Development of Concrete Damage Classification in Beam-Column Joint based on Ultrasonic Pulse Velocity

The concreted conditions assessment of the systems is an essential aspect of security assessment programs. In situ measurements of Ultrasonic Pulse Velocity (UPV) may be indicative of the level of damage in the original concrete. UPV influenced by the specific characteristics of the mixture. In situ UPV measurements can be indicative of the level of damage in the original concrete. The research purpose is the damage classification, UPV test interpretation (strength, density, elasticity modulus, Concrete Quality Designation (CQD)), and determines the level of structural damage visually so that more accurate inspection results. The research result showed that the plastic hinge was more damaged than other parts of the beam-column joints. The UPV test obtained density 0.84-1.03 g/cm3, CQD 10% -20%, static elastic modulus 7.68-8.39 Gpa according to [3],[4] including very poor and visually is included in category IV spalling off of covering concrete (crack width > 2mm). The use of UPV as supporting assessment for classification, repair, and maintenance of structures. If density, CQD, and elastic modulus of defining very poor classification, the structure that needs immediate repair. The use of UPV is faster, without damaging parts of the structure, and also induces damage to the core specimens as a result of the coring process, making it faster and more economical.

Few-Shot Learning for Post-Earthquake Urban Damage Detection

Among natural disasters, earthquakes are recorded to have the highest rates of human loss in the past 20 years. Their unexpected nature has severe consequences on both human lives and material infrastructure, demanding urgent action to be taken. For effective emergency relief, it is necessary to gain awareness about the level of damage in the affected areas. The use of remotely sensed imagery is popular in damage assessment applications; however, it requires a considerable amount of labeled data, which are not always easy to obtain. Taking into consideration the recent developments in the fields of Machine Learning and Computer Vision, this study investigates and employs several Few-Shot Learning (FSL) strategies in order to address data insufficiency and imbalance in post-earthquake urban damage classification. While small datasets have been tested against binary classification problems, which usually divide the urban structures into collapsed and non-collapsed, the potential of limited training data in multi-class classification has not been fully explored. To tackle this gap, four models were created, following different data balancing methods, namely cost-sensitive learning, oversampling, undersampling and Prototypical Networks. After a quantitative comparison among them, the best performing model was found to be the one based on Prototypical Networks, and it was used for the creation of damage assessment maps. The contribution of this work is twofold: we show that oversampling is the most suitable data balancing method for training Deep Convolutional Neural Networks (CNN) when compared to cost-sensitive learning and undersampling, and we demonstrate the appropriateness of Prototypical Networks in the damage classification context.

Automatic Car Damage detection by Hybrid Deep Learning Multi Label Classification

Automating image-based automobile insurance claims processing is a significant opportunity. In this research work, car damage categorization that is aided by the hybrid convolutional neural network approach is addressed and hence the deep learning-based strategies are applied. Insurance firms may leverage this paper's design and implementation of an automobile damage classification/detection pipeline to streamline car insurance claim policy. Using deep convolutional networks to detect car damage is now possible because of recent improvements in the artificial intelligence sector, mainly due to less computation time and higher accuracy with a hybrid transformation deep learning algorithm. In this paper, multiclass classification proposed to categorize the car damage parts such as broken headlight/taillight, glass fragments, damaged bonnet etc. are compiled into the proposed dataset. This model has been pre-trained on a wide-ranging and benchmark dataset due to the dataset's limited size to minimize overfitting and to understand more common properties of the dataset. To increase the overall proposed model’s performance, the CNN feature extraction model is trained with Resnet architecture with the coco car damage detection datasets and reaches a higher accuracy of 90.82%, which is much better than the previous findings on the comparable test sets.

Study of the RBE depth dependence of protons using a damage diagnostic algorithm and its application in proton therapy based on Monte Carlo simulation

The present study aimed to calculate the yields of DNA breaks and the variation of relative biological effectiveness (RBE) at different depths for protons using Geant4-DNA. For this purpose, an atomic model of DNA and a DNA damage classification matrix were used to calculate different DNA break yields for 62-MeV protons. As the reference radiation, the secondary electron spectrum produced by 60Co was evaluated. This helped to calculate the SSB and DSB yields. Moreover, RBE was found to be between 1.1 at the first point and 1.51 in the Bragg peak region. In this region, it was 37% greater than the 5-mm depth in the plateau region. Considering different threshold energies, the energy deposition at 10.79 eV had the most contribution to the total damage. As the results suggested, the depth dependence of RBE should be taken into account for proton therapy. It was also found that DNA break yields significantly depend on the threshold energy value.

Laboratory investigations on the quality of leak tests and visual inspections of wastewater connection pipes carried out by specialist contractors

In addition to stability and operational safety, leak tightness is the permanent functional objective of wastewater pipes. Tests to determine the tightness of wastewater pipes can in some cases produce results that are worthy of discussion. Therefore, laboratory tests were carried out by 29 specialist contractors to obtain results on the quality of leak tests and visual inspections of connection pipes. The results showed that different test errors can be observed for leak test methods (air overpressure, air underpressure and water pressure). However, only in the case of the water pressure tests did the observed test errors occasionally lead to incorrect test results, i.e. the ‘leaking pipe’ was tested as ‘test passed (tight)’. The investigations into the accuracy (trueness and precision) of the test methods showed that all test methods examined were sufficiently accurate to determine the tightness of the connection pipes. In general, correct test results were achieved if the expert testers did not make any serious test errors and the test equipment used functioned properly. In contrast, the investigations on the quality of visual inspection showed that the procedure is not sufficiently reliable to fulfil all normative requirements regarding damage detection and naming as well as damage classification.