间歇性
机器学习
人工智能
计算机科学
克里金
朴素贝叶斯分类器
吸引子
期限(时间)
贝叶斯概率
水准点(测量)
工业工程
数据挖掘
支持向量机
工程类
数学
地理
气象学
数学分析
物理
量子力学
湍流
大地测量学
标识
DOI:10.1080/24725854.2023.2255887
摘要
AbstractThe performance of long-term prediction models is currently impeded due to the mismatch between the nonstationary representations of statistical learning models and the underlying dynamics from real-world systems, which results in low long-term prediction accuracies for many real-world applications. We present a Recurrent Gated Unit-based Mixture Kriging Machine Bayesian Filtering (ReGU-MKMBF) approach for characterizing nonstationary and nonlinear behaviors of one ubiquitous real-world process—dynamic intermittency. It models the transient dynamics in the state space as recurrent transitions between localized stationary segments/attractors. Then, a case study on predicting the onset of pathological symptoms associated with Electrocardiogram signals is presented. The results suggest that ReGU-MKMBF improves the forecasting performance by extending the prediction time horizon with an order of magnitudes while maintaining high accuracies on the foreseen estimates. Implementing the presented approach can subsequently change the current scheme of online monitoring and aftermath mitigation into a prediction and timely prevention for telecardiology.Keywords: Long-term predictionnonstationary and nonlinear dynamicsrecurrent neural networkprognosis for telehealth Additional informationFundingThis work is partially supported by the Binghamton University Data Science Transdisciplinary Areas of Excellence (TAE) seed grant.Notes on contributorsQiyang MaQiyang Ma is a PhD student and research assistant in the Systems Science and Industrial Engineering Department at the State University of New York at Binghamton. He received a bachelor’s degree in Geophysics from Yunnan University and a master’s degree in Geophysics from the University of Chinese Academy of Sciences, China. His current research interests focus on explainable machine learning and data analytics with applications in advanced manufacturing processes and healthcare systems.Zimo WangZimo Wang is an assistant professor in the Department of Systems Science and Industrial Engineering at the State University of New York at Binghamton, Binghamton, NY. His research focuses on smart sensing approaches with their implementations into the cyber-physical platform to allow in-process characterizations, diagnosis/prognosis, and control for autonomous systems. Dr. Wang is the director of IISE Quality Engineering and Reliability Engineering (QCRE) division and Data Analytics and Information Systems (DAIS) division.
科研通智能强力驱动
Strongly Powered by AbleSci AI