• Journal of the Korean Society for Heat Treatment
• /
• v.16 no.1
• /
• pp.2-9
• /
• 2003

The aluminum alloy which is light and has excellent thermal conductivity and iron base alloy that is remarkable heat-resistece and wear resistence properties were bonded together. The bond was created between a stationary and a rotating member by using the frictional heat generated between them while subjected to high normal forces on the interface of Al alloy and iron base alloy. The microstructure of the bonded interface of friction welding and the strength in the bonded interface formed under various bonding conditions were examined through TEM, SEM with EDX and triple bending test. In interface of bonding materials formed after various heat treatment, bonding strength was substantially different, resulting from formation of intermetallic compound or softening during annealing.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.11
• /
• pp.4426-4442
• /
• 2020

Since scene segmentation is becoming a hot topic in the field of autonomous driving and medical image analysis, researchers are actively trying new methods to improve segmentation accuracy. At present, the main issues in image semantic segmentation are intra-class inconsistency and inter-class indistinction. From our analysis, the lack of global information as well as macroscopic discrimination on the object are the two main reasons. In this paper, we propose a Densely connected residual Attention network (DA-Res2Net) which consists of a dense residual network and channel attention guidance module to deal with these problems and improve the accuracy of image segmentation. Specifically, in order to make the extracted features equipped with stronger multi-scale characteristics, a densely connected residual network is proposed as a feature extractor. Furthermore, to improve the representativeness of each channel feature, we design a Channel-Attention-Guide module to make the model focusing on the high-level semantic features and low-level location features simultaneously. Experimental results show that the method achieves significant performance on various datasets. Compared to other state-of-the-art methods, the proposed method reaches the mean IOU accuracy of 83.2% on PASCAL VOC 2012 and 79.7% on Cityscapes dataset, respectively.

• Journal of Korea Multimedia Society
• /
• v.24 no.3
• /
• pp.382-395
• /
• 2021

In this study, character recognition using deep learning is performed among the various defects in the PCB, the purpose of which is to check whether the printed characters are printed correctly on top of components, or the incorrect parts are attached. Generally, character recognition may be perceived as not a difficult problem when considering MNIST, but the printed letters on the PCB component data are difficult to collect, and have very high redundancy. So if a deep learning model is trained with original data without any preprocessing, it can lead to over fitting problems. Therefore, this study aims to reduce the redundancy to the smallest dataset that can represent large amounts of data collected in limited production sites, and to create datasets through data enhancement to train a flexible deep learning model can be used in various production sites. Moreover, ResNet model verifies to determine which combination of datasets is the most effective. This study discusses how to reduce and augment data that is constantly occurring in real PCB production lines, and discusses how to select coresets to learn and apply deep learning models in real sites.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.1
• /
• pp.30-40
• /
• 2022

Electrocardiogram (ECG) signal's shape and characteristic varies through each individual, so it is difficult to classify with one neural network. It is difficult to classify the given data directly, but if corresponding normal beat is given, it is relatively easy and accurate to classify the beat by comparing two beats. In this study, we classify the ECG signal by generating the reference normal beat through the template cluster, and combining with the input ECG signal. It is possible to detect abnormal beats of various individual's records with one neural network by learning and classifying with the imaged ECG beats which are combined with corresponding reference normal beat. Especially, various neural networks, such as GoogLeNet, ResNet, and DarkNet, showed excellent performance when using the comparative learning. Also, we can confirmed that GoogLeNet has 99.72% sensitivity, which is the highest performance of the three neural networks.

• Korean journal of applied entomology
• /
• v.46 no.1 s.145
• /
• pp.153-158
• /
• 2007

This study was conducted to develope the observing methods for density of stink bugs in soybean reproductive stage. The adults and nymphs of bean bug, Riptortus clavatus, red-banded shield bug, Piezodous hybneri, green stink bug, Nezara antennata, Sole bug, Dolycoris baccarum, and brown marmorated stink bug, Halyomorpha halys were observed by three observing methods such as beating, sweeping net, and visual counting methods in the full bloom (R2), full pod (R4) and beginning maturity (R7) of soybean. As a result, total number of stink bugs observed was the highest with 5,214.2 by beating method, and then was 2,581.8 by visual counting method, and was the lowest with 103.1 by sweeping net method. Total number of stink bugs observed by the beating and visual counting methods was P. hybneri, followed by N. antennata, H. halys, R. clavatus and D. baccarum with clear difference in observed number of each stink bugs while total number of stink bugs observed by sweeping net method was very low in the range of 18 to 23. Accordingly, the observed density of stink bugs exception of R. clavatus adult by beating method was generally high. However, the number of R. clavatus adult was more observed by flushing method than that by beating method from the beginning bloom (R1) to full maturity (R8), and was more observed at morning time than that at afternoon time. Therefore, two observation methods that flushing method for R. clavatus and beating method for the other stink bugs were recommended for the occurring density of stink bugs in soybean because both bean bug and pentatomidae stink bugs have distinct behavior characteristics such as flying and dropping.

• Korean journal of applied entomology
• /
• v.46 no.1 s.145
• /
• pp.159-164
• /
• 2007

Pea weevil was easily observed in the flower and pod of garden pea, but not observed in soybean at various locations in Yeongnam district through 2001 to 2003. Number of pea weevil observed in pea flower was the highest at Milyang (20), followed by Yangsan (15), Sacheon (14) and Changnyong (13), and was the lowest at Pohang (3). On the other hand, number of pea weevil observed in pea pod was the highest at Tongyeong (192), followed by Changnyong (171), Sacheon (157) and Changwon (138), and was the lowest at Pohang (12) which showed simila. tendency with the result of pea flower. Number of pea weevil occurrence observed in pea pod after one and two times applications of Insecticides in pea field were different at harvest day of 30th May while were not significantly different at harvest day of 5th June. Likewise, number of pea pod damage after one and two times applications of insecticides were different at harvest day of 10th May while was not different at harvest day of 5th June. Thus, control efficacies of insecticides according to application times against pea weevil showed very high with above 95% at harvest day of 6th June while showed variable control efficacies at harvest of 30th May.

• Journal of Bio-Environment Control
• /
• v.9 no.3
• /
• pp.156-160
• /
• 2000

The Plasma film treated with a high electric voltage was developed to enhance flow down of condensation drops on inside plastic film. Arch type greenhouse framed with iron pipe of 25mm diameter defand 1.5mm thickness were covered with either the developed plasma film or surfactant film(control). Green pepper seedlings raised for 40 days in plug trays were transplanted at a density of 110cm by 30cm in each greenhouse. The mount of condensational water on film surface, generated by 7$0^{\circ}C$ water bath chimney systems and flew down, was collected and measured. The amount of collected water after 150 minutes was 2.56 mL.100c $m^{-2}$ and 0.94mL.100c $m^{-2}$ , respectively, in the plasma film and surfactant film-covered greenhouses. The amount of condensational water drops attached on the cover at 08:20 a.m. at 60 days filter covering was 0.34mL.100c $m^{02}$ and 0.32mL.100c $m^{-2}$ , respectively, in the plasma film- and surfactant film-covered greenhouses. Solar irradiance transmitted into greenhouse was 2.0% higher in the greenhouse covered with the plasma film tan that in the greenhouse covered with the surfactant film. Air temperature in the plasma film-covered greenhouse was higher than the surfactant film-covered greenhouse by 0.5$^{\circ}C$. However, there was no difference in relative humidity between the two greenhouse. Plant height, leaf area, dry weight and early yield showed no significant differences.s.

• Journal of agriculture & life science
• /
• v.44 no.3
• /
• pp.15-21
• /
• 2010

We estimated the biomass productivity and the storage potential of nitrogen, the major contributor of non-point source pollution, with four three-year-old four poplar clones in a riparian woody buffer established in the Anseong River in Anseong, Korea. Stem of Populus alba ${\times}$ P. glandulosa clone 72-31 and Populus deltoides ${\times}$ P. nigra clone Dorskamp showed the highest percentage of aboveground biomass components, followed by branch and leaf. Nitrogen content in aboveground biomass components of two poplar clones was the highest in leaf and the lowest in stem. Nitrogen content in leaf and branch of clone 72-31 was higher than that of clone Dorskamp, while it in stem was lower. Populus deltoides clone Ay48 showed the highest above-ground biomass productivity, which was estimated as $37.5ton\;ha^{-1}$ at age 3. However, clone 72-31 was the lowest in above-ground biomass productivity. Nitrogen storage potential in aboveground biomass of 3-year-old poplar clones was high in order of aboveground biomass. Clone Ay48 showed the highest nitrogen storage potential in aboveground biomass, which was estimated as $218.3kg\;ha^{-1}$ at age 3.

• Korean Journal of Radiology
• /
• v.23 no.10
• /
• pp.949-958
• /
• 2022

Objective: To investigate the feasibility of using a deep learning-based analysis of auscultation data to predict significant stenosis of arteriovenous fistulas (AVF) in patients undergoing hemodialysis requiring percutaneous transluminal angioplasty (PTA). Materials and Methods: Forty patients (24 male and 16 female; median age, 62.5 years) with dysfunctional native AVF were prospectively recruited. Digital sounds from the AVF shunt were recorded using a wireless electronic stethoscope before (pre-PTA) and after PTA (post-PTA), and the audio files were subsequently converted to mel spectrograms, which were used to construct various deep convolutional neural network (DCNN) models (DenseNet201, EfficientNetB5, and ResNet50). The performance of these models for diagnosing ≥ 50% AVF stenosis was assessed and compared. The ground truth for the presence of ≥ 50% AVF stenosis was obtained using digital subtraction angiography. Gradient-weighted class activation mapping (Grad-CAM) was used to produce visual explanations for DCNN model decisions. Results: Eighty audio files were obtained from the 40 recruited patients and pooled for the study. Mel spectrograms of "pre-PTA" shunt sounds showed patterns corresponding to abnormal high-pitched bruits with systolic accentuation observed in patients with stenotic AVF. The ResNet50 and EfficientNetB5 models yielded an area under the receiver operating characteristic curve of 0.99 and 0.98, respectively, at optimized epochs for predicting ≥ 50% AVF stenosis. However, Grad-CAM heatmaps revealed that only ResNet50 highlighted areas relevant to AVF stenosis in the mel spectrogram. Conclusion: Mel spectrogram-based DCNN models, particularly ResNet50, successfully predicted the presence of significant AVF stenosis requiring PTA in this feasibility study and may potentially be used in AVF surveillance.

• Journal of the Korean Chemical Society
• /
• v.12 no.2
• /
• pp.51-54
• /
• 1968

Rapid flame spectrophotometric method is developed to determine a small amount of sodium in zircon frit and high purity zirconium compounds. The instrumental characteristics and the optimum conditions are studied and a comparison between calibration curve method and standard addition method is made.