Deep learning for enhanced free-space optical communications
Atmospheric effects, such as turbulence and background thermal noise, inhibit the propagation of light used in ON–OFF keying (OOK) free-space optical (FSO) communication. Here we present and experimentally validate a convolutional neural network (CNN) to reduce the bit error rate of FSO communicatio...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2023-01-01
|
| Series: | Machine Learning: Science and Technology |
| Subjects: | |
| Online Access: | https://doi.org/10.1088/2632-2153/ad10cd |
| _version_ | 1827593537386971136 |
|---|---|
| author | M P Bart N J Savino P Regmi L Cohen H Safavi H C Shaw S Lohani T A Searles B T Kirby H Lee R T Glasser |
| author_facet | M P Bart N J Savino P Regmi L Cohen H Safavi H C Shaw S Lohani T A Searles B T Kirby H Lee R T Glasser |
| author_sort | M P Bart |
| collection | DOAJ |
| description | Atmospheric effects, such as turbulence and background thermal noise, inhibit the propagation of light used in ON–OFF keying (OOK) free-space optical (FSO) communication. Here we present and experimentally validate a convolutional neural network (CNN) to reduce the bit error rate of FSO communication in post-processing that is significantly simpler and cheaper than existing solutions based on advanced optics. Our approach consists of two neural networks, the first determining the presence of bit sequences in thermal noise and turbulence and the second demodulating the bit sequences. All data used for training and testing our network is obtained experimentally by generating OOK bit streams, combining these with thermal light, and passing the resultant light through a turbulent water tank which we have verified mimics turbulence in the air to a high degree of accuracy. Our CNN improves detection accuracy over threshold classification schemes and has the capability to be integrated with current demodulation and error correction schemes. |
| first_indexed | 2024-03-09T02:12:07Z |
| format | Article |
| id | doaj.art-d25a41fa37d74f50b7dac4c8aa6b5d02 |
| institution | Directory Open Access Journal |
| issn | 2632-2153 |
| language | English |
| last_indexed | 2024-03-09T02:12:07Z |
| publishDate | 2023-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | Machine Learning: Science and Technology |
| spelling | doaj.art-d25a41fa37d74f50b7dac4c8aa6b5d022023-12-07T09:01:51ZengIOP PublishingMachine Learning: Science and Technology2632-21532023-01-014404504610.1088/2632-2153/ad10cdDeep learning for enhanced free-space optical communicationsM P Bart0https://orcid.org/0000-0002-6791-4232N J Savino1https://orcid.org/0000-0002-2358-9714P Regmi2L Cohen3H Safavi4H C Shaw5https://orcid.org/0000-0001-7241-3793S Lohani6https://orcid.org/0000-0003-0699-0669T A Searles7B T Kirby8https://orcid.org/0000-0002-2698-9887H Lee9R T Glasser10https://orcid.org/0000-0001-7257-9064Department of Physics and Engineering Physics, Tulane University , New Orleans, LA 70118, United States of America; NASA Goddard Space Flight Center , Greenbelt, MD 20771, United States of AmericaDepartment of Physics and Engineering Physics, Tulane University , New Orleans, LA 70118, United States of AmericaDepartment of Physics and Astronomy, Louisiana State University , Baton Rouge, LA 70803, United States of AmericaDepartment of Electrical, Computer and Energy Engineering, University of Colorado Boulder , Boulder, CO 80309, United States of AmericaNASA Goddard Space Flight Center , Greenbelt, MD 20771, United States of AmericaNASA Goddard Space Flight Center , Greenbelt, MD 20771, United States of AmericaDepartment of Electrical & Computer Engineering, University of Illinois Chicago , Chicago, IL 60607, United States of AmericaDepartment of Electrical & Computer Engineering, University of Illinois Chicago , Chicago, IL 60607, United States of AmericaDepartment of Physics and Engineering Physics, Tulane University , New Orleans, LA 70118, United States of America; DEVCOM Army Research Laboratory , Adelphi, MD 20783, United States of AmericaDepartment of Physics and Astronomy, Louisiana State University , Baton Rouge, LA 70803, United States of AmericaDepartment of Physics and Engineering Physics, Tulane University , New Orleans, LA 70118, United States of AmericaAtmospheric effects, such as turbulence and background thermal noise, inhibit the propagation of light used in ON–OFF keying (OOK) free-space optical (FSO) communication. Here we present and experimentally validate a convolutional neural network (CNN) to reduce the bit error rate of FSO communication in post-processing that is significantly simpler and cheaper than existing solutions based on advanced optics. Our approach consists of two neural networks, the first determining the presence of bit sequences in thermal noise and turbulence and the second demodulating the bit sequences. All data used for training and testing our network is obtained experimentally by generating OOK bit streams, combining these with thermal light, and passing the resultant light through a turbulent water tank which we have verified mimics turbulence in the air to a high degree of accuracy. Our CNN improves detection accuracy over threshold classification schemes and has the capability to be integrated with current demodulation and error correction schemes.https://doi.org/10.1088/2632-2153/ad10cdoptical communicationfree space communicationdeep learningconvolutional neural networks |
| spellingShingle | M P Bart N J Savino P Regmi L Cohen H Safavi H C Shaw S Lohani T A Searles B T Kirby H Lee R T Glasser Deep learning for enhanced free-space optical communications Machine Learning: Science and Technology optical communication free space communication deep learning convolutional neural networks |
| title | Deep learning for enhanced free-space optical communications |
| title_full | Deep learning for enhanced free-space optical communications |
| title_fullStr | Deep learning for enhanced free-space optical communications |
| title_full_unstemmed | Deep learning for enhanced free-space optical communications |
| title_short | Deep learning for enhanced free-space optical communications |
| title_sort | deep learning for enhanced free space optical communications |
| topic | optical communication free space communication deep learning convolutional neural networks |
| url | https://doi.org/10.1088/2632-2153/ad10cd |
| work_keys_str_mv | AT mpbart deeplearningforenhancedfreespaceopticalcommunications AT njsavino deeplearningforenhancedfreespaceopticalcommunications AT pregmi deeplearningforenhancedfreespaceopticalcommunications AT lcohen deeplearningforenhancedfreespaceopticalcommunications AT hsafavi deeplearningforenhancedfreespaceopticalcommunications AT hcshaw deeplearningforenhancedfreespaceopticalcommunications AT slohani deeplearningforenhancedfreespaceopticalcommunications AT tasearles deeplearningforenhancedfreespaceopticalcommunications AT btkirby deeplearningforenhancedfreespaceopticalcommunications AT hlee deeplearningforenhancedfreespaceopticalcommunications AT rtglasser deeplearningforenhancedfreespaceopticalcommunications |