Systematic Data Analytics with Bayesian Networks: From a Latent Variable Version to its Dynamic Variant
Bayesian networks are appropriate candidates for systematic data analytics with complex causalities and decision-making under uncertainties. However, multidimensional influencing variables incorporated in general Bayesian networks would result in expensive computations and non-robust parameter estimations. To simplify parameters and enhance their estimations, we propose a novel latent variable structured Bayesian network with its parameters adaptively learned through multivariate spatiotemporal data. Theoretical analyses are provided regarding the network structure, parameter space, and convergence of the associated parameter learning algorithm. Then, its dynamic variant with a hidden Markov paradigm is introduced for forecasting tasks with data fluctuations and uncertainties. The network and its dynamic variant have been employed for environmental data analytics in multivariate systems. Several cases with real-world data have demonstrated that they provide intelligent data-driven decision support and deliver modeling and managerial insights.
Bio: Peng Jiang is an associate professor in the Department of Industrial Engineering and Management at Sichuan University. He obtained a Ph.D. from Shanghai Jiao Tong University and completed a joint Ph.D. program at National University of Singapore. Prior to joining the Sichuan faculty, he successively held positions as Postdoctoral Fellow at SJTU, Research Fellow at NUS Environmental Research Institute, and Research Scientist at Agency for Science, Technology and Research, Singapore.
His research focuses on systems modeling and sustainability science. Prof. Jiang has published in journals including Science, Engineering, Environmental Science & Technology, Water Research, Renewable & Sustainable Energy Reviews, Applied Energy, European Journal of Operational Research, and Decision Support Systems. His work has been cited in 27 international policy documents on energy and environmental sustainability, including reports by the United Nations (IPCC Climate Change Reports), the World Bank, the WHO, and the United Nations Environment Programme. He served as Conference Chair for the 3rd Global Symposium on Waste Plastic, hosted by the American Institute of Chemical Engineers (AIChE) and the Institute for Sustainability. Prof. Jiang is ranked among the top 2% of scientists globally by Stanford University.