• 대한전기학회논문지:시스템및제어부문D
• /
• 제52권1호
• /
• pp.45-50
• /
• 2003

Texture analysis has been efficiently utilized in the area of terrain classification. In this application features have been obtained in the 2D image domain. This paper suggests 3D co-occurrence texture features by extending the concept of co-occurrence to 3D world. The suggested 3D features are described using co-occurrence histogram of digital elevations at two contiguous position as co-occurrence matrix. The practical construction of co-occurrence matrix limits the number of levels of digital elevation. If the digital elevation is quantized into the number of levels over the whole DEM(Digital Elevation Map), the distinctive features can not be obtained. To resolve the quantization problem, we employ local quantization technique which preserves the variation of elevations. Experiments has been carried out to verify the proposed 3D co-occurrence features, and the addition of the suggested features significantly improves the classification accuracy.

• Asian Journal of Innovation and Policy
• /
• 제8권1호
• /
• pp.73-96
• /
• 2019

This study suggests a new approach for identifying core robot tech-nologies based on technological cross-impact. Specifically, the approach applies data mining techniques and multi-criteria decision-making methods to the co-classification information of registered patents on the robots. First, a cross-impact matrix is constructed with the confidence values by applying association rule mining (ARM) to the co-classification information of patents. Analytic network process (ANP) is applied to the co-classification frequency matrix for deriving weights of each robot technology. Then, a technique for order performance by similarity to ideal solution (TOPSIS) is employed to the derived cross-impact matrix and weights for identifying core robot technologies from the overall cross-impact perspective. It is expected that the proposed approach could help robot technology managers to formulate strategy and policy for technology planning of robot area.

• 신재생에너지
• /
• 제7권1호
• /
• pp.36-44
• /
• 2011

Technology is developed from the efficient interaction with other technology files while building up its own research field. This study analyzes the structure of solar cell research area and describes its paths of the technology development in terms of interdisciplinary diversity using the Co-Classification method during 1979-2009. As a results, 1,380 studies are determined as the interdisciplinary among the 2,605 studies. It shows that 52.98% of the solar cell researches have interdisciplinary relationships with two or more research fields. In addition, we show that the research area of solar cell technology is composed by Material Science, Multidisciplinary and Energy & Fuel, Physics, Applied, Chemistry, Physical from the Co-Classification matrix and network analysis. It means the complexity of the technological knowledge production increased with the concept of interdisciplinary. The results can be used for the planning of the efficient solar cell technology development.

• Computers and Concrete
• /
• 제4권3호
• /
• pp.243-257
• /
• 2007

A novel method for recognition, characterization, and quantification of deterioration in bridge components and laboratory concrete samples is presented in this paper. The proposed scheme is based on grey level co-occurrence matrix texture analysis using Haar's discrete wavelet transform on concrete imagery. Each image is described by a subset of band-filtered images containing wavelet coefficients, and then reconstructed images are employed in characterizing the texture, using grey level co-occurrence matrices, of the different types and degrees of damage: map-cracking, spalling and steel corrosion. A comparative study was conducted to evaluate the efficiency of the supervised maximum likelihood and unsupervised K-means classification techniques, in order to classify and quantify the deterioration and its extent. Experimental results show both methods are relatively effective in characterizing and quantifying damage; however, the supervised technique produced more accurate results, with overall classification accuracies ranging from 76.8% to 79.1%.

• IEIE Transactions on Smart Processing and Computing
• /
• 제5권1호
• /
• pp.43-48
• /
• 2016

We propose plain fingerprint classification based on a core stochastic algorithm that effectively uses a core stochastic model, acquiring more fingerprint minutiae and direction, in order to increase matching performance. The proposed core stochastic algorithm uses core presence/absence and contains a ridge direction and distribution map. Simulations show that the fingerprint classification accuracy is improved by more than 14%, on average, compared to other algorithms.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제31권8호
• /
• pp.991-998
• /
• 2004

생물 정보학 등 많은 응용 분야에서 데이타 분석을 할 때는 적은 수의 분류표시된 데이터 (labeled data)와 많은 수의 비분류표시된 데이타(unlabeled data)가 있을 수 있다 분류표시된 자료는 사람의 노력이 요구되기 때문에 얻기가 어렵고 비용이 많이 들지만, 비분류표시된 자료는 별 어려움 없이 쉽게 얻을 수 있다. 이때 비분류표시된 자료를 이용하여 자료를 분류하고 분석하는데 널리 이용되고 있는 방법이 co-training 알고리즘이다. 이 방법은 적은 수의 분류표시된 자료에서 두 가지 뷰(view)로 각 분류자를 학습한다. 그리고 각 분류자는 분석하고자 하는 모든 비분류표시된 자료에서 가장 만족할만한 예측자들을 만들어 나간다. 이렇게 훈련 데이타 셋에서 실험을 여러 번 반복적으로 하게 되면 각 뷰에서 새로운 분류자가 학습되어 분류표시된 자료의 수가 증가한다. 본 논문에서는 비분류표시된 데이타를 이용하여 새로운 co-training 방법을 제시한다. 이 방법은 두 가지 분류자와 WebKB 및 BIND XML의 2가지 실험 데이타를 가지고 평가하였다. 실험 결과로서, 이 논문에서 제안한 co-training 방법이 분류표시된 자료의 수가 매우 적을 때 분류정확성을 효과적으로 향상시킬 수 있음을 보였다.

• Communications for Statistical Applications and Methods
• /
• 제29권5호
• /
• pp.603-614
• /
• 2022

The naive Bayes classifier is one of the most straightforward classification tools and directly estimates the class probability. However, because it relies on the independent assumption of the predictor, which is rarely satisfied in real-world problems, its application is limited in practice. In this article, we propose employing sufficient dimension reduction (SDR) to substantially improve the performance of the naive Bayes classifier, which is often deteriorated when the number of predictors is not restrictively small. This is not surprising as SDR reduces the predictor dimension without sacrificing classification information, and predictors in the reduced space are constructed to be uncorrelated. Therefore, SDR leads the naive Bayes to no longer be naive. We applied the proposed naive Bayes classifier after SDR to build a recommendation system for the eyewear-frames based on customers' face shape, demonstrating its utility in the top-k classification problem.

• 한국레이저가공학회지
• /
• 제5권3호
• /
• pp.21-30
• /
• 2002

In automotive industry, the studies about light weight vehicle and improving the productivity have been accomplished. For that, TRIP steel was developed and research for the laser welding process have been performed. In this study, the monitoring system using photodiode was developed for laser welding process of TRIP steel. With measuring light, neural network model for estimating bead width and tensile strength was made and weld quality classification algorithm was formulated with fuzzy inference method.

• 한국지구물리탐사학회:학술대회논문집
• /
• 한국지구물리탐사학회 2005년도 제7회 특별심포지움 논문집
• /
• pp.37-42
• /
• 2005

우리나라 지형 여건 상 도로나 철도의 시공에는 터널이 포함되는 경우가 많다. 이 경우 터널의 미시추 구간에 대한 암반분류 도출에는 물리탐사가 유력한 수단이 된다. 탄성파 속도에 근거한 암반분류는 터널의 계획고가 깊을 경우 지표 및 시추공을 동시에 이용하는 대심도 토모그래피 기법이 적합하나 대심도 토모그래피 결과는 현재 국내에서 적용되고 있는 암반분류 기준으로 하면 통상 실제보다 암질을 양호하게 평가하는 경향이 있다. 본 연구에서는 암반상태와 탄성파 속도와의 상관관계를 보다 합리적으로 결정하기 위한 방법의 일환으로 셈블런스에 근거한 탄성파 기준속도비를 이용하는 암반분류방법을 제안하고 아울러 현장자료를 이용하여 그의 적용성을 고찰하였다.

• 시스템엔지니어링학술지
• /
• 제17권2호
• /
• pp.91-97
• /
• 2021

User interface for cancer classification system is a software application with clinician's friendly tools and functions to diagnose cancer from pathology images. Pathology evolved from manual diagnosis to computer-aided diagnosis with the help of Artificial Intelligence tools and algorithms. In this paper, we explained each block of the project life cycle for the implementation of automated breast cancer classification software using AI and machine learning algorithms to classify normal and invasive breast histology images. The system was designed to help the pathologists in an automatic and efficient diagnosis of breast cancer. To design the classification model, Hematoxylin and Eosin (H&E) stained breast histology images were obtained from the ICIAR Breast Cancer challenge. These images are stain normalized to minimize the error that can occur during model training due to pathological stains. The normalized dataset was fed into the ResNet-34 for the classification of normal and invasive breast cancer images. ResNet-34 gave 94% accuracy, 93% F Score, 95% of model Recall, and 91% precision.