• 대한전기학회논문지
• /
• 제43권7호
• /
• pp.1193-1205
• /
• 1994

This paper presents a fuzzy system that adaptively classifies subimages to four classes according to image activity distribution. In adaptive transform image coding, subimage classification improves the compression performance by assigning different bit maps to different classes. A conventional classification method sorts subimages by their AC energy and divides them to classes with equal number of subimages. The fuzzy system provides more flexible classification to natural images with various distribution of image details than does the conventional method. Clustering of training data in the input-output product space generated the fuzzy rules for subimage classification. The fuzzy system of small number of fuzzy rules successfully classified subimages to improve the compression performance of the transform image coding without sorting of AC energies.

• 한국지능시스템학회논문지
• /
• 제2권2호
• /
• pp.42-60
• /
• 1992

An adaptive fuzzy system can efficiently classify subimages into four categories according to image activity level for image data compression. The system estimates fuzzy rules by clustering input-output data generated from a given adaptive transform image coding process. The system encodes different images without modification and reduces side information when encoding multiple images. In the second part, a fuzzy system estimates optimal bit maps for the four subimage classes in noisy channels assuming a Gauss-Markov image model. The fuzzy systems respectively estimate the sampled subimage classification and the bit-allocation processes without a mathematical model of how outputs depend on inputs and without rules articulated by experts.

• 대한산업공학회지
• /
• 제17권2호
• /
• pp.17-26
• /
• 1991

This paper discusses an expert system to generate part codes and construct part families, ESPCC, for the group technology application. The ESPCC, that is developed by using VP-Expert rule-based expert system development tool, embodies the specific knowledge of human experts to determine part codes consistent with the OPITZ classification and coding system. The ESPCC is implemented on an IBM compatible personal computers running MS-DOS.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권7호
• /
• pp.3286-3300
• /
• 2016

High Efficiency Video Coding (HEVC) Standard, as the latest coding standard, introduces satisfying compression structures with respect to its predecessor Advanced Video Coding (H.264/AVC). The new coding standard can offer improved encoding performance compared with H.264/AVC. However, it also leads to enormous computational complexity that makes it considerably difficult to be implemented in real time application. In this paper, based on machine learning, a fast partitioning method is proposed, which can search for the best splitting structures for Intra-Prediction. In view of the video texture characteristics, we choose the entropy of Gray-Scale Difference Statistics (GDS) and the minimum of Sum of Absolute Transformed Difference (SATD) as two important features, which can make a balance between the computation complexity and classification performance. According to the selected features, adaptive decision trees can be built for the Coding Units (CU) with different size by offline training. Furthermore, by this way, the partition of CUs can be resolved as a binary classification problem. Experimental results have shown that the proposed algorithm can save over 34% encoding time on average, with a negligible Bjontegaard Delta (BD)-rate increase.

• 공학교육연구
• /
• 제17권4호
• /
• pp.43-47
• /
• 2014

The rapid development of science & technology and the globalization of society have accelerated the fractionation and specialization of academic disciplines. Accordingly, Korean colleges and universities are continually dropping antiquated courses to make room for new courses that better meet societal demands. With emphasis placed on providing students with a broader range of choices in terms of course selection, compulsory courses have given way to elective courses. On average, 4 year institutions of higher learning in Korea currently offer somewhere in the neighborhood of 1,000 different courses yearly. The classification of an ever growing list of courses offered and the practical use of such data would not be possible without the aid of computers. For example, if we were able to show the pre/post requisite relationship among various courses as well as the commonalities in substance among courses, such data generated regarding the interrelationship of different courses would undoubtedly greatly benefit the students, as well as the professors, during course registration. Furthermore, the GT system's relatively simple approach to course classification and coding will obviate the need for the development of a more complicated keyword based search engine, and hopefully contribute to the standardization of the course coding scheme in the future..Therefore, as a sample case project, this study will use GT to classify and code all courses offered at the College of Engineering of K University, thereby developing a system that will facilitate the scanning of relevant courses.

• Communications for Statistical Applications and Methods
• /
• 제14권2호
• /
• pp.377-388
• /
• 2007

As one of multi-class classification methods, ECOC (Error Correcting Output Coding) method is known to have low classification error rate. This paper aims at suggesting effective multi-class classification method (1) by comparing various encoding methods and decoding methods in ECOC method and (2) by comparing ECOC method and direct classification method. Both SVM (Support Vector Machine) and logistic regression model were used as binary classifiers in comparison.

• International Journal of Advanced Culture Technology
• /
• 제8권1호
• /
• pp.165-172
• /
• 2020

Industrial Revolution means the improvement of productivity through technological innovation and has been a driving force of the whole change of economic system and social structure as the characteristic of technology as the tool of this productivity has changed. Since the first industrial revolution of the 18th century, productivity efficiency has been advanced through three industrial revolutions so far, and this fourth industrial revolution is expected to bring about another revolution of production. In this study, the demand for the introduction of artificial intelligence(AI) technology has been increasing in various business fields due to the rapid development of ICT technology, and the classification of HS(harmonized commodity description and coding system) items has been decided using artificial intelligence technology, which is the core of the fourth industrial revolution. And it is enough to construct HS classification system based on AI technology using inference and deep learning. Performing the HS item classification is not an easy task. Implementation of item classification system using artificial intelligence technology to analyze information of HS item classification which is performed manually by the current person more accurately and without any mistake, And the customs administrations, customs offices, and customs agencies, it is expected to be highly utilized in the innovation of trade practice and the customs administration innovation FTA origin agent.

• 한국통신학회논문지
• /
• 제22권8호
• /
• pp.1722-1732
• /
• 1997

In this paper, we propose a coding method of remotely sensed satellite image data using region classification and interband correlation. This method classifies each pixel vector consider spectral characteristics. Then we perform the classified intraband VQ to remove spatial (intraband redundancy for a reference band image. To remove interband redundancy effectively, we perform the classified interband prediction for the band images that the high correlation spectrally and perform the classified interband VQ for the remaining band images. Experiments on LANDSAT TM image show that the coding efficiency of the proposed method is better than that of the conventional Gupta's method. Especially, this method removes redundancies effectively for satellite iamge including various geographical objects and for and images that have low interband correlation.

• 한국정보전자통신기술학회논문지
• /
• 제16권5호
• /
• pp.239-246
• /
• 2023

본 논문에서는 오디오 부호화기를 위한 스펙트럼 변화 파라미터와 Mel Frequency Cepstral Coefficients(MFCC) 파라미터를 이용하여 음성과 음악 신호를 분류하는 개루프 방식의 알고리즘을 제안한다. 반응성을 높이기 위해 단구간 특징 파라미터로 MFCC를 사용하고 정확도를 높이기 위해 장구간 특징 파라미터로 스펙트럼 변화를 사용하였다. 전체적인 음성/음악 신호 분류 결정은 단구간 분류와 장구간 분류를 결합하여 이루어진다. 패턴인식을 위해 Gaussian Mixed Model(GMM)을 사용하였고, Expectation Maximization(EM) 알고리즘을 사용하여 최적의 GMM 파라미터를 추출하였다. 제안된 장단구간 결합 음성/음악 신호 분류 방법은 다양한 오디오 음원에서 평균적으로 1.5% 분류 오류율을 보였고 단구간 단독 분류 방법 보다 0.9%, 장구간 단독 분류 방법보다 0.6%의 분류 오류율의 성능 개선을 이룰 수 있었다. 제안된 장단구간 결합 음성/음악 신호 분류 방법은 USAC 오디오 분류 방법보다 타악기 음악 신호에서 9.1% 분류 오류율, 음성신호에서 5.8% 분류 오류율의 성능 개선을 이룰 수 있었다.

• 한국융합학회논문지
• /
• 제12권4호
• /
• pp.23-30
• /
• 2021

본 산업/직업 자동코딩 시스템은 조사 대상자들이 응답한 방대한 양의 산업/직업을 설명하는 자연어 데이터에 통계 분류 코드를 자동으로 부여하는 시스템이다. 본 연구는 기존의 정보검색 기반의 산업/직업 자동코딩시스템과 다르게 딥러닝을 이용하여 색인 DB가 필요하지 않고 분류 수준에 상관없이 코드를 부여할 수 있는 시스템을 제안한다. 또한, 자연어 처리에 특화된 딥러닝 기법인 KoBERT를 적용한 제안 모델은 인구주택총조사 산업/직업 코드 분류, 그리고 사업체기초조사 산업 코드 분류에서 각각 95.65%, 91.45%, 97.66%의 Top 10 정확도를 보인다. 제안한 모델 실험 후 향후 개선 가능성을 데이터/모델링 관점으로 분석한다.