• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권7호
• /
• pp.2667-2682
• /
• 2015

Due to the wide application of face recognition (FR) in information security, surveillance, access control and others, it has received significantly increased attention from both the academic and industrial communities during the past several decades. However, partial face occlusion is one of the most challenging problems in face recognition issue. In this paper, a novel method based on linear regression-based classification (LRC) algorithm is proposed to address this problem. After all images are downsampled and divided into several blocks, we exploit the evaluator of each block to determine the clear blocks of the test face image by using linear regression technique. Then, the remained uncontaminated blocks are utilized to partial occluded face recognition issue. Furthermore, an improved Distance-based Evidence Fusion approach is proposed to decide in favor of the class with average value of corresponding minimum distance. Since this occlusion removing process uses a simple linear regression approach, the completely computational cost approximately equals to LRC and much lower than sparse representation-based classification (SRC) and extended-SRC (eSRC). Based on the experimental results on both AR face database and extended Yale B face database, it demonstrates the effectiveness of the proposed method on issue of partial occluded face recognition and the performance is satisfactory. Through the comparison with the conventional methods (eigenface+NN, fisherfaces+NN) and the state-of-the-art methods (LRC, SRC and eSRC), the proposed method shows better performance and robustness.

• 한국멀티미디어학회논문지
• /
• 제23권2호
• /
• pp.146-154
• /
• 2020

Negative emotion causes stress and lack of attention concentration. The classification of negative emotion is important to recognize risk factors. To classify emotion status, various methods such as questionnaires and interview are used and it could be changed by personal thinking. To solve the problem, we acquire multi modal bio-signals such as electrocardiogram (ECG), skin temperature (ST), galvanic skin response (GSR) and extract features. The neural network (NN), the deep neural network (DNN), and the deep belief network (DBN) is designed using the multi modal bio-signals to analyze emotion status. As a result, the DBN based on features extracted from ECG, ST and GSR shows the highest accuracy (93.8%). It is 5.7% higher than compared to the NN and 1.4% higher than compared to the DNN. It shows 12.2% higher accuracy than using only single bio-signal (GSR). The multi modal bio-signal acquisition and the deep learning classifier play an important role to classify emotion.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2003년도 추계학술대회 논문집 전기물성,응용부문
• /
• pp.195-197
• /
• 2003

In this paper, Neural Networks is studied for estimation of XLPE cable specimen according to degradation. And these data making use of a computer-aided discharge analyser, a combination of statistical and discharge parameter was calculated to discrimination processing stage of degradation. NN has not bad recognition rate result of discrimination for degradation stage because discharge characteristics are very similar to between degradation stage. So, there is some improvement for applied NN.

• Communications for Statistical Applications and Methods
• /
• 제26권6호
• /
• pp.591-610
• /
• 2019

Deep Learning is one of the machine learning methods to find features from a huge data using non-linear transformation. It is now commonly used for supervised learning in many fields. In particular, Convolutional Neural Network (CNN) is the best technique for the image classification since 2012. For users who consider deep learning models for real-world applications, Keras is a popular API for neural networks written in Python and also can be used in R. We try examine the parameter estimation procedures of Deep Neural Network and structures of CNN models from basics to advanced techniques. We also try to figure out some crucial steps in CNN that can improve image classification performance in the CIFAR10 dataset using Keras. We found that several stacks of convolutional layers and batch normalization could improve prediction performance. We also compared image classification performances with other machine learning methods, including K-Nearest Neighbors (K-NN), Random Forest, and XGBoost, in both MNIST and CIFAR10 dataset.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회 1996년도 추계학술대회발표논문집; 고려대학교, 서울; 26 Oct. 1996
• /
• pp.31-34
• /
• 1996

The extensive researches have compared the performance of neural networks(NN) with those of various statistical techniques for the classification problem. The empirical results of these comparative studies have indicated that the neural networks often outperform the traditional statistical techniques. Moreover, there are some efforts that try to combine various classification methods, especially multivariate discriminant analysis with neural networks. While these efforts improve the performance, there exists a problem violating robust assumptions of multivariate discriminant analysis that are multivariate normality of the independent variables and equality of variance-covariance matrices in each of the groups. On the contrary, cluster analysis alleviates this assumption like neural networks. We propose a new approach to classification problems by combining the cluster analysis with neural networks. The resulting predictions of the composite model are more accurate than each individual technique.

• 대한의용생체공학회:의공학회지
• /
• 제38권3호
• /
• pp.129-136
• /
• 2017

외골격 로봇은 군사, 산업 및 의료와 같은 다양한 분야에서 사용되도록 개발된 기술이다. 외골격 로봇은 착용자의 움직임을 감지하여 작동한다. 외골격 로봇이 착용자의 일상적인 행동을 인지함으로써 착용자를 신속하게 보조하고 시스템을 효율적으로 활용할 수 있다. 본 연구에서는 피실험자로부터 얻은 운동학적 데이터를 통해 LDA, QDA, kNN을 활용하여 보행유형을 분류한다. 보행은 주로 일상생활에서 수행되는 일반보행과 계단보행을 선정하였다. 피실험자에게 7개의 IMUs 센서를 정해진 위치에 부착하여 운동학적 요소를 측정 하였다. 결과적으로, LDA는 78.42%, QDA는 86.16%, kNN는 k값에 따라 87.10% ~ 94.49%의 정확도로 분류하였다.

• 정보관리학회지
• /
• 제29권2호
• /
• pp.155-171
• /
• 2012

텍스트 범주화에 있어서 일반적인 문제는 문헌을 표현하는 핵심적인 용어라도 학습문헌 집합에 나타나지 않으면 이 용어는 분류자질로 선정되지 않는다는 것과 형태가 다른 동의어들은 서로 다른 자질로 사용된다는 점이다. 이 연구에서는 위키피디아를 활용하여 문헌에 나타나는 동의어들을 하나의 분류자질로 변환하고, 학습문헌 집합에 출현하지 않은 입력문헌의 용어를 가장 유사한 학습문헌의 용어로 대체함으로써 범주화 성능을 향상시키고자 하였다. 분류자질 선정 실험에서는 (1) 비학습용어 추출 시 범주 정보의 사용여부, (2) 용어의 유사도 측정 방법(위키피디아 문서의 제목과 본문, 카테고리 정보, 링크 정보), (3) 유사도 척도(단순 공기빈도, 정규화된 공기빈도) 등 세 가지 조건을 결합하여 실험을 수행하였다. 비학습용어를 유사도 임계치 이상의 최고 유사도를 갖는 학습용어로 대체하여 kNN 분류기로 분류할 경우 모든 조건 결합에서 범주화 성능이 0.35%~1.85% 향상되었다. 실험 결과 범주화 성능이 크게 향상되지는 못하였지만 위키피디아를 활용하여 분류자질을 선정하는 방법이 효과적인 것으로 확인되었다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 ITC-CSCC -2
• /
• pp.818-821
• /
• 2002

In this paper, we propose Neuro-Fuzzy discrimination method of the new and old bill using bill money acoustic data. The concept of the histogram is introduced to improve the processing time into the proposal system. The adaptative filter is used in order to remove the motor sound from an observed bill money acoustic data. The output signal of this adaptive digital filter is converted into not only a spectrum but also a histogram. It became easy that features of the paper money sound were extracted from the bill money acoustic data. The spectral data and the histogram is obtained like this, and it become an input pattern of the neural network(NN). Then, the discrimination result of the NN is finally judged by the fuzzy inferece in the new bill or the exhaustion bill.

• 한국정밀공학회지
• /
• 제17권7호
• /
• pp.98-105
• /
• 2000

In this study, we developed rotating machine vibration condition monitoring system based upon Windows NT and DSP Board. Developed system includes signal analysis module, trend monitoring and simple diagnosis using threshold value. Trend analysis and report generation are offered with database management tool which was developed in MS-ACCESS environment. Post-processor, based upon Matlab, is developed for vibration signal analysis and fault detection using statistical pattern recognition scheme based upon Bayes discrimination rule and neural networks. Concerning to Bayes discrimination rule, the developed system contains the linear discrimination rule with common covariance matrices and the quadratic discrimination rule under different covariance matrices. Also the system contains k-nearest neighbor method to directly estimate a posterior probability of each class. The result of case studies with the data acquired from Pyung-tak LNG pump and experimental setup show that the system developed in this research is very effective and useful.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권7호
• /
• pp.3050-3065
• /
• 2016

Neural networks (NNs) are extensively used in applications requiring signal classification and regression analysis. In this paper, a NN based threshold selection algorithm for 60 GHz millimeter wave (MMW) time of arrival (TOA) estimation using an energy detector (ED) is proposed which is based on the skewness, kurtosis, and curl of the received energy block values. The best normalized threshold for a given signal-to-noise ratio (SNR) is determined, and the influence of the integration period and channel on the performance is investigated. Results are presented which show that the proposed NN based algorithm provides superior precision and better robustness than other ED based algorithms over a wide range of SNR values. Further, it is independent of the integration period and channel model.