Search results

Crack detection of pavement is a critical task in the periodic survey. Efficient, effective and consistent tracking of the road conditions by identifying and locating crack contributes to establishing an appropriate road maintenance and repair strategy from the promptly informed managers but still remaining a significant challenge. This research seeks to propose practical solutions for targeting the automatic crack detection from images with efficient productivity and cost-effectiveness, thereby improving the pavement performance.

This research applies a novel deep learning method named TransUnet for crack detection, which is structured based on Transformer, combined with convolutional neural networks as encoder by leveraging a global self-attention mechanism to better extract features for enhancing automatic identification. Afterward, the detected cracks are used to quantify morphological features from five indicators, such as length, mean width, maximum width, area and ratio. Those analyses can provide valuable information for engineers to assess the pavement condition with efficient productivity.

In the training process, the TransUnet is fed by a crack dataset generated by the data augmentation with a resolution of 224 × 224 pixels. Subsequently, a test set containing 80 new images is used for crack detection task based on the best selected TransUnet with a learning rate of 0.01 and a batch size of 1, achieving an accuracy of 0.8927, a precision of 0.8813, a recall of 0.8904, an F1-measure and dice of 0.8813, and a Mean Intersection over Union of 0.8082, respectively. Comparisons with several state-of-the-art methods indicate that the developed approach in this research outperforms with greater efficiency and higher reliability.

The developed approach combines TransUnet with an integrated quantification algorithm for crack detection and quantification, performing excellently in terms of comparisons and evaluation metrics, which can provide solutions with potentially serving as the basis for an automated, cost-effective pavement condition assessment scheme.

This study aims to understand the socioeconomic impact of flood events on households, especially household welfare in terms of changes in consumption and coping strategies to deal with flood risk. This study is based on Bihar, one of the most frequently flood-affected, most populous and economically backward states in India.

Primary data were collected from 700 households in the seven most frequently flood-affected districts in Bihar. A total of 100 individuals from each district were randomly selected from flood-affected villages. Based on a detailed literature review, an econometric (probit) model was developed to test the null hypothesis of the availability of consumption insurance, and the multivariate probability approach was used to analyze the various coping strategies of these households.

The results of this study suggest that flood-affected households maintain their consumption by overcoming various losses, including income, house damage and livestock loss. Households depend on financial transfers, borrowings and relief, and migrate to overcome losses. Borrowing could be an extra burden as the government compensates for house damage and crop loss late to the affected households. Again, there is no compensation to overcome livelihood loss and deal with occurrences of post-flood diseases, which further emphasizes the policy implications of strengthening the health infrastructure in the state and generating alternative livelihood opportunities.

This study discusses flood risk in terms of changes in household welfare, identifies the most effective risk-coping capabilities of rural communities and contributes to the shortcomings of the government insurance and relief model.

The peer review history for this article is available at: https://publons.com/publon/10.1108/IJSE-07-2023-0569

To ensure the motion attitude and stable contact force of massage robot working on unknown human tissue environment, this study aims to propose a robotic system for autonomous massage path planning and stable interaction control.

First, back region extraction and acupoint recognition based on deep learning is proposed, which provides a basis for determining the working area and path points of the robot. Second, to realize the standard approach and movement trajectory of the expert massage, 3D reconstruction and path planning of the massage area are performed, and normal vectors are calculated to control the normal orientation of robot-end. Finally, to cope with the soft and hard changes of human tissue state and body movement, an adaptive force tracking control strategy is presented to compensate the uncertainty of environmental position and tissue hardness online.

Improved network model can accomplish the acupoint recognition task with a large accuracy and integrate the point cloud to generate massage trajectories adapted to the shape of the human body. Experimental results show that the adaptive force tracking control can obtain a relatively smooth force, and the error is basically within ± 0.2 N during the online experiment.

This paper incorporates deep learning, 3D reconstruction and impedance control, the robot can understand the shape features of the massage area and adapt its planning massage path to carry out a stable and safe force tracking control during dynamic robot–human contact.

This paper aims to investigate the impact of combining grain-oriented electrical steel (GOES) grades on specific iron losses and the flux density distribution within a single-phase magnetic core.

This paper presents the results of finite-element method (FEM) simulations investigating the impact of mixing two different GOES grades on losses of a single-phase magnetic core. The authors used different models: a 3D model with a highly detailed geometry including both saturation and anisotropy, as well as a simplified 2D model to save computation time. The behavior of the flux distribution in the mixed magnetic core is analyzed. Finally, the results from the numerical simulations are compared with experimental results.

The specific iron losses of a mixed magnetic core exhibit a nonlinear decrease with respect to the GOES grade with the lowest losses. Analyzing the magnetic core behavior using 2D and 3D FEM shows that the rolling direction of the GOES grades plays a critical role on the nonlinearity variation of the specific losses.

The novelty of this research lies in achieving an optimum trade-off between the manufacturing cost and the core efficiency by combining conventional and high-performance GOES grade in a single-phase magnetic core.

To improve the speed and accuracy of turbine blade film cooling design process, the most advanced deep learning models were introduced into this study to investigate the most suitable define for prediction work. This paper aims to create a generative surrogate model that can be applied on multi-objective optimization problems.

The latest backbone in the field of computer vision (Swin-Transformer, 2021) was introduced and improved as the surrogate function for prediction of the multi-physics field distribution (film cooling effectiveness, pressure, density and velocity). The basic samples were generated by Latin hypercube sampling method and the numerical method adopt for the calculation was validated experimentally at first. The training and testing samples were calculated at experimental conditions. At last, the surrogate model predicted results were verified by experiment in a linear cascade.

The results indicated that comparing with the Multi-Scale Pix2Pix Model, the Swin-Transformer U-Net model presented higher accuracy and computing speed on the prediction of contour results. The computation time for each step of the Swin-Transformer U-Net model is one-third of the original model, especially in the case of multi-physics field prediction. The correlation index reached more than 99.2% and the first-order error was lower than 0.3% for multi-physics field. The predictions of the data-driven surrogate model are consistent with the predictions of the computational fluid dynamics results, and both are very close to the experimental results. The application of the Swin-Transformer model on enlarging the different structure samples will reduce the cost of numerical calculations as well as experiments.

The number of U-Net layers and sample scales has a proper relationship according to equation (8). Too many layers of U-Net will lead to unnecessary nonlinear variation, whereas too few layers will lead to insufficient feature extraction. In the case of Swin-Transformer U-Net model, incorrect number of U-Net layer will reduce the prediction accuracy. The multi-scale Pix2Pix model owns higher accuracy in predicting a single physical field, but the calculation speed is too slow. The Swin-Transformer model is fast in prediction and training (nearly three times faster than multi Pix2Pix model), but the predicted contours have more noise. The neural network predicted results and numerical calculations are consistent with the experimental distribution.

This paper creates a generative surrogate model that can be applied on multi-objective optimization problems. The generative adversarial networks using new backbone is chosen to adjust the output from single contour to multi-physics fields, which will generate more results simultaneously than traditional surrogate models and reduce the time-cost. And it is more applicable to multi-objective spatial optimization algorithms. The Swin-Transformer surrogate model is three times faster to computation speed than the Multi Pix2Pix model. In the prediction results of multi-physics fields, the prediction results of the Swin-Transformer model are more accurate.

This paper examines household and community characteristics that influence the entry of rural households into non-farm entrepreneurship and investigates the various factors that influence the market exit of non-farm enterprises (NFEs).

The authors use data from three rounds (2011/12, 2013/14 and 2015/16) of the World Bank’s Living Standards Measurement Study – Integrated Surveys on Agriculture (LSMS-ISA). The authors employ panel logit and multilevel logit models to examine the probability of opening one or more enterprises and the enterprise exit rates.

Results indicate that the likelihood of starting a NFE is positively associated with primary education attainment, access to credit, experiencing idiosyncratic shocks and availability of formal financial institutions. Age, higher education attainment and rising farm input prices constrain entry into non-farm entrepreneurship. The enterprise exit rate is negatively associated with small-town residence, wealth, access to tar/gravel roads and cellphone communication.

Policymakers and administrators should strive to address the challenges that communities face in transportation, communication and financial services. Policies aimed at stabilizing prices and increasing access to mobile communication, primary education and road infrastructure could help expand the rural non-farm sector.

Previous studies primarily examined the determinants of participation in NFEs at a given time using cross-sectional data. The current study uses panel data to study the dynamics of NFE ownership by investigating households’ decisions to enter into or exit from the sector.

The peer review history for this article is available at https://publons.com/publon/10.1108/IJSE-09-2022-0611

This study aims to empirically examine the influence of Islamic corporate social responsibility (ICSR) on social welfare moderated by financial fraud.

The method used was the mix method. The number of respondents was 410. They combined the moderate regression analysis with PROCESS Andrew F Hayes to test the research hypothesis. After conducting the survey, it was continued by conducting interviews with the village community and the head of the village.

The first finding of this study is that ICSR has a significant positive effect on social welfare. The second finding is that financial fraud weakens the influence of ICSR on social welfare. The results of the interviews also confirmed the two findings of this study.

The high level of bias in answering the questions is due to the low public knowledge of ICSR. In addition, the interviews still needed to involve the oil and gas companies and government.

The main implication is improving social welfare, especially for those affected by offshore oil drilling. Furthermore, stakeholders are more sensitive to the adverse effects of financial fraud. Finally, to make drilling companies more transparent and on target in implementing ICSR.

The main novelty in this research is using of the mixed method. In addition, applying financial fraud as a moderating variable is rarely studied empirically.

Despite the susceptibility of cotton crops to pest attacks in the Malwa Region of Indian Punjab, no crop insurance policy has been implemented there– not even the Pradhan Mantri Fasal Bima Yojana (PMFBY), which is a central scheme. Therefore, this paper attempts to gauge the likely impact of the PMFBY on Punjab cotton farmers and assess the changes needed for greater uptake and effectiveness of PMFBY.

The authors have conducted a primary survey to conduct this study. Initially, the authors compared the costs of cotton production with the returns in two scenarios (with and without insurance). Additionally, the authors have applied a logistic regression framework to examine the determinants of the willingness of farmers to participate in the crop insurance market.

The study finds that net returns of cotton crops are conventionally small and insufficient to cope with damages from crop failure. Yet, PMFBY will require some modifications in the premium rate and the level of indemnity for its greater uptake among Punjab cotton farmers. Additionally, using the logistic regression framework, the authors find that an increase in awareness about crop insurance and farmers' perceptions about their crop failure in the near future reduces the willingness of the farmers to participate in the crop insurance markets.

The present study looks for the viability of PMFBY in Indian Punjab for the cotton crop, which can also be extended to other crops.

Punjab could also use crop insurance to encourage diversification in agriculture. There is a need for special packages for diversified crops under any crop insurance policy. Crops susceptible to volatility due to climate-related factors should be identified and provided with a special insurance package.

There exist very scant studies that have discussed the viability of a central crop insurance scheme in the agricultural-rich state of India, i.e. Punjab. Moreover, they do not also focus on crop losses accruing due to pest and insect attacks.

This study aims to examine how the legitimacy of internal auditing is reconstructed during enterprise resource planning (ERP)-driven technological change.

The study is based on the comparative analysis of internal auditing and its transformation due to ERP implementations at two case firms operating in the food sector in Egypt – one a major Egyptian multinational corporation (MNC) and the other a major domestic company (DC).

Internal auditors (IAs) at MNC saw ERP implementation as an opportunity to reconstruct the legitimacy of internal auditing work by engaging and partnering with actors involved with the ERP change. In doing so, the IAs acquired system certifications and provided line functions and external auditors with data-driven business insights. The “practical coping mechanism” adopted by the IAs led to the acceptance (and legitimacy) of their work. In contrast, IAs at DC adopted a purposeful strategy of disengaging, blaming and rejecting since they were skeptical of the top management team's (TMT's) sincerity. The “disinterestedness” led to the loss of legitimacy in the eyes of the stakeholders.

The article offers two contributions. First, it extends the literature by highlighting a spectrum of behavior displayed by IAs (coping with impending issues vs strategic purposefulness) during ERP-driven technological change. Second, the article contributes to the literature on legitimacy by highlighting four intertwined micro-processes – participating, socializing, learning and role-forging – that contribute to reconstructing the legitimacy of internal auditing.

The outset of the COVID-19 pandemic caused disruptions of all forms in the supply chain globally for almost two and a half years. This study identifies various challenges in the effective functioning of the existing supply chain during COVID-19. The focus is to see the disruptions impacting the energy storage supply chains.

The procedure entails a thorough analysis of scholarly literature pertaining to various supply chain interruptions, confirmed and verified by experts working in an energy storage company in India. These experts also confirmed the occurrence of more disruptive factors during their interviews and questionnaire survey. Moreover, this process attempts to filter out the relevant causal disruption factors in an energy storage company by using the integrated approach of qualitative and quantitative methodologies.

The results provide practical insights for the company management in planning and devising new strategies to manage supply chain disruptions. Supply chains for companies in other industry sectors can also benefit from the proposed framework and results in making them more robust to counter future disastrous events.

The study provides an easily adaptable decision framework to different industries by closely examining supply chain disruptions and identifying associated causes for building a robust supply chain focused on the energy storage sector. It examines four disruption dimensions and investigates possible outcomes and impacts of disruptions.