Výsledky vyhledávání - "Chen, Gecheng"

Report

Co-training partial domain adaptation networks for industrial Fault Diagnosis

Autor: Chen, Gecheng

The partial domain adaptation (PDA) challenge is a prevalent issue in industrial fault diagnosis. Drawing inspiration from traditional classification settings where such partial challenge is not a concern, we propose a novel PDA framework called Inte

Externí odkaz: http://arxiv.org/abs/2410.16737

Zobrazit plný text záznamu

Report

Self-degraded contrastive domain adaptation for industrial fault diagnosis with bi-imbalanced data

Autor: Chen, Gecheng, Yang, Zeyu, Luo, Chengwen, Li, Jianqiang

Modern industrial fault diagnosis tasks often face the combined challenge of distribution discrepancy and bi-imbalance. Existing domain adaptation approaches pay little attention to the prevailing bi-imbalance, leading to poor domain adaptation perfo

Externí odkaz: http://arxiv.org/abs/2405.20700

Zobrazit plný text záznamu

Report

Fixed-budget optimal designs for multi-fidelity computer experiments

Autor: Chen, Gecheng, Tuo, Rui

This work focuses on the design of experiments of multi-fidelity computer experiments. We consider the autoregressive Gaussian process model proposed by Kennedy and O'Hagan (2000) and the optimal nested design that maximizes the prediction accuracy s

Externí odkaz: http://arxiv.org/abs/2405.20644

Zobrazit plný text záznamu

Report

Renewing Iterative Self-labeling Domain Adaptation with Application to the Spine Motion Prediction

Autor: Chen, Gecheng, Zhou, Yu, Zhang, Xudong, Tuo, Rui

The area of transfer learning comprises supervised machine learning methods that cope with the issue when the training and testing data have different input feature spaces or distributions. In this work, we propose a novel transfer learning algorithm

Externí odkaz: http://arxiv.org/abs/2211.09064

Zobrazit plný text záznamu

Akademický článek

Reordered short-term autocorrelation-driven long-range discriminative convolutional autoencoder for dynamic process monitoring

Autor: Wang, Kai, He, Daojie, Chen, Gecheng, Yuan, Xiaofeng, Wang, Yalin, Yang, Chunhua

Publikováno v: In Journal of Process Control March 2024 135

Zobrazit plný text záznamu

Report

Projection Pursuit Gaussian Process Regression

Autor: Chen, Gecheng, Tuo, Rui

A primary goal of computer experiments is to reconstruct the function given by the computer code via scattered evaluations. Traditional isotropic Gaussian process models suffer from the curse of dimensionality, when the input dimension is relatively

Externí odkaz: http://arxiv.org/abs/2004.00667

Zobrazit plný text záznamu