fourier descriptors as local shape features are defined by using distance function. One global feature vector and four local feature vectors are used as input data for multiple MLPs to determine final identification result of the target. In the experiments, we show that the proposed method is superior to the traditional feature sets with respect to the identification performance.

• Annual Conference of KIPS
• /
• 2002.04a
• /
• pp.565-568
• /
• 2002

본 논문에서는 에이전트간의 통신이 불가능한 다중 에이전트 환경에서 각 에이전트들이 독립적이면서 대표적인 강화학습법인 Q-학습을 전개함으로써 서로 효과적으로 협조할 수 있는 행동전략을 학습하려고 한다. 하지만 단일 에이전트 경우에 비해 보다 큰 상태-행동공간을 갖는 다중 에이전트환경에서는 강화학습을 통해 효과적으로 최적의 행동 전략에 도달하기 어렵다는 문제점이 있다. 이 문제에 대한 기존의 접근방법은 크게 모듈화 방법과 일반화 방법이 제안되었으나 모두 나름의 제한을 가지고 있다. 본 논문에서는 대표적인 다중 에이전트 학습 문제의 예로서 the Prey and Hunters Problem를 소개하고 이 문제영역을 통해 이와 같은 강화학습의 문제점을 살펴보고, 해결책으로 신경망 SOM 을 이용한 일반화 방법을 제안한다. 이 방법은 다층 퍼셉트론 신경망과 역전파 알고리즘을 이용한 기존의 일반화 방법과는 달리 군집화 기능을 제공하는 신경망 SOM 을 이용함으로써 명확한 다수의 훈련 예가 없어도 효과적으로 채 경험하지 못한 상태-행동들에 대한 Q 값을 예측하고 이용할 수 있다는 장점이 있다.

• Journal of Korea Water Resources Association
• /
• v.38 no.7 s.156
• /
• pp.575-584
• /
• 2005

The judgement model to warn of possible pollution accident is constructed by multi-perceptron, multi layer neural network, neuro-fuzzy and it is trained stability, notice, and warming situation due to developed standard axis. The water quality forecasting model is linked to the runoff forecasting model, and joined with the judgement model to warn of possible pollution accident, which completes the artificial intelligence warning system. And GUI (Graphic User Interface) has been designed for that system. GUI screens, in order of process, are main page, data edit, discharge forecasting, water quality forecasting, warming system. The application capability of the system was estimated by the pollution accident scenario. Estimation results verify that the artificial intelligence warning system can be a reasonable judgement of the noized water pollution data.

• Journal of the Korea Convergence Society
• /
• v.10 no.9
• /
• pp.23-29
• /
• 2019

In this paper, the mood of images was classified into eight categories through a deep convolutional neural network and video was automatically generated using proper background music. Based on the collected image data, the classification model is learned using a multilayer perceptron (MLP). Using the MLP, a video is generated by using multi-class classification to predict image mood to be used for video generation, and by matching pre-classified music. As a result of 10-fold cross-validation and result of experiments on actual images, each 72.4% of accuracy and 64% of confusion matrix accuracy was achieved. In the case of misclassification, by classifying video into a similar mood, it was confirmed that the music from the video had no great mismatch with images.