Semi-supervised contrastive regression for pharmaceutical processes

Li, Yinlong; Liao, Yilin; Sun, Ziyue; Liu, Xinggao

doi:10.1016/j.eswa.2023.121974

Cited by 5 publications

(1 citation statement)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Leveraging JIT SSL, it effectively constructs local semi-supervised models, yielding a highly effective predictive performance. Li et al [22] A new semi-supervised contrast regression framework (SCRF) is proposed using a supervised contrast learning error LA loss specifically designed for the regression task and using an adaptive segmentation enhancement approach. Dong et al [23] divide the process variables into different sub-blocks by partial least squares, construct a subset of similar samples based on the sub-blocks, build various real-time semi-supervised sub-models to estimate the output of the query samples, and finally, fuse the predicted values of the sub-models.…”

Section: Introductionmentioning

confidence: 99%

A soft sensor model based on an improved semi-supervised stacked autoencoder for just-in-time updating of cement clinker production process data f-CaO

Zheng,

Liu,

Zhou

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

The free calcium oxide (f-CaO) content in cement clinker serves as a critical quality indicator for cement production. However, many soft sensor models employed for predicting f-CaO content utilize a limited amount of labeled data, leading to the underutilization of a substantial volume of unlabeled data and its associated information. To tackle these challenges, this study introduces soft sensor methodology based on improved semi-supervised AttentionStacked Autoencoders (ASS-SAE). We propose an enhanced confidence-generating pseudo-labeling technique to identify high-confidence pseudo-labeled samples from pseudo-labels within a subset of correlated samples, addressing the issue of inadequate labeled data. To fully utilize the information hidden in the unlabeled data, the proposed method incorporating the confidence attention mechanism then assigns weights to the high-confidence pseudo-labeled data and inputs them into the SAE along with labeled data from a subset of similar samples for re-fine-tuning. By conducting an illustrative analysis using authentic cement data proposed for this study, the effectiveness of the approaches employed in this research is substantiated.substantiated.

show abstract

Section: Introductionmentioning

confidence: 99%