• ETRI Journal
• /
• 제39권6호
• /
• pp.851-858
• /
• 2017

Parkinson's disease is a growing and chronic movement disorder, and its diagnosis is difficult especially at the initial stages. In this paper, movement characteristics extracted by a computer using multilayer back propagation neural network mapping are converted to the symptoms of this disease. Then, modulation of three classifiers of C4.5, k-nearest neighbors, and support vector machine with majority voting are applied to support experts in diagnosing the disease. The purpose of this study is to choose appropriate characteristics and increase the accuracy of the diagnosis. Experiments were performed to demonstrate the improvement of Parkinson's disease diagnosis using this method.

• 전자공학회지
• /
• 제39권2호
• /
• pp.45-54
• /
• 2012

Object detection is a fundamental task for many high-level computer vision applications such as image retrieval, scene understanding, activity recognition, visual surveillance and many others. Although object detection is one of the most popular problems in computer vision and various algorithms have been proposed thus far, it is also notoriously difficult, mainly due to lack of proper models for object representation, that handle large variations of object structure and appearance. In this article, we review a branch of object detection algorithms based on Support Vector Machines (SVMs), a well-known max-margin technique to minimize classification error. We introduce a few variations of SVMs-Structural SVMs and Latent SVMs-and discuss their applications to object detection and localization.

• International Journal of Advanced Culture Technology
• /
• 제7권2호
• /
• pp.19-27
• /
• 2019

The purpose of this study was to assess mental health and quality of life (QOL) including factors influencing QOL among early North Korean defectors in South Korea. Participants were 151 early North Korean defectors residing in a settlement support center. All measures were self-administered. Unlike refugees living in communities, early defectors did not experience a high rate of mental health problems and reported a good QOL. Psychoticism was the most predictive factor affecting QOL. Findings from this study suggest the importance of mental health assessment and support over time. Psychoticism, significant in explaining QOL of early North Korean defectors, needs early diagnosis and treatment to prevent progression. Mental health issues among refugees may not be evident while they are in a structured, supportive environment. Evaluation and treatment are needed over time.

• 인간식물환경학회지
• /
• 제22권4호
• /
• pp.365-373
• /
• 2019

This study was conducted to determine the effects of horticultural therapy on self-esteem of women with hearing impairment. Ten women with hearing impairment registered in the Mokpo Branch of the Korean Association of the Deaf participated in the horticultural therapy programs (HTP) for self-esteem. The self-esteem scale was used to evaluate the effects of the programs and scores were compared to determine the difference before and after the programs. Self-esteem was improved in all 10 subjects, and its mean value increased with statistical significance from 22.5 points before the programs to 29.8 points after the programs. The programs preferred by women with hearing impairment included 'making a centerpiece using scented candles and flowers', 'packing and planting pot spray chrysanthemum', 'making a topiary', 'planting Hedera helix', and 'planting cyclamen'. Therefore, it was suggested that self-esteem of women with hearing impairment were improved by increasing social and family support, emotional stability, positive feedback, and self-expression through horticultural therapy programs.

• Journal of Hospice and Palliative Care
• /
• 제13권3호
• /
• pp.143-152
• /
• 2010

목적: 본 연구는 호스피스 완화의료 기관 조사와 통계청 자료를 이용하여 호스피스 완화의료 기관 현황과 장애요인, 그에 따른 활성화 방안을 조사하고 분석하여 향후 정책수립을 위한 기초자료를 제공하고자 실시되었다. 방법: 현황조사를 위해 국내 호스피스 완화의료 관련 단체 및 기관을 통해 호스피스 완화의료 제공 기관을 선정 하여 2009년 2월에서 3월까지 설문을 시행하였으며 설문내용은 기관의 일반현황, 대상자, 서비스 제공인력, 시설, 재정, 활성화 방안으로 구성되었다. 또한 필요병상수 및 병상충족률 산출을 위해 통계청의 지역별 인구수 자료를 이용하였다. 결과: 전체 53개 호스피스 완화의료 기관 가운데 42개 기관이 종합병원 이상으로 총 설문대상 기관 중 의원급 기관은 6개였다. 전체 53개 기관 중 18.8%의 기관이 수도권 지역에 분포하고 있었다. 전반적인 호스피스 완화의료 병상충족률은 21.9%로 낮은 것으로 나타났으며 4개 광역시도의 경우 호스피스 완화의료 전용병상이 없는 것으로 보고되었다. 2008년 호스피스 완화의료기관의 사망자는 전체 암사망자의 6.3%에 불과했다. 기관의 재정 관련한 설문에서 86%의 시설이 재정이 부족하다고 답변하였으며 그 외 인력수급 장애요인 및 시설기준 미충족의 원인으로도 재정 부족을 원인으로 꼽은 기관이 과반수를 넘는 것으로 나타났다. 호스피스 완화의료 활성화를 위한 정부의 지원으로 가장 필요한 부분으로 재정지원이었으며(71.2%), 기부문화 활성화 방안으로 기부금 전액 세금 공제(43.1%), 공익재단 설립(23.5%) 등으로 나타났다. 결론: 본 연구는 이처럼 기관의 현황 자료조사 및 설문조사를 통해 국내의 호스피스 완화의료 이용률 및 병상충족률이 낮은 문제점, 지역별 병상충족률 편차가 큰 문제점 등을 파악하였으며 호스피스 완화의료의 장애요인으로 재정부족, 인력수급 장애, 인식부족 등을 파악하였다. 또한 이를 위해 호스피스 완화의료 기관의 재정마련 방안이 필수적이며 인식 부족에 대한 개선 노력도 동시에 이루어질 필요가 있을 것으로 결론지었다. 이 중 재정 부족에 대한 방안으로는 정부의 재정 지원과 기부금 전액 세금공제와 공익재단 설립이 검토해 볼 만한 대안으로 제시할 수 있겠다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권11호
• /
• pp.5436-5458
• /
• 2017

Automatic Video Surveillance System (AVSS) has become important to computer vision researchers as crime has increased in the twenty-first century. As a new branch of AVSS, baggage detection has a wide area of security applications. Some of them are, detecting baggage in baggage restricted super shop, detecting unclaimed baggage in public space etc. However, in this paper, a detection & classification framework of baggage is proposed. Initially, background subtraction is performed instead of sliding window approach to speed up the system and HSI model is used to deal with different illumination conditions. Then, a model is introduced to overcome shadow effect. Then, occlusion of objects is detected using proposed mirroring algorithm to track individual objects. Extraction of rotational signal descriptor (SP-RSD-HOG) with support plane from Region of Interest (ROI) add rotation invariance nature in HOG. Finally, dynamic human body parameter setting approach enables the system to detect & classify single or multiple pieces of carried baggage even if some portions of human are absent. In baggage detection, a strong classifier is generated by boosting similarity measure based multi layer Support Vector Machine (SVM)s into HOG based SVM. This boosting technique has been used to deal with various texture patterns of baggage. Experimental results have discovered the system satisfactorily accurate and faster comparative to other alternatives.

• Smart Structures and Systems
• /
• 제23권6호
• /
• pp.641-651
• /
• 2019

The stochastic stability control of the parameter-excited vibration of an inclined stay cable with multiple modes coupling under random and periodic combined support disturbances is studied by using the direct eigenvalue analysis approach based on the response moment stability, Floquet theorem, Fourier series and matrix eigenvalue analysis. The differential equation with time-varying parameters for the transverse vibration of the inclined cable with control under random and deterministic support disturbances is derived and converted into the randomly and deterministically parameter-excited multi-degree-of-freedom vibration equations. As the stochastic stability of the parameter-excited vibration is mainly determined by the characteristics of perturbation moment, the differential equation with only deterministic parameters for the perturbation second moment is derived based on the $It{\hat{o}}$ stochastic differential rule. The stochastically and deterministically parameter-excited vibration stability is then determined by the deterministic parameter-varying response moment stability. Based on the Floquet theorem, expanding the periodic parameters of the perturbation moment equation and the periodic component of the characteristic perturbation moment expression into the Fourier series yields the eigenvalue equation which determines the perturbation moment behavior. Thus the stochastic stability of the parameter-excited cable vibration under the random and periodic combined support disturbances is determined directly by the matrix eigenvalues. The direct eigenvalue analysis approach is applicable to the stochastic stability of the control cable with multiple modes coupling under various periodic and/or random support disturbances. Numerical results illustrate that the multiple cable modes need to be considered for the stochastic stability of the parameter-excited cable vibration under the random and periodic support disturbances, and the increase of the control damping rather than control stiffness can greatly enhance the stochastic stability of the parameter-excited cable vibration including the frequency width increase of the periodic disturbance and the critical value increase of the random disturbance amplitude.

• 동아시아경상학회지
• /
• 제8권2호
• /
• pp.29-41
• /
• 2020

Purpose - This study incorporated the success factors of bio cluster and provided the ways to utilize them for managing the performance of bio cluster. The aim of this study was to present an integrated framework for the success factors of the bio cluster by combining the literature and case studies, and to measure and manage the performance of the bio cluster. Research design, data, and methodology - This study combined the literature review with the case study. We reviewed the literature on the success factors of the bio cluster presented by existing studies. We studied some cases of how these factors are actually applied in the bio cluster also. We integrated the success factors of bio cluster based on both the literature review and the case study. Results - The success factors of the bio cluster presented in this study as an integrated framework were defined as six factors: knowledge base and expertise, industrial infrastructure, funding and investment, government support, start-up activities and innovation activities. These success factors can be measured and managed by some performance indicators of each factor. Conclusions - Through this study, we can identify the integrated success factors of the bio cluster and understand how these factors work in bio cluster. In addition, this integrated framework of success factors will be effectively utilized to measure and manage the performance of the bio cluster.

• 한국정보통신학회논문지
• /
• 제10권10호
• /
• pp.1869-1876
• /
• 2006

최근에 시공간 부호화(Space-Time Code, STC)는 차세 대 이동 통신에서 고속의 신뢰성 있는 통신을 위 해 각광받고 있다. 본 논문에서는 다중경로 페이딩 채널에서 고속의 데이터를 전송하고자 할 경우에 성능을 향상시키고자 트렐리스 부호화된(Trellis-Coded, TC) 차동 시공간 변조(Differential Space Time Modulation, DSTM)를 사용한 MDPSK에서 다중 심벌 검파 시스템을 제안한다 차동 시공간 부호화된 MDPSK의 성능을 향상시키기 위해 DUSTM(differential unitary space-time modulation)을 이용하여 송신기를 설계하고 수신단에서 다중 심 벌 검파를 수행하는 수신기와 디코딩 알고리듬을 개발하며, 이를 위한 새로운 가지 메트릭을 유도한다.

• Smart Structures and Systems
• /
• 제21권1호
• /
• pp.123-137
• /
• 2018

Structural monitoring is the most important part of the construction and operation of the embankment dams. Appropriate instruments selection for dams is vital, as inappropriate selection causes irreparable loss in critical condition. Due to the lack of a systematic approach to determine adequate instruments, a framework based on three comparable Multi-Attribute Decision Making (MADM) methods, which are VIKOR, technique of order preference by similarity to ideal solution (TOPSIS) and Preference ranking organization method for enrichment evaluation (PROMETHEE), has been developed. MADM techniques have been widely used for optimizing priorities and determination of the most suitable alternatives. However, the results of the different methods of MADM have indicated inconsistency in ranking alternatives due to closeness of judgements from decision makers. In this study, 9 criteria and 42 geotechnical instruments have been applied. A new method has been developed to determine the decision makers' importance weights and an aggregation method has been introduced to optimally select the most suitable instruments. Consequently, the outcomes of the aggregation ranking correlate about 94% with TOPSIS and VIKOR, and 83% with PROMETHEE methods' results providing remarkably appropriate prioritisation of instruments for embankment dams.