Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Defect Detection Using Deep Learning-Based YOLOv3 in Cross-Sectional Image of Additive Manufacturing

Choi Byungjoo, Choi Yongjun, Lee Moon-Gu, Kim Jung-Sub, Lee Sang-Won, Jeon Yongho

Archives of Metallurgy and Materials

2021

Vol. 66, iss. 4

1037--1041

Deposition defects like porosity, crack and lack of fusion in additive manufacturing process is a major obstacle to commercialization of the process. Thus, metallurgical microscopy analysis has been mainly conducted to optimize process conditions by detecting and investigating the defects. However, these defect detection methods indicate a deviation from the operator’s experience. In this study, artificial intelligence based YOLOv3 of object detection algorithm was applied to avoid the human dependency. The algorithm aims to automatically find and label the defects. To enable the aim, 80 training images and 20 verification images were prepared, and they were amplified into 640 training images and 160 verification images using augmentation algorithm of rotation, movement and scale down, randomly. To evaluate the performance of the algorithm, total loss was derived as the sum of localization loss, confidence loss, and classification loss. In the training process, the total loss was 8.672 for the initial 100 sample images. However, the total loss was reduced to 5.841 after training with additional 800 images. For the verification of the proposed method, new defect images were input and then the mean Average Precision (mAP) in terms of precision and recall was 0.3795. Therefore, the detection performance with high accuracy can be applied to industry for avoiding human errors.

Simultaneous determination of seven sesquiterpene lactone glucosides in Ixeris dentata by high-performance liquid chromatography coupled with tandem mass spectrometry and their antiviral activities

Park SeonJu, Kim Nanyoung, Park Jun Hyung, Lee Sang-Won, Song Jae-Hyoung, Ko Hyun-Jeong, Chae Han-Jung, Kim Hyung-Ryong, Kim Seung Hyun

Acta Chromatographica

2019

Vol. 31, no. 4

280--285

Ixeris dentata (Thunb. ex Thunb.) Nakai (Asteraceae), a well-known edible vegetable in Asia, contains various bioactive secondary metabolites, including sesquiterpene lactones. In this study, a high-performance liquid chromatography–tandem mass spectrometry (HPLC–MS/MS) method has been developed and validated for simultaneous determination of seven sesquiterpene lactone glucosides isolated from the roots of I. dentata. In addition, these compounds were evaluated in terms of their antiviral activities against coxsackievirus B3 (CVB3) and human enterovirus 71 (EV71). The developed method was validated in terms of linearity (R2 > 0.9996), precision (RSD < 2.24%), accuracy (96.30–102.77%), and stability (RSD < 1.94%) and successfully applied to the quantitation of the I. dentata root samples collected from six different regions of Korea. The content of sesquiterpene lactone glucosides varied significantly based on the region. For the antiviral activities, guaianolides with an ester group at C-8 (compounds 6 and 7) showed the most potent activities against CBV3, while germacranolide (compound 5) showed the most consistent antiviral activity against both CVB3 and EV71. The method was validated to be simple and reliable to simultaneously determine seven putative bioactive sesquiterpene lactone glucosides, the substantial chemotaxonomic markers, in I. dentata root samples