Revitalizing urban industrial heritage: Enhancing public trust in government through smart city development and open big data analysis using artificial neural network (ANN) modeling

This study shows how smart city development revitalizes urban industrial heritage (UIH) and traditional industrial areas, especially by fostering public trust in government through open big data analysis. Rapid urbanization and industrialization have led to the degradation of many old industrial areas, causing urban decay and environmental concerns. However, smart city technologies show new opportunities for rejuvenating these locations, transforming them into vibrant, sustainable, and livable environments. The research shows challenges faced by UIH, such as outdated infrastructure, pollution, and neglect, and explores how smart city technologies can enhance resource efficiency, mobility, connectivity, and the built environment. It indicates the potential of open big data analysis to foster transparency and accountability, thereby enhancing public trust in government efforts. Various international examples of smart city initiatives illustrate the benefits of these technologies, stressing the importance of community involvement to ensure the success and sustainability of revitalization efforts. Additionally, the study shows an artificial neural network (ANN) to analyze relationships among various parameters, showing its effectiveness in understanding complex functions, even with training data errors. By modeling the connections between aging infrastructure, pollution, and factors such as resource use and mobility, the research achieves high predictive accuracy. The study advocates for a holistic approach to urban revitalization that emphasizes social, economic, and environmental sustainability. It suggests that integrating smart city development with open big data analysis can transform urban industrial heritage into vibrant, resilient areas, effectively addressing 21st-century challenges and enhancing public trust in government initiatives.