• 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.

• 한국컴퓨터정보학회논문지
• /
• 제20권11호
• /
• pp.9-16
• /
• 2015

We propose a hybrid pattern recognition method that effectively combines two different features for improving data classification. We first extract the PCA (Principal Component Analysis) and LDA (Linear Discriminant Analysis) features, both of which are widely used in pattern recognition, to construct a set of basic features, and then evaluate the separability of each basic feature. According to the results of evaluation, we select only the basic features that contain a large amount of discriminative information for construction of the combined features. The experimental results for the various data sets in the UCI machine learning repository show that using the proposed combined features give better recognition rates than when solely using the PCA or LDA features.

• 대한의용생체공학회:의공학회지
• /
• 제21권2호
• /
• pp.137-144
• /
• 2000

Clustered microcalcifications in X-ray mammograms are an important sign for the diagnosis of breast cancer. A shape-based method, which is based on the morphological features of clustered microcalcifications, is proposed for classifying clustered microcalcifications into benign or malignant categories. To verify the effectiveness of the proposed shape features, clinical mammograms were used to compare the classification performance of the proposed shape features with those of conventional textural features, such as the spatial gray-leve dependence method and the wavelet-based method. Image features extracted from these methods were used as inputs to a three-layer backpropagation neural network classifier. The classification performance of features extracted by each method was studied by using receiver operating-characteristics analysis. The proposed shape features were shown to be superior to the conventional textural features with respect to classification accuracy.

• 한국실내디자인학회논문집
• /
• 제24권6호
• /
• pp.128-136
• /
• 2015

This research, which has been planned to appreciate the features of continuous observation of space, has applied the procedure of acquiring continuous visual information when the act of watching takes place along the time to analyze the space characteristics through the scenes and time so that the features of attention shown in the process of acquiring visual information at the time of observing continuous scenes might be estimated. For analysis of the features of continuous observation was set up the premise that the features of observation and perception vary depending on gender, when the women shops in department stores were selected as research objects. The observation features found at the time of continuous observation of selling spaces in department stores were focused on two analysis methods in order to compare the differences and characteristics of the two. The followings are the findings. First, the area with predominant observation was found to be 87.1% in both methods. It was found that the analysis of observation features by "Analysis I" was useful for inter-sectional comparison of continuous images. Second, in case of extracting predominant sections, the ceiling or the structures which are the backgrounds rarely attracted any eyes. Depending on analysis method, there was the gap of 14.3%~25.0% between observed sections. Third, in case that the hall is curved, the eyes were found to be expanded from side to side and up and down. The review of observation numbers of predominant sections makes it possible to decide whether it should be regarded as (1) unstability or (2) expanding search, and when the images are enlarged from distant view to close-range view, the weakening vanishing point results in the increase of expanded search of surroundings. Accordingly, it was found that the characteristics of images has effects on the observation features when any space was continuously observed. Furthermore, the difference of analysis methods also was found to be likely to cause big differences in the results of analyzing observation features.

• Communications for Statistical Applications and Methods
• /
• 제22권5호
• /
• pp.415-434
• /
• 2015

In this paper we overview the literature on common features analysis of economic time series. Starting from the seminal contributions by Engle and Kozicki (1993) and Vahid and Engle (1993), we present and discuss the various notions that have been proposed to detect and model common cyclical features in macroeconometrics. In particular, we analyze in details the link between common cyclical features and the reduced-rank regression model. We also illustrate similarities and differences between the common features methodology and other popular types of multivariate time series modelling. Finally, we discuss some recent developments in this area, such as the implications of common features for univariate time series models and the analysis of common autocorrelation in medium-large dimensional systems.

• 한국멀티미디어학회논문지
• /
• 제11권12호
• /
• pp.1635-1648
• /
• 2008

The extraction of important features in cancer cell image analysis is a key process in grading renal cell carcinoma. In this study, we applied three-dimensional (3D) texture feature extraction methods to cell nuclei images and evaluated the validity of them for computerized cell nuclei grading. Individual images of 2,423 cell nuclei were extracted from 80 renal cell carcinomas (RCCs) using confocal laser scanning microscopy (CLSM). First, we applied the 3D texture mapping method to render the volume of entire tissue sections. Then, we determined the chromatin texture quantitatively by calculating 3D gray-level co-occurrence matrices (3D GLCM) and 3D run length matrices (3D GLRLM). Finally, to demonstrate the suitability of 3D texture features for grading, we performed a discriminant analysis. In addition, we conducted a principal component analysis to obtain optimized texture features. Automatic grading of cell nuclei using 3D texture features had an accuracy of 78.30%. Combining 3D textural and 3D morphological features improved the accuracy to 82.19%. As a comparative study, we also performed a stepwise feature selection. Using the 4 optimized features, we could obtain more improved accuracy of 84.32%. Three dimensional texture features have potential for use as fundamental elements in developing a new nuclear grading system with accurate diagnosis and predicting prognosis.

• Spatial Information Research
• /
• 제6권1호
• /
• pp.11-23
• /
• 1998

GIS 분야에서 지도 일반화는 공간자료의 상세도를 결정하여 효과적으로 자료를 가시화(Visualixation)하거나 자료의 해상력을 변화시켜 변환하는 기능을 수행한다. 최근까지 지도 일반화는 선사상 (Line Features)에 집중되었고, 수치지도를 구성하고 있는 정보량과 그 중요성에 비하여 점사상 (Point Features)에 대한 연구는 상대적으로 미미하였다. 이러한 맥락에서 본 연구는 점사상에 대한 구체적인 일반화 방안을 모색하는데 목적을 둔다. 특히 점사상의 일반화에서 원자료의 기하학적 특성을 파악하는데 가장 중요하게 고려한 요소로 점사상의 분포패턴을 선정하였다. 즉 'Grieg-Smith방법'을 활용한 방격분석 (Quadrat Analysis)과 최근린분석 (Nearest-Neighbour Analysis)를 통해 점사상이 갖고 있는 분포패턴의 특성을 찾아낸 다음, 이를 변형시키지 않도록 일반화의 기준거리(Threshold)를 설정하여 점사상을 제거하는 방법을 통해 점사상의 일반화를 시도하였다. 따라서 이 연구에서 제시한 점사상의 일반화 방안은 원래 점사상이 갖고 있는 기하학적 특성을 최대한 유지한다.

• 한국지리정보학회지
• /
• 제8권3호
• /
• pp.84-95
• /
• 2005

본 논문은 가시권역의 최대화를 만족하는 가시권 분석에 있어 지형요소가 어떻게 이용될 수 있으며 이러한 최적 다중 가시점 탐색 문제에 있어 지형요소의 이용이 얼마나 효과적인지를 살펴보는 연구이다. 이를 위하여 다양한 지형상태를 반영하는 지역의 DEM 자료와 각 DEM자료에 대한 지형요소 (peak, pass, pit)의 특정을 반영한 여섯 종류의 탐색방법을 제시하고 전통적인 공간 휴리스틱 (spatial heuristic)과의 비교 분석 (계산 시간과 총 가시권역 크기)을 통해서 지형요소를 이용한 방법의 효율성과 적용 가능성을 살펴보았다. 연구결과로써, 가시구역의 중복을 최소화하기 위해 제시된 버퍼링을 이용한 방법의 경우, 비록 공간 휴리스틱 방법에 비해 적은 가시구역 면적을 제시하였지만, 컴퓨팅 시간적인 측면에서 많은 이점을 제공하고 있음을 볼 수 있다. 또한 연구지역의 DEM상의 각각의 개별 그리드 셀을 대상으로 전체 DEM에 대해 계산된 가시구역을 이용한 방법의 경우, 비록 부가적인 계산 시간이 소요됨에도 불구하고 단순한 지형요소를 이용한 방법보다 향상된 분석 결과를 제시하였음을 알 수 있다.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제8권8호
• /
• pp.343-348
• /
• 2019

최근의 문서요약 시스템은 인공신경망을 이용한 End-to-End 방식이 주류를 이루고 있다. 이러한 시스템은 인간의 자질 추출 과정이 필요 없으며 데이터 중심의 접근 방법을 채택한다. 그러나 기존의 관련 연구들은 품사 정보, 개체명 정보, 단어의 빈도 정보와 같은 언어 분석 자질이 중요 문장을 선택하여 요약을 작성하는데 유용함을 보여왔다. 본 연구에서는 기존의 언어 분석 자질을 활용하여 인공신경망을 기반으로 한 단일 문서의 추출 요약 시스템을 제안한다. 언어 분석 자질의 유용성을 보이기 위해 자질을 사용하는 모델과 사용하지 않는 모델을 비교하였다. 실험 결과 자질을 사용하는 모델이 그렇지 않은 모델에 비해 약 0.5점의 Rouge-2 F1점수 향상을 보였다.

• ETRI Journal
• /
• 제38권3호
• /
• pp.494-501
• /
• 2016

Sentiment analysis incorporates natural language processing and artificial intelligence and has evolved as an important research area. Sentiment analysis on product reviews has been used in widespread applications to improve customer retention and business processes. In this paper, we propose a method for performing an intensified sentiment analysis on customer product reviews. The method involves the extraction of two feature sets from each of the given customer product reviews, a set of acoustic features (representing emotions) and a set of lexical features (representing sentiments). These sets are then combined and used in a supervised classifier to predict the sentiments of customers. We use an audio speech dataset prepared from Amazon product reviews and downloaded from the YouTube portal for the purposes of our experimental evaluations.