• 대한가정학회지
• /
• 제29권2호
• /
• pp.135-154
• /
• 1991

The purposes of this study are: 1) To find out overall family life issues percieved by the middle-classhousewives in their forties. 2) To examine detailed aspects related to middle years crises, leisure activities, children issues, family economy issues, and housing issues. 3) To clarify solutions to, and provide basic data on family issues raised by the middle-class families. The middle-class housewives in their forties living in the Seoul area were the subject of the survey. The sample size analysed in this study was 422. Data were analysed by the frequency, mean, percentile, standard deviation, X2-test, analysis of variance, multiple classification analysis, analysis of multiple regression, and Scheffe-test as a post-hoc analysis. The conclusions are as follows: First, the middle-class housewives tend to give more importance on children issues, especially on academic achievement and career development. Second, family cohesion of middle-class families is comparatively high and intra-familial conflict is low, and middle years crisis of housewives is comparatively low, too. Third, the stability of middle-class families can be found in household economic management patterns. one fourth of the families own stocks and two fifths of the families own real estate except their own dwelling house. Be based on their property income add to their labor income, middle-class families are showed their economic stability, however, intra-class inequality is found, too. Fourth, the great part of middle-class families that possess their own house, tend to be unsatisfied with their housig scale, and a half of the families expect to enlarge their housing scale for more comfortable and convient living.

• 한국안전학회지
• /
• 제38권6호
• /
• pp.72-78
• /
• 2023

The purpose of this paper is to derive a quantified approach for Operator Manual Actions (OMAs) based on the existing fire Human Reliability Analysis (HRA) methodology developed by the Korea Atomic Energy Research Institute (KAERI). The existing fire HRA method was reviewed, and supplementary considerations for OMA quantification were established through a comparative analysis with NUREG-1852 criteria and the review of the existing literature. The OMA quantification approach involves a timeline that considers the occurrence of Multiple Spurious Operations (MSOs) during a Main Control Room Abandonment (MCRA) determination and movement towards the Remote Shutdown Panel (RSP) in the event of a Main Control Room (MCR) fire. The derived failure probability of an OMA from the approach proposed in this paper is expected to enhance the understanding of its reliability. Therefore, it allows moving beyond the deterministic classification of "reliable" or "unreliable" in NUREG-1852. Also, in the event of a nuclear power plant fire where multiple OMAs are required within a critical time range, it is anticipated that the OMA failure probability could serve as a criterion for prioritizing OMAs and determining their order of importance.

• Journal of Electrical Engineering and Technology
• /
• 제12권2호
• /
• pp.830-839
• /
• 2017

Support vector machine (SVM) is introduced as an effective fault diagnosis technique based on dissolved gases analysis (DGA) for oil-immersed transformers with maximum generalization ability; however, the applicability of the SVM is highly affected due to the difficulty of selecting the SVM parameters appropriately. Therefore, a novel approach combing SVM with improved imperialist competitive algorithm (IICA) for fault diagnosis of oil-immersed transformers was proposed in the paper. The improved ICA, which is proved to be an effective optimization approach, is employed to optimize the parameters of SVM. Cross validation and normalizations were applied in the training processes of SVM and the trained SVM model with the optimized parameters was established for fault diagnosis of oil-immersed transformers. Three classification benchmark sets were studied based on particle swarm optimization SVM (PSOSVM) and IICASVM with four multiple classification schemes to select the best scheme for transformer fault diagnosis. The results show that the proposed model can obtain higher diagnosis accuracy than other methods. The comparisons confirm that the proposed model is an effective approach for classification problems.

• Journal of Information Processing Systems
• /
• 제14권4호
• /
• pp.892-903
• /
• 2018

The paper proposes a novel gait recognition algorithm based on feature fusion of gait energy image (GEI) dynamic region and Gabor, which consists of four steps. First, the gait contour images are extracted through the object detection, binarization and morphological process. Secondly, features of GEI at different angles and Gabor features with multiple orientations are extracted from the dynamic part of GEI, respectively. Then averaging method is adopted to fuse features of GEI dynamic region with features of Gabor wavelets on feature layer and the feature space dimension is reduced by an improved Kernel Principal Component Analysis (KPCA). Finally, the vectors of feature fusion are input into the support vector machine (SVM) based on multi classification to realize the classification and recognition of gait. The primary contributions of the paper are: a novel gait recognition algorithm based on based on feature fusion of GEI and Gabor is proposed; an improved KPCA method is used to reduce the feature matrix dimension; a SVM is employed to identify the gait sequences. The experimental results suggest that the proposed algorithm yields over 90% of correct classification rate, which testify that the method can identify better different human gait and get better recognized effect than other existing algorithms.

• 한국직업건강간호학회지
• /
• 제28권2호
• /
• pp.75-82
• /
• 2019

Purpose: This study aimed to determine the influence of injury and/or injured area classification on depression in patients with industrial injuries. Methods: The participants comprised438 patients who consented to participate and completed self-reported questionnaires. Data were analyzed using SPSS/WIN version 22.0 for descriptive statistics, $x^2$ test, fisher's exact test, ANOVA, and post-hoc $Scheff{\acute{e}}$ test. A stepwise multiple regression analysis was used to identify factors influencing depression. Results: The results indicated that the effect of disease classification and injured areas on depression were significantly different in patients with industrial injuries. The results further showed that severe depression was significantly higher in cardiovascular patients and patients with an injured area of the head and waist. The most powerful predictor was age (50~59 years), return to work (reemployment), disease classification (cardiovascular), and injured area (head, including vascular disease). Conclusion: This study showed that the most influential variable of depression in patients with industrial injuries were cardiovascular issues, injury areas of the head and waist, being aged 50~59 years, and reemployment. To reduce depression in these patients, it is important to develop and implement a psychiatric rehabilitation program that helps patients to formulate a concrete plan and goal for recovery, enabling patients to actively engage in their rehabilitation.

• The Plant Pathology Journal
• /
• 제39권4호
• /
• pp.319-334
• /
• 2023

Plant disease is an important factor affecting crop yield. With various types and complex conditions, plant diseases cause serious economic losses, as well as modern agriculture constraints. Hence, rapid, accurate, and early identification of crop diseases is of great significance. Recent developments in deep learning, especially convolutional neural network (CNN), have shown impressive performance in plant disease classification. However, most of the existing datasets for plant disease classification are a single background environment rather than a real field environment. In addition, the classification can only obtain the category of a single disease and fail to obtain the location of multiple different diseases, which limits the practical application. Therefore, the object detection method based on CNN can overcome these shortcomings and has broad application prospects. In this study, an annotated apple leaf disease dataset in a real field environment was first constructed to compensate for the lack of existing datasets. Moreover, the Faster R-CNN and YOLOv3 architectures were trained to detect apple leaf diseases in our dataset. Finally, comparative experiments were conducted and a variety of evaluation indicators were analyzed. The experimental results demonstrate that deep learning algorithms represented by YOLOv3 and Faster R-CNN are feasible for plant disease detection and have their own strong points and weaknesses.

• 한국수자원학회논문집
• /
• 제57권5호
• /
• pp.321-332
• /
• 2024

하천 공간의 지표 피복 현황 파악은 하천 관리 및 홍수 재해 예방에 필수적이다. 기존 조사 방법은 전문가에 의한 식생 판독을 통한 식생도 작도 방법이나 식생지수를 활용하는 방법이 활용되어 왔으나, 역동적으로 변화하는 하천 환경을 반영하기에 한계가 있다. 이러한 배경에서 본 연구는 내성천을 대상으로 위성영상 자료를 활용한 랜덤 포레스트 기법을 활용하여 다수 연도의 하천 내 식생 분포를 파악하고, 적용성을 검토하였다. 원격탐사 자료 Sentinel-2 위성 영상을 사용하였으며, 지상 참값(ground truth)은 2016년 내성천 지표 피복 자료를 활용하였다. 랜덤 포레스트 머신러닝 알고리듬을 활용하여 미리 선정된 10개 샘플링 영역으로부터 분류군 별로 1,000개의 표본을 추출하여 훈련 및 검증하였으며, 민감도 분석, 연도별 지표 피복 분석, 정확도 분석을 통하여 적용성을 평가하였다. 연구 결과, 검증 자료 기반의 정확도는 85.1%로 나타났다. 트리 수, 샘플 수, 하천 구역에 대한 민감도 분석 결과, 각각 30개, 800개, 하류에서 효율성이 높았다. 지표 분류 유형은 6개 항목에서 높은 정확도를 보여 지표 피복 분류 결과가 실제 하천 환경을 잘 반영하는 것으로 나타났다. 정확도 분석 결과, 전체 샘플 중 14.9%의 경계오류와 내부오류를 확인하였으며, 지표 피복 분류 중 산발 식생과 초본 식생을 제외한 항목들은 높은 정확도를 보였다. 본 연구에서는 단일 하천을 대상으로 적용하였지만, 보다 정확하고 많은 자료의 구축을 위해서는 다수의 하천에 대해 지표 피복 분류 기법의 적용이 요구된다.

• 한국전기전자재료학회:학술대회논문집
• /
• 한국전기전자재료학회 2009년도 추계학술대회 논문집
• /
• pp.44-44
• /
• 2009

Fault detection is necessary for yield enhancement and cost reduction in semiconductor manufacturing. Sensory data acquired from the semiconductor processing tool is too large to analyze for the purpose of fault detection and classification(FDC). We studied the techniques of fault detection using statistical method. Multiple regression analysis smoothly detected faults and can be easy made a model. For real-time and fast computing time, the huge data was analyzed by each step. We also considered interaction and critical factors in tool parameters and process.

• 한국인구학
• /
• 제2권1호
• /
• pp.5-16
• /
• 1978

The main purpose of this study is to examine the recent level of fertility and potentiality of the Korean population in Japan and to investigate some forces which influence the fertility of them using survey data. Some estimates of the level of fertility for the Korean population in Japan in 1974 are presented in Table 1. Comparing the some estimates for 1974 with those for 1969, the level of fertility in 1974 was realistically declined. It also indicated that potentiality of Koreans in Japan showed decreasing population. For investigating some factors affecting fertility, total births is selected which regressed on some variables believed in general to be influential in determiaing fertility. It was used a step-wise multiple regression to determine the independent as well as the combined effects of each of the variables. The SPSS computer program was used to perform the anlysis. Result from this data reveals that wife's family size preference as relevant predictor does influence the fertility of Koreans in Japan at this point considering that the age group of 20-29 is very much related. By employing multiple classification analysis, the analysis is concluded by nothing that the wi 3 family size preference has an even stronger relationship with economic factors than any other facto 3.

• Journal of Multimedia Information System
• /
• 제9권3호
• /
• pp.177-182
• /
• 2022

A deep neural network (DNN) includes variables whose values keep on changing with the training process until it reaches the final point of convergence. These variables are the co-efficient of a polynomial expression to relate to the feature extraction process. In general, DNNs work in multiple 'dimensions' depending upon the number of channels and batches accounted for training. However, after the execution of feature extraction and before entering the SoftMax or other classifier, there is a conversion of features from multiple N-dimensions to a single vector form, where 'N' represents the number of activation channels. This usually happens in a Fully connected layer (FCL) or a dense layer. This reduced 2D feature is the subject of study for our analysis. For this, we have used the FCL, so the trained weights of this FCL will be used for the weight-class correlation analysis. The popular DNN models selected for our study are ResNet-101, VGG-19, and GoogleNet. These models' weights are directly used for fine-tuning (with all trained weights initially transferred) and scratch trained (with no weights transferred). Then the comparison is done by plotting the graph of feature distribution and the final FCL weights.