• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2001년도 하계종합학술대회 논문집(5)
• /
• pp.115-118
• /
• 2001

In this paper we propose an FDI(fault detection and isolation) algorithm using neural network-based multi-fault models to detect and isolate single faults in nonlinear systems. When a change in the system occurs, the errors between the system output and the neural network nominal system output cross a threshold, and once a fault in the system is detected, the fault classifier statistically isolates the fault by using the error between each neural network-based fault model output and the system output.

• 대한공간정보학회지
• /
• 제4권2호
• /
• pp.137-147
• /
• 1996

본 논문에서는 통계적 분류방법인 최대유사 분류법(MLC: maximum likelihood classifier)과 신경회로망을 이용한 분류법인 다층퍼셉트론(MLP: multiayer perceptron) 분류법간의 분류성능을 비교 평가하였으며, 또한 MLP 분류법에서 문제가 되고 있는 학습률(learning rate), 운동량 상수(,momentum constant), 은닉층의 노드수에 따른 MLP 분류법의 분류성능을 평가하였다. 부산지역에 대한 실제 인공위성 화상데이타인 Landsat TM 화상데이타를 사용하여 MLP 분류법과 MLC 분류법의 성능을 비교한 결과 MLP 분류법의 성능이 더 우사함을 확인할 수 있었으며, 학습률, 운동량 상수 및 은닉층의 노드수에 따른 분류성능도 평가하였다.

• 전기전자학회논문지
• /
• 제22권3호
• /
• pp.700-705
• /
• 2018

본 논문에서는 restricted coulomb energy(RCE) 신경망 기반 가스 분류기를 제안하고, 이의 실시간 학습 및 분류를 위한 하드웨어 구현 결과를 제시한다. RCE 신경망은 네트워크 구조가 학습에 따라 유동적이며, 실시간 학습 및 분류가 가능하므로, 가스 분류 응용에 적합한 특징을 갖는다. 설계된 가스 분류기는 UCI gas dataset에 대해 99.2%의 분류 정확도를 보였으며, Intel-Altera cyclone IV FPGA 기반 구현 결과, 26,702개의 logic elements로 구현 가능함을 확인하였다. 또한, FPGA test system을 구성하여 63MHz의 동작 주파수로 실시간 검증을 수행하였다.

• Journal of Multimedia Information System
• /
• 제9권1호
• /
• pp.21-32
• /
• 2022

Early-stage diagnosis of Alzheimer's Disease (AD) from Cognitively Normal (CN) patients is crucial because treatment at an early stage of AD can prevent further progress in the AD's severity in the future. Recently, computer-aided diagnosis using magnetic resonance image (MRI) has shown better performance in the classification of AD. However, these methods use a traditional machine learning algorithm that requires supervision and uses a combination of many complicated processes. In recent research, the performance of deep neural networks has outperformed the traditional machine learning algorithms. The ability to learn from the data and extract features on its own makes the neural networks less prone to errors. In this paper, a dense neural network is designed for binary classification of Alzheimer's disease. To create a classifier with better results, we studied result of different activation functions in the prediction. We obtained results from 5-folds validations with combinations of different activation functions and compared with each other, and the one with the best validation score is used to classify the test data. In this experiment, features used to train the model are obtained from the ADNI database after processing them using FreeSurfer software. For 5-folds validation, two groups: AD and CN are classified. The proposed DNN obtained better accuracy than the traditional machine learning algorithms and the compared previous studies for AD vs. CN, AD vs. Mild Cognitive Impairment (MCI), and MCI vs. CN classifications, respectively. This neural network is robust and better.

• 대한방사선기술학회지:방사선기술과학
• /
• 제26권1호
• /
• pp.71-82
• /
• 2003

T1강조 자기공명영상과 계층적 신경회로망을 이용하여 간경변증을 단계별로 분류하고자 제안한다. 데이터는 2001년 6월부터 12월까지 부산대학교병원에서 얻었으며, 각 단계별 분류는 정상, 1, 2, 3단계별로 분류하였다. 그리고 46명의 데이터를 분석하였다. T1강조 자기공명 간영상으로부터 정상간 실질과 간경변 결절을 추출하였다. 그 다음에 T1강조 자기공명 간 영상에서 간 경화증의 단계를 객관적으로 해석 분류하였다. 간경변 분류기 구현은 계층적 신경회로망을 이용하였고, 명암도 분석과 간 결절 특성을 통하여 정상간과 3단계의 간경변으로 구분하였다. 제안한 신경회로망 분류기는 오류 역전과 알고리즘을 이용하였다. 분류결과 인식율이 정상군은 100%, 1 단계는 82.3%, 2 단계는 86.7%, 3 단계는 83.7%의 분류율을 나타내었다. 신경회로망 분류 결과와 전문의 판독 결과를 서로 비교한 결과 인식률은 매우 높게 나타났다. 만일 더욱더 충분한 데이터나 파라미터를 가지고 지속적으로 수행한다면 간경변 환자들에게 임상적으로 지원하는 도구뿐만 아니라 의료전문 신경회로망으로도 기대된다.

• 한국데이터정보과학회:학술대회논문집
• /
• 한국데이터정보과학회 2003년도 추계학술대회
• /
• pp.57-72
• /
• 2003

This article provides integrated neural network models for the interest rate forecasting using change-point detection. The model is composed of three phases. The first phase is to detect successive structural changes in interest rate dataset. The second phase is to forecast change-point group with data mining classifiers. The final phase is to forecast the interest rate with BPN. Based on this structure, we propose three integrated neural network models in terms of data mining classifier: (1) multivariate discriminant analysis (MDA)-supported neural network model, (2) case based reasoning (CBR)-supported neural network model and (3) backpropagation neural networks (BPN)-supported neural network model. Subsequently, we compare these models with a neural network model alone and, in addition, determine which of three classifiers (MDA, CBR and BPN) can perform better. For interest rate forecasting, this study then examines the predictability of integrated neural network models to represent the structural change.

• International Journal of Computer Science & Network Security
• /
• 제21권11호
• /
• pp.89-96
• /
• 2021

This work is an extension of my work presented a robust and economically efficient method for the Discrimination of four Mung-Beans [1] varieties based on quantitative parameters. Due to the advancement of technology, users try to find the solutions to their daily life problems using smartphones but still for computing power and memory. Hence, there is a need to find the best classifier to classify the Mung-Beans using already suggested features in previous work with minimum memory requirements and computational power. To achieve this study's goal, we take the experiments on various supervised classifiers with simple architecture and calculations and give the robust performance on the most relevant 10 suggested features selected by Fisher Co-efficient, Probability of Error, Mutual Information, and wavelet features. After the analysis, we replace the Artificial Neural Network and Deep learning with a classifier that gives approximately the same classification results as the above classifier but is efficient in terms of resources and time complexity. This classifier is easily implemented in the smartphone environment.

• 한국전자통신학회논문지
• /
• 제18권5호
• /
• pp.817-826
• /
• 2023

본 논문에서는 스마트 그리드 배전 계통에서 선로상의 고장으로부터 계통을 보호하기 위한 인공 신경 회로망을 기반으로 하는 고장 판단 방법론을 제안하였다. 제안된 방법론에서는 먼저 전류 실효값 크기를 기반으로 일반 고장 여부를 판단하고 다음, 정상 전류로 판단되는 경우 인공 신경 회로망을 기반으로 하는 normal/HIF classifier를 이용하여 고 임피던스 지락 고장 여부를 판단하도록 설계하였다. 반복적인 DSP 모듈 기반 알고리즘 검증 시험들 중에서, 실효 값 크기가 최소 동작전류보다 작은 정상 전류 파형 시험인 경우에 normal/HIF classifier가 전류 파형을 정상상태로 인식하여 부 동작하였으며, 반면에, 저 임피던스 고장의 경우는 고장 상태로 인식하여 정해진 절차에 따라 재폐로 동작을 보임으로써 제안된 방법론의 유효성을 확인할 수 있었다.

• International journal of advanced smart convergence
• /
• 제8권1호
• /
• pp.141-146
• /
• 2019

These days, there are many applications using neural networks as parts of their system. On the other hand, adversarial examples have become an important issue concerining the security of neural networks. A classifier in neural networks can be fooled and make it miss-classified by adversarial examples. There are many research to encounter adversarial examples by using denoising methods. Some of them using GAN (Generative Adversarial Network) in order to remove adversarial noise from input images. By producing an image from generator network that is close enough to the original clean image, the adversarial examples effects can be reduced. However, there is a chance when adversarial noise can survive the approximation process because it is not like a normal noise. In this chance, we propose a research that utilizes high-level representation in the classifier by combining GAN network with a trained U-Net network. This approach focuses on minimizing the loss function on high representation terms, in order to minimize the difference between the high representation level of the clean data and the approximated output of the noisy data in the training dataset. Furthermore, the generated output is checked whether it shows minimum error compared to true label or not. U-Net network is trained with true label to make sure the generated output gives minimum error in the end. At last, the remaining adversarial noise that still exist after low-level approximation can be removed with the U-Net, because of the minimization on high representation terms.

• Journal of Information Processing Systems
• /
• 제9권1호
• /
• pp.117-140
• /
• 2013

Hindi is the most widely spoken language in India, with more than 300 million speakers. As there is no separation between the characters of texts written in Hindi as there is in English, the Optical Character Recognition (OCR) systems developed for the Hindi language carry a very poor recognition rate. In this paper we propose an OCR for printed Hindi text in Devanagari script, using Artificial Neural Network (ANN), which improves its efficiency. One of the major reasons for the poor recognition rate is error in character segmentation. The presence of touching characters in the scanned documents further complicates the segmentation process, creating a major problem when designing an effective character segmentation technique. Preprocessing, character segmentation, feature extraction, and finally, classification and recognition are the major steps which are followed by a general OCR. The preprocessing tasks considered in the paper are conversion of gray scaled images to binary images, image rectification, and segmentation of the document's textual contents into paragraphs, lines, words, and then at the level of basic symbols. The basic symbols, obtained as the fundamental unit from the segmentation process, are recognized by the neural classifier. In this work, three feature extraction techniques-: histogram of projection based on mean distance, histogram of projection based on pixel value, and vertical zero crossing, have been used to improve the rate of recognition. These feature extraction techniques are powerful enough to extract features of even distorted characters/symbols. For development of the neural classifier, a back-propagation neural network with two hidden layers is used. The classifier is trained and tested for printed Hindi texts. A performance of approximately 90% correct recognition rate is achieved.