본문 바로가기
KERD
논문KCI 등재

합성곱 신경망을 적용한 Optical Camera Communication 시스템 성능 분석

Performance Analysis of Optical Camera Communication with Applied Convolutional Neural Network

김정현|박현선|김종인
(사)한국스마트미디어학회 (Korean Institute of Smart Media)|2023.04|스마트미디어저널 (Smart Media Journal)|제12권 제3호|pp. 49-59|DOI https://dx.doi.org/10.30693/SMJ.2023.12.3.49

0

조회

0

다운로드

0

인용

0

참고문헌

키워드

딥러닝Deep Learning합성곱 신경망Convolutional Neural NetworkOptical Camera Communication광학 카메라 통신
주제분류컴퓨터학

초록

차세대 무선 통신기술로 알려져 있는 Optical Camera Communication(OCC)은 많은 연구가 진행 되고 있다. 이러한 OCC 기술은 통신 환경에 의해 성능이 좌우되며 이를 개선하기 위해 다양한 전략이 연구되고 있다. 그중 가장 두각을 나타내고 있는 방법은 딥러닝 기술을 사용하여 OCC의 수신기에 CNN을 적용하는 방법이다. 하지만 대부분의 연구에서는 CNN을 단순히 송신기를 검출하는데 사용하고 있다. 본 논문에서는 CNN을 송신기 검출 뿐만 아니라 Rx 복조 시스템에 적용하여 실험한다. 그리고 OCC 시스템의 데이터 이미지는 다른 이미지 데이터셋과는 다르게 비교적 분류가 간단하기 때문에 대부분의 CNN 모델에서 높은 정확도의 결과가 나타날 것이라는 가설을 세웠다. 가설을 증명하기 위해 OCC 시스템을 설계 및 구현하여 데이터를 수집하였고 12가지의 다양한 CNN 모델에 적용하여 실험했다. 실험 결과 파라미터수가 많은 고성능의 CNN 모델 뿐만 아니라 경량화 CNN 모델에서도 99% 이상의 정확도를 달성하였고 이를 통해 스마트폰과 같은 저성능 계산 장치에 OCC 시스템 적용이 가능함을 확인했다.

Abstract

Optical Camera Communication (OCC), known as the next-generation wireless communication technology, is currently under extensive research. The performance of OCC technology is affected by the communication environment, and various strategies are being studied to improve it. Among them, the most prominent method is applying convolutional neural networks (CNN) to the receiver of OCC using deep learning technology. However, in most studies, CNN is simply used to detect the transmitter. In this paper, we experiment with applying the convolutional neural network not only for transmitter detection but also for the Rx demodulation system. We hypothesize that, since the data images of the OCC system are relatively simple to classify compared to other image datasets, high accuracy results will appear in most CNN models. To prove this hypothesis, we designed and implemented an OCC system to collect data and applied it to 12 different CNN models for experimentation. The experimental results showed that not only high-performance CNN models with many parameters but also lightweight CNN models achieved an accuracy of over 99%. Through this, we confirmed the feasibility of applying the OCC system in real-time on mobile devices such as smartphones.

참고문헌 (51)

  1. "The LiFi Technology"[URL]
  2. "IEEE P802.11-Light Communication (LC) Task Group (TG)"[URL]
  3. "IEEE 802.15 WPAN Task Group 7 (TG7) Visible Light Communication"[URL]
  4. Ahmed A, "An Empirical Study of Deep Learning Models for LED Signal Demodulation in Optical Camera Communication", Network, 1(3), pp.261~278 (2021)
  5. P. H. Pathak, "Visible Light Communication, Networking, and Sensing : A Survey, Potential and Challenges", IEEE Communications Surveys & Tutorials, 17(4), pp.2047~2077 (2015)
  6. Ghassemlooy, Zabih, "Visible light communications : theory and applications" (2017), CRC press
  7. "What Is a Photodiode? Working, Characteristics, Applications"[URL]
  8. Cahyadi, "Optical Camera Communications: Principles, Modulations, Potential and Challenges", Electronics, 9(9), pp.1339~ (2020)
  9. T. Nguyen, "Current Status and Performance Analysis of Optical Camera Communication Technologies for 5G Networks", IEEE Access, 5, pp.4574~4594 (2017)
  10. Saha, Nirzhar, "Survey on optical camera communications : challenges and opportunities", Iet Optoelectronics, 9(5), pp.172~183 (2015)
  11. Nam-Tuan Le, "Invisible watermarking optical camera communication and compatibility issues of IEEE 802.15.7r1 specification", Optics Communications, 390, pp.144~155 (2017)
  12. T. Yamazato, "Vehicle Motion and Pixel Illumination Modeling for Image Sensor Based Visible Light Communication", IEEE Journal on Selected Areas in Communications, 33(9), pp.1793~1805 (2015)
  13. I. Takai, "Optical Vehicle-to-Vehicle Communication System Using LED Transmitter and Camera Receiver", IEEE Photonics Journal, 6(5), pp.1~14 (2014)
  14. B. Lin, "An Indoor Visible Light Positioning System Based on Optical Camera Communications", IEEE Photonics Technology Letters, 29(7), pp.579~582 (2017)
  15. J. Armstrong, "Visible light positioning : a roadmap for international standardization", IEEE Communications Magazine, 51(12), pp.68~73 (2013)
  16. Shahjalal, Md, "An implementation approach and performance analysis of image sensor based multilateral indoor localization and navigation system", Wireless Communications and Mobile Computing, 2018 (2018)
  17. P. Luo, "Undersampled phase shift ON-OFF keying for camera communication", 2014 Sixth International Conference on Wireless Communications and Signal Processing (WCSP), pp.1~6 (2014)
  18. Hasan M. K., "Performance Analysis and Improvement of Optical Camera Communication", Applided Sciences, 8(12), pp.2527~ (2018)
  19. H. Lee, "Deep Learning Framework for Wireless Systems : Applications to Optical Wireless Communications", IEEE Communications Magazine, 57(3), pp.35~41 (2019)
  20. Choi, D.N, "Deep Learning Technique for Improving Data Reception in Optical Camera Communication-Based V2I", Proceedings of the 28th International Conference on Computer Communication and Networks (ICCCN), pp.1~2 (2019)
  21. P. G. Pachpande, "Visible Light Communication Using Deep Learning Techniques", 2018 IEEE 39th Sarnoff Symposium, pp.1~6 (2018)
  22. He, W., "Design and Implementation of Adaptive Filtering Algorithm for VLC Based on Convolutional Neural Network", Proceedings of the 2019 IEEE 5th International Conference on Computer and Communications (ICCC), pp.317~321 (2019)
  23. Langer, K.;, "Recent Developments in Optical Wireless Communications using Infrared and Visible Light", Proceedings of the 2007 9th International Conference on Transparent Optical Networks, 3, pp.146~151 (2007)
  24. Lee, Hoon, "Binary signaling design for visible light communication: a deep learning framework", Optics express, 26(14), pp.18131~18142 (2018)
  25. Wang, Chunxi, "Reinforcement learning based network selection for hybrid VLC and RF systems", MATEC Web of Conferences, 173 (2018)
  26. B. Turan, "Machine Learning Based Channel Modeling for Vehicular Visible Light Communication", IEEE Transactions on Vehicular Technology, 70(10), pp.9659~9672 (2021)
  27. Wu, Xi, "Deep neural network method for channel estimation in visible light communication", Optics communications, 462, pp.125272~ (2020)
  28. A. KRIZHEVSKY, "Imagenet classification with deep convolutional neural networks", Communications of the ACM, 60(6), pp.84~90 (2017)
  29. Y. Lecun, "Gradient-based learning applied to document recognition", Proc. IEEE, 86(11), pp.2278~2324 (1998)
  30. K. SIMONYAN, "Very deep convolutional networks for large-scale image recognition" (2014)
  31. C. SZEGEDY, "Going deeper with convolutions", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.1~9 (2015)
  32. K. HE, "Deep residual learning for image recognition", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.770~778 (2016)
  33. G. HUANG, "Densely connected convolutional networks", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.4700~4708 (2017)
  34. A. VASWANI, "Attention is all you need", Advances in neural information processing systems (2017)
  35. A. e. a. DOSOVITSKIY, "An image is worth 16x16 words: Transformers for image recognition at scale" (2020)
  36. F. WANG, "Residual attention network for image classification", Proceedings of the IEEE conference on computer vision and pattern recognition, pp, pp.3156~3164 (2017)
  37. J. HU, "Squeeze-and-excitation networks", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.7132~7141 (2018)
  38. Jongchan, P, "BAM: Bottleneck Attention Module" (2018)
  39. Sanghyun, W, "CBAM: Convolutional Block Attention Module" (2018)
  40. Alexey, D, "An image is worth 16x16 words: Transformers for image recognition at scale" (2020)
  41. Touvron, H, "Training data-efficient image transformers & distillation through attention", Proceedings of the International Conference on Machine Learning (2021)
  42. Chollet, F., "Xception: “Deep learning with depthwise separable convolutions,”", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.1251~1258 (2017)
  43. Iandola, I.N, "SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 0.5 MB model size" (2016)
  44. Howard, A.G, "Mobilenets: Efficient convolutional neural networks for mobile vision applications" (2017)
  45. Xiangyu, Z, "Shufflenet: “An extremely efficient convolutional neural network for mobile devices,”", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.6848~6856 (2018)
  46. Mark, S, "MobileNetV2: “Inverted Residuals and Linear Bottlenecks,”", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.4510~4520 (2018)
  47. Ningning, M, "Shufflenet v2: “Practical guidelines for efficient cnn architecture design,”", Proceedings of the European Conference on Computer Vision (ECCV), pp.116~131 (2018)
  48. Deng, J, "Imagenet: “A large-scale hierarchical image database", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.248~255 (2009)
  49. Van Horn, G, "Building a bird recognition app and large scale dataset with citizen scientists: The fine print in fine-grained dataset collection", CVPR, pp.595~604 (2015)
  50. "Butterfly & Moths Image Classification 100 Species"[URL]
  51. Kim J-I, "EffShuffNet: An Efficient Neural Architecture for Adopting a Multi-Model", Applied Sciences, 13, pp.3505~ (2023)

관련 논문AI추천

비직교 다중변조 방식을 이용한 고속 가시광통신 시스템에 대한 연구이규진, 한두희중소기업융합학회 · 융합정보논문지2020 · 제10권 제2호CNN을 활용한 M-PSK변조 기반 무선 광통신 시스템에서의 Log-Normal 모델과 Gamma-Gamma 모델의 대기 난류 채널 분류 성능 비교김소은, 이충규, 황용운한국차세대컴퓨팅학회 · 한국차세대컴퓨팅학회 논문지2024 · 제20권 제4호Comparison of Modulation Methods and Readout Modes of Optical Camera Communications송범, 김소은, 이충규한국차세대컴퓨팅학회 · 한국차세대컴퓨팅학회 논문지2020 · 제16권 제2호차량 사이의 텍스트메시지 교환을 위한 단거리 광카메라통신시스템 시연송판, 이충규한국차세대컴퓨팅학회 · 한국차세대컴퓨팅학회 논문지2022 · 제18권 제6호딥 러닝 기반의 이기종 무선 신호 구분을 위한 데이터 수집 효율화 기법최재혁한국전기전자학회 · 전기전자학회논문지2022 · 제26권 제1호계층적 CNN을 이용한 방송 매체 내의 객체 인식 시스템 성능향상 방안권명규, 양효식한국디지털정책학회 · 디지털융복합연구2017 · 제15권 제3호

이 간행물의 다른 논문 (12건)

스마트폰 센서를 통한 우울증 탐지 및 위급상황 탐지 모델 연구최민, 박재용, 손민근, 이강표pp. 9-18웨어러블向 시선추적 기법에 관한 연구정지우, 장재혁, 박정훈pp. 19-29Diagnosis of Alzheimer’s Disease using Wrapper Feature Selection Method권구락, Vyshnavi Raminenipp. 30-37불변 개인정보에 기반하여 소유자 신원 드러나지 않도록 적격성 검증박준철pp. 38-48Hyperledger Indy의 가용성을 위한 모니터링 시스템 구현최규현, 김근형pp. 60-67
원문 보기