• 한국음향학회지
• /
• 제24권1호
• /
• pp.29-37
• /
• 2005

본 논문은 한국의 전통 음악, 즉 국악 장르를 자동으로 분류하는 시스템을 제안한다. 제안된 시스템은 입력 음악의 내용기반 분석을 통하여 궁중음악, 풍류방음악, 민속성악, 민속기악, 불교음악, 무속음악 등 6가지 장르중 하나로 자동분류하여 해당 음악의 장르 결과를 보여준다. 국악 장르 분류에 사용된 내용기반 알고리즘은 크게 음악의 특징 벡터 추출 그리고 장르 분류를 위한 패턴인식 과정 2가지로 구성된다. 음악의 특징 벡터 추출은 디지탈 신호 처리기술을 이용하여 해당 음악의 spectral centroid, rolloff, flux 등 STFT (Short Time Fourier Transform) 기반의 특징 계수들과 MFCC (Mel frequency cepstral coefficient), LPC (Linear predictive coding) 등의 계수들을 구한 후 SFS (Sequential Forward Selection) 최적 특징 벡터 열을 선별하여 사용하였으며 패틴 분류 알고리즘으로는 k-NN (k -Nearest Neighbor), Gaussian, GMM (Gaussian Mixture Model), SVM (Support Vector Machine) 분류기를 사용하였다. 특히 본 연구에서는 입력 질의의 패턴 (혹은 구간) 변화에 따른 시스템의 불확실성을 개선하기 위하여 MFC (Multi Feature Clustring) 방법을 이용하여 DB를 구축하였다. 모의실험 결과 k-NN 과 SVM 분류기 모두 $97{\%}$ 이상의 장르 분류 성공률을 보였으나, SVM 이 k-NN에 비해 약 3배 이상의 빠른 분류 성능을 가지고 있음을 확인하였다.

• Journal of Information Processing Systems
• /
• 제10권4호
• /
• pp.555-567
• /
• 2014

Biometric performance improvement is a challenging task. In this paper, a hierarchical strategy fusion based on multimodal biometric system is presented. This strategy relies on a combination of several biometric traits using a multi-level biometric fusion hierarchy. The multi-level biometric fusion includes a pre-classification fusion with optimal feature selection and a post-classification fusion that is based on the similarity of the maximum of matching scores. The proposed solution enhances biometric recognition performances based on suitable feature selection and reduction, such as principal component analysis (PCA) and linear discriminant analysis (LDA), as much as not all of the feature vectors components support the performance improvement degree.

• 한국컴퓨터정보학회논문지
• /
• 제19권11호
• /
• pp.43-52
• /
• 2014

본 논문에서는 적외선 영상에서 영상 변위를 이용하여 기동 표적 영역을 탐지하고, SURF(Speeded Up Robust Features) 특징점에 대한 BAS(Beam Angle Statistics)를 이용하여 분류하는 시스템에 대하여 설명한다. 영상 기반 기술 분야에서 대표적인 대응점 정합 알고리즘인 SURF 기법은 SIFT(Scale Invariant Feature Transform) 기법에 비해 정합 속도가 매우 빠르고 비슷한 정합 성능을 보이기 때문에 널리 사용되고 있다. SURF를 이용한 대부분의 객체 인식의 경우 특징점 추출과 정합의 과정을 수행하지만, 제안하는 기법은 표적의 기동 특성을 반영하여 영상의 변위 추정을 통하여 표적의 영역을 탐지하고 SURF 특징점 들의 기하구조를 판단함으로써 표적 분류를 수행한다. 제안하는 기법은 무인 표적 탐지/인지 시스템의 초기모델 구축을 위하여 연구가 진행되었으며, 모의 표적을 이용한 가상 영상과 적외선 실 영상을 이용하여 실험한 결과 약 73~85%의 분류 성능을 확인하였다.

• Journal of Information Processing Systems
• /
• 제14권5호
• /
• pp.1167-1175
• /
• 2018

Microarray data plays an essential role in diagnosing and detecting cancer. Microarray analysis allows the examination of levels of gene expression in specific cell samples, where thousands of genes can be analyzed simultaneously. However, microarray data have very little sample data and high data dimensionality. Therefore, to classify microarray data, a dimensional reduction process is required. Dimensional reduction can eliminate redundancy of data; thus, features used in classification are features that only have a high correlation with their class. There are two types of dimensional reduction, namely feature selection and feature extraction. In this paper, we used k-means algorithm as the clustering approach for feature selection. The proposed approach can be used to categorize features that have the same characteristics in one cluster, so that redundancy in microarray data is removed. The result of clustering is ranked using the Relief algorithm such that the best scoring element for each cluster is obtained. All best elements of each cluster are selected and used as features in the classification process. Next, the Random Forest algorithm is used. Based on the simulation, the accuracy of the proposed approach for each dataset, namely Colon, Lung Cancer, and Prostate Tumor, achieved 85.87%, 98.9%, and 89% accuracy, respectively. The accuracy of the proposed approach is therefore higher than the approach using Random Forest without clustering.

• International Journal of Quality Innovation
• /
• 제3권2호
• /
• pp.113-131
• /
• 2002

The relationships among multi-dimensional data (such as medical examination data) with ambiguity and variation are difficult to explore. The traditional approach to building a data classification system requires the formulation of rules by which the input data can be analyzed. The formulation of such rules is very difficult with large sets of input data. This paper first describes two classification approaches using back-propagation (BP) neural network and Mahalanobis distance (MD) classifier, and then proposes two classification approaches for multi-dimensional feature selection. The first one proposed is a feature selection procedure from the trained back-propagation (BP) neural network. The basic idea of this procedure is to compare the multiplication weights between input and hidden layer and hidden and output layer. In order to simplify the structure, only the multiplication weights of large absolute values are used. The second approach is Mahalanobis-Taguchi system (MTS) originally suggested by Dr. Taguchi. The MTS performs Taguchi's fractional factorial design based on the Mahalanobis distance as a performance metric. We combine the automatic thresholding with MD: it can deal with a reduced model, which is the focus of this paper In this work, two case studies will be used as examples to compare and discuss the complete and reduced models employing BP neural network and MD classifier. The implementation results show that proposed approaches are effective and powerful for the classification.

• 대한원격탐사학회지
• /
• 제15권1호
• /
• pp.39-50
• /
• 1999

위성에서 관측된 다 대역 위성영상 데이터를 이용목적에 따라 분류하기 위해서는 복잡한 처리과정과 많은 시간을 필요로 하며, 감독분류시 훈련 데이터의 선택과 고려되는 다양한 특징 값들은 분류 정확도를 좌우할 만큼 민감한 특성을 나타내고 있다. 따라서 본 논문에서는 훈련데이터의 선택과 다양한 특징 값들 중 실제 영상분류에 기여도가 높은 특징을 추출하기 위하여 퍼지 기반의 $\gamma$모델을 이용한 분류네트웍을 구성하였다. 훈련집합 선택시 분류하고자 하는 지역의 밝기 분포도, 텍스쳐 특징 그리고 NDVI(Normalized Difference Vegetation Index)를 분류에 사용될 특징으로 선택하였고, 분류네트웍 출력 값의 오류가 최소화 되도록 Gradient Desoent 방법을 이용하여 각 노드의 $\gamma$파라미터를 훈련시키는 과정을 채택하였다. 이러한 훈련을 통하여 얻어진 파라미터를 이용하면 각 노드의 연결특성을 알 수 있으며, 다양한 입력 노드의 특징들 중 영상분류에 기여도가 적은 특징들을 추출하여 제거할 수 있다.

• 한국군사과학기술학회지
• /
• 제13권4호
• /
• pp.683-688
• /
• 2010

The ability to navigate autonomously in off-road terrain is the most critical technology needed for Unmanned Ground Vehicles(UGV). In this paper, we present a method for vision-based terrain cover classification using DCT features. To classify the terrain, we acquire image from a CCD sensor, then the image is divided into fixed size of blocks. And each block transformed into DCT image then extracts features which reflect frequency band characteristics. Neural network classifier is used to classify the features. The proposed method is validated and verified through many experiments and we compare it with wavelet feature based method. The results show that the proposed method is more efficiently classify the terrain-cover than wavelet feature based one.

• 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.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.1281-1285
• /
• 2004

There are numerous emotions in the human world. Human expresses and recognizes their emotion using various channels. The example is an eye, nose and mouse. Particularly, in the emotion recognition from facial expression they can perform the very flexible and robust emotion recognition because of utilization of various channels. Hybrid-feature extraction algorithm is based on this human process. It uses the geometrical feature extraction and the color distributed histogram. And then, through the independently parallel learning of the neural-network, input emotion is classified. Also, for the natural classification of the emotion, advancing two-dimensional emotion space is introduced and used in this paper. Advancing twodimensional emotion space performs a flexible and smooth classification of emotion.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제13권1호
• /
• pp.73-82
• /
• 2013

In pattern classification, feature selection is an important factor in the performance of classifiers. In particular, when classifying a large number of features or variables, the accuracy and computational time of the classifier can be improved by using the relevant feature subset to remove the irrelevant, redundant, or noisy data. The proposed method consists of two parts: a wrapper part with an improved genetic algorithm(GA) using a new reproduction method and a filter part using mutual information. We also considered feature selection methods based on mutual information(MI) to improve computational complexity. Experimental results show that this method can achieve better performance in pattern recognition problems than other conventional solutions.