• 한국전자통신학회논문지
• /
• 제5권4호
• /
• pp.363-371
• /
• 2010

특징벡터의 분류를 개선시켜 화자독립 음성인식의 오류율을 줄이려는 노력의 일환으로서, 우리는 MFCC의 추출에 있어서 푸리에 스펙트럼을 기울이는 방법이 미치는 효과를 연구한다. 음성신호에 FIR 필터링을 적용하는 효과의 조사도 병행된다. 제안된 방법은 두 가지 독립적인 방법에 의해 평가된다. 즉, 피셔의 차별함수에 의한 방법과 은닉 마코브 모델 및 퍼지 벡터양자화를 사용한 음성인식 오류율 조사 방법이다. 실험 결과, 적절한 파라미터의 선택에 의해 기존의 방법에 비해 10% 정도 낮은 인식 오류율이 얻어짐을 확인하였다.

• Asian Pacific Journal of Cancer Prevention
• /
• 제17권11호
• /
• pp.4913-4916
• /
• 2016

Objective: As a source of information, medical data can feature hidden relationships. However, the high volume of datasets and complexity of decision-making in medicine introduce difficulties for analysis and interpretation and processing steps may be needed before the data can be used by clinicians in their work. This study focused on the use of Bayesian models with different numbers of nodes to aid clinicians in breast cancer risk estimation. Methods: Bayesian networks (BNs) with a retrospectively collected dataset including mammographic details, risk factor exposure, and clinical findings was assessed for prediction of the probability of breast cancer in individual patients. Area under the receiver-operating characteristic curve (AUC), accuracy, sensitivity, specificity, and positive and negative predictive values were used to evaluate discriminative performance. Result: A network incorporating selected features performed better (AUC = 0.94) than that incorporating all the features (AUC = 0.93). The results revealed no significant difference among 3 models regarding performance indices at the 5% significance level. Conclusion: BNs could effectively discriminate malignant from benign abnormalities and accurately predict the risk of breast cancer in individuals. Moreover, the overall performance of the 9-node BN was better, and due to the lower number of nodes it might be more readily be applied in clinical settings.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1997년도 추계학술대회 논문집
• /
• pp.454-457
• /
• 1997

The purpose of this study is to develop an optimal model, using existing models, that is able to estimate the amount of spatter utilizing artificial neural network in the short circuit transfer mode of gas metal arc (GMA) welding. The amount of spatter generated during welding can become a barometer which represents the process stability of metal transfer in GMA welding, and it depends on some factors which constitute a periodic waveforms of welding current and arc voltage in short circuit GMA welding. So, the 12 factors, which could express the characteristics for the waveforms, and the amount of spatter are used as input and output variables of the neural network, respectively. Two neural network models to estimate the amount of spatter are proposed: A neural network model, where arc extinction is not considered, and a combined neural network model where it is considered. In order to reduce the calculation time it take to produce an output, the input vector and hidden layers for each model are optimized using the correlation coefficients between each factor and the amount of spattcr. The est~mation performance of each optimized model to the amount of spatter IS assessed and compared to the est~mation performance of the model proposed by Kang. Also, through the evaluation for the estimation performance of each optimized model, it is shown that the combined neural network model can almost perfectly predict the amount of spatter.

• 한국의류학회지
• /
• 제18권3호
• /
• pp.368-386
• /
• 1994

The primary purpose of this study was to identify the diversity and embellishment of American Indian clothing and relationship between culture and clothing in American Indian Culture Areas. After the introduction of European material culture, change in American Indian clothing was conducted. The result of the Study as follows: 1. The most influential factors affecting the diversity of American Indian clothing were environmental factors. Climates and geographical features, Raw material were reflected in clothing style and clothing material in each culture Area. 2. Economic situation and life style were shown to be influential to clothing development. The best known instance of this was greatly elaborated clothing and personal adornment of the Plains who had higher stand of life and nomadic life style. 3. Religious concepts were important factors influencing American Indian clothing. Indian tribes had different ritual performance they used particular motifs in clothing. Clothing, such as "ghost shirt", Apache medicine shirt and Pueblo ceremonial clothing, served hidden pur- poses. 4. Techenology was another factor identified in this study as influencing American Indian clothing. Especially, weaving skills of Southwest played a great role in textile development. Pueblo "manta" and Navaho "bil" were famous for Indian costume. 5. European material culture allowed great change of traditional native Indian clothing. American Indian had new material, new styles, new concept of clothing. 6. American Indian, although Indian applicated European trade goods, was actually quite conservative in retaining traditional designs and modes of decoration. Asthetics and traction of American Indian were reflected in American Indian clothing.d in American Indian clothing.

• 복식문화연구
• /
• 제28권3호
• /
• pp.344-355
• /
• 2020

The purpose of this study was to develop a workwear design that takes into account the characteristics of people with severe developmental disabilities who can engage in vocational activities. The aim was to identify needs according to the specific characteristics of people with severe disabilities to design work clothes and develop products according to universal design guidelines. This research method was conducted through representative interviews from a company employing people with severe dis- abilities in Daegu to determine the requirements for workers-related work clothes, and then applied universal design guidelines to perform appropriate design. The results of the study show that the hygiene and warmth of clothing are important for people with developmental disabilities. Therefore, the use of bright materials is required. Second, people with brain lesions often have low body temperature due to difficulties with blood circulation, for which warmth is a required factor. Third, people with severe developmental disabilities should not be differentiated in comparison to people without disabilities, therefore, it was important to use nondiscriminatory designs. Accordingly, it was more efficient to modify and supplement clothing designed for non-disabled people with hidden functions to suit specific characteristics, rather than to develop specialized clothing. These demands were found to conform to what is referred to as a universal design concept, through which three nondiscriminatory shirt designs and two easy-to-use pants were designed.

• 대한인간공학회지
• /
• 제35권2호
• /
• pp.75-84
• /
• 2016

Objective: The aim of this study is to suggest some improvement ideas based on the validity and the reliability analyses of the current safety culture measurement method applied to the Korean nuclear power industry. Background: Wrong safety culture is known as one of the major causes of the disasters such as the space shuttle Columbia disaster or the Fukushima Nuclear Power Plant accident. Assessment of safety culture of an organization is important to build a safer organizational environment as well as to identify the risks hidden in the organization. Method: A face validity of the current safety culture measurement method was analyzed by comparison of the key factors of safety culture in the Korean nuclear power industry with those factors reviewed in the previous studies. The current interview method was analyzed to identify the problems which degrade the consistency of evaluation. Results: Most safety culture factors reviewed in the literatures are covered in the list of the Korean nuclear power industry safety culture factors. However the unstructured questions used in the interview may result in inconsistency of safety culture evaluation among interviewers. Conclusion: This study suggests some examples which might improve the consistency of interviewers' evaluation on safety culture such as a post interview evaluation form. Application: An extended post interview evaluation form might help to increase the accuracy of the interviewing method for Korean nuclear industry safety culture evaluation.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제31권5호
• /
• pp.537-542
• /
• 2004

다층 퍼셉트론(Multi-Layer Perceptron, MLP) 구조는 그의 비선형 적합능력으로 인하여 매우 다양한 실제 문제에 적용되고 있다. 그러나 일반화된 MLP 구조의 적합능력은 은닉노드의 개수. 초기 가중 값 그리고 학습 회수 또는 학습 오차와 같은 구조인자(factor)들에 크게 영향을 받는다. 만약 이들 구조인자가 부적절하게 선택되면 일반화된 MLP 구조의 적합능력이 매우 왜곡될 수 있다. 따라서 MLP구조에 영향을 주는 인자들의 결합 영향을 살펴보는 것은 중요한 문제이다. 이 논문에서는 제어상자(controller box)를 통한 학습결과와 더불어 MLP구조를 일반화할 때 영향을 줄 수 있는 신경망의 일반적인 구조인자 들을 실증적으로 살펴보고 이들의 상대효과를 비교한다.

• 전기전자학회논문지
• /
• 제25권4호
• /
• pp.650-663
• /
• 2021

Subsurface topology estimation is an important factor in the geophysical survey. Electrical impedance tomography is one of the popular methods used for subsurface imaging. The EIT inverse problem is highly nonlinear and ill-posed; therefore, reconstructed conductivity distribution suffers from low spatial resolution. The subsurface region can be approximated as piece-wise separate regions with constant conductivity in each region; therefore, the conductivity estimation problem is transformed to estimate the shape and location of the layer boundary interface. Each layer interface boundary is treated as an open boundary that is described using front points. The subsurface domain contains multi-layers with very complex configurations, and, in such situations, conventional methods such as the modified Newton Raphson method fail to provide the desired solution. Therefore, in this work, we have implemented a 7-layer artificial neural network (ANN) as an inverse problem algorithm to estimate the front points that describe the multi-layer interface boundaries. An ANN model consisting of input, output, and five fully connected hidden layers are trained for interlayer boundary reconstruction using training data that consists of pairs of voltage measurements of the subsurface domain with three-layer configuration and the corresponding front points of interface boundaries. The results from the proposed ANN model are compared with the gravitational search algorithm (GSA) for interlayer boundary estimation, and the results show that ANN is successful in estimating the layer boundaries with good accuracy.

• 대한본초학회지
• /
• 제35권5호
• /
• pp.33-39
• /
• 2020

Objectives : Increasing evidence supports the biological and pharmacological activities of essential oils on the central nervous system such as pain, anxiety, attention, arousal, relaxation, sedation and learning and memory. The purpose of present work is to investigate the protective effect and molecular mechanism of cypress essential oil (CEO) against scopolamine (SCO)-induced cognitive impairments in C57BL/6 mice. Methods : A series of behavior tests such as Morris water maze, passive avoidance, and fear conditioning tests were conducted to monitor learning and memory functions. Immunoblotting and RT-PCR were also performed in the hippocampal tissue to determine the underlying mechanism of CEO. Results : SCO induced cognitive impairments as assessed by decreased step-through latency in passive avoidance test, relatively low freezing time in fear conditioning test, and increased time spent to find the hidden platform in Morris water maze test. Conversely, CEO inhalation significantly reversed the SCO-induced cognitive impairments in C57BL/6 mice comparable to control levels. To elucidate the molecular mechanisms of memory enhancing effect of CEO we have examined the expression of brain-derived neurotrophic factor (BDNF) in the hippocampus. CEO effectively elevated the protein as well as mRNA expression of BDNF via activation of cAMP response element binding protein (CREB). Conclusions : Our findings suggest that CEO inhalation effectively restored the SCO-impaired cognitive functions in C56BL/6 mice. This learning and memory enhancing effect of CEO was partly mediated by up-regulation of BDNF via activation of CREB.

• 한국건축시공학회지
• /
• 제22권6호
• /
• pp.619-630
• /
• 2022

콘크리트의 배합설계와 압축강도 평가는 지속가능한 구조물의 내구성을 위한 기초적인 자료로서 활용되고 있다. 하지만, 콘크리트 배합설계는 최근 배합요소의 다변화 등의 이유로 인하여 정확한 배합요소 산정이나 기준값 설정에 어려움을 겪고 있다. 본 연구에서는 인공지능 기법 중 하나인 딥러닝 기법을 사용하여 삼성분계 콘크리트의 배합요소를 산정하는 양방향 해석의 예측모델을 설계하는 것을 목적으로 한다. 콘크리트 배합요소 산정을 위한 DNN 기반 예측모 델은 층 수, 은닉 뉴런 수를 변수로 한 총 8개의 모델을 사용하여 성능평가 및 비교를 실시하였으며, 이후 학습된 DNN 모델을 사용하여 소요압축강도에 따른 콘크리트 배합 산정 결과를 출력하였다. 모델의 성능평가 결과, 콘크리트 압축 강도 인자에 대하여 평균 약 1.423%의 오류율을 나타내었으며, 삼성분계 콘크리트 배합인자 예측에 대하여 평균 8.22%의 MAPE 오차를 만족하였다. DNN 모델의 구조별 성능평가 비교 결과, 모든 배합인자에 대하여 DNN5L-2048 모델이 가장 높은 성능을 보였다. 학습된 DNN 모델을 사용하여 30, 50MPa의 소요압축강도를 가지는 삼성분계 콘크 리트 배합표 예측을 진행하였으며, 추후 학습을 위한 데이터 세트 확장과 실제 콘크리트 배합표와 DNN 모델 출력 콘 크리트 배합표 간의 비교를 통한 검증 과정이 필요할 것으로 판단된다.