• Journal of Platform Technology
• /
• v.9 no.3
• /
• pp.52-62
• /
• 2021

Quality control is critical at manufacturing sites and is key to predicting the risk of quality defect before manufacturing. However, the reliability of manual quality control methods is affected by human and physical limitations because manufacturing processes vary across industries. These limitations become particularly obvious in domain areas with numerous manufacturing processes, such as the manufacture of major nuclear equipment. This study proposed a novel method for predicting the risk of quality defects by using natural language processing and machine learning. In this study, production data collected over 6 years at a factory that manufactures main equipment that is installed in nuclear power plants were used. In the preprocessing stage of text data, a mapping method was applied to the word dictionary so that domain knowledge could be appropriately reflected, and a hybrid algorithm, which combined n-gram, Term Frequency-Inverse Document Frequency, and Singular Value Decomposition, was constructed for sentence vectorization. Next, in the experiment to classify the risky processes resulting in poor quality, k-fold cross-validation was applied to categorize cases from Unigram to cumulative Trigram. Furthermore, for achieving objective experimental results, Naive Bayes and Support Vector Machine were used as classification algorithms and the maximum accuracy and F1-score of 0.7685 and 0.8641, respectively, were achieved. Thus, the proposed method is effective. The performance of the proposed method were compared and with votes of field engineers, and the results revealed that the proposed method outperformed field engineers. Thus, the method can be implemented for quality control at manufacturing sites.

• Journal of the Korea Computer Graphics Society
• /
• v.27 no.3
• /
• pp.65-74
• /
• 2021

3D reconstruction means that reconstructing the 3D shape of the object in an image and a video. We proposed a progressive occupancy network architecture that can recover not only the overall shape of the object but also the local details. Unlike the original occupancy network, which uses a feature vector embedding information of the whole image, we extract and utilize the different levels of image features depending on the receptive field size. We also propose a novel network architecture that applies the image features sequentially to the decoder blocks in the decoder and improves the quality of the reconstructed 3D shape progressively. In addition, we design a novel decoder block structure that combines the different levels of image features properly and uses them for updating the input point feature. We trained our progressive occupancy network with ShapeNet. We compare its representation power with two prior methods, including prior occupancy network(ONet) and the recent work(DISN) that used different levels of image features like ours. From the perspective of evaluation metrics, our network shows better performance than ONet for all the metrics, and it achieved a little better or a compatible score with DISN. For visualization results, we found that our method successfully reconstructs the local details that ONet misses. Also, compare with DISN that fails to reconstruct the thin parts or occluded parts of the object, our progressive occupancy network successfully catches the parts. These results validate the usefulness of the proposed network architecture.

• Journal of Bio-Environment Control
• /
• v.28 no.4
• /
• pp.311-321
• /
• 2019

Greenhouse farmers often use thermal screens to reduce greenhouse heating expenses during the winter, and for shade during hot, sunny days in the summer, as it is an inexpensive solution to temperature control relative to other available options. However, accurate measurements of their emitted and absorbed radiations are important for the selection of suitable screens that offer maximum performance. Material's ability to save energy is highly dependent on these properties. Limited studies have investigated the measurement of these properties under natural conditions, but they are only applicable to materials having partial porosities. In this work, we describe a new radiation balance method for determining emissive power and absorptive capacity, as well as reflectivity, transmissivity and emissivity of materials having complete and partial transparency by using pyrgeometer and net radiometer. In this study, four materials with zero porosity, were tested. The emissivity value of PE, LD-13, LD-15 and PH-20 was $0.439{\pm}0.020$, $0.460{\pm}0.010$, $0.454{\pm}0.004$, and $0.499{\pm}0.006$, respectively. All tested samples showed high emitted radiation as compared to absorbed radiation.

• Journal of Internet Computing and Services
• /
• v.20 no.5
• /
• pp.105-111
• /
• 2019

Core technologies that lead the Fourth Industrial Revolution era, such as artificial intelligence, big data, and autonomous driving, are implemented and serviced through the rapid development of computing power and hyper-connected networks based on the Internet of Things. In this paper, we implement two different models for drivable area segmentation in various environment, and propose a better model by comparing the results. The models for drivable area segmentation are using DeepLab V3+ and Mask R-CNN, which have great performances in the field of image segmentation and are used in many studies in autonomous driving technology. For driving information in various environment, we use BDD dataset which provides driving videos and images in various weather conditions and day&night time. The result of two different models shows that Mask R-CNN has higher performance with 68.33% IoU than DeepLab V3+ with 48.97% IoU. In addition, the result of visual inspection of drivable area segmentation on driving image, the accuracy of Mask R-CNN is 83% and DeepLab V3+ is 69%. It indicates Mask R-CNN is more efficient than DeepLab V3+ in drivable area segmentation.

• The Korean Journal of Applied Statistics
• /
• v.33 no.6
• /
• pp.791-804
• /
• 2020

Residential electricity consumption can be predicted more accurately by utilizing the realtime household electricity consumption reference that can be collected by the AMI as the ICT developed under the smart grid circumstance. This paper studied the model that predicts residential power load using the ARIMA, TBATS, NNAR model based on the data of hour unit amount of household electricity consumption, and unlike forecasting the consumption of the whole households at once, it computed the anticipated amount of the electricity consumption by aggregating the predictive value of each established model of cluster that was collected by the households which show the similiar load profile. Especially, as the typical time series data, the electricity consumption data chose the clustering analysis method that is appropriate to the time series data. Therefore, Dynamic Time Warping and Periodogram based method is used in this paper. By the result, forecasting the residential elecrtricity consumption by clustering the similiar household showed better performance than forecasting at once and in summertime, NNAR model performed best, and in wintertime, it was TBATS model. Lastly, clustering method showed most improvements in forecasting capability when the DTW method that was manifested the difference between the patterns of each cluster was used.

• Journal of Internet of Things and Convergence
• /
• v.8 no.6
• /
• pp.99-113
• /
• 2022

This study is descriptive research to investigate the effects of COVID-19 stress, interpersonal (caregiver-patient) stress, and emotional labor on burnout in emergency room (ER) nurses during the COVID-19 pandemic. The data collection of this study was conducted from December 9 to 23, 2021 with ER nurses working at five tertiary general hospitals and general hospitals of Medical Center H. The data was collected with a questionnaire using tools measuring the subjects' general & job-related characteristics, COVID-19 stress, interpersonal(caregiver-patient) stress, emotional labor and burnout. The collected data was analyzed using the SPSS/WIN 25.0 statistical program for frequency analysis, descriptive statistical analysis, independent sample t-test, one-way ANOVA, Scheffé test, correlation analysis, and multiple regression analysis. The average score of COVID-19 stress in ER nurses was 3.64, interpersonal(caregiver-patient) stress 4.35, emotional labor 3.38, and burnout 3.44. As a result of analyzing differences according to general & job-related characteristics, burnout showed a significant difference according to gender, marital status, total clinical experience, and working organization. And burnout showed a significant positive correlation with COVID-19 stress, interpersonal stress and emotional labor. As a result of multiple linear regression analysis, regional emergency medical centers and local emergency medical centers among the work organization types, interpersonal stress, COVID-19 stress, and gender and the explanatory power was 28.6%. Through these results, we intend to provide basic data for the development of an intervention program to prevent burnout of emergency room nurses and improve nursing performance at the time of a new infectious disease pandemic.

• Applied Chemistry for Engineering
• /
• v.32 no.4
• /
• pp.361-370
• /
• 2021

Carbon fiber reinforced polymer (CFRP) is one of the composite materials, which has a unique property that is lightweight but strong. The CFRPs are widely used in various industries where their unique characteristics are required. In particular, electric and unmanned aerial vehicles critically need lightweight parts and bodies with sufficient mechanical strengths. Vehicles using the battery as a power source should simultaneously meet two requirements that the battery has to be safely protected. The vehicle should be light of increasing the mileage. The CFRP has considered as the one that satisfies the requirements and is widely used as battery housing and other vehicle parts. On the other hand, in the battery area, carbon fibers are intensively tested as battery components such as electrodes and/or current collectors. Furthermore, using carbon fibers as both structure reinforcements and battery components to build a structural battery is intensively investigated in Sweden and the USA. This mini-review encompasses recent research trends that cover the classification of structural batteries in terms of functionality of carbon fibers and issues and efforts in the battery and discusses the prospect of structural batteries.

• Journal of agriculture & life science
• /
• v.51 no.1
• /
• pp.187-192
• /
• 2017

In various crops, seedlings are preferred to seeds for faster and more effective growth, so transplanters are used for them. This 2-row transplanter was developed to promote the mechanization of vegetable transplanting work which depends on human power. and it can automatically supply seedling tray and transport picked up seedling to the planting hopper. Also, we judged performance of transplanter with comparing seedling missing plant ration according to two types of pick-up method. Result of experiment, in finger-type picking up of 265 seedlings, missing plant ratio was 13.7% with 17 failures of pick-up and 15 collapse of bed soil. and In fork-type picking up of 200 seedlings, failure of pick-up was not appeared and missing plant ratio was low as 4% with 6 dropped during transfer. Therefore for 2-row automatic transplanter, fork-type pick-up device was found to be compatible.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.13 no.4
• /
• pp.63-70
• /
• 2003

In the modern electronic world, the authentication of a person is an important task in many areas of online-transactions. Using biometrics to authenticate a person's identity has several advantages over the present practices of Personal Identification Numbers(PINs) and passwords. To gain maximum security in the verification system using biometrics, the computation of the verification as well as the store of the biometric pattern has to be taken place in the security token(smart card, USB token). However, there is an open issue of integrating biometrics into the security token because of its limited resources(memory space, processing power). In this paper, we describe our implementation of the USB security token system having 206MHz StrongARM CPU, 16MBytes flash memory, and 1MBytes RAM. Also, we evaluate the performance of a light-weighted In-gerprint verification algorithm that can be executed in the restricted environments. Based on experimental results, we confirmed that the RAM requirement of the proposed algorithm was about 6.8 KBytes and the Equal Error Rate(EER) was 1.7%.

• Journal of the Korean Applied Science and Technology
• /
• v.38 no.3
• /
• pp.813-823
• /
• 2021

This study was conducted to identify the factors affecting the compliance of standard precautions for nurses working in long term care hospitals. As a result of the analysis, 8.50 points in perception of the standard precautions, 3.76 points in health beliefs(subcategories- 4.03 points in perceived sensitivity, 4.04 points in perceived seriousness, 3.91 points in perceived benefits, 3.54 points in perceived barrier, 2.92 points in cues to action), 37.90 points in compliance status of the standard precautions. The performance of the standard precautions was positively correlated with perception of the standard precautions(r=0.419, p=.001) and health beliefs (r=0.443, p<.001), perceived sensitivity (r=0.169, p=.044), perceived barrier(r=0.486, p<.001), perceived benefits (r=0.207, p=.013), cues to action (r=0.204, p=.014). The compliance status of the standard precautions was influenced by the perceived barrier(β=0.373, p<.001), cues to action (β=0.271, p<.001), perception of the standard precautions(β=0.245, p=.004)explanatory power was 32.5%.