DBSCAN-PCA-INFORMER-Based Droplet Motion Time Prediction Model for Digital Microfluidic Systems

In recent years, emerging digital microfluidic technology has shown great application potential in fields such as biology and medicine due to its simple structure, sample-saving properties, ease of integration, and wide range of manipulation. Currently, due to potential faults in chips during produc...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhijie Luo, Bin Zhao, Wenjin Liu, Jianhua Zheng, Wenwen Chen
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Micromachines
Subjects:
Online Access:https://www.mdpi.com/2072-666X/16/5/594
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849710865039753216
author Zhijie Luo
Bin Zhao
Wenjin Liu
Jianhua Zheng
Wenwen Chen
author_facet Zhijie Luo
Bin Zhao
Wenjin Liu
Jianhua Zheng
Wenwen Chen
author_sort Zhijie Luo
collection DOAJ
description In recent years, emerging digital microfluidic technology has shown great application potential in fields such as biology and medicine due to its simple structure, sample-saving properties, ease of integration, and wide range of manipulation. Currently, due to potential faults in chips during production and usage, as well as high safety requirements in their application domains, thorough testing of chips is essential. This study records data using a machine vision-based digital microfluidic driving control system. As chip usage frequency rises, device degradation introduces seasonal and trend patterns in droplet motion time data, complicating predictive modeling. This paper first employs the density-based spatial clustering of applications with noise (DBSCAN) clustering algorithm to analyze the droplet motion time data in digital microfluidic systems. Subsequently, principal component analysis (PCA) is applied for dimensionality reduction on the clustered data. Using the INFORMER model, we predict changes in droplet motion time and conduct correlation analysis, comparing results with traditional long short-term memory (LSTM), frequency-enhanced decomposed transformer (FEDformer), inverted transformer (iTransformer), INFORMER, and DBSCAN-INFORMER prediction models. Experimental results show that the DBSCAN-PCA-INFORMER model substantially outperforms LSTM and other benchmark models in prediction accuracy. It achieves an R<sup>2</sup> of 0.9864, an MSE of 3.1925, and an MAE of 1.3661, indicating an excellent fit between predicted and observed values.The results demonstrate that the DBSCAN-PCA-INFORMER model achieves higher prediction accuracy than traditional LSTM and other approaches, effectively identifying the health status of experimental devices and accurately predicting failure times, underscoring its efficacy and superiority.
format Article
id doaj-art-d2e057a1dcd24f2c94cda5e1a34e57dd
institution DOAJ
issn 2072-666X
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Micromachines
spelling doaj-art-d2e057a1dcd24f2c94cda5e1a34e57dd2025-08-20T03:14:46ZengMDPI AGMicromachines2072-666X2025-05-0116559410.3390/mi16050594DBSCAN-PCA-INFORMER-Based Droplet Motion Time Prediction Model for Digital Microfluidic SystemsZhijie Luo0Bin Zhao1Wenjin Liu2Jianhua Zheng3Wenwen Chen4College of Information Science and Technology, Zhongkai University of Agriculture and Engineering, Guangzhou 510225, ChinaCollege of Information Science and Technology, Zhongkai University of Agriculture and Engineering, Guangzhou 510225, ChinaCollege of Information Science and Technology, Zhongkai University of Agriculture and Engineering, Guangzhou 510225, ChinaCollege of Information Science and Technology, Zhongkai University of Agriculture and Engineering, Guangzhou 510225, ChinaCollege of Information Science and Technology, Zhongkai University of Agriculture and Engineering, Guangzhou 510225, ChinaIn recent years, emerging digital microfluidic technology has shown great application potential in fields such as biology and medicine due to its simple structure, sample-saving properties, ease of integration, and wide range of manipulation. Currently, due to potential faults in chips during production and usage, as well as high safety requirements in their application domains, thorough testing of chips is essential. This study records data using a machine vision-based digital microfluidic driving control system. As chip usage frequency rises, device degradation introduces seasonal and trend patterns in droplet motion time data, complicating predictive modeling. This paper first employs the density-based spatial clustering of applications with noise (DBSCAN) clustering algorithm to analyze the droplet motion time data in digital microfluidic systems. Subsequently, principal component analysis (PCA) is applied for dimensionality reduction on the clustered data. Using the INFORMER model, we predict changes in droplet motion time and conduct correlation analysis, comparing results with traditional long short-term memory (LSTM), frequency-enhanced decomposed transformer (FEDformer), inverted transformer (iTransformer), INFORMER, and DBSCAN-INFORMER prediction models. Experimental results show that the DBSCAN-PCA-INFORMER model substantially outperforms LSTM and other benchmark models in prediction accuracy. It achieves an R<sup>2</sup> of 0.9864, an MSE of 3.1925, and an MAE of 1.3661, indicating an excellent fit between predicted and observed values.The results demonstrate that the DBSCAN-PCA-INFORMER model achieves higher prediction accuracy than traditional LSTM and other approaches, effectively identifying the health status of experimental devices and accurately predicting failure times, underscoring its efficacy and superiority.https://www.mdpi.com/2072-666X/16/5/594digital microfluidicsmicrodropletsDBSCAN-PCA-INFORMER modeltime prediction
spellingShingle Zhijie Luo
Bin Zhao
Wenjin Liu
Jianhua Zheng
Wenwen Chen
DBSCAN-PCA-INFORMER-Based Droplet Motion Time Prediction Model for Digital Microfluidic Systems
Micromachines
digital microfluidics
microdroplets
DBSCAN-PCA-INFORMER model
time prediction
title DBSCAN-PCA-INFORMER-Based Droplet Motion Time Prediction Model for Digital Microfluidic Systems
title_full DBSCAN-PCA-INFORMER-Based Droplet Motion Time Prediction Model for Digital Microfluidic Systems
title_fullStr DBSCAN-PCA-INFORMER-Based Droplet Motion Time Prediction Model for Digital Microfluidic Systems
title_full_unstemmed DBSCAN-PCA-INFORMER-Based Droplet Motion Time Prediction Model for Digital Microfluidic Systems
title_short DBSCAN-PCA-INFORMER-Based Droplet Motion Time Prediction Model for Digital Microfluidic Systems
title_sort dbscan pca informer based droplet motion time prediction model for digital microfluidic systems
topic digital microfluidics
microdroplets
DBSCAN-PCA-INFORMER model
time prediction
url https://www.mdpi.com/2072-666X/16/5/594
work_keys_str_mv AT zhijieluo dbscanpcainformerbaseddropletmotiontimepredictionmodelfordigitalmicrofluidicsystems
AT binzhao dbscanpcainformerbaseddropletmotiontimepredictionmodelfordigitalmicrofluidicsystems
AT wenjinliu dbscanpcainformerbaseddropletmotiontimepredictionmodelfordigitalmicrofluidicsystems
AT jianhuazheng dbscanpcainformerbaseddropletmotiontimepredictionmodelfordigitalmicrofluidicsystems
AT wenwenchen dbscanpcainformerbaseddropletmotiontimepredictionmodelfordigitalmicrofluidicsystems