Impacts of Social Media (Facebook) on Human Communication and Relationships

Tang-Mui Joo,Chan-Eang Teng 건국대학교 지식콘텐츠연구소 2017 International Journal of Knowledge Content Develop Vol.7 No.4

Deep learning-based post-disaster building inspection with channel-wise attention and semi-supervised learning

Rih-Teng Wu,Wen Tang,Tarutal Ghosh Mondal,Abhishek Subedi,Mohammad R. Jahanshahi 국제구조공학회 2023 Smart Structures and Systems, An International Jou Vol.31 No.4

The existing vision-based techniques for inspection and condition assessment of civil infrastructure are mostly manual and consequently time-consuming, expensive, subjective, and risky. As a viable alternative, researchers in the past resorted to deep learning-based autonomous damage detection algorithms for expedited post-disaster reconnaissance of structures. Although a number of automatic damage detection algorithms have been proposed, the scarcity of labeled training data remains a major concern. To address this issue, this study proposed a semi-supervised learning (SSL) framework based on consistency regularization and cross-supervision. Image data from post-earthquake reconnaissance, that contains cracks, spalling, and exposed rebars are used to evaluate the proposed solution. Experiments are carried out under different data partition protocols, and it is shown that the proposed SSL method can make use of unlabeled images to enhance the segmentation performance when limited amount of ground truth labels are provided. This study also proposes DeepLab-AASPP and modified versions of U-Net++ based on channel-wise attention mechanism to better segment the components and damage areas from images of reinforced concrete buildings. The channel-wise attention mechanism can effectively improve the performance of the network by dynamically scaling the feature maps so that the networks can focus on more informative feature maps in the concatenation layer. The proposed DeepLab-AASPP achieves the best performance on component segmentation and damage state segmentation tasks with mIoU scores of 0.9850 and 0.7032, respectively. For crack, spalling, and rebar segmentation tasks, modified U-Net++ obtains the best performance with Igou scores (excluding the background pixels) of 0.5449, 0.9375, and 0.5018, respectively. The proposed architectures win the second place in IC-SHM2021 competition in all five tasks of Project 2.

Ensemble-based deep learning for autonomous bridge component and damage segmentation leveraging Nested Reg-UNet

Rih-Teng Wu,Abhishek Subedi,Wen Tang,Tarutal Ghosh Mondal,Mohammad R. Jahanshahi 국제구조공학회 2023 Smart Structures and Systems, An International Jou Vol.31 No.4

Computer vision-based damage detection enables non-contact, efficient and low-cost bridge health monitoring, which reduces the need for labor-intensive manual inspection or that for a large number of on-site sensing instruments. By leveraging recent semantic segmentation approaches, we can detect regions of critical structural components and identify damages at pixel level on images. However, existing methods perform poorly when detecting small and thin damages (e.g., cracks); the problem is exacerbated by imbalanced samples. To this end, we incorporate domain knowledge to introduce a hierarchical semantic segmentation framework that imposes a hierarchical semantic relationship between component categories and damage types. For instance, certain types of concrete cracks are only present on bridge columns, and therefore the noncolumn region may be masked out when detecting such damages. In this way, the damage detection model focuses on extracting features from relevant structural components and avoid those from irrelevant regions. We also utilize multi-scale augmentation to preserve contextual information of each image, without losing the ability to handle small and/or thin damages. In addition, our framework employs an importance sampling, where images with rare components are sampled more often, to address sample imbalance. We evaluated our framework on a public synthetic dataset that consists of 2,000 railway bridges. Our framework achieves a 0.836 mean intersection over union (IoU) for structural component segmentation and a 0.483 mean IoU for damage segmentation. Our results have in total 5% and 18% improvements for the structural component segmentation and damage segmentation tasks, respectively, compared to the best-performing baseline model.

Crack segmentation in high-resolution images using cascaded deep convolutional neural networks and Bayesian data fusion

Rih-Teng Wu,Wen Tang,Mohammad R. Jahanshahi 국제구조공학회 2022 Smart Structures and Systems, An International Jou Vol.29 No.1

Manual inspection of steel box girders on long span bridges is time-consuming and labor-intensive. The quality of inspection relies on the subjective judgements of the inspectors. This study proposes an automated approach to detect and segment cracks in high-resolution images. An end-to-end cascaded framework is proposed to first detect the existence of cracks using a deep convolutional neural network (CNN) and then segment the crack using a modified U-Net encoder-decoder architecture. A Naive Bayes data fusion scheme is proposed to reduce the false positives and false negatives effectively. To generate the binary crack mask, first, the original images are divided into 448 × 448 overlapping image patches where these image patches are classified as cracks versus non-cracks using a deep CNN. Next, a modified U-Net is trained from scratch using only the crack patches for segmentation. A customized loss function that consists of binary cross entropy loss and the Dice loss is introduced to enhance the segmentation performance. Additionally, a Naive Bayes fusion strategy is employed to integrate the crack score maps from different overlapping crack patches and to decide whether a pixel is crack or not. Comprehensive experiments have demonstrated that the proposed approach achieves an 81.71% mean intersection over union (mIoU) score across 5 different training/test splits, which is 7.29% higher than the baseline reference implemented with the original U-Net.

CT Experimental Study on the Damage Characteristics of Anchored Layered Rocks

Junyang Teng,Jianxin Tang,Yuning Zhang,Xinyi Li 대한토목학회 2018 KSCE JOURNAL OF CIVIL ENGINEERING Vol.22 No.9

A laboratory physical simulation and a CT scan test were conducted to analyze the anchoring mechanism of a system anchor bolt and a steel floral pipe in a layered rock mass. The following conclusions were drawn: (1) The anchoring effect of the system anchor bolt and steel floral pipe improves the strength parameter of the layered rock, and the system anchor bolt provides higher improvement. Neglecting the jointing effect, the improvement in the strength parameter of the layered rock due to the anchor bolt is primarily reflected by the following three aspects: the compressive zone effect of the preload, the repairing effect of the anchoring agent on defects in country rocks, and the reinforcement effect of the anchor bolt on the overall strength and density of the anchoring object. Considering the jointing effect, the improvement in the strength parameter of the layered rock due to the anchor bolt is reflected by improvement in the deformability and shear strength of the joint surface. (2) The stress-strain curves of the anchored specimens can be divided into different stages of damage evolution, based on the angles of bedding. (3) The crack-arresting effect of the anchor bolt is due to the weakening, cutting, and arresting of the cracks in the anchorage zone. The larger the anchorage zone, the better is the crack-arresting effect.

The Last Call

Xiaohan Teng,Qingxia Li,Libo Tang 한국콘텐츠학회 2017 ICCC International Digital Design Invitation Exhib Vol.2017 No.8

Representation of Disabled Community in Mainstream Media

Chan Eang Teng,Tang Mui Joo 건국대학교 지식콘텐츠연구소 2020 International Journal of Knowledge Content Develop Vol.10 No.2

miR-458b-5p regulates ovarian granulosa cells proliferation through Wnt/β‐catenin signaling pathway by targeting catenin beta-1

Wang Wenwen,Teng Jun,Han Xu,Zhang Shen,Zhang Qin,Tang Hui 아세아·태평양축산학회 2021 Animal Bioscience Vol.34 No.6

Objective: Ovarian follicular development, which dependent on the proliferation and differentiation of granulosa cells (GCs), is a complex biological process in which miRNA plays an important role. Our previous study showed that miR-458b-5p is associated with ovarian follicular development in chicken. The detailed function and molecular mechanism of miR-458b-5p in GCs is unclear. Methods: The luciferase reporter assay was used to verify the targeting relationship between miR-458b-5p and catenin beta-1 (CTNNB1), which is an important transcriptional regulatory factor of the Wnt/β-catenin pathway. The cell counting kit-8 (CCK-8) assay, flow cytometry with propidium iodide (PI) and annexin V-fluorescein isothiocyanate (FITC) labeling were applied to explore the effect of miR-458b-5p on proliferation, cell cycle and apoptosis of chicken GCs. Quantitative real-time polymerase chain reaction and Western blot were used to detect the mRNA and protein expression levels. Results: We demonstrated that the expression of miR-458b-5p and CTNNB1 showed the opposite relationship in GCs and theca cells of hierarchical follicles. The luciferase reporter assay confirmed that CTNNB1 is the direct target of miR-458b-5p. Using CCK-8 assay and flow cytometry with PI and Annexin V-FITC labeling, we observed that transfection with the miR-458b-5p mimics significantly reduced proliferation and has no effects on apoptosis of chicken GCs. In addition, miR-458b-5p decreased the mRNA and protein expression of CD44 molecule and matrix metallopeptidase 7, which are the downstream effectors of CTNNB1 in Wnt/β-Catenin pathway and play functional roles in cell proliferation. Conclusion: Taken together, the data indicate that miR-458b-5p regulates ovarian GCs proliferation through Wnt/β-catenin signaling pathway by targeting CTNNB1, suggesting that miR-458b-5p and its target gene CTNNB1 may potentially play a role in chicken ovarian follicular development. Objective: Ovarian follicular development, which dependent on the proliferation and differentiation of granulosa cells (GCs), is a complex biological process in which miRNA plays an important role. Our previous study showed that miR-458b-5p is associated with ovarian follicular development in chicken. The detailed function and molecular mechanism of miR-458b-5p in GCs is unclear.Methods: The luciferase reporter assay was used to verify the targeting relationship between miR-458b-5p and catenin beta-1 (<i><i>CTNNB1</i></i>), which is an important transcriptional regulatory factor of the Wnt/β-catenin pathway. The cell counting kit-8 (CCK-8) assay, flow cytometry with propidium iodide (PI) and annexin V-fluorescein isothiocyanate (FITC) labeling were applied to explore the effect of miR-458b-5p on proliferation, cell cycle and apoptosis of chicken GCs. Quantitative real-time polymerase chain reaction and Western blot were used to detect the mRNA and protein expression levels.Results: We demonstrated that the expression of miR-458b-5p and <i>CTNNB1</i> showed the opposite relationship in GCs and theca cells of hierarchical follicles. The luciferase reporter assay confirmed that <i>CTNNB1</i> is the direct target of miR-458b-5p. Using CCK-8 assay and flow cytometry with PI and Annexin V-FITC labeling, we observed that transfection with the miR-458b-5p mimics significantly reduced proliferation and has no effects on apoptosis of chicken GCs. In addition, miR-458b-5p decreased the mRNA and protein expression of CD44 molecule and matrix metallopeptidase 7, which are the downstream effectors of <i>CTNNB1</i> in Wnt/β-Catenin pathway and play functional roles in cell proliferation.Conclusion: Taken together, the data indicate that miR-458b-5p regulates ovarian GCs proliferation through Wnt/β-catenin signaling pathway by targeting <i>CTNNB1</i>, suggesting that miR-458b-5p and its target gene <i>CTNNB1</i> may potentially play a role in chicken ovarian follicular development.

WDRP, a DWD protein component of CUL4-based E3 ligases, acts as a receptor of CDPK-related protein kinase 5 to mediate kinase degradation in Arabidopsis

Hui-Juan Teng,Yue Guo,Jian-Qi Wang,Rongjun Li,Ying-Tang Lu,Lei Zhang 한국식물학회 2016 Journal of Plant Biology Vol.59 No.6

CRK5 is a member of the Arabidopsis thaliana Ca2+-dependent protein kinase-related kinase family. Here, a yeast two-hybrid screen was performed with a truncated form of AtCRK5 as bait to identify interacting proteins and determine its physiological roles. One gene encoding the DWD protein WDRP was isolated. Furthermore, in vitro and in vivo co-immunoprecipitation results strongly supported that these two proteins interact with each other. Using a cell-free degradation assay, we also established that CRK5 was an unstable protein that was degraded through the proteasome pathway. The rate of CRK5 degradation was delayed in a WDRP knockout line. On the other hand, the degradation of CRK5 mediated by WDRP might not affect the phosphorylation of PIN2 by CRK5. Overall, we demonstrated that AtCRK5 interacted with a DWD protein, AtWDRP; the protein AtWDRP targets the kinase for ubiquitin-dependent degradation. Therefore, this report describes a new kinase regulation pathway for CRK family proteins in Arabidopsis.

Adsorption Mechanism of Magnetic Induction Free- Abrasive Grain and Its Effect on Cutting Performance of Wire Saws

Wei Peng,Teng-wei Qiu,Chun-yan Yao,Chen Tang,Wei Zhang 한국정밀공학회 2015 International Journal of Precision Engineering and Vol. No.

This paper proposes a method of free-abrasive wire sawing in the magnetic field. Magnetic abrasive grains are absorbed on surface of the wire by magnetic force, and therefore more magnetic abrasive grains are carried into cutting area. This mechanism is helpful to improve the cutting performance of wire saws. Theoretical modeling of the movement trajectory of magnetic abrasive grains is done in the magnetic field, and it is also verified by observation experiments of movement trajectory of magnetic abrasive grains. Absorption angle, which is used as the indicator of adsorption capacity about magnetic abrasive grain on surface of the wire, is proposed in this paper. The effect of magnetic field intensity on absorption angle is analyzed through computer simulations and observation experiments. Practical experiments and cutting results show that the change of magnetic field intensity has a significant impact on cutting efficiency, surface roughness, and kerf width.