Search

The study critically reviewed the cognitive and environmental factors that influence individual disaster preparedness behavior, focusing on the unique term of "ishiki (awareness)" in Japanese research. The 474 articles reviewed were extracted from 27 journals published between 2010 and 2020 that mentioned the keywords "disaster preparedness (bosai)" and "awareness (ishiki)." By extracting and coding the factor-behavior associations for the reviewed articles, it was found that the following cognitive and environmental factors were discussed. Cognitive factors that influence individuals' disaster preparedness behavior include seven components: awareness, risk perception, worry, self-efficacy, knowledge, intention, and dependence and trust; environmental factors include ten components: information, direct experience, disaster experience, recovery period institution, disaster preparedness program, elapsed time, demographic factors, social-economic factors, geographic factors, and social contexts. Paradoxical associations were observed for both cognitive and environmental factors, which was also discussed from four perspectives: discrepancy between prior plans and actual behavior, positive feedback to cognitive factors, formation of action habits, and change in awareness; all of which suggested that individuals' disaster preparedness behavior is a process rather than a result caused by cognitive factors. This study reveals that "ishiki (awareness)" has functioned as a term coined to desaturate diverse backgrounds in Japanese research, and points to the need for an approach that encompasses environmental factors such as physical, human, social, and economic resources. The contributions of this study cast light on aspects of the term that have been masked by its culturally unique development and point to a new direction by uncovering its internal contradictions. [ABSTRACT FROM AUTHOR]

To present a hybrid theory of disaster prevention actions and develop a common framework, this study theoretically and systematically reviewed recent research in Japan on actions from three perspectives: definition, multidisciplinarity, and multidimensionality. First, this research validated that the definition of actions on disaster prevention and reduction should be understood in three contexts: responsibility, willingness, and habituation; the diversity of terminology; and the type of measure. Second, the multidisciplinary nature of the approach affirmed that the motivations and approaches could be organized according to the axes of individual and social models and epistemic and design sciences. Third, per the multidimensional nature of theories explaining actions, the applied theories were organized based on the four perspectives: process, motivation, internal experience, and context. Furthermore, it was suggested that there are three critical perspectives: complicity in neoliberalism, invisibility of social inequalities, and bias in reporting desirable results (expert-serving bias). Taking an approach that emphasizes interdisciplinarity and multidimensionality, this study details the background of Japanese research used to employ a theoretical approach to understand individual cognition and demonstrates the need for research to understand the political, cultural, social, and economic environments that support disaster prevention behavior, noting that this is tied to the unique Japanese context of individual will and dependence on the government. This study is significant in that it provides a map for positioning one's research and pointing the way toward future collaboration in the direction showing definition, interdisciplinarity, and multidimensionality are important components in understanding disaster prevention behavior. This study reviewed three aspects of recent disaster research in Japan to better understand disaster prevention behavior: what it is and what areas and aspects of it are being studied. First, Japanese disaster prevention behavior can be understood in relation to "responsibility," "will," and "habit"; the diversity of behaviors; and the types of measures applied. Second, motivations and approaches could be amenable to organization along the axes of whether the coping subject is an individual or society and whether the science focuses on "what it is" or "what it can do." Third, explanations of disaster prevention behaviors were found to be viewable in relation to four perspectives: process, motivation, experience, and context. Three criticisms were also found: social inequalities are less visible, many results that are preferable to the researcher are reported, and there is a risk of becoming connected to particular political policies. This study found that although many theories that explain individuals' perceptions are used to explain their disaster prevention behavior, it is also important to understand the environment of the political, cultural, social, and economic aspects that surround the individual. [ABSTRACT FROM AUTHOR]

The successful application of deep learning in bridge damage diagnosis relies on the assumption that the training and test data sets obey the same distribution. However, it is difficult to obtain labeled data of damage status for a bridge in using. Otherwise, it is difficult to apply a model trained with bridge A (source domain) to diagnose bridge B (target domain) because of the distribution discrepancy of data from different working environments or bridges. In response to these problems, motivated by transfer learning, a new bridge damage diagnosis method, namely, the multichannel domain adaptation deep transfer learning based method (MDADTL), is proposed in this paper. First, a CNN based multichannel multi‐scale feature extractor is introduced to extract features. Second, a multichannel domain adaptation module based on maximum mean discrepancy (MMD) is proposed for transfer learning, so that the learned features are domain‐invariant. Through the above process, MDADTL trained with labeled data obtained in the laboratory or the testing bridge is expected to diagnose other bridges with unlabeled data. Experiments prove the effectiveness and advancement of the proposed method. This exploration will promote the practical application of deep learning in bridge damage diagnosis. © 2022 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC. [ABSTRACT FROM AUTHOR]

In recent years, intelligent structural damage diagnosis algorithms using machine learning have achieved much success. However, because of the fact that in real bridge applications, the working environment (load, temperature, and noise) is changing all the time, degradation of the performance of intelligent structural damage diagnosis methods is very serious. To address these problems, a novel bridge diagnosis algorithm based on deep learning is proposed. Our contributions include: First, we proposed an improved denoising auto‐encoder‐based deep neural networks, which is optimized by the gray relational analysis. It is able to automatically extract high‐level features from raw signals via a multi‐layer extraction to satisfy any damage diagnosis objective and thus does not need any time consuming denoising prepossessing. The model can achieve high accuracy under noisy environment. Second, the algorithm does not rely on any domain adaptation algorithm or require information of the target domain. It can achieve high accuracy when working environment is changed. Numerical simulations and experimental investigations on real bridges conducted to present the accuracy and efficiency of the proposed algorithm, comparing with other commonly machine learning‐based algorithms. The result shows it is deemed as an ideal and effective method for damage diagnosis of bridge structures. © 2021 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC. [ABSTRACT FROM AUTHOR]