• Communications for Statistical Applications and Methods
• /
• v.15 no.2
• /
• pp.283-292
• /
• 2008

Smoothing parameter or bandwidth plays a key role in nonparametric classification based on kernel density estimation. We consider choosing smoothing parameter in nonparametric classification, which optimize the Bayes risk. Hall and Kang (2005) clarified the theoretical properties of smoothing parameter in terms of minimizing Bayes risk and derived the optimal order of it. Bootstrap method was used in their exploring numerical properties. We compare cross-validation and bootstrap method numerically in terms of optimal order of bandwidth. Effects on misclassification rate are also examined. We confirm that bootstrap method is superior to cross-validation in both cases.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.3
• /
• pp.242-247
• /
• 2015

In this study, we propose the design of Radial Basis Function Neural Network(RBFNN) classifier in order to classify between precipitation and non-precipitation echo. The characteristics of meteorological radar data is analyzed for classifying precipitation and non-precipitation echo. Input variables is selected as DZ, SDZ, VGZ, SPN, DZ_FR, VR by performing pre-processing of UF data based on the characteristics analysis and these are composed of training and test data. Finally, QC data being used in Korea Meteorological Administration is applied to compare with the performance results of proposed classifier.

• Journal of Korea Society of Industrial Information Systems
• /
• v.4 no.2
• /
• pp.1-6
• /
• 1999

We propose a new algorithm for pattern classification by extracting feature vectors based on Gibbs distributions which are well suited for representing the characteristic of an images. The extracted feature vectors are comprised of 2-D moments which are invariant under translation rotation, and scale of the image less sensitive to noise. This implementation contains two puts: feature extraction and pattern classification First of all, we extract feature vector which consists of an improved 2-D moments on the basis of estimated Gibbs distribution Next, in the classification phase the minimization of the discrimination cost function for a specific pattern determines the corresponding template pattern. In order to evaluate the performance of the proposed scheme, classification experiments with training document sets of characters have been carried out on SUN ULTRA 10 Workstation Experiment results reveal that the proposed scheme had high classification rate over 98%.

• The Journal of the Korea Contents Association
• /
• v.21 no.3
• /
• pp.616-625
• /
• 2021

Deep neural networks are an approximation method that approximates an arbitrary function to a linear model and then repeats additional approximation using a nonlinear active function. In this process, the method of evaluating the performance of approximation uses the loss function. Existing in-depth learning methods implement approximation that takes into account loss functions in the linear approximation process, but non-linear approximation phases that use active functions use non-linear transformation that is not related to reduction of loss functions of loss. This study proposes parametric activation functions that introduce scale parameters that can change the scale of activation functions and location parameters that can change the location of activation functions. By introducing parametric activation functions based on scale and location parameters, the performance of nonlinear approximation using activation functions can be improved. The scale and location parameters in each hidden layer can improve the performance of the deep neural network by determining parameters that minimize the loss function value through the learning process using the primary differential coefficient of the loss function for the parameters in the backpropagation. Through MNIST classification problems and XOR problems, parametric activation functions have been found to have superior performance over existing activation functions.

• Journal of Digital Convergence
• /
• v.11 no.8
• /
• pp.273-279
• /
• 2013

The purpose of the study was to present basic data to evaluation of the spatial resolution for exposure class(EC) in computed radiography(CR) by using the modulation transfer function(MTF). In this study, MTF was measured the edge method by using image plate(IP) of $100{\mu}mm$ pixels. A standard beam quality RQA5 based on an international electro-technical commission(IEC) standard was used to perform the X-ray imaging studies. Digital imaging began to set the sensitivity to EC 50, 100, 200, 300, 400, 600, 800, 1200 in X-ray irradiated to IP. The MTF 50% and 10% in the final images was analysis by using an authorized image analysis program the Origin 8.0 and the image J. As a results, the EC 200 was the best spatial resolution at MTF 50% ($1.979{\pm}0.114lp/mm$) and MTF 10% ($3.932{\pm}0.041$). Therefore, the EC 200 could be useful for the diagnosis of diseases that require high spatial resolution such as fractures.

• The KIPS Transactions:PartB
• /
• v.9B no.2
• /
• pp.202-214
• /
• 2002

In this paper, we propose a modified FCM (MFCM) algorithm to solve the problems of the FCM algorithm and the fuzzy clustering algorithm using an average intracluster distance (FCAID). The MFCM algorithm grants the regular grade of membership in the small size of cluster. And it clears up the convergence problem of objective function because its objective function is designed according to the grade of membership of it, verified, and used for clustering data. So, it can solve the problem of the FCM algorithm in different size of cluster and the FCAID algorithm in the convergence problem of objective function. To verify the MFCM algorithm, we compared with the result of the FCM and the FCAID algorithm in data clustering. From the experimental results, the MFCM algorithm has a good performance compared with others by classification entropy.

• Journal of Advanced Navigation Technology
• /
• v.16 no.1
• /
• pp.151-157
• /
• 2012

Recently, owing to the technology advances in computer science and image processing, age of face classification have become prevalent topics. It is difficult to estimate age of facial shape with statistical figures because facial shape of the person should change due to not only biological gene but also personal habits. In this paper, we proposed a robust age of face classification method by using Gabor feature and fuzzy support vector machine(SVM). Gabor wavelet function is used for extracting facial feature vector and in order to solve the intrinsic age ambiguity problem, a fuzzy support vector machine(FSVM) is introduced. By utilizing the FSVM age membership functions is defined. Some experiments have conducted to testify the proposed approach and experimental results showed that the proposed method can achieve better age of face classification precision.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.6
• /
• pp.586-591
• /
• 2014

In this study, we introduce Radial Basis Function Neural Networks(RBFNNs) classifier using Artificial Bee Colony(ABC) algorithm in order to classify between precipitation event and non-precipitation event from given radar data. Input information data is rebuilt up through feature analysis of meteorological radar data used in Korea Meteorological Administration. In the condition phase of the proposed classifier, the values of fitness are obtained by using Fuzzy C-Mean clustering method, and the coefficients of polynomial function used in the conclusion phase are estimated by least square method. In the aggregation phase, the final output is obtained by using fuzzy inference method. The performance results of the proposed classifier are compared and analyzed by considering both QC(Quality control) data and CZ(corrected reflectivity) data being used in Korea Meteorological Administration.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2014.11a
• /
• pp.798-801
• /
• 2014

여행 정보 시스템(ATIS), 교통 관리 시스템 (ITS) 등 궤적 기반 서비스에서, 서비스 품질을 향상시키기 위해서는 주어진 궤적 질의에 대한 정확한 주행시간을 예측하는 것이 필수적이다. 이를 위한 대표적인 공간 데이터 분석 기법으로는 데이터 분류에서 높은 정확도를 보장하는 규칙 기반 분류화 기법이 존재한다. 그러나 기존 규칙 기반 분류화 기법은 단일 컴퓨터 환경만을 고려하기 때문에, 대용량 공간 데이터 처리에 적합하지 않은 문제점이 존재한다. 이를 해결하기 위해, 본 연구에서는 맵리듀스 환경에서 규칙 기반 분류화를 이용한 궤적 데이터 주행 시간 예측 알고리즘을 개발하고자 한다. 제안하는 알고리즘은 첫째, 맵리듀스를 이용하여 대용량 공간 데이터를 병렬적으로 분석함으로써, 활용도 높은 궤적 데이터 규칙을 생성한다. 이를 통해 대용량 공간 데이터 기반의 규칙 생성 시간을 감소시킨다. 둘째, 그리드 구조 기반의 지도 데이터 분할을 통해, 사용자 질의처리 시 탐색 성능을 향상시킨다. 즉, 주행 시간 예측을 위한 규칙 그룹을 탐색 시 질의를 포함하는 그리드 셀만을 탐색하기 때문에, 질의처리 성능이 향상된다. 마지막으로 맵리듀스 구조에 적합한 질의처리 알고리즘을 설계하여, 효율적인 병렬 질의처리를 지원한다. 이를 위해 맵 함수에서는 선정된 그리드 셀에 대해, 질의에 포함된 도로 구간에서의 주행 시간을 병렬적으로 측정한다. 아울러 리듀스 함수에서는 출발 시간 및 구간별 주행 시간을 바탕으로 맵 함수의 결과를 병합함으로써, 최종 결과를 생성한다. 이를 통해 공간 빅데이터 분석을 통한 주행 시간 예측 기법의 처리 시간 및 결과 정확도를 향상시킨다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2005.11a
• /
• pp.110-113
• /
• 2005

본 논문은 가중 퍼지소속함수 기반 신경망(Neural Network with Weighted fuzzy Membership Funcstions, NEWFM)을 이용하여 심전도 신호로부터 조기심실수축(Premature Ventricular Contraction, PVC)을 판별하는 퍼지규칙을 추출하고 있다. NEWFM은 자기적응적(self adaptive) 가중 퍼지소속함수를 가지고 주어진 입력 데이터로부터 학습하여 퍼지규칙을 생성하고 이를 기반으로 정상 파형과 PVC 파형을 구분한다. 분류 성능 평가를 위하여 MIT/BIH 부정맥 데이터 베이스를 사용하였으며, NEWFM의 입력은 심전도의 파형에 웨이블릿 변환을 적용하여 추출된 웨이블릿 계수를 사용하였다. 여기에 비중복면적 분산 측정법을 적용하여 중요도가 낮은 계수를 제거하면서 최소의 m 개 특징입력만을 사용한 하이퍼박스로 단순화 시킨다. 이러한 방법으로 추출된 2개의 웨이블릿 계수를 사용한 퍼지규칙은 $96\%$의 PVC 분류성능을 보여준다.