Comparing machine learning and deep learning regression frameworks for accurate prediction of dielectrophoretic force
Abstract An intelligent sensing framework using Machine Learning (ML) and Deep Learning (DL) architectures to precisely quantify dielectrophoretic force invoked on microparticles in a textile electrode-based DEP sensing device is reported. The prediction accuracy and generalization ability of the fr...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-07-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-022-16114-5 |
| _version_ | 1818196677369004032 |
|---|---|
| author | Sunday Ajala Harikrishnan Muraleedharan Jalajamony Midhun Nair Pradeep Marimuthu Renny Edwin Fernandez |
| author_facet | Sunday Ajala Harikrishnan Muraleedharan Jalajamony Midhun Nair Pradeep Marimuthu Renny Edwin Fernandez |
| author_sort | Sunday Ajala |
| collection | DOAJ |
| description | Abstract An intelligent sensing framework using Machine Learning (ML) and Deep Learning (DL) architectures to precisely quantify dielectrophoretic force invoked on microparticles in a textile electrode-based DEP sensing device is reported. The prediction accuracy and generalization ability of the framework was validated using experimental results. Images of pearl chain alignment at varying input voltages were used to build deep regression models using modified ML and CNN architectures that can correlate pearl chain alignment patterns of Saccharomyces cerevisiae(yeast) cells and polystyrene microbeads to DEP force. Various ML models such as K-Nearest Neighbor, Support Vector Machine, Random Forest, Neural Networks, and Linear Regression along with DL models such as Convolutional Neural Network (CNN) architectures of AlexNet, ResNet-50, MobileNetV2, and GoogLeNet have been analyzed in order to build an effective regression framework to estimate the force induced on yeast cells and microbeads. The efficiencies of the models were evaluated using Mean Absolute Error, Mean Absolute Relative, Mean Squared Error, R-squared, and Root Mean Square Error (RMSE) as evaluation metrics. ResNet-50 with RMSPROP gave the best performance, with a validation RMSE of 0.0918 on yeast cells while AlexNet with ADAM optimizer gave the best performance, with a validation RMSE of 0.1745 on microbeads. This provides a baseline for further studies in the application of deep learning in DEP aided Lab-on-Chip devices. |
| first_indexed | 2024-12-12T01:37:53Z |
| format | Article |
| id | doaj.art-9488dc8e3924432db195bc8228d1d2d7 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-12-12T01:37:53Z |
| publishDate | 2022-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-9488dc8e3924432db195bc8228d1d2d72022-12-22T00:42:48ZengNature PortfolioScientific Reports2045-23222022-07-0112111710.1038/s41598-022-16114-5Comparing machine learning and deep learning regression frameworks for accurate prediction of dielectrophoretic forceSunday Ajala0Harikrishnan Muraleedharan Jalajamony1Midhun Nair2Pradeep Marimuthu3Renny Edwin Fernandez4Department of Engineering, Norfolk State UniversityDepartment of Engineering, Norfolk State UniversityAPJ Abdul Kalam Technological UniversityRajeev Gandhi College of Engineering and TechnologyDepartment of Engineering, Norfolk State UniversityAbstract An intelligent sensing framework using Machine Learning (ML) and Deep Learning (DL) architectures to precisely quantify dielectrophoretic force invoked on microparticles in a textile electrode-based DEP sensing device is reported. The prediction accuracy and generalization ability of the framework was validated using experimental results. Images of pearl chain alignment at varying input voltages were used to build deep regression models using modified ML and CNN architectures that can correlate pearl chain alignment patterns of Saccharomyces cerevisiae(yeast) cells and polystyrene microbeads to DEP force. Various ML models such as K-Nearest Neighbor, Support Vector Machine, Random Forest, Neural Networks, and Linear Regression along with DL models such as Convolutional Neural Network (CNN) architectures of AlexNet, ResNet-50, MobileNetV2, and GoogLeNet have been analyzed in order to build an effective regression framework to estimate the force induced on yeast cells and microbeads. The efficiencies of the models were evaluated using Mean Absolute Error, Mean Absolute Relative, Mean Squared Error, R-squared, and Root Mean Square Error (RMSE) as evaluation metrics. ResNet-50 with RMSPROP gave the best performance, with a validation RMSE of 0.0918 on yeast cells while AlexNet with ADAM optimizer gave the best performance, with a validation RMSE of 0.1745 on microbeads. This provides a baseline for further studies in the application of deep learning in DEP aided Lab-on-Chip devices.https://doi.org/10.1038/s41598-022-16114-5 |
| spellingShingle | Sunday Ajala Harikrishnan Muraleedharan Jalajamony Midhun Nair Pradeep Marimuthu Renny Edwin Fernandez Comparing machine learning and deep learning regression frameworks for accurate prediction of dielectrophoretic force Scientific Reports |
| title | Comparing machine learning and deep learning regression frameworks for accurate prediction of dielectrophoretic force |
| title_full | Comparing machine learning and deep learning regression frameworks for accurate prediction of dielectrophoretic force |
| title_fullStr | Comparing machine learning and deep learning regression frameworks for accurate prediction of dielectrophoretic force |
| title_full_unstemmed | Comparing machine learning and deep learning regression frameworks for accurate prediction of dielectrophoretic force |
| title_short | Comparing machine learning and deep learning regression frameworks for accurate prediction of dielectrophoretic force |
| title_sort | comparing machine learning and deep learning regression frameworks for accurate prediction of dielectrophoretic force |
| url | https://doi.org/10.1038/s41598-022-16114-5 |
| work_keys_str_mv | AT sundayajala comparingmachinelearninganddeeplearningregressionframeworksforaccuratepredictionofdielectrophoreticforce AT harikrishnanmuraleedharanjalajamony comparingmachinelearninganddeeplearningregressionframeworksforaccuratepredictionofdielectrophoreticforce AT midhunnair comparingmachinelearninganddeeplearningregressionframeworksforaccuratepredictionofdielectrophoreticforce AT pradeepmarimuthu comparingmachinelearninganddeeplearningregressionframeworksforaccuratepredictionofdielectrophoreticforce AT rennyedwinfernandez comparingmachinelearninganddeeplearningregressionframeworksforaccuratepredictionofdielectrophoreticforce |