• 한국콘텐츠학회논문지
• /
• 제7권1호
• /
• pp.215-224
• /
• 2007

위성영상의 분류는 원격탐사의 가장 기본적인 분야이다. 위성영상분리도 위성영상의 분류에 있어 영상 정확도 향상에 매우 효율적이라 할 수 있다. 영상분류를 향상시키기 위해서 분리도의 특성을 파악하여 분류의 정확도와의 상관관계를 분석하였다. 영상은 영상마다의 분리도를 비교, 분석하기 위해 IKONOS 영상, SPOT 5 영상, Landsat IM 영상을 1m의 해상도로 리샘플링하였다. 본 연구에서 위성영상별로 클래스 분리도를 측정한 결과 분리도 값이 대체로 $1,600{\sim}2,000$으로 높게 나타났다.

• International Journal of Computer Science & Network Security
• /
• 제22권10호
• /
• pp.406-412
• /
• 2022

Scene classification of very high-resolution (VHR) imagery can attribute semantics to land cover in a variety of domains. Real-world application requirements have not been addressed by conventional techniques for remote sensing image classification. Recent research has demonstrated that deep convolutional neural networks (CNNs) are effective at extracting features due to their strong feature extraction capabilities. In order to improve classification performance, these approaches rely primarily on semantic information. Since the abstract and global semantic information makes it difficult for the network to correctly classify scene images with similar structures and high interclass similarity, it achieves a low classification accuracy. We propose a VHR remote sensing image classification model that uses extracts the global feature from the original VHR image using an EfficientNet-V2L CNN pre-trained to detect similar classes. The image is then classified using a multilayer perceptron (MLP). This method was evaluated using two benchmark remote sensing datasets: the 21-class UC Merced, and the 38-class PatternNet. As compared to other state-of-the-art models, the proposed model significantly improves performance.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 춘계학술대회
• /
• pp.444-447
• /
• 2022

최근 몇 년 동안 더 깊은 신경망 아키텍처로 인해 컴퓨터 비전 이미지 분류 작업이 더 빠르고 더 좋아졌다. 그러나 대부분의 이미지 분류 작업은 특정 이미지 모양(예: 고양이와 개 구별)을 기반으로 분류하도록 설계되었지만 낮과 밤 또는 사계절과 같은 기간을 구별하도록 훈련된 분류 모델은 많지 않다. 같은 장소의 사계절 이미지를 구분하기 위한 선행 연구는 있는 반면 일반 영상의 계절 분류 연구는 현재 부재한 실정이다. 그래서 본 논문에서는 일반 영상의 계절 분류 문제에 대한 다양한 접근 방식을 제시한다. 간단한 특징 추출부터 합성곱 신경망 구축, 전이 학습에 이르기까지 계절별 이미지 분류를 위한 세 가지 방법을 연구하고 정확도 결과를 비교, 분석하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권3호
• /
• pp.591-609
• /
• 2024

In this study, preprocessings with all combinations were examined in terms of the effects on decreasing word number, shortening the duration of the process and the classification success in balanced and imbalanced datasets which were unbalanced in different ratios. The decreases in the word number and the processing time provided by preprocessings were interrelated. It was seen that more successful classifications were made with Turkish datasets and English datasets were affected more from the situation of whether the dataset is balanced or not. It was found out that the incorrect classifications, which are in the classes having few documents in highly imbalanced datasets, were made by assigning to the class close to the related class in terms of topic in Turkish datasets and to the class which have many documents in English datasets. In terms of average scores, the highest classification was obtained in Turkish datasets as follows: with not applying lowercase, applying stemming and removing stop words, and in English datasets as follows: with applying lowercase and stemming, removing stop words. Applying stemming was the most important preprocessing method which increases the success in Turkish datasets, whereas removing stop words in English datasets. The maximum scores revealed that feature selection, feature size and classifier are more effective than preprocessing in classification success. It was concluded that preprocessing is necessary for text classification because it shortens the processing time and can achieve high classification success, a preprocessing method does not have the same effect in all languages, and different preprocessing methods are more successful for different languages.

• International Journal of Computer Science & Network Security
• /
• 제24권2호
• /
• pp.150-154
• /
• 2024

In recent years, there are extensive researches on the applications of machine learning to the automation and decision support for medical experts during disease detection. However, the performance of machine learning still needs improvement so that machine learning model produces result that is more accurate and reliable for disease detection. Selecting the hyper-parameter that could produce the possible maximum classification accuracy on medical dataset is the most challenging task in developing decision support systems with machine learning algorithms for medical dataset classification. Moreover, selecting the features that best characterizes a disease is another challenge in developing machine-learning model with better classification accuracy. In this study, we have proposed an optimized decision tree model for heart disease classification by using heart disease dataset collected from kaggle data repository. The proposed model is evaluated and experimental test reveals that the performance of decision tree improves when an optimal number of features are used for training. Overall, the accuracy of the proposed decision tree model is 98.2% for heart disease classification.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2001년도 제14회 신호처리 합동 학술대회 논문집
• /
• pp.619-622
• /
• 2001

In this paper, an efficient approach to classification of transient and harmonic disturbances in power systems is proposed. First, the Stop-and-Go CA CFAR Detector is utilized to detect a disturbance from the power signals which are mixed with other disturbances and noise. Then, (i) Wigner Distribution, SVD(Singular Value Decomposition) and Fisher´s Criterion (ii) DWT and Fisher´s Criterion, are applied to extract an efficient feature vector. For the classification procedure, a combined neural network classifier is proposed to classify each corresponding disturbance class. Finally, the 10 class data simulated by Matlab power system blockset are used to demonstrate the performance of the proposed classification system.

• 전기학회논문지
• /
• 제56권7호
• /
• pp.1224-1230
• /
• 2007

In this paper, we study the classification of defects at steam generator tube in nuclear power plant using eddy current testing (ECT). We consider 4 defect patterns of SG tube: I-In type, I-Out type, V-In type, and V-Out type. Through numerical analysis program based on finite element modeling, 400 ECT signals are generated by varying width and depth of each defect type. In order to improve the classification performance, we propose new feature extraction technique. After extracting new features from the generated ECT signals, multi-layer perceptron is used to classify the defect patterns. Through the computer simulation study, it is shown that the proposed method achieves 100% classification success rate while the previous method yields 91% success rate.

• 전자공학회논문지B
• /
• 제30B권6호
• /
• pp.67-75
• /
• 1993

ECG pattern was classified using a back-propagation neural network. An improved feature extractor of ECG is proposed for better classification capability. It is consisted of preprocessing ECG signal by an FIR filter faster than conventional one by a factor of 5. QRS complex recognition by moving-window integration, and peak extraction by quadratic approximation. Since the FIR filter had a periodic frequency spectrum, only one-fifth of usual processing time was required. Also, segmentation of ECG signal followed by quadratic approximation of each segment enabled accurate detection of both P and T waves. When improtant features were extracted and fed into back-propagation neural network for pattern classification, the required number of nodes in hidden and input layers was reduced compared to using raw data as an input, also reducing the necessary time for study. Accurate pattern classification was possible by an appropriate feature selection.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2002년도 Proceedings of International Symposium on Remote Sensing
• /
• pp.23-28
• /
• 2002

Among effective feature extraction methods from the small-patched image set, independent component analysis (ICA) is recently well known stochastic manner to find informative basis images. The ICA simultaneously learns both basis images and independent components using high order statistic manners, because that information underlying between pixels are sensitive to high-order statistic models. The topographic ICA model is adapted in our experiment. This paper deals with an unsupervised classification strategies using learned ICA basis images. The experimental result by proposed classification technique shows superior performance than classic texture analysis techniques for the panchromatic KOMPSAT imagery.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.1307-1309
• /
• 2003

The EO-1 spacecraft, launched November 21, 2000 into a sun synchronous orbit behind Landsat 7, hosts advanced technology demonstration instruments, whose capabilities are currently being assessed by the user community for future missions. A significant part of the EO-1 program is to perform data comparisons between Hyperion, ALI and Landsat 7 ETM+. In this paper, a comparison of forest classification results from Hyperion, ALI, and the ETM+ of Landsat-7 are provided for Wangqing Forest Bureau, Jilin Province, Northeast China. The data have been radiometrically corrected and geometrically resampled. Feature selection and statistical transforms are used to reduce the Hyperion feature space from 86 channels to 14 features. Classes chosen for discrimination included Larch, Spruce, Oak, Birch, Popular and Mixed forest and other landuses. Classification accuracies have been obtained for each sensor. Comparison of the classification results shows : Hyperion classification results were the best, ALI's were much better than ETM+.