• 방송공학회논문지
• /
• 제18권5호
• /
• pp.771-774
• /
• 2013

본 연구는 감정상태와 음색특성의 관계를 확인하고, 추가로 cepstral 피쳐와 조합하여 감정인식을 진행하였다. Open quotient, harmonic-to-noise ratio, spectral tilt, spectral sharpness를 포함하는 특징들을 음색검출을 위해 적용하였고, 일반적으로 사용되는 피치와 에너지를 기반한 운율피쳐를 적용하였다. ANOVA분석을 통해 각 특징벡터의 유효성을 살펴보고, sequential forward selection 방법을 적용하여 최종 감정인식 성능을 분석하였다. 결과적으로, 제안된 피쳐들으로부터 성능이 향상되는 것을 확인하였고, 특히 화남과 기쁨에 대하여 에러가 줄어드는 것을 확인하였다. 또한 음색관련 피쳐들이 cepstral 피쳐와 결합할 경우 역시 인식 성능이 향상되었다.

• 한국컴퓨터정보학회논문지
• /
• 제27권5호
• /
• pp.77-84
• /
• 2022

본 논문에서는 새로운 비지도 특징 선별 기법을 제안한다. 기존 비지도 방식의 특징 선별 기법들은 특징을 선별하기 위해 가상의 레이블 데이터를 정하고 주어진 데이터를 이 레이블 데이터에 사영하는 회귀 분석 방식으로 특징을 선별하였다. 하지만 가상의 레이블은 데이터로부터 생성되기 때문에 사영된 공간이 비슷하게 형성될 수 있다. 따라서 기존의 방법들에서는 제한된 공간에서만 특징이 선택될 수 있었다. 이를 해소하기 위해 본 논문에서는 직교 사영과 저랭크 근사를 이용하여 특징을 선별한다. 이 문제를 해소하기 위해 가상의 레이블을 직교 사영하고 이 공간에 데이터를 사영할 수 있도록 한다. 이를 통해 더 주요한 특징 선별을 기대할 수 있다. 그리고 사영을 위한 변환 행렬에 저랭크 제한을 두어 더 효과적으로 저차원 공간의 특징을 선별할 수 있도록 한다. 이 목표를 달성하기 위해 본 논문에서는 비용 함수를 설계하고 효율적인 최적화 방법을 제안한다. 여섯 개의 데이터에 대한 실험 결과는 제안된 방법이 대부분의 경우 기존의 비지도 특징 선별 기법보다 좋은 성능을 보여주었다.

• 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.

• ETRI Journal
• /
• 제34권5호
• /
• pp.743-752
• /
• 2012

Semantic interpretation of the relationship between noun compound (NC) elements has been a challenging issue due to the lack of contextual information, the unbounded number of combinations, and the absence of a universally accepted system for the categorization. The current models require a huge corpus of data to extract contextual information, which limits their usage in many situations. In this paper, a new semantic relations interpreter for NCs based on novel lightweight binary features is proposed. Some of the binary features used are novel. In addition, the interpreter uses a new feature selection method. By developing these new features and techniques, the proposed method removes the need for any huge corpuses. Implementing this method using a modular and plugin-based framework, and by training it using the largest and the most current fine-grained data set, shows that the accuracy is better than that of previously reported upon methods that utilize large corpuses. This improvement in accuracy and the provision of superior efficiency is achieved not only by improving the old features with such techniques as semantic scattering and sense collocation, but also by using various novel features and classifier max entropy. That the accuracy of the max entropy classifier is higher compared to that of other classifiers, such as a support vector machine, a Na$\ddot{i}$ve Bayes, and a decision tree, is also shown.

• 한국의학물리학회지:의학물리
• /
• 제34권3호
• /
• pp.23-32
• /
• 2023

Purpose: In radiomics analysis, to evaluate features, and predict genetic characteristics and survival time, the pixel values of lesions depicted in computed tomography (CT) and magnetic resonance imaging (MRI) images are used. CT and MRI offer three-dimensional images, thus producing three-dimensional features (Features_3d) as output. However, in reports, the superiority between Features_3d and two-dimensional features (Features_2d) is distinct. In this study, we aimed to investigate whether a difference exists in the prediction accuracy of radiomics analysis of lung cancer using Features_2d and Features_3d. Methods: A total of 38 cases of large cell carcinoma (LCC) and 40 cases of squamous cell carcinoma (SCC) were selected for this study. Two- and three-dimensional lesion segmentations were performed. A total of 774 features were obtained. Using least absolute shrinkage and selection operator regression, seven Features_2d and six Features_3d were obtained. Results: Linear discriminant analysis revealed that the sensitivities of Features_2d and Features_3d to LCC were 86.8% and 89.5%, respectively. The coefficients of determination through multiple regression analysis and the areas under the receiver operating characteristic curve (AUC) were 0.68 and 0.70 and 0.93 and 0.94, respectively. The P-value of the estimated AUC was 0.87. Conclusions: No difference was found in the prediction accuracy for LCC and SCC between Features_2d and Features_3d.

• 디지털산업정보학회논문지
• /
• 제20권2호
• /
• pp.1-10
• /
• 2024

For the purpose of predicting credit card customer churn accurately through data analysis, a model can be constructed with various machine learning algorithms, including decision tree. And feature importance has been utilized in selecting better input features that can improve performance of data analysis models for several application areas. In this paper, a method of utilizing feature importance calculated from the MDI method and its effects are investigated in the credit card customer churn prediction problem with classification trees. Compared with several random feature selections from case data, a set of input features selected from higher value of feature importance shows higher predictive power. It can be an efficient method for classifying and choosing input features necessary for improving prediction performance. The method organized in this paper can be an alternative to the selection of input features using feature importance in composing and using classification trees, including credit card customer churn prediction.

• 로봇학회논문지
• /
• 제9권2호
• /
• pp.117-123
• /
• 2014

Localization is one of the essential tasks necessary to achieve autonomous navigation of a mobile robot. One such localization technique, Monte Carlo Localization (MCL) is often applied to a digital surface model. However, there are differences between range data from laser rangefinders and the data predicted using a map. In this study, commonly observed from air and ground (COAG) features and candidate selection based on the shape of sensor data are incorporated to improve localization accuracy. COAG features are used to classify points consistent with both the range sensor data and the predicted data, and the sample candidates are classified according to their shape constructed from sensor data. Comparisons of local tracking and global localization accuracy show the improved accuracy of the proposed method over conventional methods.

• 한국지능시스템학회논문지
• /
• 제8권3호
• /
• pp.16-25
• /
• 1998

본 논문에서는 초 다중 밴드 환경의 효과적인 데이터 분류를 위해서 Roungh 집합 이론을 이용한 특징 추출 방법을 제안한다. 다중 분광 이미지 데이터의 특성을 분석하고, 그 분석 결과를 토대로 Rough집합이론의 식별 능력을 이용하여 가장 효과적인 밴드를 선택할 수 있도록 한다. 실험으로는 Landsat TM으로부터 취득한 데이터에 적용시켰으며, 이를 통해 전통적인 밴드 특성에 의한 밴드 선택 방법과 본 논문에서 제안하는 러프 집합 이론을 이용한 밴드 선택 방법이 일치됨을 보이고 이를 통해 초다중 밴드 환경에서의 특징 추출에 대한 이론적 근거를 제시한다.

• 한국컴퓨터정보학회논문지
• /
• 제5권3호
• /
• pp.215-219
• /
• 2000

The purpose of this paper is to propose a method to maximize the efficiency of a content-based image retrieval for various kinds of images. This paper discuss the self-adaptivity for the change of image domain and the self-selection of optimal features for query image, and present the efficient method to maximize content-based retrieval for various kinds of images. In this method, a content-based retrieval system is adopted to select automatically distinctive feature patterns which have a maximum efficiency of image retrieval in various kinds of images. Experimental results show that the Proposed method is improved 3% than the method using individual features.

• 디지털융복합연구
• /
• 제12권6호
• /
• pp.223-229
• /
• 2014

대용량의 지식베이스 시스템에서 유용한 정보를 추출하여 효율적인 의사결정을 수행하기 위해서는 정제된 특징추출이 필수적이고 중요한 부분이다. 러프집합이론에 있어서 최적의 리덕트의 추출과 효율적인 객체의 분류에 대한 문제점을 극복하고 자, 본 연구에서는 조건 및 결정속성의 효율적인 특징추출을 위한 러프엔트로피 기반 퀵리덕트 알고리듬을 제안한다. 제안된 알고리듬에 의해 유용한 특징을 추출하기 위한 조건부 정보엔트로피를 정의하여 중요한 특징들을 분류하는 과정을 기술한다. 또한 본 연구의 적용사례로써 실제로 UCI의 5개의 데이터에 적용하여 특징을 추출하는 시뮬레이션을 통하여 본 연구의 모델링이 기존의 방법과 비교결과, 제안된 방법이 효율성이 있음을 보인다.