This paper investigates the transformative role of Artificial Intelligence (AI) in enhancing infrastructure governance and economic outcomes. Through a bibliometric analysis spanning more than two decades of research from 2000 to 2024, the study examines global trends in AI applications within infrastructure projects. The analysis reveals significant research themes across diverse sectors, including urban development, healthcare, and environmental management, highlighting the broad relevance of AI technologies. In urban development, the integration of AI and Internet of Things (IoT) technologies is advancing smart city initiatives by improving infrastructure systems through enhanced data-driven decision-making. In healthcare, AI is revolutionizing patient care, improving diagnostic accuracy, and optimizing treatment strategies. Environmental management is benefiting from AI’s potential to monitor and conserve natural resources, contributing to sustainability and crisis management efforts. The study also explores the synergy between AI and blockchain technology, emphasizing its role in ensuring data security, transparency, and efficiency in various applications. The findings underscore the importance of a multidisciplinary approach in AI research and implementation, advocating for ethical considerations and strong governance frameworks to harness AI’s full potential responsibly.

The proposed research work encompasses implications for infrastructure particularly the cybersecurity as an essential in soft infrastructure, and policy making particularly on secure access management of infrastructure governance. In this study, we introduce a novel parameter focusing on the timestamp duration of password entry, enhancing the algorithm titled EPSBalgorithmv01 with seven parameters. The proposed parameter incorporates an analysis of the historical time spent by users entering their passwords, employing ARIMA for processing. To assess the efficacy of the updated algorithm, we developed a simulator and employed a multi-experimental approach. The evaluation utilized a test dataset comprising 617 authentic records from 111 individuals within a selected company spanning from 2017 to 2022. Our findings reveal significant advancements in EPSBalgorithmv01 compared to its predecessor namely EPSBalgorithmv00. While EPSBalgorithmv00 struggled with a recognition rate of 28.00% and a precision of 71.171, EPSBalgorithmv01 exhibited a recognition rate of 17% with a precision of 82.882%. Despite a decrease in recognition rate, EPSBalgorithmv01 demonstrates a notable improvement of approximately 14% over EPSBalgorithmv00.