• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제12권3호
• /
• pp.193-197
• /
• 2012

This paper focuses on identifying which appliance is currently operating by analyzing electrical load signature for home energy monitoring system. The identification framework is comprised of three steps. Firstly, specific appliance features, or signatures, were chosen, which are DC (Duty Cycle), SO (Slope of On-state), VO (Variance of On-state), and ZC (Zero Crossing) by reviewing observations of appliances from 13 houses for 3 days. Five appliances of electrical rice cooker, kimchi-refrigerator, PC, refrigerator, and TV were chosen for the identification with high penetration rate and total operation-time in Korea. Secondly, K-NN and Naive Bayesian classifiers, which are commonly used in many applications, are employed to estimate from which appliance the signatures are obtained. Lastly, one of candidates is selected as final identification result by majority voting. The proposed identification frame showed identification success rate of 94.23%.

• Journal of Information Processing Systems
• /
• 제15권1호
• /
• pp.67-90
• /
• 2019

Accurate detection, tracking and analysis of human movement using robots and other visual surveillance systems is still a challenge. Efforts are on to make the system robust against constraints such as variation in shape, size, pose and occlusion. Traditional methods of detection used the sliding window approach which involved scanning of various sizes of windows across an image. This paper concentrates on employing a state-of-the-art, hierarchical graph based method for segmentation. It has two stages: part level segmentation for color-consistent segments and object level segmentation for category-consistent regions. The tracking phase is achieved by employing SIFT keypoint descriptor based technique in a combined matching and tracking scheme with validation phase. Localization of human region in each frame is performed by keypoints by casting votes for the center of the human detected region. As it is difficult to avoid incorrect keypoints, a consensus-based framework is used to detect voting behavior. The designed methodology is tested on the video sequences having 3 to 4 persons.

• 한국정보기술학회 영문논문지
• /
• 제10권1호
• /
• pp.25-36
• /
• 2020

Motivation: Fibers as the extracellular filamentous structures determine the shape of the cytoskeletal structures. Their characterization and reconstruction from a 3D cellular image represent very useful quantitative information at the cellular level. In this paper, we presented a novel automatic method to extract fiber diameter distribution through a pipeline to reconstruct fibers from 3D fluorescence confocal images. The pipeline is composed of four steps: segmentation, skeletonization, template fitting and fiber tracking. Segmentation of fiber is achieved by defining an energy based on tensor voting framework. After skeletonizing segmented fibers, we fit a template for each seed point. Then, the fiber tracking step reconstructs fibers by finding the best match of the next fiber segment from the previous template. Thus, we define a fiber as a set of templates, based on which we calculate a diameter distribution of fibers.

• Nuclear Engineering and Technology
• /
• 제55권10호
• /
• pp.3716-3724
• /
• 2023

Loose parts monitoring and detecting alarm type in real Nuclear Power Plant have challenges such as background noise, insufficient alarm data, and difficulty of distinction between alarm data that occur during start and stop. Although many signal processing methods and alarm determination algorithms have been developed, it is not easy to determine valid alarm and extract the meaning data from alarm signal including background noise. To address these issues, this paper proposes a denoising autoencoder-based majority vote classification. Training and test data are prepared by acquiring alarm data from real NPP and simulation facility for data augmentation, and noisy data is reproduced by adding Gaussian noise. Using DAEs with 3, 5, 7, and 9 layers, features are extracted for each model and classified into neural networks. Finally, the results obtained from each DAE are classified by majority voting. Also, through comparison with other methods, the accuracy and the false alarm rate are compared, and the excellence of the proposed method is confirmed.

• Journal of Nutrition and Health
• /
• 제36권5호
• /
• pp.515-527
• /
• 2003

Objectives： A meta-analysis of the literatures was conducted to evaluate the cost-effectiveness of medical nutrition therapy by dietitians. Methods : The 30 studies were identified from a computerized search of published research on MEDLINE, Science-Direct and the PQD database until May, 2002 and a review of reference lists. The main search terms were“dietitian”,“dietary intervention”,“nutrition intervention”, “cost”,“cost-effectiveness”and“cost-benefit analysis”. The subgroup analysis was performed by publication year, study design, intervention provider, type of patient (in/out-patient) and type of cost (total cost/direct cost). Two reviewers independently selected trials for inclusion, assessed the quality and extracted the data. Results : The 30 studies were identified using the electric database search and bibliographies. The 17 trials were eligible for inclusion criteria, then the systematic review and a meta-analysis were conducted on effectiveness and cost-effectiveness of medical nutrition therapy. The quality of the studies was evaluated using the quality assessment tool for observational studies. The quality score was 0.515 $\pm$ 0.121 (range : 0.279-0.711, median : 0.466). The meta-analysis of 17 studies based on the random effect model showed that medical nutrition therapy was highly effective in treating the diseases (effect size 0.3092 : 95% confidence interval 0.2282-0.3303). The vote-counting method, one of meta-analysis methods, was applied to evaluate the cost-effectiveness of medical nutrition therapy conducted by dietitians. Two criteria (method 1, method 2) for voting were used. The calculated p-values for method 1 (more conservative method) and method 2 (less conservative method) were 0.1250 and 0.0106, respectively. Medical nutrition therapy by dietitians was significantly cost-effective in the method 2. Conclusion. This meta-analysis showed that the effectiveness of medical nutrition therapy was statistically significant in treating disease (effect size 0.3092), and that the cost-effectiveness of medical nutrition therapy was statistically significant in the method 2 (less conservative method) of vote counting. (Korean J Nutrition 36(5): 515~527, 2003)

• 한국컴퓨터그래픽스학회논문지
• /
• 제28권1호
• /
• pp.1-9
• /
• 2022

비소세포폐암(NSCLC)은 전체 폐암 중 85%의 높은 비중을 차지하며 사망률(22.7%)이 다른 암에 비해 현저히 높은 암으로 비소세포폐암 환자의 수술 후 예후에 대한 예측은 매우 중요하다. 본 연구에서는 종양을 관심영역으로 갖는 비소세포폐암 환자의 수술 전 흉부 CT 영상 패치의 종류를 종양 관련 정보에 따라 총 다섯 가지로 다양화하고, 이를 입력데이터로 갖는 사전 학습 된 ResNet 과 EfficientNet CNN 네트워크를 사용하여 단일 모델과 간접 투표 방식을 이용한 앙상블 모델, 그리고 3 개의 입력 채널을 활용한 앙상블 모델에서의 실험 결과 및 성능을 오분류의 사례와 Grad-CAM 시각화를 통해 비교 분석한다. 실험 결과, 종양 주변부 패치를 학습한 ResNet152 단일 모델과 EfficientNet-b7 단일 모델은 각각 87.93%와 81.03%의 정확도를 보였다. 또한 ResNet152 에서 총 3 개의 입력 채널에 각각 영상 패치, 종양 주변부 패치, 형상 집중 종양 내부 패치를 넣어 앙상블 모델을 구성한 경우에는 정확도 87.93%를, EfficientNet-b7 에서 간접 투표 방식으로 영상 패치와 종양 주변부 패치 학습 모델을 앙상블 한 경우에는 정확도 84.48%를 도출하며 안정적인 성능을 보였다.

• 한국차세대컴퓨팅학회논문지
• /
• 제13권4호
• /
• pp.29-39
• /
• 2017

다양한 전자전 상황에서 단위 위협체에 대하여 전자전 모델링과 시뮬레이션을 수행할 수 있는 통합 전자전 시뮬레이터의 개발 필요성이 대두되고 있다. 본 논문에서는 전자전 상황에서 전자정보 수집신호의 변수를 기반으로 전자파 신호를 발산하는 레이더 위협을 역추정하기 위한 시뮬레이션 시스템의 구성요소를 분석하고, 역추정 모델을 점진적으로 유지할 수 있는 방법을 제안한다. 또한, 실험을 통하여 점진적 역추정 모델 갱신 기법의 유효성 및 개별 역추정 결과의 통합 기법을 평가한다. 개별 역추정 모델의 생성을 위하여 의사결정트리, 베이지안 분류기, 인공신경망 및 유클리디안 거리 측정방식과 코사인 유사도 측정방식을 활용하는 군집화 알고리즘을 이용하였다. 첫 번째 실험에서 레이더 위협체에 대한 역추정 모델을 구축하기 위한 위협 예제의 크기를 점진적으로 증가시키면 역추정 모델의 정확도는 향상되었으며, 이러한 과정이 반복되면 역추정 모델에 대한 정확도는 일정한 값으로 수렴하였다. 두 번째 실험에서는 개별 역추정 모델의 결과를 통합하기 위하여 투표, 가중투표 및 뎀스터-쉐이퍼 알고리즘을 이용하였으며, 역추정 모델의 통합 결과는 뎀스터-쉐이퍼 알고리즘에 의한 역추정 정확도가 가장 좋은 성능을 보였다.

• The Journal of the Acoustical Society of Korea
• /
• 제20권2E호
• /
• pp.17-24
• /
• 2001

In this paper, we propose the bootstrap and aggregating (bagging) vector quantization (VQ) classifier to improve the performance of the text-independent speaker recognition system. This method generates multiple training data sets by resampling the original training data set, constructs the corresponding VQ classifiers, and then integrates the multiple VQ classifiers into a single classifier by voting. The bagging method has been proven to greatly improve the performance of unstable classifiers. Through two different experiments, this paper shows that the VQ classifier is unstable. In one of these experiments, the bias and variance of a VQ classifier are computed with a waveform database. The variance of the VQ classifier is compared with that of the classification and regression tree (CART) classifier[1]. The variance of the VQ classifier is shown to be as large as that of the CART classifier. The other experiment involves speaker recognition. The speaker recognition rates vary significantly by the minor changes in the training data set. The speaker recognition experiments involving a closed set, text-independent and speaker identification are performed with the TIMIT database to compare the performance of the bagging VQ classifier with that of the conventional VQ classifier. The bagging VQ classifier yields improved performance over the conventional VQ classifier. It also outperforms the conventional VQ classifier in small training data set problems.

• 방송공학회논문지
• /
• 제17권4호
• /
• pp.659-669
• /
• 2012

이 논문에서는 이진 핑거프린트의 결합을 이용해 새로운 이진 오디오 핑거프린트를 만드는 방법을 제안하다. 필립스 핑거프린팅 시스템을 활용하여, 그 시스템에서 활용한과 비슷한 특성을 가질 것이라 예상되는 기본 이진 핑거프린트를 여러 개 추출하고, 기본 이진 핑거프린트들의 투표로 하나의 이진 오디오 핑거프린트를 결정한다. 정합단에서는 이진 핑거프린트를 이용하는 것이 아니라, 기본 이진 핑거프린트들의 합을 이용하여 거리를 계산한다. 실험을 통해서 제안하는 방법으로 만들어진 핑거프린트가 그것의 기초가 되는 기본 이진 핑거프린트들보다 향상된 성능을 보임을 확인할 수 있었다. 이 방법을 이용해서 기존의 이진 핑거프린트의 성능을 강화하거나 새로운 이진 핑거프린트를 만들 수 있을 것이라 기대된다.

• 한국조사연구학회지:조사연구
• /
• 제3권2호
• /
• pp.77-90
• /
• 2002

본 논문은 임의표집법(Random Sampling)에 의거한 전화조사방법을 2002년 울산시장선거조사에 적용하여 실시한 사례를 다루었다. 임의로 표집된 1,233개 가정용 전화번호에 전화하여 생일법으로 추출된 응답자를 대상으로 최대 5회에 걸쳐 접촉을 시도하였다. 최대 5회 전화시도의 접촉 차수를 분석하여 부재와 약속 등에 대한 재접촉의 효과를 살펴보고, 표집된 표본집단의 인구사회학적 특성을 모집단과 비교하였으며 조사결과와 실제 투표결과와의 비교도 다양하게 검토하였다. 또한 생일법을 통한 임의표집법의 어려움과 조사시간대 조정 및 지속적 재접촉 등 임의표집법 활성화 방안에 대해 논의한다.