• 응용통계연구
• /
• 제31권1호
• /
• pp.13-28
• /
• 2018

우리나라 환경부에서는 지난 2005년과 2006년, 매 2년마다 세 번에 걸친 추적 조사를 하여 두 개의 독립적인 자료를 구축하였고, 2010년에 두 자료를 병합하여 Children's Health and Environmental Research (CHEER) 자료라 명명하였다. 본 연구는 CHEER 자료를 이용한 Kim 등 (Journal of the Korean Data and Information Science Society, 25, 987-998, 2014)과 Lee 등 (The Korean Journal of Applied Statistics, 29, 1295-1310, 2016)의 후속 연구로서, 두 동집단을 병합한 자료에서도 기존 연구에서 보고되었던 결과가 재현되는지 확인하고 ADHD를 종점으로 한 혈중 납 농도의 95% 신뢰 하한 (BMDL) 도출하였다. Lee 등 (2016)에서 제시한 벌점화 스플라인 모형을 이용하여 모든 년도의 ADHD 척도를 통일하였고, 경시적 자료의 특성과 아동의 나이에 대한 평균으로의 회귀 현상을 반영하여 임의 기울기 모형과 AR(1) 모형을 구축하였다. 두 모형을 바탕으로 혈중 납 농도의 벤치마크 용량 하한을 공식과 모의실험을 이용하여 도출한 결과, 종전의 연구보다 작은 벤치마크 용량의 분산 값으로 인하여 벤치마크 용량 하한 값이 증가한다는 사실을 확인할 수 있었다.

• 유통과학연구
• /
• 제13권6호
• /
• pp.97-104
• /
• 2015

Purpose - The distribution of agricultural products is changing due to recent shifts in environmental free trade. Specifically, the competitiveness of domestic agricultural products has weakened as a result of the Korea-China Financial Trade Agreement. Agricultural producers are faced with increasing difficulties and organized production centers are growing in importance daily. To overcome this crisis, agricultural producer organizations are vying for environment-friendly agricultural certifications, Good Agriculture Practices (GAP) and Hazard Analysis and Critical Control Point (HACCP). In particular, as consumer demand for higher safety grows, farmers are increasing their certification rates. Therefore, this certification system is expected to help strengthen the competitiveness of agricultural producer organizations. Research design/data/methodology - Organized production centers are classified by certification. A survey was conducted with 91 organizations using factor analysis and logistic regression analysis for the examination. The factor analysis results are as follows. Raw material procurement, education·specialization, marketing, joint business, organizing ability, business management, effectiveness, certification, and larger organizations were classified as the nine types of factors. These factors affect the organized production centers and are used in the logistic regression analysis. The purpose of such research and analysis is to suggest a direction for future production center policies. Results - The basic statistical results are as follows: analysis of the producer organizations of 91 sites, average number of members per site of 1,624, and average sales of 25,961 million won. Additionally, the average income per farmer is 175 million won, and the pooling system rate is 53.5%. The factor analysis results are as follows. Factor 1 consists of contract cultivation, ongoing shipment, selection subdivision, traceability, and major retailer management. Factor 2 consists of manual cultivation, specialty selection, education program, and R&D. Factor 3 consists of advertising, various dealers, various sales strategies, and a unified sales counter. Factor 4 consists of agricultural materials co-purchase, policy support, co-shipment, and incentives. Factor 5 consists of the co-selection and pooling system. Factor 6 consists of co-branding and operating by the organization's article. Factor 7 consists of the buy-sell ratio and rate of operation of the agriculture promotion center. Factor 8 consists of bargaining power in volume and participation rate of farmer certification. Factor 9 consists of increasing new subscribers. The logistic regression analysis results are as follows. Considering the results by type of certification, the environment-friendly agricultural certification type and the GAP certification type have a (+) influence. GAP and HACCP certification types affecting the education·specialization factor have a (+) influence. Considering the results for each type of certification, the environment-friendly agricultural certification types on the effectiveness factor have (-) influence; the HACCP certification types on the organizing ability and effectiveness factor have a (-) influence. Conclusions - Agricultural producer organizations should develop plans as follows: The organizations need to secure education for agricultural production; increase the pooling system ratio for sustainable organizational development; and, finally, expand the number of agricultural producer organizations.

• 인터넷정보학회논문지
• /
• 제19권4호
• /
• pp.35-44
• /
• 2018

Monitoring through Synthesis Aperture Radar (SAR) is responsible for marine safety from floating icebergs. However, there are limits to distinguishing between icebergs and ships in SAR images. Convolutional Neural Network (CNN) is used to distinguish the iceberg from the ship. The goal of this paper is to increase the accuracy of identifying icebergs from SAR images. The metrics for performance evaluation uses the log loss. The two-layer CNN model proposed in research of C.Bentes et al.[1] is used as a benchmark model and compared with the four-layer CNN model using data augmentation. Finally, the performance of the final CNN model using the VGG-16 pre-trained model is compared with the previous model. This paper shows how to improve the benchmark model and propose the final CNN model.

• ETRI Journal
• /
• 제46권3호
• /
• pp.526-537
• /
• 2024

Monitoring fetal growth in utero is crucial to anomaly diagnosis. However, current computer-vision models struggle to accurately assess the key metrics (i.e., head circumference and occipitofrontal and biparietal diameters) from ultrasound images, largely owing to a lack of training data. Mitigation usually entails image augmentation (e.g., flipping, rotating, scaling, and translating). Nevertheless, the accuracy of our task remains insufficient. Hence, we offer a U-Net fetal head measurement tool that leverages a hybrid Dice and binary cross-entropy loss to compute the similarity between actual and predicted segmented regions. Ellipse-fitted two-dimensional ultrasound images acquired from the HC18 dataset are input, and their lower feature layers are reused for efficiency. During regression, a novel region of interest pooling layer extracts elliptical feature maps, and during segmentation, feature pyramids fuse field-layer data with a new scale attention method to reduce noise. Performance is measured by Dice similarity, mean pixel accuracy, and mean intersection-over-union, giving 97.90%, 99.18%, and 97.81% scores, respectively, which match or outperform the best U-Net models.

• 한국구조물진단유지관리공학회 논문집
• /
• 제23권6호
• /
• pp.38-44
• /
• 2019

본 연구에서는 아스팔트 콘크리트 도로포장의 표면균열 검출을 위해 합성곱 신경망을 이용하였다. 합성곱 신경망의 학습에 사용되는 표면균열 이미지 데이터의 양에 따른 합성곱 신경망의 성능향상 정도를 평가하였다. 사용된 합성곱 신경망의 구조는 5개의 층으로 구성되어있으며, 3×3 크기의 convolution filter와 2×2 크기의 pooling kernel을 사용하였다. 합성곱 신경망의 학습을 위해서 도로노면 조사 장비를 통해 구축된 국내 도로포장 표면균열 이미지를 활용하였다. 표면균열 이미지 데이터를 학습한 합성곱 신경망 모델의 표면균열 검출 정확도, 정밀도, 재현율, 미검출율, 과검출율을 평가하였다. 가장 많은 양의 데이터를 학습한 합성곱 신경망 모델의 표면균열 검출 정확도, 정밀도, 재현율은 96.6% 이상, 미검출율, 과검출율은 3.4% 이하의 성능을 나타내었다.

• IEIE Transactions on Smart Processing and Computing
• /
• 제6권1호
• /
• pp.10-17
• /
• 2017

We propose classification algorithms for human and dog movement. The proposed algorithms use micro-Doppler signals obtained from humans and dogs moving in four different directions. A two-stage classifier based on a support vector machine (SVM) is proposed, which uses a radial-based function (RBF) kernel and $16^{th}$-order linear predictive code (LPC) coefficients as feature vectors. With the proposed algorithms, we obtain the best classification results when a first-level SVM classifies the type of movement, and then, a second-level SVM classifies the moving object. We obtain the correct classification probability 95.54% of the time, on average. Next, to deal with the difficult classification problem of human and dog running, we propose a two-layer convolutional neural network (CNN). The proposed CNN is composed of six ($6{\times}6$) convolution filters at the first and second layers, with ($5{\times}5$) max pooling for the first layer and ($2{\times}2$) max pooling for the second layer. The proposed CNN-based classifier adopts an auto regressive spectrogram as the feature image obtained from the $16^{th}$-order LPC vectors for a specific time duration. The proposed CNN exhibits 100% classification accuracy and outperforms the SVM-based classifier. These results show that the proposed classifiers can be used for human and dog classification systems and also for classification problems using data obtained from an ultra-wideband (UWB) sensor.

• Journal of Preventive Medicine and Public Health
• /
• 제50권2호
• /
• pp.91-99
• /
• 2017

Objectives: As in many low-income and middle-income countries, out-of-pocket (OOP) payments by patients or their families are a key healthcare financing mechanism in Bangladesh that leads to economic burdens for households. The objective of this study was to identify whether and to what extent socioeconomic, demographic, and behavioral factors of the population had an impact on OOP expenditures in Bangladesh. Methods: A total of 12 400 patients who had paid to receive any type of healthcare services within the previous 30 days were analyzed from the Bangladesh Household Income and Expenditure Survey data, 2010. We employed regression analysis for identify factors influencing OOP health expenditures using the ordinary least square method. Results: The mean total OOP healthcare expenditures was US dollar (USD) 27.66; while, the cost of medicines (USD 16.98) was the highest cost driver (61% of total OOP healthcare expenditure). In addition, this study identified age, sex, marital status, place of residence, and family wealth as significant factors associated with higher OOP healthcare expenditures. In contrary, unemployment and not receiving financial social benefits were inversely associated with OOP expenditures. Conclusions: The findings of this study can help decision-makers by clarifying the determinants of OOP, discussing the mechanisms driving these determinants, and there by underscoring the need to develop policy options for building stronger financial protection mechanisms. The government should consider devoting more resources to providing free or subsidized care. In parallel with government action, the development of other prudential and sustainable risk-pooling mechanisms may help attract enthusiastic subscribers to community-based health insurance schemes.

• International Journal of Computer Science & Network Security
• /
• 제22권5호
• /
• pp.175-181
• /
• 2022

COVID-19 is an acute respiratory syndrome that affects the host's breathing and respiratory system. The novel disease's first case was reported in 2019 and has created a state of emergency in the whole world and declared a global pandemic within months after the first case. The disease created elements of socioeconomic crisis globally. The emergency has made it imperative for professionals to take the necessary measures to make early diagnoses of the disease. The conventional diagnosis for COVID-19 is through Polymerase Chain Reaction (PCR) testing. However, in a lot of rural societies, these tests are not available or take a lot of time to provide results. Hence, we propose a COVID-19 classification system by means of machine learning and transfer learning models. The proposed approach identifies individuals with COVID-19 and distinguishes them from those who are healthy with the help of Deep Visual Embeddings (DVE). Five state-of-the-art models: VGG-19, ResNet50, Inceptionv3, MobileNetv3, and EfficientNetB7, were used in this study along with five different pooling schemes to perform deep feature extraction. In addition, the features are normalized using standard scaling, and 4-fold cross-validation is used to validate the performance over multiple versions of the validation data. The best results of 88.86% UAR, 88.27% Specificity, 89.44% Sensitivity, 88.62% Accuracy, 89.06% Precision, and 87.52% F1-score were obtained using ResNet-50 with Average Pooling and Logistic regression with class weight as the classifier.

• 한국방사선학회논문지
• /
• 제14권1호
• /
• pp.39-44
• /
• 2020

본 연구에서는 CNN과 빅데이터 기술을 이용한 Deep Learning을 통해 흉부 X-ray 영상 분류 및 정확성 연구에 대하여 알아보고자 한다. 총 5,873장의 흉부 X-ray 영상에서 Normal 1,583장, Pneumonia 4,289장을 사용하였다. 데이터 분류는 train(88.8%), validation(0.2%), test(11%)로 분류하였다. Convolution Layer, Max pooling layer pool size 2×2, Flatten layer, Image Data Generator로 구성하였다. Convolution layer가 3일 때와 4일 때 각각 filter 수, filter size, drop out, epoch, batch size, 손실함수 값을 설정하였다. test 데이터로 Convolution layer가 4일 때, filter 수 64-128-128-128, filter size 3×3, drop out 0.25, epoch 5, batch size 15, 손실함수 RMSprop으로 설정 시 정확도가 94.67%였다. 본 연구를 통해 높은 정확성으로 분류가 가능하였으며, 흉부 X-ray 영상뿐만 아니라 다른 의료영상에서도 많은 도움이 될 것으로 사료된다.

• 한국멀티미디어학회논문지
• /
• 제21권12호
• /
• pp.1407-1416
• /
• 2018

The purpose of this study was to train a model for the ulna and radius bone segmentation based on Convolutional Neural Networks and to verify the segmentation model. The data consisted of 840 training data, 210 tuning data, and 200 verification data. The learning model for the ulna and radius bone bwas based on U-Net (19 convolutional and 8 maximum pooling) and trained with 8 batch sizes, 0.0001 learning rate, and 200 epochs. As a result, the average sensitivity of the training data was 0.998, the specificity was 0.972, the accuracy was 0.979, and the Dice's similarity coefficient was 0.968. In the validation data, the average sensitivity was 0.961, specificity was 0.978, accuracy was 0.972, and Dice's similarity coefficient was 0.961. The performance of deep convolutional neural network based models for the segmentation was good for ulna and radius bone.