• 한국멀티미디어학회논문지
• /
• 제20권8호
• /
• pp.1175-1186
• /
• 2017

Human emotion recognition is one of the promising applications in the era of artificial super intelligence. Thus far, facial expression traits are considered to be the most widely used information cues for realizing automated emotion recognition. This paper proposes a novel facial expression recognition (FER) method that works well for recognizing emotion from image sequences. To this end, we develop the so-called weighted soft voting classification (WSVC) algorithm. In the proposed WSVC, a number of classifiers are first constructed using different and multiple feature representations. In next, multiple classifiers are used for generating the recognition result (namely, soft voting) of each face image within a face sequence, yielding multiple soft voting outputs. Finally, these soft voting outputs are combined through using a weighted combination to decide the emotion class (e.g., anger) of a given face sequence. The weights for combination are effectively determined by measuring the quality of each face image, namely "peak expression intensity" and "frontal-pose degree". To test the proposed WSVC, CK+ FER database was used to perform extensive and comparative experimentations. The feasibility of our WSVC algorithm has been successfully demonstrated by comparing recently developed FER algorithms.

• 좋은식품
• /
• 통권173호
• /
• pp.104-111
• /
• 2003

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.1163-1168
• /
• 2005

This paper proposes a soft-remote-control (soft-remocon) system based on EMG signals for the Intelligent Sweet Home. The proposed system is applied to Intelligent Sweet Home which was developed to help the independence living of the elderly and physically handicapped individuals. The goal of proposed system is to control home-installed electronic devices such as TV, air-conditioner, curtain and lamp in Intelligent Sweet Home using EMG signals. Features such as VAR and DAMV having good separability performance are selected for pattern classification. FMMNN is adopted as a pattern classifier. Classification results are allowed to a developed remote control module and then corresponding infrared pulses can operate home-installed electronic devices. We concluded that EMG as an input interface for home-installed electronic devices in Intelligent Sweet Home.

• 대한세포병리학회지
• /
• 제6권1호
• /
• pp.27-35
• /
• 1995

We reviewed 93 cases of fine needle aspiration of skin/subcutaneous and soft tissue lesions with histologic confirmation. On the basis of the most prominent cytologic features, morphologic classification of the aspirates was done. Skin and subcutaneous lesions included endometriosis, epidermal inclusion cyst, fat necrosis, pilomatrixoma and nodular fasciitis. Neoplastic lesions of soft tissue were categorized as ; round cell, spindle cell, polygonal cell, well-differentiated and myxoid tumor. This classification is convenient to recognize and categorize most soft tissue tumors.

• Journal of Periodontal and Implant Science
• /
• 제51권2호
• /
• pp.100-113
• /
• 2021

Purpose: Previous studies have solely focused on fresh extraction sockets, whereas in clinical settings, alveolar sockets are commonly associated with chronic inflammation. Because the extent of tissue destruction varies depending on the origin and the severity of inflammation, infected alveolar sockets may display various configurations of their remaining soft and hard tissues following tooth extraction. The aim of this study was to classify infected alveolar sockets and to provide the appropriate treatment approaches. Methods: A proposed classification of extraction sockets with chronic inflammation was developed based upon the morphology of the bone defect and soft tissue at the time of tooth extraction. The prevalence of each type of the suggested classification was determined retrospectively in a cohort of patients who underwent, between 2011 and 2015, immediate bone grafting procedures (ridge preservation/augmentation) after tooth extractions at Seoul National University Dental Hospital. Results: The extraction sockets were classified into 5 types: type I, type II, type III, type IV (A & B), and type V. In this system, the severity of bone and soft tissue breakdown increases from type I to type V, while the reconstruction potential and treatment predictability decrease according to the same sequence of socket types. The retrospective screening of the included extraction sites revealed that most of the sockets assigned to ridge preservation displayed features of type IV (86.87%). Conclusions: The present article classified different types of commonly observed infected sockets based on diverse levels of ridge destruction. Type IV sockets, featuring an advanced breakdown of alveolar bone, appear to be more frequent than the other socket types.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2007년도 춘계학술대회 학술발표 논문집 제17권 제1호
• /
• pp.257-260
• /
• 2007

인간의 행위에는 외부환경으로부터 감각정보가 입력되어 반응되는 무의식적인 행동과 뇌에 의한 추론과 인지에 의한 행동으로 분류할 수 있다. 동일한 환경 조건하에서의 인간 행위분류의 통해 활용 적합한 응용프로그램을 개발하여 적용하여 본다. 본 논문에서는 인간의 몸에 부착하여 움직임을 데이터로 분석할 수 있도록 행동인식 시스템을 개발하였다. 인간행동의 인식패턴을 분류하기 위해 Soft-Computing Algorithm을 행위 추출센서에 적용시킨 단독 시스템을 개발하여 센서모듈로부터 인간의 행동 패턴을 분류할 수 있도록 한다. 이러한 센서모듈은 3축 각속도 및 가속도 센서를 부착시킨 모듈로 Micro-Processor를 사용하여 모듈을 구성하였으며, 구축된 모듈은 인간의 몸에 착용하여 인간의 움직임을 디지털 데이터로 변환된다. 변환된 데이터를 무선통신을 통해 워크스테이션에 전달되어 인간행위에 대한 패턴분류 알고리즘 처리가 가능하며, 추출된 데이터를 기반으로 인간의 행동분석과 교정이 이루어 질 수 있도록 한다. 본 논문에서의 최종 시나리오는 운전자의 행동패턴을 이용한 행동 감지 및 서비스 시스템을 구성하는 데에 목적을 둔다.

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 2009년도 춘계 학술발표회
• /
• pp.999-1008
• /
• 2009

A series of sedimentary rocks which are formed in the Tertiary are distributed around Samcheok(Samcheok-Pukpyoung basin), Younghae(Younghae basin), Pohang(Pohang basin), Gyeongju(Yangnam basin), Ulsan(Ulsan basin), Jeju(Seogyuipo formation) in the southern region of the Korean Peninsula. This study concerned with geological, geophysical, geotechnical properties of the unconsolidated rocks in the Pohang area. A consolidated rocks are classified as hard rock - soft rock - weathered rock - residual soil follows in degree of weathering. But unconsolidated rocks has soil properties as well as rock's at the same time. The results of field excursion, boring, borehole-logging, rock testing, geophysical survey, laboratory test are soft rock range, but the durability of the rock until the residual soil from the weathered rock. We accomplished the rock mass classification of the unconsolidated rocks.

• 대한두개안면성형외과학회지
• /
• 제20권4호
• /
• pp.255-259
• /
• 2019

Craniofacial cleft is a rare disease, and has multiple variations with a wide spectrum of severity. Among several classification systems of craniofacial clefts, the Tessier classification is the most widely used because of its simplicity and treatment-oriented approach. We report the case of a Tessier number 3 cleft with wide soft tissue and skeletal defect that resulted in direct communication among the orbital, maxillary sinus, nasal, and oral cavities. We performed soft tissue reconstruction using the straight-line advanced release technique that was devised for unilateral cleft lip repair. The extension of the lateral mucosal and medial mucosal flaps, the turn over flap from the outward turning lower eyelid, and wide dissection around the orbicularis oris muscle enabled successful soft tissue reconstruction without complications. Through this case, we have proved that the straight-line advanced release technique can be applied to severe craniofacial cleft repair as well as unilateral cleft lip repair.

• 동아시아식생활학회지
• /
• 제3권1호
• /
• pp.19-25
• /
• 1993

The types and processing characteristics of traditional soft drinks base in omija broth and their historical back grounds were surveyed trough the old literatures published. Three group classification of Korean traditional soft drinks base in omija broth. 1. Honeyed juice mixed fruits base in omija broth 2. Honeyed juice mixed cereal cooking and noodles base on omija borth 3. A water shortage and tea base in omija broth

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제6권3호
• /
• pp.149-154
• /
• 2017

MCT-Adaboost 학습 알고리즘은 각 학습 단계에서 배경과 객체를 구분하는 가장 좋은 특징을 찾는 학습 알고리즘이다. 각 학습 단계에서는 최적의 특징을 검출하기 위해 학습 데이터에서 각 특징의 각 커널에서 모든 오차율을 산정하고, 각 특징에서 모든 커널들의 합을 하였을 경우 최소 오차율을 가지는 특징을 선택하도록 되어 있다. 이를 선택하고 다음 학습때 영향을 주는 약분류기에서 기존의 MCT-Adaboost 방법은 경판정 방법으로 사용하였다. 이 방법은 특정 커널에서 객체 데이터와 배경 데이터의 오류율이 유사할 경우, 한쪽으로 판정하기 때문에, 제대로 된 결과값을 산정할 수 없는 문제가 있다. 이를 유연하게 하기 위해 본 연구에서는 연판정을 이용한 약분류기 방법을 제안한다. 기존의 MCT-Adaboost는 초기 가중치를 동일하게 산정한다. 하지만, 이는 데이터의 특성을 모른다는 가정하에 설계된 초기 가중치 설정이다. 본 논문에서는 데이터 분포를 이용하여 가중치를 확률적으로 다르게 할당함으로서, 적은 학습에도 좋은 결과를 보이는 방법을 제안한다. 실험 결과에는 기존의 MCT-Adaboost가 제안하는 성능평가를 통해, 본 연구가 제안하는 방법이 기존 방법에 비해 좋은 결과를 보였다.