Heritage tourism-led urban renewal and regeneration has recently become a critical way of creating a city brand, designing tourism destinations, and attracting property developers and investors to cities. However, current practice points to a lack of proper understanding and consideration in preserving and interpreting elements of authentic identity in the Chinese historic urban landscape. In this study, we used the ancient city of Datong, China, under urban regeneration as a case study to explore how urban history and cultural resources are manifested in preserving and reconstructing historic urban landscapes. The methods included in-depth interviews with multiple stakeholders and groups, integrated with the analysis of planning documents and field observations. By categorising and evaluating the research data, we developed a new conceptual framework with applicable measures, contributing to heritage-tourism urban regeneration and shaping place identity in both theoretical and practical aspects. The conceptual framework and its corresponding concepts and measures developed from this research could provide guidelines for academics and practitioners to explore more potential aspects and concepts that focus on the research and development of Chinese cities with historic urban landscapes.

Cracks in building facades are inevitable due to the age of the building. Cracks found in the building facade may be further exacerbated if not corrected immediately. Considering the extensive size of some buildings, there is definitely a need to automate the inspection routine to facilitate the inspection process. The incorporation of deep learning technology for the classification of images has proven to be an effective method in many past civil infrastructures like pavements and bridges. There is, however, limited research in the built environment sector. In order to align with the Smart Nation goals of the country, the use of Smart technologies is necessary in the building and construction industry. The focus of the study is to identify the effectiveness of deep learning technology for image classification. Deep learning technology, such as Convolutional Neural Networks (CNN), requires a large amount of data in order to obtain good performance. It is, however, difficult to collect the images manually. This study will cover the transfer learning approach, where image classification can be carried out even with limited data. Using the CNN method achieved an accuracy level of about 89%, while using the transfer learning model achieved an accuracy of 94%. Based on this, it can be concluded that the transfer learning method achieves better performance as compared to the CNN method with the same amount of data input.

(1) Background: Youth’s physical and mental health is of increasing concern today. However, gaining a more comprehensive knowledge of young people’s landscape preferences for urban parks is challenging. Additionally, young adults’ voices (aged from 20 to 24) are often neglected. (2) Methods: This study collected 349 interview questionnaires from 2014 to 2020 and recorded them into Nvivo10. Firstly, the study did a thematic analysis using the preliminary coding framework based on the landscape perception model to code the interview data and statistics on the frequencies of each theme and code. Then, we used diffractive analysis to interpret original materials to comprehend the underlying significance. (3) Results: Our research showed that young adults’ landscape perceptions are richer in diversity and express more subjective feelings. Their landscape preferences are also related to behavioral activities in addition to environmental features, which have some differences from teenagers. (4) Conclusions: It is helpful to attract more young adults by creating sound and smell landscapes, accommodating more dynamic sports and recreation facilities, and controlling unhygienic and noise problems, which can offer better design, planning, and management for creating inclusive urban parks. The landscape perception model developed in this paper can also provide a reference for related studies in the future.

Animal husbandry is a vital sector in China’s agriculture sector, contributing to over one-third of its agricultural output, and more than 40% of farmers’ income. However, this industry is vulnerable to risks arising from production and operation, such as disease outbreaks, natural disasters, and market fluctuations. Livestock insurance can help mitigate these risks, but the lack of reliable data on shed environments has hindered its effectiveness. The objective of this study is to propose a livestock shed environmental regulatory platform that utilizes blockchain and the Internet of Things to ensure data authenticity, real-time monitoring, and transparency in the regulatory process. The platform also automates the insurance process, reducing costs and improving efficiency. The proposed platform employs blockchain to ensure data authenticity and devices to monitor and collect real-time environmental data. It also utilizes smart contracts to automate the insurance process, from negotiating and signing contracts to making insurance claims. The system’s design rationale, architecture, and implementation are detailed. The proposed platform has been implemented and currently manages over 300,000 livestock animals with more than 350,000 insurance contracts signed. The use of blockchain and the Internet of Things has ensured data authenticity, real-time monitoring, and transparency in the regulatory process, while the automation of the insurance process has reduced costs and improved efficiency. The proposed livestock shed environmental regulatory platform has the potential to improve the effectiveness of livestock insurance in China by addressing the critical issue of data reliability. The use of blockchain and the Internet of Things has enabled real-time monitoring, data authenticity, and transparency in the regulatory process, while the automation of the insurance process has improved efficiency and reduced costs. This platform could serve as a model for other countries looking to improve the effectiveness of their livestock insurance programs.

Under the digital revolution that spawned in recent years, AI support is raised in the context of urban design and governance as it aims to match the operation of the urban developing process. It offers more chances for ensuring equality in public participation and empowerment, with the possibility of projection and computation of integrated social, cultural, and physical spaces. Therefore, this research explored how scenario simulation of social attributes and social interaction dimensions can be incorporated into digital twin city research and development, which is seen as a problem to be addressed in the refinement and planning of future digital platforms and management in terms of decision-making. To achieve the research aim, this paper examined the evolution of social governance state and strain decision models, built a simulation method for the evolution of complex systems of social governance driven by the fusion of data and knowledge, and proposed a system response to residents’ ubiquitous perception and ubiquitous participation. The findings can help inspire the application of computational decision-making support in urban governance, and enhance the internal drive for comprehensive and sustainable urban regeneration. Moreover, they imply the role of the updated iterations of physical space and social interaction on social attributes.

Since the start of 2020, the outbreak of the Coronavirus disease (COVID-19) has been a global public health emergency, and it has caused unprecedented economic and social disaster. In order to improve the diagnosis efficiency of COVID-19 patients, a number of researchers have conducted extensive studies on applying artificial intelligence techniques to the analysis of COVID-19-related medical images. The automatic segmentation of lesions from computed tomography (CT) images using deep learning provides an important basis for the quantification and diagnosis of COVID-19 cases. For a deep learning-based CT diagnostic method, a few of accurate pixel-level labels are essential for the training process of a model. However, the translucent ground-glass area of the lesion usually leads to mislabeling while performing the manual labeling operation, which weakens the accuracy of the model. In this work, we propose a method for correcting rough labels; that is, to hierarchize these rough labels into precise ones by performing an analysis on the pixel distribution of the infected and normal areas in the lung. The proposed method corrects the incorrectly labeled pixels and enables the deep learning model to learn the infected degree of each infected pixel, with which an aiding system (named DLShelper) for COVID-19 CT image diagnosis using the hierarchical labels is also proposed. The DLShelper targets lesion segmentation from CT images, as well as the severity grading. The DLShelper assists medical staff in efficient diagnosis by providing rich auxiliary diagnostic information (including the severity grade, the proportions of the lesion and the visualization of the lesion area). A comprehensive experiment based on a public COVID-19 CT image dataset is also conducted, and the experimental results show that the DLShelper significantly improves the accuracy of segmentation for the lesion areas and also achieves a promising accuracy for the severity grading task.