No abstract

Cracks in concrete cause initial structural damage to civil infrastructures such as buildings, bridges, and highways, which in turn causes further damage and is thus regarded as a serious safety concern. Early detection of it can assist in preventing further damage and can enable safety in advance by avoiding any possible accident caused while using those infrastructures. Machine learning-based detection is gaining favor over time-consuming classical detection approaches that can only fulfill the objective of early detection. To identify concrete surface cracks from images, this research developed a transfer learning approach (TL) based on Convolutional Neural Networks (CNN). This work employs the transfer learning strategy by leveraging four existing deep learning (DL) models named VGG16, ResNet18, DenseNet161, and AlexNet with pre-trained (trained on ImageNet) weights. To validate the performance of each model, four performance indicators are used: accuracy, recall, precision, and F1-score. Using the publicly available CCIC dataset, the suggested technique on AlexNet outperforms existing models with a testing accuracy of 99.90%, precision of 99.92%, recall of 99.80%, and F1-score of 99.86% for crack class. Our approach is further validated by using an external dataset, BWCI, available on Kaggle. Using BWCI, models VGG16, ResNet18, DenseNet161, and AlexNet achieved the accuracy of 99.90%, 99.60%, 99.80%, and 99.90% respectively. This proposed transfer learning-based method, which is based on the CNN method, is demonstrated to be more effective at detecting cracks in concrete structures and is also applicable to other detection tasks.

Purpose Corporate social responsibility (CSR) influences an organization in deciding its ethical approaches in the corporate practices and also important to maintain sustainable development. Islamic banks are capturing almost 40% of the total bank account holders in Bangladesh and contributing to the socio-economic and environmental development of the country through their CSR activities. The purpose of this paper is to investigate the impacts of CSR activities of Islamic banks for sustainable development in Bangladesh from the perception of the beneficiaries. Design/methodology/approach This study is based on a questionnaire survey of 200 conveniently selected beneficiaries from five purposively selected Islamic banks in Bangladesh. Respondents’ agreement score for various CSR-related activities has been observed in a five-point Likert scale and, finally, to identify the impact of CSR, exploratory factor analysis has been done. Findings Results revealed that respondents are expressing strong agreement for almost all the activities, and they are much satisfied with ongoing CSR activities by Islamic banks, which implies positive attitudes of beneficiaries regarding CSR activities. The results of factor analysis further confirm the perception of respondents toward CSR activities of Islamic banks in terms of social enhancement, education and health, socio-economic well-being and contemporary arts and culture. Originality/value The Islamic banks should enhance their CSR activities for socio-economic development, provide more allocation in education programs, increase sponsorship in sports events and assist in flourishing Bangladeshi arts and culture.

Background In low- and middle- income countries such as Bangladesh, urban slum dwellers are particualry vulnerable to hypertension due to inadequate facilities for screening and management, as well as inadequate health literacy among them. However, there is scarcity of evidence on hypertension among the urban slum dwellers in Bangladesh. The present study aimed to determine the prevalence and factors associated with hypertension among urban slum dwellers in Bangladesh. Methods Data were collected as part of a large-scale cross-sectional survey conducted by Building Resources Across Communities (BRAC) between October 2015 and January 2016. The present analysis was performed among 1155 urban slum dwellers aged 35 years or above. A structured questionnaire was adminstered to collect data electronically and blood pressure measurements were taken using standardised procedures. Binary logistic regression with generalized estimating equation modelling was performed to estimate the factors associated with hypertension. Results The prevalence of hypertension was 28.3% among urban slum dwellers aged 35 years and above. In adjusted analysis, urban slum dwellers aged 45–54 years (AOR: 1.64, 95% CI: 1.17–2.28), 55–64 years (AOR: 2.47, 95% CI: 1.73–3.53) and ≥ 65 years (AOR: 2.34, 95% CI: 1.47–3.72), from wealthier households (AOR: 1.94, 95% CI: 1.18–3.20), sleeping < 7 h per day (AOR: 1.87, 95% CI: 1.39–2.51), who were overweight (AOR: 1.53, 95% CI: 1.09–2.14) or obese (AOR: 2.34, 95% CI: 1.71–3.20), and having self-reported diabetes (AOR: 3.08, 95% CI: 1.88–5.04) had an increased risk of hypertension. Moreover, 51.0% of the participants were taking anti-hypertensive medications and 26.4% of them had their hypertension in control. Conclusions The findings highlight a high burden of hypertension and poor management of it among the slum dwellers in Bangladesh requiring a novel approach to improve care. It is integral to effectively implement the available national non-communicable disease (NCD) control guidelines and redesign the current urban primary health care system to have better coordination.