Doctoral candidate Lanyu Shang successfully defended her dissertation, "A Human-Centric Artificial Intelligence Approach Towards Equality, Well-Being, and Responsibility in Sustainable Communities," on June 19.
Her doctoral committee included Associate Professor Dong Wang (chair); Assistant Professor Jessie Chin; Ximing Cai, professor of civil and environmental engineering; and Na Wei, associate professor of civil and environmental engineering.
Abstract: This dissertation introduces a human-centric artificial intelligence for sustainable communities (HAI4SC) approach that harnesses the complementary strengths of artificial intelligence (AI) and human intelligence (HI) to foster equality, well-being, and responsibility. AI has shown superiority in processing large amounts of data, identifying latent patterns, and making predictions, addressing the scalability and complexity of sustainability challenges. On the other hand, HI excels in providing context, domain expertise, and human-centric insights, which are essential for understanding the complex social and physical factors for community sustainability. This dissertation develops a holistic HAI4SC approach by addressing three fundamental challenges: multimodality, adaptability, and trustworthiness. First, we develop a multimodal information fusion system to seamlessly integrate multimodal content in enhancing community information credibility. Moreover, we design an adaptive cross-domain analytic framework that explicitly incorporates and adapts domain knowledge from well-studied source domains for improving the resilience and well-being of sustainable communities. Additionally, we develop a trustworthy social-physical knowledge distillation scheme that effectively models the diverse and uncertain human inputs from community stakeholders to strengthen the community responsibility and sustainability.