A Hard Voting Policy-Driven Deep Learning Architectural Ensemble Strategy for Industrial Products Defect Recognition and Classification
Manual or traditional industrial product inspection and defect-recognition models have some limitations, including process complexity, time-consuming, error-prone, and expensiveness. These issues negatively impact the quality control processes. Therefore, an efficient, rapid, and intelligent model i...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/20/7846 |
| _version_ | 1797470024267464704 |
|---|---|
| author | Okeke Stephen Samaneh Madanian Minh Nguyen |
| author_facet | Okeke Stephen Samaneh Madanian Minh Nguyen |
| author_sort | Okeke Stephen |
| collection | DOAJ |
| description | Manual or traditional industrial product inspection and defect-recognition models have some limitations, including process complexity, time-consuming, error-prone, and expensiveness. These issues negatively impact the quality control processes. Therefore, an efficient, rapid, and intelligent model is required to improve industrial products’ production fault recognition and classification for optimal visual inspections and quality control. However, intelligent models obtained with a tradeoff of high accuracy for high latency are tedious for real-time implementation and inferencing. This work proposes an ensemble deep-leaning architectural framework based on a deep learning model architectural voting policy to compute and learn the hierarchical and high-level features in industrial artefacts. The voting policy is formulated with respect to three crucial viable model characteristics: model optimality, efficiency, and performance accuracy. In the study, three publicly available industrial produce datasets were used for the proposed model’s various experiments and validation process, with remarkable results recorded, demonstrating a significant increase in fault recognition and classification performance in industrial products. In the study, three publicly available industrial produce datasets were used for the proposed model’s various experiments and validation process, with remarkable results recorded, demonstrating a significant increase in fault recognition and classification performance in industrial products. |
| first_indexed | 2024-03-09T19:30:53Z |
| format | Article |
| id | doaj.art-9fa3a6e88dc547af83c048df6c5ba4eb |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T19:30:53Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-9fa3a6e88dc547af83c048df6c5ba4eb2023-11-24T02:27:12ZengMDPI AGSensors1424-82202022-10-012220784610.3390/s22207846A Hard Voting Policy-Driven Deep Learning Architectural Ensemble Strategy for Industrial Products Defect Recognition and ClassificationOkeke Stephen0Samaneh Madanian1Minh Nguyen2Computer Science & Software Engineering, Auckland University of Technology, Auckland 1010, New ZealandComputer Science & Software Engineering, Auckland University of Technology, Auckland 1010, New ZealandComputer Science & Software Engineering, Auckland University of Technology, Auckland 1010, New ZealandManual or traditional industrial product inspection and defect-recognition models have some limitations, including process complexity, time-consuming, error-prone, and expensiveness. These issues negatively impact the quality control processes. Therefore, an efficient, rapid, and intelligent model is required to improve industrial products’ production fault recognition and classification for optimal visual inspections and quality control. However, intelligent models obtained with a tradeoff of high accuracy for high latency are tedious for real-time implementation and inferencing. This work proposes an ensemble deep-leaning architectural framework based on a deep learning model architectural voting policy to compute and learn the hierarchical and high-level features in industrial artefacts. The voting policy is formulated with respect to three crucial viable model characteristics: model optimality, efficiency, and performance accuracy. In the study, three publicly available industrial produce datasets were used for the proposed model’s various experiments and validation process, with remarkable results recorded, demonstrating a significant increase in fault recognition and classification performance in industrial products. In the study, three publicly available industrial produce datasets were used for the proposed model’s various experiments and validation process, with remarkable results recorded, demonstrating a significant increase in fault recognition and classification performance in industrial products.https://www.mdpi.com/1424-8220/22/20/7846deep learning ensemblevisual inspectiondefect recognition and classificationvoting policyconvolutional neural networksindustrial products |
| spellingShingle | Okeke Stephen Samaneh Madanian Minh Nguyen A Hard Voting Policy-Driven Deep Learning Architectural Ensemble Strategy for Industrial Products Defect Recognition and Classification Sensors deep learning ensemble visual inspection defect recognition and classification voting policy convolutional neural networks industrial products |
| title | A Hard Voting Policy-Driven Deep Learning Architectural Ensemble Strategy for Industrial Products Defect Recognition and Classification |
| title_full | A Hard Voting Policy-Driven Deep Learning Architectural Ensemble Strategy for Industrial Products Defect Recognition and Classification |
| title_fullStr | A Hard Voting Policy-Driven Deep Learning Architectural Ensemble Strategy for Industrial Products Defect Recognition and Classification |
| title_full_unstemmed | A Hard Voting Policy-Driven Deep Learning Architectural Ensemble Strategy for Industrial Products Defect Recognition and Classification |
| title_short | A Hard Voting Policy-Driven Deep Learning Architectural Ensemble Strategy for Industrial Products Defect Recognition and Classification |
| title_sort | hard voting policy driven deep learning architectural ensemble strategy for industrial products defect recognition and classification |
| topic | deep learning ensemble visual inspection defect recognition and classification voting policy convolutional neural networks industrial products |
| url | https://www.mdpi.com/1424-8220/22/20/7846 |
| work_keys_str_mv | AT okekestephen ahardvotingpolicydrivendeeplearningarchitecturalensemblestrategyforindustrialproductsdefectrecognitionandclassification AT samanehmadanian ahardvotingpolicydrivendeeplearningarchitecturalensemblestrategyforindustrialproductsdefectrecognitionandclassification AT minhnguyen ahardvotingpolicydrivendeeplearningarchitecturalensemblestrategyforindustrialproductsdefectrecognitionandclassification AT okekestephen hardvotingpolicydrivendeeplearningarchitecturalensemblestrategyforindustrialproductsdefectrecognitionandclassification AT samanehmadanian hardvotingpolicydrivendeeplearningarchitecturalensemblestrategyforindustrialproductsdefectrecognitionandclassification AT minhnguyen hardvotingpolicydrivendeeplearningarchitecturalensemblestrategyforindustrialproductsdefectrecognitionandclassification |