Convolutional neural network classification of beam profiles from silicon photonics gratings
Convolutional neural network (CNN) models consist of CNN block(s) and dense neural network (DNN) block(s) are used to perform image classification on beam profiles in light beam coupled out from silicon photonics (SiPh) mixed pitch gratings. The beam profiles are first simulated and segregated into...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/179965 |
| _version_ | 1811688454642204672 |
|---|---|
| author | Lim, Yu Dian Tan, Chuan Seng |
| author2 | School of Electrical and Electronic Engineering |
| author_facet | School of Electrical and Electronic Engineering Lim, Yu Dian Tan, Chuan Seng |
| author_sort | Lim, Yu Dian |
| collection | NTU |
| description | Convolutional neural network (CNN) models consist of CNN block(s) and dense neural network (DNN) block(s) are used to perform image classification on beam profiles in light beam coupled out from silicon photonics (SiPh) mixed pitch gratings. The beam profiles are first simulated and segregated into 3 categories based on their corresponding height above the SiPh gratings. With 1 CNN block, 1 DNN block, and 128 nodes in the DNN block, classification accuracy of 98.68% is achieved when classifying 454 beam profile images to their corresponding categories. Expanding the number of CNN blocks, DNN blocks, and the number of nodes, 64 CNN models are constructed, trained, and evaluated. Out of the 64 CNN models, 52 of them achieved classification accuracy of >95%. |
| first_indexed | 2024-10-01T05:32:28Z |
| format | Journal Article |
| id | ntu-10356/179965 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T05:32:28Z |
| publishDate | 2024 |
| record_format | dspace |
| spelling | ntu-10356/1799652024-09-10T01:41:16Z Convolutional neural network classification of beam profiles from silicon photonics gratings Lim, Yu Dian Tan, Chuan Seng School of Electrical and Electronic Engineering Institute of Microelectronics, A*STAR Engineering Convolutional neural networks Beam profiles Convolutional neural network (CNN) models consist of CNN block(s) and dense neural network (DNN) block(s) are used to perform image classification on beam profiles in light beam coupled out from silicon photonics (SiPh) mixed pitch gratings. The beam profiles are first simulated and segregated into 3 categories based on their corresponding height above the SiPh gratings. With 1 CNN block, 1 DNN block, and 128 nodes in the DNN block, classification accuracy of 98.68% is achieved when classifying 454 beam profile images to their corresponding categories. Expanding the number of CNN blocks, DNN blocks, and the number of nodes, 64 CNN models are constructed, trained, and evaluated. Out of the 64 CNN models, 52 of them achieved classification accuracy of >95%. Ministry of Education (MOE) This work was supported by the Ministry of Education of Singapore AcRF Tier 2 (T2EP50121-0002 (MOE-000180-01)) and AcRF Tier 1 (RG135/23, RT3/23). 2024-09-10T01:41:16Z 2024-09-10T01:41:16Z 2024 Journal Article Lim, Y. D. & Tan, C. S. (2024). Convolutional neural network classification of beam profiles from silicon photonics gratings. Applied Optics, 63(20), 5479-5486. https://dx.doi.org/10.1364/AO.531306 1559-128X https://hdl.handle.net/10356/179965 10.1364/AO.531306 20 63 5479 5486 en T2EP50121-0002 (MOE-000180-01) RG135/23 RT3/23 Applied Optics © 2024 Optica Publishing Group. All rights reserved. |
| spellingShingle | Engineering Convolutional neural networks Beam profiles Lim, Yu Dian Tan, Chuan Seng Convolutional neural network classification of beam profiles from silicon photonics gratings |
| title | Convolutional neural network classification of beam profiles from silicon photonics gratings |
| title_full | Convolutional neural network classification of beam profiles from silicon photonics gratings |
| title_fullStr | Convolutional neural network classification of beam profiles from silicon photonics gratings |
| title_full_unstemmed | Convolutional neural network classification of beam profiles from silicon photonics gratings |
| title_short | Convolutional neural network classification of beam profiles from silicon photonics gratings |
| title_sort | convolutional neural network classification of beam profiles from silicon photonics gratings |
| topic | Engineering Convolutional neural networks Beam profiles |
| url | https://hdl.handle.net/10356/179965 |
| work_keys_str_mv | AT limyudian convolutionalneuralnetworkclassificationofbeamprofilesfromsiliconphotonicsgratings AT tanchuanseng convolutionalneuralnetworkclassificationofbeamprofilesfromsiliconphotonicsgratings |