Anomaly Detection in the Molecular Structure of Gallium Arsenide Using Convolutional Neural Networks
This paper concerns the development of a machine learning tool to detect anomalies in the molecular structure of Gallium Arsenide. We employ a combination of a CNN and a PCA reconstruction to create the model, using real images taken with an electron microscope in training and testing. The methodolo...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Published: |
Multidisciplinary Digital Publishing Institute
2023
|
| Online Access: | https://hdl.handle.net/1721.1/152072 |
| _version_ | 1811092622810284032 |
|---|---|
| author | Roche, Timothy Wood, Aihua Cho, Philip Johnstone, Chancellor |
| author_facet | Roche, Timothy Wood, Aihua Cho, Philip Johnstone, Chancellor |
| author_sort | Roche, Timothy |
| collection | MIT |
| description | This paper concerns the development of a machine learning tool to detect anomalies in the molecular structure of Gallium Arsenide. We employ a combination of a CNN and a PCA reconstruction to create the model, using real images taken with an electron microscope in training and testing. The methodology developed allows for the creation of a defect detection model, without any labeled images of defects being required for training. The model performed well on all tests under the established assumptions, allowing for reliable anomaly detection. To the best of our knowledge, such methods are not currently available in the open literature; thus, this work fills a gap in current capabilities. |
| first_indexed | 2024-09-23T15:21:01Z |
| format | Article |
| id | mit-1721.1/152072 |
| institution | Massachusetts Institute of Technology |
| last_indexed | 2024-09-23T15:21:01Z |
| publishDate | 2023 |
| publisher | Multidisciplinary Digital Publishing Institute |
| record_format | dspace |
| spelling | mit-1721.1/1520722023-09-09T03:07:31Z Anomaly Detection in the Molecular Structure of Gallium Arsenide Using Convolutional Neural Networks Roche, Timothy Wood, Aihua Cho, Philip Johnstone, Chancellor This paper concerns the development of a machine learning tool to detect anomalies in the molecular structure of Gallium Arsenide. We employ a combination of a CNN and a PCA reconstruction to create the model, using real images taken with an electron microscope in training and testing. The methodology developed allows for the creation of a defect detection model, without any labeled images of defects being required for training. The model performed well on all tests under the established assumptions, allowing for reliable anomaly detection. To the best of our knowledge, such methods are not currently available in the open literature; thus, this work fills a gap in current capabilities. 2023-09-08T19:29:27Z 2023-09-08T19:29:27Z 2023-08-07 2023-08-11T14:33:37Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/152072 Mathematics 11 (15): 3428 (2023) PUBLISHER_CC http://dx.doi.org/10.3390/math11153428 Creative Commons Attribution 4.0 International license https://creativecommons.org/licenses/by/4.0/ application/pdf Multidisciplinary Digital Publishing Institute Multidisciplinary Digital Publishing Institute |
| spellingShingle | Roche, Timothy Wood, Aihua Cho, Philip Johnstone, Chancellor Anomaly Detection in the Molecular Structure of Gallium Arsenide Using Convolutional Neural Networks |
| title | Anomaly Detection in the Molecular Structure of Gallium Arsenide Using Convolutional Neural Networks |
| title_full | Anomaly Detection in the Molecular Structure of Gallium Arsenide Using Convolutional Neural Networks |
| title_fullStr | Anomaly Detection in the Molecular Structure of Gallium Arsenide Using Convolutional Neural Networks |
| title_full_unstemmed | Anomaly Detection in the Molecular Structure of Gallium Arsenide Using Convolutional Neural Networks |
| title_short | Anomaly Detection in the Molecular Structure of Gallium Arsenide Using Convolutional Neural Networks |
| title_sort | anomaly detection in the molecular structure of gallium arsenide using convolutional neural networks |
| url | https://hdl.handle.net/1721.1/152072 |
| work_keys_str_mv | AT rochetimothy anomalydetectioninthemolecularstructureofgalliumarsenideusingconvolutionalneuralnetworks AT woodaihua anomalydetectioninthemolecularstructureofgalliumarsenideusingconvolutionalneuralnetworks AT chophilip anomalydetectioninthemolecularstructureofgalliumarsenideusingconvolutionalneuralnetworks AT johnstonechancellor anomalydetectioninthemolecularstructureofgalliumarsenideusingconvolutionalneuralnetworks |