• 전기학회논문지
• /
• 제60권12호
• /
• pp.2352-2360
• /
• 2011

In this paper, we introduce a comprehensive design methodology of Radial Basis Function Neural Networks (RBFNN) that is based on mechanism of clustering and optimization algorithm. We can divide some clusters based on similarity of input dataset by using clustering algorithm. As a result, the number of clusters is equal to the number of nodes in the hidden layer. Moreover, the centers of each cluster are used into the centers of each receptive field in the hidden layer. In this study, we have applied Fuzzy-C Means(FCM) and K-Means(KM) clustering algorithm, respectively and compared between them. The weight connections of model are expanded into the type of polynomial functions such as linear and quadratic. In this reason, the output of model consists of relation between input and output. In order to get the optimal structure and better performance, Particle Swarm Optimization(PSO) is used. We can obtain optimized parameters such as both the number of clusters and the polynomial order of weights connection through structural optimization as well as the widths of receptive fields through parametric optimization. To evaluate the performance of proposed model, NXT equipment offered by National Instrument(NI) is exploited. The situation awareness system-related intelligent model was built up by the experimental dataset of distance information measured between object and diverse sensor such as sound sensor, light sensor, and ultrasonic sensor of NXT equipment.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2001년도 추계학술발표논문집 (상)
• /
• pp.535-538
• /
• 2001

Since 1990s, many literatures have shown that connectionist models, such as back propagation, recurrent network, and RBF (Radial Basis Function) outperform the traditional models, MA (Moving Average), AR (Auto Regressive), and ARIMA (Auto Regressive Integrated Moving Average) in time series prediction. Neural based approaches to time series prediction require the enough length of historical measurements to generate the enough number of training patterns. The more training patterns, the better the generalization of MLP is. The researches about the schemes of generating artificial training patterns and adding to the original ones have been progressed and gave me the motivation of developing VTG schemes in 1996. Virtual term is an estimated measurement, X(t+0.5) between X(t) and X(t+1), while the given measurements in the series are called actual terms. VTG (Virtual Tern Generation) is the process of estimating of X(t+0.5), and VTG schemes are the techniques for the estimation of virtual terms. In this paper, the alternative VTG schemes to the VTG schemes proposed in 1996 will be proposed and applied to multivariate time series prediction. The VTG schemes proposed in 1996 are called deterministic VTG schemes, while the alternative ones are called stochastic VTG schemes in this paper.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제32권11호
• /
• pp.1021-1028
• /
• 2005

분류 및 회계문제에서의 일반적인 해법은, 현실 세계에서 얻은 정보를 행렬로 사상하거나, 이진정보로 변형하는 등 주어진 데이타의 가공과 이를 이용한 학습에서 찾을 수 있다. 본 논문은 현실세계에 존재하는 순수한 데이타를 근원공간이라 칭하며, 근원 데이타가 커널에 의해 사상된 행렬을 이원공간이라 한다. 근원공간 혹은 이원공간에서의 분류문제는 그 역이 존재하는 문제 즉, 완전해가 존재하는 문제와, 그 역이 존재하지 않거나, 역의 원소 값들이 무한히 커지는 불량조건 흑은 특이조건인 두 가지 형태로 존재한다. 특히, 실제 문제에 있어서 완전 해를 가진 문제이기 보다는 후자에 가까운 형태로 나타나게 된다. 결론적으로 근원데이타나 이원데이타를 이용한 문제를 해결하기 위해서는 많은 경우에 완전 해를 갖는 문제로 변형시키는 정규화과정이 필요하다. 본 논문에서는 이러한 정규화 인수를 찾는 문제를 기존의 GCV, L-Curve, 그리고 이원공간에서의 데이타를 RBF 신경회로망에 적용시킨 커널 학습법에 대한 각각의 성능을 비교실험을 통해 고찰한다. GCV와 L-Curve는 정규화 인수를 찾는 대표적인 방법으로 두 방법 모두 성능면에서 동등하며 문제의 조건에 따라 다소 차이를 보인다. 그러나 이러한 두 방법은 문제해를 구하기 위해서는 정규화 인수를 구한후 문제를 재정의하는 이원적인 문제해결이라는 취약점을 갖는다. 반면, RBF 신경회로망을 이용한 방법은 정규화 인수와 해를 동시에 학습하는 단일화된 방법이 된다. 이때 커널을 이용한 학습법의 성능을 향상하기 위해, 전체학습과 성능의 제한적 비례관계라는 설정아래, 각각의 학습에 따라 능동적으로 변화하는 동적모멘텀의 도입을 제안한다. 동적모멘트는 바이어스 학습을 포함한 방법과 포함하지 않은 방법에 각각 적용분석하였다. 끝으로 제안된 동적모멘텀이 분류문제의 표준인 Iris 데이터, Singular 시스템의 대표적 모델인 가우시안 데이타, 그리고 마지막으로 1차원 이미지 복구문제인 Shaw데이타를 이용한 각각의 실험에서 분류문제와 회계문제 양쪽 모두에 있어 기존의 GCV, L-Curve와 동등하거나 우수한 성능이 있음을 보인다.

• 전자공학회논문지SC
• /
• 제39권1호
• /
• pp.76-84
• /
• 2002

본 논문은 심전도 신호의 잡음제거에 있어 ST 세그먼트의 왜곡을 최소화함과 동시에 기저선 변동 잡음을 제거하기 위한 연구이다. 일반적인 표준필터와 적응필터는 심전도신호의 기저선 변동잡음을 제거하기 위해 주로 사용된다. 그러나 표준필터는 기저선 잡음의 시변 특성 때문에 고정된 주파수 대역으로 잡음을 제거하기가 어렵고, 적응필터를 이용하여 필터링 할 경우에는 참조신호를 설정하기가 매우 어렵다. 따라서 본 연구에서는 시-지연신경망과 RBF 신경망을 이용하여 참조신호 없이 잡음을 제거하는 새로운 구조의 적응 필터를 제안하였다. 그리고 제안된 기법의 성능을 평가하기 위해 MIT-BIH 심전도데이터를 이용하였고, 실험결과에서 평균 잡음 제거비는 표준 필터가 -16.3[dB], 적응 필터가 -44.9[dB]이고 제안된 필터의 경우에는 -53.3[dB]로 나타나 다른 필터의 경우보다 우수한 잡음 제거 성능을 보였다.

• Imaging Science in Dentistry
• /
• 제43권3호
• /
• pp.153-161
• /
• 2013

Purpose: To prevent low bone mineral density (BMD), that is, osteoporosis, in postmenopausal women, it is essential to diagnose osteoporosis more precisely. This study presented an automatic approach utilizing a histogram-based automatic clustering (HAC) algorithm with a support vector machine (SVM) to analyse dental panoramic radiographs (DPRs) and thus improve diagnostic accuracy by identifying postmenopausal women with low BMD or osteoporosis. Materials and Methods: We integrated our newly-proposed histogram-based automatic clustering (HAC) algorithm with our previously-designed computer-aided diagnosis system. The extracted moment-based features (mean, variance, skewness, and kurtosis) of the mandibular cortical width for the radial basis function (RBF) SVM classifier were employed. We also compared the diagnostic efficacy of the SVM model with the back propagation (BP) neural network model. In this study, DPRs and BMD measurements of 100 postmenopausal women patients (aged >50 years), with no previous record of osteoporosis, were randomly selected for inclusion. Results: The accuracy, sensitivity, and specificity of the BMD measurements using our HAC-SVM model to identify women with low BMD were 93.0% (88.0%-98.0%), 95.8% (91.9%-99.7%) and 86.6% (79.9%-93.3%), respectively, at the lumbar spine; and 89.0% (82.9%-95.1%), 96.0% (92.2%-99.8%) and 84.0% (76.8%-91.2%), respectively, at the femoral neck. Conclusion: Our experimental results predict that the proposed HAC-SVM model combination applied on DPRs could be useful to assist dentists in early diagnosis and help to reduce the morbidity and mortality associated with low BMD and osteoporosis.

• IEIE Transactions on Smart Processing and Computing
• /
• 제6권1호
• /
• pp.10-17
• /
• 2017

We propose classification algorithms for human and dog movement. The proposed algorithms use micro-Doppler signals obtained from humans and dogs moving in four different directions. A two-stage classifier based on a support vector machine (SVM) is proposed, which uses a radial-based function (RBF) kernel and $16^{th}$-order linear predictive code (LPC) coefficients as feature vectors. With the proposed algorithms, we obtain the best classification results when a first-level SVM classifies the type of movement, and then, a second-level SVM classifies the moving object. We obtain the correct classification probability 95.54% of the time, on average. Next, to deal with the difficult classification problem of human and dog running, we propose a two-layer convolutional neural network (CNN). The proposed CNN is composed of six ($6{\times}6$) convolution filters at the first and second layers, with ($5{\times}5$) max pooling for the first layer and ($2{\times}2$) max pooling for the second layer. The proposed CNN-based classifier adopts an auto regressive spectrogram as the feature image obtained from the $16^{th}$-order LPC vectors for a specific time duration. The proposed CNN exhibits 100% classification accuracy and outperforms the SVM-based classifier. These results show that the proposed classifiers can be used for human and dog classification systems and also for classification problems using data obtained from an ultra-wideband (UWB) sensor.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권6호
• /
• pp.2168-2187
• /
• 2021

The smart grid replaces the traditional power structure with information inventiveness that contributes to a new physical structure. In such a field, malicious information injection can potentially lead to extreme results. Incorrect, FDI attacks will never be identified by typical residual techniques for false data identification. Most of the work on the detection of FDI attacks is based on the linearized power system model DC and does not detect attacks from the AC model. Also, the overwhelming majority of current FDIA recognition approaches focus on FDIA, whilst significant injection location data cannot be achieved. Building on the continuous developments in deep learning, we propose a Deep Learning based Locational Detection technique to continuously recognize the specific areas of FDIA. In the development area solver gap happiness is a False Data Detector (FDD) that incorporates a Convolutional Neural Network (CNN). The FDD is established enough to catch the fake information. As a multi-label classifier, the following CNN is utilized to evaluate the irregularity and cooccurrence dependency of power flow calculations due to the possible attacks. There are no earlier statistical assumptions in the architecture proposed, as they are "model-free." It is also "cost-accommodating" since it does not alter the current FDD framework and it is only several microseconds on a household computer during the identification procedure. We have shown that ANN-MLP, SVM-RBF, and CNN can conduct locational detection under different noise and attack circumstances through broad experience in IEEE 14, 30, 57, and 118 bus systems. Moreover, the multi-name classification method used successfully improves the precision of the present identification.