A Socio-Technical Framework for AI-Driven Digital Integration in Sustainable Construction

The digital transformation of construction increasingly depends on the ability to integrate artificial intelligence (AI), data-driven analytics, and interconnected digital systems into operational environments characterized by heterogeneous data, distributed stakeholders, and complex information flows. However, technological integration alone does not guarantee effective digital transformation because organizational processes, human decision-making, information governance, and system interoperability influence how computational capabilities are translated into practical outcomes. This research develops a conceptual socio-technical framework for AI-driven digital integration in sustainable construction by synthesizing the methodological and technical insights contained in seven provided studies concerning encrypted traffic classification, deep learning, convolutional neural networks, representation learning, and anonymous traffic identification. Although the source literature is primarily situated in network-security contexts, its underlying principles concerning data characterization, deep feature extraction, end-to-end learning, and traffic identification provide transferable foundations for understanding secure and intelligent information infrastructures. The proposed framework integrates five layers: data acquisition and characterization, AI-based representation and classification, secure digital integration, socio-technical decision coordination, and sustainability-oriented operational application. The analysis indicates that AI-driven construction integration should be treated as an adaptive information system rather than as an isolated algorithmic deployment. The framework emphasizes the importance of reliable data representation, contextual classification, secure information exchange, human oversight, and continuous learning. The study contributes a conceptual bridge between AI-enabled information processing and socio-technical digital integration while identifying limitations arising from the indirect transfer of findings from cybersecurity research to construction management.

Artificial Intelligence, Digital Integration, Sustainable Construction, Socio-Technical Systems

G. DraperGil, A. H. Lashkari, M. S. I. Mamun and A. A. Ghorbani, “Characterization of encrypted and VPN traffic using time related,” in Proc. of the 2nd Int. Conf. on Information Systems Security and Privacy (ICISSP), Rome, Italy, pp. 407–414, 2016.

T. Len, “A survey of encrypted traffic classification based on deep learning,” Computer and Modernization, vol. 3, no. 8, pp. 112–120, 2021.

S. Rezaei and X. Liu, “Deep learning for encrypted traffic classification: An overview,” IEEE Communications Magazine, vol. 57, no. 5, pp. 76–81, 2019.

W. Wang, M. Zhu, X. Zeng, X. Ye and Y. Sheng, “Malware traffic classification using convolutional neural network for representation learning,” in Int. Conf. on Information Networking (ICOIN), Da Nang, Vietnam, pp. 1145–1150, 2017.

W. Wang, M. Zhu, J. Wang, X. Zeng and Y. Zhongzhen, “End-to-end encrypted traffic classification with one-dimensional convolution neural networks,” in 2017 IEEE Int. Conf. on Intelligence and Security Informatics (ISI), Beijing, China, pp. 875–885, 2017.

J. Xu, X. Chen, B. Wang and J. Cui, “A deep learning network traffic classification method,” 2016.

J. Y. Zhang, “Research on Shadowsocks anonymous traffic identification technology based on website fingerprint,” Tianjin: University of Technology, 2017.

K. Ramamurthy, “AI-Driven Test Automation Frameworks for the Modern Software Quality Engineering,” International Journal of Emerging Trends in Computer Science and Information Technology, vol. 4, no. 4, pp. 257–269, 2023.

G. Philip Paulson, “Robotics-Enabled Sustainable Construction Management: A Socio-Technical Framework for Operational Efficiency, Digital Integration, and Sustainability Performance.” Available at SSRN: https://ssrn.com/abstract=6845167 or http://dx.doi.org/10.2139/ssrn.6845167