Model Input-Output Configuration Search With Embedded Feature Selection for Sensor Time-Series and Image Classification
Machine learning is a powerful tool for extracting valuable information and making various predictions from diverse datasets. Traditional machine learning algorithms rely on well-defined input and output variables; however, there are scenarios where the separation between the input and output variab...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10943129/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849702198883123200 |
|---|---|
| author | Anh Tuan Hoang Zsolt Janos Viharos |
| author_facet | Anh Tuan Hoang Zsolt Janos Viharos |
| author_sort | Anh Tuan Hoang |
| collection | DOAJ |
| description | Machine learning is a powerful tool for extracting valuable information and making various predictions from diverse datasets. Traditional machine learning algorithms rely on well-defined input and output variables; however, there are scenarios where the separation between the input and output variables and the underlying, associated input and output layers of the model are unknown. Feature Selection (FS) and Neural Architecture Search (NAS) have emerged as promising solutions in such scenarios. This paper proposes MICS-EFS, a Model Input-Output Configuration Search with Embedded Feature Selection. The methodology explores internal dependencies in the complete input parameter space for classification tasks involving both 1D sensor time-series and 2D image data. MICS-EFS employs a modified encoder-decoder model and the Sequential Forward Search (SFS) algorithm, combining input-output configuration search with embedded feature selection. Experimental results demonstrate MICS-EFS’s superior performance compared to other FS algorithms. Across all tested datasets, MICS-EFS delivered an average accuracy improvement of 1.5% over baseline models, with the accuracy gains ranging from 0.5% to 5.9%. Moreover, the algorithm reduced feature dimensionality to just 2–5% of the original data, significantly enhancing computational efficiency. These results highlight the potential of MICS-EFS to improve model accuracy and efficiency in various machine learning tasks. Furthermore, the proposed method has been validated in a real-world industrial application focused on machining processes, underscoring its effectiveness and practicality in addressing complex input-output challenges. |
| format | Article |
| id | doaj-art-3766579869ea404c865e3c9a011e2e1e |
| institution | DOAJ |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-3766579869ea404c865e3c9a011e2e1e2025-08-20T03:17:44ZengIEEEIEEE Access2169-35362025-01-0113589605897710.1109/ACCESS.2025.355537910943129Model Input-Output Configuration Search With Embedded Feature Selection for Sensor Time-Series and Image ClassificationAnh Tuan Hoang0https://orcid.org/0000-0003-4316-0373Zsolt Janos Viharos1https://orcid.org/0000-0002-9561-6857HUN-REN Institute for Computer Science and Control, Center of Excellence in Production Informatics and Control (EPIC), Center of Excellence of the Hungarian Academy of Sciences (MTA), Budapest, HungaryHUN-REN Institute for Computer Science and Control, Center of Excellence in Production Informatics and Control (EPIC), Center of Excellence of the Hungarian Academy of Sciences (MTA), Budapest, HungaryMachine learning is a powerful tool for extracting valuable information and making various predictions from diverse datasets. Traditional machine learning algorithms rely on well-defined input and output variables; however, there are scenarios where the separation between the input and output variables and the underlying, associated input and output layers of the model are unknown. Feature Selection (FS) and Neural Architecture Search (NAS) have emerged as promising solutions in such scenarios. This paper proposes MICS-EFS, a Model Input-Output Configuration Search with Embedded Feature Selection. The methodology explores internal dependencies in the complete input parameter space for classification tasks involving both 1D sensor time-series and 2D image data. MICS-EFS employs a modified encoder-decoder model and the Sequential Forward Search (SFS) algorithm, combining input-output configuration search with embedded feature selection. Experimental results demonstrate MICS-EFS’s superior performance compared to other FS algorithms. Across all tested datasets, MICS-EFS delivered an average accuracy improvement of 1.5% over baseline models, with the accuracy gains ranging from 0.5% to 5.9%. Moreover, the algorithm reduced feature dimensionality to just 2–5% of the original data, significantly enhancing computational efficiency. These results highlight the potential of MICS-EFS to improve model accuracy and efficiency in various machine learning tasks. Furthermore, the proposed method has been validated in a real-world industrial application focused on machining processes, underscoring its effectiveness and practicality in addressing complex input-output challenges.https://ieeexplore.ieee.org/document/10943129/Feature selectioninput output configuration searchmachine learningneural network architecturesoptimal model structure |
| spellingShingle | Anh Tuan Hoang Zsolt Janos Viharos Model Input-Output Configuration Search With Embedded Feature Selection for Sensor Time-Series and Image Classification IEEE Access Feature selection input output configuration search machine learning neural network architectures optimal model structure |
| title | Model Input-Output Configuration Search With Embedded Feature Selection for Sensor Time-Series and Image Classification |
| title_full | Model Input-Output Configuration Search With Embedded Feature Selection for Sensor Time-Series and Image Classification |
| title_fullStr | Model Input-Output Configuration Search With Embedded Feature Selection for Sensor Time-Series and Image Classification |
| title_full_unstemmed | Model Input-Output Configuration Search With Embedded Feature Selection for Sensor Time-Series and Image Classification |
| title_short | Model Input-Output Configuration Search With Embedded Feature Selection for Sensor Time-Series and Image Classification |
| title_sort | model input output configuration search with embedded feature selection for sensor time series and image classification |
| topic | Feature selection input output configuration search machine learning neural network architectures optimal model structure |
| url | https://ieeexplore.ieee.org/document/10943129/ |
| work_keys_str_mv | AT anhtuanhoang modelinputoutputconfigurationsearchwithembeddedfeatureselectionforsensortimeseriesandimageclassification AT zsoltjanosviharos modelinputoutputconfigurationsearchwithembeddedfeatureselectionforsensortimeseriesandimageclassification |