Open Access

ARTICLE

EventTracker Based Regression Prediction with Application to Composite Sensitive Microsensor Parameter Prediction

Hongrong Wang^1,2, Xinjian Li^3,4, Xingjing She¹, Wenjian Ma^1,*

1 University of Electronic Science and Technology of China, Chengdu, 611731, China
2 Sichuan Provincial Institute of Forest and Grassland Survey and Planning, Chengdu, 610081, China
3 Guangxi University, Nanning, 530004, China
4 Guangxi Institute of Industrial Technology for Space-Time Information Co., Ltd., Nanning, 530201, China

* Corresponding Author: Wenjian Ma. Email:

(This article belongs to the Special Issue: Incomplete Data Test, Analysis and Fusion Under Complex Environments)

Computer Modeling in Engineering & Sciences 2025, 145(2), 2039-2055. https://doi.org/10.32604/cmes.2025.072572

Received 29 August 2025; Accepted 16 October 2025; Issue published 26 November 2025

Abstract

In modern complex systems, real-time regression prediction plays a vital role in performance evaluation and risk warning. Nevertheless, existing methods still face challenges in maintaining stability and predictive accuracy under complex conditions. To address these limitations, this study proposes an online prediction approach that integrates event tracking sensitivity analysis with machine learning. Specifically, a real-time event tracking sensitivity analysis method is employed to capture and quantify the impact of key events on system outputs. On this basis, a mutual-information–based self-extraction mechanism is introduced to construct prior weights, which are then incorporated into a LightGBM prediction model. Furthermore, iterative optimization of the feature selection threshold is performed to enhance both stability and accuracy. Experiments on composite microsensor data demonstrate that the proposed method achieves robust and efficient real-time prediction, with potential extension to industrial monitoring and control applications.

---

Keywords

---