• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1995.04b
• /
• pp.457-462
• /
• 1995

This paper describes diagnosis strategy of the Flexible Multiple Fault Diagnosis Module for forecasting faults in system and deciding current machine state form sensor information. Most studydeal with diagnosis control stategy about single fault in a system, this studies deal with multiple fault diagnosis. This strategy is consist of diagnosis control module such as backward tracking expert system shell, various neural network, numerical model to predict machine state and communication module for information exchange and cooperate between each model. This models are used to describe structure, function and behavior of subsystem, complex component and total system. Hierarchical structure is very efficient to represent structural, functional and behavioral knowledge. FT(Fault Tree). ST(Symptom Tree), FCD(Fault Consequence Diagrapy), SGM(State Graph Model) and FFM(Functional Flow Model) are used to represent hierachical structure. In this study, IA(Intelligent Agent) concept is introduced to match FT component and event symbol in diagnosed system and to transfer message between each event process. Proposed diagnosis control module is made of IPC(Inter Process Communication) method under UNIX operating system.

• Proceedings of the KIEE Conference
• /
• 2007.10a
• /
• pp.329-330
• /
• 2007

지능형 로봇에서 환경인식과 이러한 환경에 따른 행동 결정능력은 로봇이 필수적으로 갖추어야 할 기능이다. 본 논문은 이족로봇 플랫폼에서 비전기반 환경인식과 이를 통한 안정적인 보행 제어시스템을 제안한다. 비전기반 환경인식 시스템은 움직임 모델을 이용한 로봇 자체 움직임 보정 모듈, Adaboost를 이용한 장애물 영역 추출, PCA를 이용한 장애물 특징 추출, Hierarchical SVM을 이용한 장애물 인식 모듈로 구성되어 있으며, 이러한 환경 인식 시스템으로부터 보행 제어 시스템은 상황에 맞는 안정적이 보행 궤적을 생성한다. 보행 제어 시스템은 neural network을 이용하여 보행 궤적 생성 모듈과 보행 오차를 보정하기 위한 fuzzy 제어기 모듈로 구성되어 있다. 본 시스템을 제작한 로봇에 적용한 결과 보다 안정적인 보행을 할 수 있었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.04a
• /
• pp.569-572
• /
• 2002

한글을 인식하기 위한 전처리 방법으로 흔히 모음의 종류 및 자음과의 결합 정도에 따라 6가지 유형으로 분류하는 방법을 많이 사용하고 있다. 간 논문에서는 이러한 한글 문자를 인식하기 위한 전처리 과정으로써 한글의 유형을 분류하는 방법에 대한 연구로 계층적인 신경회로망을 도입하여 빠르고 신뢰성 있는 분류 방법을 제안한다. 실험에 사용된 글자는 KS X 1001(KS C 5601) 완성형 글자 2,350개에 대한 굴림, 바탕, 돋움, 궁서 글꼴로 총 9400개의 이미지 파일을 사용하였으며. 이 중 일부는 훈련에 사용하고 나머지는 분류를 위한 테스트 데이터로 사용한 결과 약 94%의 유형 분류율과 개별 패턴을 5.67ms에 분류하는 빠른 분류 속도를 나타내었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2003.05a
• /
• pp.281-284
• /
• 2003

본 연구는 웨이블릿 변환을 통하여 객체 영상에서 질감 특징 값을 추출하고, 신경망을 계층적으로 구성하여 분류하는 방법을 제안한다. 기존의 신경망을 이용한 영상의 분류는 단일 신경망을 이용하는 것이 대부분이었다. 하지만 단일 신경망은 분류하고자 하는 클래스의 수가 많거나 분류하고자 하는 대상이 유사한 입력패턴을 가질 경우 학습시간이 오래 걸리고, 인식률이 크게 떨어지는 문제를 가지고 있다. 그래서 본 연구에서는 효과적인 객체 영상 분류를 위해서 여러 개의 단일 신경망을 계층적으로 결합하는 방법을 제안한다. 실험결과 분류 대상 클래스가 증가함에도 불구하고 단일 신경망에 비해 학습시간이 단축되고, 높은 인식률을 보여주었다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.06a
• /
• pp.71-72
• /
• 2019

본 논문에서는 계층구조 합성곱 신경망 기반의 고해상도 동영상 프레임 고속 보간 방법을 제안한다. 기존의 고해상도 동영상 프레임 보간 방법은 시간 해상도와 공간 해상도를 분리하여 보간 하기 때문에, 예측된 보간 프레임이 블러(blur) 열화를 갖는 문제를 보인다. 제안하는 방법에서는 이러한 문제를 해결하기 위하여 계층구조 합성곱 신경망 기반의 보간 방법을 이용한다. 제안하는 계층구조 합성곱 신경망은 우선 저해상도의 광학 흐름 추정지도를 생성하고 이를 고해상도로 복원하여 프레임 보간을 수행한다. 이때, 저해상도 광학 흐름 지도를 추정할 때 사용된 특징 정보들을 활용하여 고품질의 고해상도 광학 흐름 지도를 추정한다. 실험을 통하여 제안하는 방법이 고해상도 프레임을 고속으로 보간하며, 동시에 블러 열화에 대한 성능 향상을 가짐을 보였다.

• Proceedings of the KSRS Conference
• /
• 2007.10a
• /
• pp.438-441
• /
• 2007

Recently, due to molecular biology and engineering technology, DNA microarray makes people watch thousands of genes and the state of variation from the tissue samples of living body. With DNA Microarray, it is possible to construct a genetic group that has similar expression patterns and grasp the progress and variation of gene. This paper practices Cluster Analysis which purposes the discovery of biological subgroup or class by using gene expression information. Hence, the purpose of this paper is to predict a new class which is unknown, open leukaemia data are used for the experiment, and MCL (Markov CLustering) algorithm is applied as an analysis method. The MCL algorithm is based on probability and graph flow theory. MCL simulates random walks on a graph using Markov matrices to determine the transition probabilities among nodes of the graph. If you look at closely to the method, first, MCL algorithm should be applied after getting the distance by using Euclidean distance, then inflation and diagonal factors which are tuning modulus should be tuned, and finally the threshold using the average of each column should be gotten to distinguish one class from another class. Our method has improved the accuracy through using the threshold, namely the average of each column. Our experimental result shows about 70% of accuracy in average compared to the class that is known before. Also, for the comparison evaluation to other algorithm, the proposed method compared to and analyzed SOM (Self-Organizing Map) clustering algorithm which is divided into neural network and hierarchical clustering. The method shows the better result when compared to hierarchical clustering. In further study, it should be studied whether there will be a similar result when the parameter of inflation gotten from our experiment is applied to other gene expression data. We are also trying to make a systematic method to improve the accuracy by regulating the factors mentioned above.

• Journal of IKEEE
• /
• v.16 no.2
• /
• pp.95-101
• /
• 2012

A novel approach for the reconstruction of 3D building model from aerial image data is proposed in this paper. In this approach, a Centroid Neural Network (CNN) with a metric of line segments is proposed for connecting low-level linear structures. After the straight lines are extracted from an edge image using the CNN, rectangular boundaries are then found by using an edge-based grouping approach. In order to avoid producing unrealistic building models from grouping lined segments, a hierarchical grouping method is proposed in this paper. The proposed hierarchical grouping method is evaluated with a set of aerial image data in the experiment. The results show that the proposed method can be successfully applied for the reconstruction of 3D building model from satellite images.

• Journal of Information Processing Systems
• /
• v.20 no.4
• /
• pp.535-549
• /
• 2024

Facial expressions (FEs) serve as fundamental components for human emotion assessment and human-computer interaction. Traditional convolutional neural networks tend to overlook valuable information during the FE feature extraction, resulting in suboptimal recognition rates. To address this problem, we propose a deep learning framework that incorporates hierarchical feature fusion, contextual data, and an attention mechanism for precise FE recognition. In our approach, we leveraged an enhanced VGGNet16 as the backbone network and introduced an improved group convolutional channel attention (GCCA) module in each block to emphasize the crucial expression features. A partial decoder was added at the end of the backbone network to facilitate the fusion of multilevel features for a comprehensive feature map. A reverse attention mechanism guides the model to refine details layer-by-layer while introducing contextual information and extracting richer expression features. To enhance feature distinguishability, we employed islanding loss in combination with softmax loss, creating a joint loss function. Using two open datasets, our experimental results demonstrated the effectiveness of our framework. Our framework achieved an average accuracy rate of 74.08% on the FER2013 dataset and 98.66% on the CK+ dataset, outperforming advanced methods in both recognition accuracy and stability.

• Journal of KIISE
• /
• v.44 no.1
• /
• pp.44-50
• /
• 2017

Pedestrian detection, an important component of autonomous driving and driving assistant system, has been extensively studied for many years. In particular, image based pedestrian detection methods such as Hierarchical classifier or HOG and, deep models such as ConvNet are well studied. The evaluation score has increased by the various methods. However, pedestrian detection requires high sensitivity to errors, since small error can lead to life or death problems. Consequently, further reduction in pedestrian detection error rate of autonomous systems is required. We proposed a new method to detect pedestrians and reduce the error rate by using the Faster R-CNN with new developed pedestrian training data sets. Finally, we compared the proposed method with the previous models, in order to show the improvement of our method.

• Journal of Broadcast Engineering
• /
• v.23 no.6
• /
• pp.886-895
• /
• 2018

In this paper, we introduce a technique to detect the video forgery by using the regularity that occurs in the video compression process. The proposed method uses the hierarchical regularity lost by the video double compression and the frame deletion. In order to extract such irregularities, the depth information of CU and TU, which are basic units of HEVC, is used. For improving performance, we make a depth map of CU and TU using local information, and then create input data by grouping them in GoP units. We made a decision whether or not the video is double-compressed and forged by using a general three-dimensional convolutional neural network. Experimental results show that it is more effective to detect whether or not the video is forged compared with the results using the existing machine learning algorithm.