• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제3권8호
• /
• pp.299-308
• /
• 2014

신체 동작, 얼굴 표정과 같이 아주 복잡한 생체 패턴을 인식하고 분류하는 인간의 능력을 모방한 정보처리 컴퓨팅 관련 연구가 최근 다수 등장하고 있다. 특히 컴퓨터비전 분야에서는 인간의 뛰어난 인지 능력 중 상황정보 없이 시각시퀀스에서 동작을 분류하는 기능을 통해 시공간적 패턴 코딩과 빠른 인식 방법을 이해하고자 한다. 본 연구는 비디오 시퀀스상의 동작인식에 생물학적 시각인지과정의 영향을 받은 생체 기반 컴퓨터비전 모델을 제시하였다. 제안 모델은 이미지 시퀀스에서 동작을 검출하고 시각 패턴을 판별하는 데 생체 시각처리과정의 신경망 구조 단계를 반영하였다. 실험을 통해 생체 기반 동작인식 모델이 인간 시각인지 처리의 여러 가지 속성을 고려했을 뿐 아니라 기존 동작인식시스템에 비해 시간 정합성이 뛰어나며 시간 변화에 강건한 분류 능력을 보임을 알 수 있다. 제안 모델은 지능형 로봇 에이전트와 같은 생체 기반 시각정보처리 시스템 구축에 기여할 수 있다.

• 한국컴퓨터정보학회논문지
• /
• 제18권7호
• /
• pp.23-35
• /
• 2013

본 논문은 고장 분류 시스템을 위해 진동 신호로부터 특징 벡터를 자동적으로 추출하는 효과적인 기법을 제안한다. 기존의 멜-주파수 캡스트럼 계수는 진동신호의 노이즈에 민감하여 분류 정확도를 감소시키는 단점이 있다. 이러한 문제를 해결하기 위해 본 논문은 4단계 필터 뱅크로 구성된 스펙트럴 엔벨로프 캡스트럼 계수 분석을 제안하며, 4단계는 (1) 모든 진동 신호의 스펙트럴 엔벨로프를 기술하기 위한 선형 예측 코딩 알고리즘 사용 단계, (2) 일반적인 스펙트럴 모양을 얻기 위해 모든 엔벨로프의 평균화 단계, (3) 평균 엔벨로프와 그 주파수의 최대값을 찾기 위한 기울기 하강 방법 사용 단계, (4) 엔벨로프의 주파수 사이의 거리로부터 계산된 중앙값을 얻는데 사용되는 비 중첩 필터 뱅크 단계로 구성된다. 이4-단계필터뱅크는 특징벡터를 추출하기위해 캡스트럼 계수 계산에 사용된다. 마지막으로 유도전동기의 결함 형태를 구분하기 위해 이러한 특수 파라미터를 사용하는 다중 계층 서포트 벡터 머신을 사용한다. 모의실험 결과, 제안하는 방법은 약 99.65%의 분류 성능을 보이며, 동시에 기존 방법들보다 우수한 성능을 보인다.

• 대한물리의학회지
• /
• 제19권1호
• /
• pp.143-154
• /
• 2024

PURPOSE: The present study was conducted to improve the understanding of the Korean Standard Functional, Disability, and Health Classification (KCF) and its ease of use in the clinical domain of the musculoskeletal system by comparing, analyzing, and linking the KCF codes with items from patient-reported outcome measures (PROMs), which are currently mainly used to evaluate patients with neck, shoulder, waist, and knee pain. METHODS: The items of the most widely used PROMs, the Neck Disability Index (NDI), Disabilities of the Arm, Shoulder, and Hand (DASH) scores, Oswestry Disability Index (ODI), Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC), and the codes of the KCF were linked by two experts according to the linking rules. RESULTS: The concordance between the items of each of the PROMs and the KCF code linked by the two experts was NDI,86.4%86.4%, DASH 83.3%, ODI 92.0%, and WOMAC 80.7%. The NDI, DASH, and WOMAC indexes were found to comprise items corresponding to physical function, activity, and participation areas, and were linked to 22, 43, and 31 KCF codes, respectively. In addition to these two areas, the ODI included items related to environmental factors and was linked to 25 codes (duplicated codes are treated as one). CONCLUSION: This research can be used by adding the KCF code to the questions of the currently used evaluation tool. This coding can be easily applied and will contribute to the easy understanding of the KCF.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 ITC-CSCC -2
• /
• pp.1007-1010
• /
• 2002

In this paper, we present a new blocking artifact reduction algorithm using interpolation and signal adaptive filter (SAF) based on the edge map. Generally, block-based coding, such as JPEG and MPEG, is the most popular image compression method. However, for high compression it produces noticeable blocking and ringing artifacts in the decoded image. In proposed method, all the block is classified into low and high frequency blocks in block classification procedure. And edge map is obtained by using Sobel operator on decoded image. And according to the block property we applied blocking artifacts reduction algorithm. Namely, four neighbor low frequency block is participated in interpolation based on edge map. And ringing artifacts is removed by applying a signal adaptive filter around the edge using edge map in high frequency block. The computer simulation results confirmed a better performance by the proposed method in both the subjective and objective image qualities.

• 한국실내디자인학회논문집
• /
• 제15권6호
• /
• pp.238-246
• /
• 2006

Recent trends of interior design have a focus on creation of more various meanings rather than past ideology which sought after the compatibility to the function of modem design. These trends requires integral understanding of social and cultural ideologies with a sens of values for a certain periods. In addition, they also require creativity which able to read, find and solve consumer's diverse demand and desire. Considering the effort of trend forecasting in Korea is still heavily rely on the foreign trend shows, it is natural to attempt to study the analytical forecasting methodology based upon more systematic principles which lead to more objective outcome, when the understanding, forcasting and analysis of interior decoration trend are required. In this thesis, the analysis and forecasting of interior decoration trend are studied by means of verbal image code process which involves the induction of design concept through data extraction, classification and analysis, in order to understanding and satisfying the diversified consumer's demand and trend. The coding process of verbal image is understanding as general concept. by extracting common elements from abstract and individual image, and/or specific concept. Therefore, it is proposed that the database building and data mining process of verbal Image, and subsequent development of programming skill can be applied as more efficient tool for various verbal image process.

• Interdisciplinary Bio Central
• /
• 제4권4호
• /
• pp.14.1-14.6
• /
• 2012

Splice site prediction in DNA sequence is a basic search problem for finding exon/intron and intron/exon boundaries. Removing introns and then joining the exons together forms the mRNA sequence. These sequences are the input of the translation process. It is a necessary step in the central dogma of molecular biology. The main task of splice site prediction is to find out the exact GT and AG ended sequences. Then it identifies the true and false GT and AG ended sequences among those candidate sequences. In this paper, we survey research works on splice site prediction based on support vector machine (SVM). The basic difference between these research works is nucleotide encoding technique and SVM kernel selection. Some methods encode the DNA sequence in a sparse way whereas others encode in a probabilistic manner. The encoded sequences serve as input of SVM. The task of SVM is to classify them using its learning model. The accuracy of classification largely depends on the proper kernel selection for sequence data as well as a selection of kernel parameter. We observe each encoding technique and classify them according to their similarity. Then we discuss about kernel and their parameter selection. Our survey paper provides a basic understanding of encoding approaches and proper kernel selection of SVM for splice site prediction.

• 한국식생활문화학회지
• /
• 제24권4호
• /
• pp.401-412
• /
• 2009

The aims of study were to provide basic data for the internationalization of Contract Foodservice Management Companies (CFMC) and to gain a better understanding of internal push-and-pull factors through in-depth interviews. The interviewees were managers of four large CFMCs and one small-to-medium CFMC. The non-structured interview format employed an interview guide of open-ended questions. All interviews were digitally recorded and notes were taken simultaneously by an interview assistant. The narrative data analysis involved transcription, coding, classification by categories, and content analysis. Eighty-eight codes were generated from the interview analyses, and the subordinate variables uncovered included seven push factors, eight pull factors, one interactive factor, and 10 internal dynamics. These factors will be useful in further studies of the internal operations of specific CFMCs, and more generally, the practical condition of the industry.

• 한국식물병리학회:학술대회논문집
• /
• 한국식물병리학회 2003년도 정기총회 및 추계학술발표회
• /
• pp.115.2-116
• /
• 2003

Complete genomic nucleotide sequence of Daphe virus S (DVS), a member of the genus Carlavirus, causing leaf distortion and chlorotic spot disease symptoms in daphne plants, has been determined in this study. The genome of DVS contained six open reading fames coding for long viral replicase, triple gene block, 36 kDa viral coat protein (CP) and 12 kDa from the 5' to 3' ends, which is a typical genome structure of carlaviruses. Two Korean isolates of DVS isolates were 98.1％ and 93.6％ amino acid identical in the CP and 12kDa, respectively. The CP gene of DVS shares 25.2-55.2％ and 42.9-56.1％ similarities with that of 19 other carlaviruses at the amino acid and nucleotide levels, respectively. The 3'-proximal 12 kDa gene of DVS shares 20.2-57.8％ amino acid identities with that of 18 other members of the genus. The 3' noncoding region of DVS consists of 73 nucleotides with long excluding poly A tract, and shares 69.1-77.1％ identities to the known carlaviruses. In the phylogenetic analyses of the two proteins, DVS was closely related to Helenium virus S and Chrysanthemum virus B. This is the first complete sequence information for the DVS, and further confirms the classification of DVS as a distinct species of the genus Carlavirus.

• 한국멀티미디어학회논문지
• /
• 제21권11호
• /
• pp.1305-1316
• /
• 2018

Graphical user interface(GUI) has a very important role to interact with software users. However, designing and coding of GUI are tedious and pain taking processes. In many studies, the researchers are trying to convert GUI elements or widgets to code or describe formally their structures by help of domain knowledge of stochastic methods. In this paper, we propose the GUI elements detection approach based on object detection strategy using deep neural networks(DNN). Object detection with DNN is the approach that integrates localization and classification techniques. From the experimental result, if we selected the appropriate object detection model, the results can be used for automatic code generation from the sketch or capture images. The successful GUI elements detection can describe the objects as hierarchical structures of elements and transform their information to appropriate code by object description translator that will be studied at future.

• 한국정보통신학회논문지
• /
• 제17권4호
• /
• pp.775-780
• /
• 2013

본 논문에서는 백색잡음 및 자동차잡음 환경 하에서 남녀 성별인식이 가능한 신경회로망에 의한 화자종속 음성인식 알고리즘을 제안한다. 본 논문에서 제안한 음성인식 알고리즘은 남성화자 및 여성화자를 인식하기 위하여 LPC 켑스트럼 계수를 사용하여 신경회로망에 의하여 학습된다. 본 실험에서는 백색잡음 및 자동차잡음에 대하여 총 6개의 신경회로망의 네크워크에 대한 인식결과를 나타낸다. 인식실험의 결과로부터 백색잡음에 대해서는 최대 96% 이상의 인식률, 자동차잡음에 대해서는 최대 88% 이상의 인식률을 구하였다. 마지막으로 본 실험에서는 제안하는 음성인식 알고리즘이 배경잡음 환경 하에서의 기존의 음성인식 알고리즘과 비교하여 본 방식의 알고리즘이 유효하다는 것을 실험으로 확인한다.