While literature reveals the positive perception of e-Learning, this study examined and assessed the impact of e-Learning crack-up perceptions on psychological distress among college students during COVID-19 pandemic. Kessler psychological distress scale (K10) was used to evaluate stress symptoms. This study first conducted an online focus group discussion (OFGD) with the target population to develop the scale of "e-Learning crack-up" and "fear of academic year loss". Afterward, a questionnaire was developed based on OFGD findings. An online survey was conducted amongst college students in Bangladesh using a purposive sampling technique. Results show that "e-Learning crack-up" perception has a significant positive impact on student's psychological distress, and fear of academic year loss is the crucial factor that is responsible for psychological distress during COVID-19 lockdown. This study can provide an understanding of how "e-Learning crack-up" and "Fear of academic year loss" influence college students' mental health. Theoretically, this study extends and validated the scope of Kessler's psychological distress scale with two new contexts. Practically, this study will help the government and policymakers identify the student's mental well-being and take more appropriate action to address these issues.
UK and EU-based applicants are invited to tender for the 2020 CRACK IT Challenges. The aim of the competition is to develop technologies with potential 3Rs* benefits into new products and methodologies for the biosciences research community. The Challenges are detailed in the Challenge briefs.
The 2020 CRACK IT Challenges competition consists of five Challenges: three Two Phase Challenges and two Single Phase Challenges. All Challenges have been developed jointly by the NC3Rs and Sponsors. The 2020 CRACK IT Challenges competition is funded by the NC3Rs with co-funding from Dstl, EPSRC and Unilever. In-kind contributions are provided by the Sponsors. There are 11 Sponsors: AstraZeneca, Agenda Vets, Bayer AG, CRUK Manchester Institute - University of Manchester, Dstl, GSK, Mary Lyon Centre, Merck Healthcare KGaA, Novartis Pharma AG, The Sainsbury Wellcome Centre (University College London) and Unilever.
LR-321 family of epoxies offer versatility for various crack injection applications. LR-321 & LR-321LPL are low viscosity formulas with LR-321LPL offering a longer pot life for larger repairs. LR-321G is a thixotropic formula for blind side injection.
Optical coherence tomography (OCT) is an imaging technique that can visualize the internal biological structure without X-ray exposure. Swept-source OCT (SS-OCT) is one of the latest version of OCT, wherein the light source is a tunable laser that sweeps near-infrared wavelength light to achieve real-time imaging. The imaging depth of OCT is highly influenced by the translucency of the medium. The medium that does not transmit light and the deeper structure beyond the range of light penetration depth are not relevant for OCT imaging. In OCT, sound enamel is almost transparent at the OCT wavelength range, and enamel and dentin can be distinguished from each other as the dentin-enamel junction (DEJ) appears as a dark border. Demineralized enamel and dentin are imaged as bright zones because of the formation of numerous micro-porosities where the backscatter of OCT signal is increased. In cavitated caries at interproximal or occlusal hidden zone, the upper margin of the cavity reflects the signal showing a distinct bright border in the SS-OCT image. SS-OCT is capable of determining crack penetration depth even when the cracks extended beyond the DEJ. SS-OCT has a high degree of sensitivity and specificity for the detection of dental caries and tooth cracks. SS-OCT is also capable of detecting non-carious cervical lesions and occlusal tooth wear in cross-sectional views to estimate the amount of tooth structure loss.
In 2016, Zhang et al.  proposed a crack detection method based on deep learning. They trained a deep CNN based on supervised learning, proving the feasibility of combining deep learning with pavement crack recognition. In 2017, Zhao et al.  proposed a pavement crack detection method based on a CNN using images of different scales and taken at different angles for training, achieving the detection of cracks of various shapes. However, owing to road surface interference and noise, the detection accuracy of this system peaked at 82.5%. In 2017, Markus et al. developed the open dataset GAPs for the training of deep neural network and evaluated the pavement damage detection technology for the first time, which is of great significance [20, 21]. In 2018, Nhat-Duc et al.  established an intelligent method for the automatic recognition of pavement crack morphology; this study constructs a machine learning model for pavement crack classification that included multiple support vector machines and an artificial swarm optimization algorithm. Using feature analysis, a set of features is extracted from the image projection integral, which can significantly improve the prediction performance. However, the algorithm is complex and programming it becomes very difficult. In 2020, Zhaoyun Sun et al.  proposed a method to detect pavement expansion cracks with the improved Faster R-CNN, which can achieve accurate expansion crack location detection through the optimization model. The aforementioned studies only detect and classify pavement cracks and their location but cannot quantify certain crack characteristics, such as crack width and area. On the other hand, there are also many studies on crack segmentation. In 2018, Zhang and Wang  proposed CrackNet, which is an efficient architecture based on CNN to predict the class of each image pixel, but its network structure is related to input image size, which prevents the generalization of the method. In the same year, Sen Wang et al.  proposed to use the full convolutional networks (FCNs) to detect cracks and built the Crack-FCN model taking into account the shortcomings of the FCN model in the crack segmentation experiment and obtained a complete crack image. However, the highest accuracy obtained by their method is only 67.95%; thus, segmentation performance needs to be improved. In 2019, Piao Weng et al.  proposed a pavement crack segmentation method based on the VGG-U-Net model. It solves the problem of fracture in the crack segmentation result in complex background, but its training time is slightly longer and its efficiency is low. In 2020, Zhun Fan et al.  proposed an encoder-decoder architecture based on hierarchical feature learning and dilated convolution (U-HDN) detects cracks in an end-to-end manner. The U-HDN method can extract and fuse different context sizes and different levels of feature mapping, so it has high performance. In the same year, Zhun Fan et al.  proposed an ensemble of convolutional neural network based on probability fusion for automatic detection and measurement of pavement cracks, and the predicted crack morphology is measured by skeleton extraction algorithm. In summary, these previous studies only use the segmentation method, which cannot achieve accurate crack classification and location determination.
Increasing the number of network layers can improve the accuracy of the network in identifying pavement cracks. Therefore, in this study, the feature extraction network structure Visual Geometry Group 16 (VGG16) in the SSD network model was replaced with a deep residual network to improve the pavement crack identification accuracy. The deep residual network [33, 34] solves this problem by fitting a residual map instead of the original map and by adding multiple connections between layers.
By replacing the feature extraction structure of the original SSD network with the deep residual network, the network accuracy and recall rate in predicting pavement cracks were substantially improved. This analysis of the experimental results shows that the proposed method achieves good results in the classification and detection of cracks. From the prediction effect, however, a classification by the pavement crack detection method based on the single SSD crack location model is incomplete, is not conducive to subsequent crack geometry parameter computation steps, and will produce larger calculation errors. Thus, as the practical application value is still lacking at this point, this study adopted the fusion segmentation model approach to address this problem.
The structure of the U-Net network is simple, and the original U-Net network has crack segmentation accuracy problems. Therefore, the feature extraction network of the U-Net crack segmentation model was also replaced with a deep residual network to fully extract crack features and ensure crack segmentation accuracy. The specific improvement steps are similar to those of the SSD model. As shown in Table 3, the two basic network feature graph outputs match the network layers. After adjusting the corresponding layers of the feature extraction network, it is still necessary to adjust the network parameters through continuous training to optimize the crack segmentation effect. The improved crack segmentation model is shown in Figure 11.
In the training of U-Net crack segmentation model, the ReLU function is used as the activation function and the input data samples are regularized many times. Regularization adjusts the output value of each convolutional network layer to the same distribution, thereby avoiding a deviation or change in the distribution of feature vectors caused by network deepening. The segmentation model uses the upsampling method. That is, the feature map with the new size is obtained by the convolution inversion operation, and the feature map with the size corresponding to the convolution layer is added as the upsampling result. The segmentation network performs upsampling of the feature extraction network feature maps with sizes of , , , and , and the upsampling process combines the feature extraction network feature maps with sizes of , , , and ; this improves the segmentation network accuracy through multilevel joint learning. 2b1af7f3a8