Journal of Internet of Things and Convergence (사물인터넷융복합논문지)

The Korea Internet of Things Society (한국사물인터넷학회)
권호 표지
DOI QR코드

DOI QR Code

Smoothed RSSI-Based Distance Estimation Using Deep Neural Network

심층 인공신경망을 활용한 Smoothed RSSI 기반 거리 추정

  • Hyeok-Don Kwon (Division of Software, Hallym University ) ;
  • Sol-Bee Lee (Department of Convergence Software, Hallym University) ;
  • Jung-Hyok Kwon (Smart Computing Laboratory, Hallym University ) ;
  • Eui-Jik Kim (Division of Software, Hallym University)
  • 권혁돈 (한림대학교 소프트웨어학부 ) ;
  • 이솔비 (한림대학교 융합소프트웨어학과 ) ;
  • 권정혁 (한림대학교 스마트컴퓨팅연구소 ) ;
  • 김의직 (한림대학교 소프트웨어학부)
  • Received : 2023.02.16
  • Accepted : 2023.03.17
  • Published : 2023.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we propose a smoothed received signal strength indicator (RSSI)-based distance estimation using deep neural network (DNN) for accurate distance estimation in an environment where a single receiver is used. The proposed scheme performs a data preprocessing consisting of data splitting, missing value imputation, and smoothing steps to improve distance estimation accuracy, thereby deriving the smoothed RSSI values. The derived smoothed RSSI values are used as input data of the Multi-Input Single-Output (MISO) DNN model, and are finally returned as an estimated distance in the output layer through input layer and hidden layer. To verify the superiority of the proposed scheme, we compared the performance of the proposed scheme with that of the linear regression-based distance estimation scheme. As a result, the proposed scheme showed 29.09% higher distance estimation accuracy than the linear regression-based distance estimation scheme.

본 논문에서는 단일 수신기가 사용되는 환경에서 정확한 거리 추정을 위해 심층 인공신경망 (Deep Neural Network, DNN)을 활용한 Smoothed Received Signal Strength Indicator (RSSI) 기반 거리 추정 기법을 제안한다. 제안 기법은 거리 추정 정확도 향상을 위해 Data Splitting, 결측치 대치, Smoothing 단계로 구성된 전처리 과정을 수행하여 Smoothed RSSI 값을 도출한다. 도출된 다수의 Smoothed RSSI 값은 Multi-Input Single-Output(MISO) DNN 모델의 Input Data로 사용되며 Input Layer와 Hidden Layer를 통과하여 최종적으로 Output Layer에서 추정 거리로 반환된다. 제안 기법의 우수성을 입증하기 위해 제안 기법과 선형회귀 기반 거리 추정 기법의 성능을 비교하였다. 실험 결과, 제안 기법이 선형회귀 기반 거리 추정 기법 대비 29.09% 더 높은 거리 추정 정확도를 보였다.

Keywords

Acknowledgement

본 연구는 2022년도 중소벤처기업부의 기술개발사업 지원에 의한 연구임 [S3278476]. 이 논문은 2020년도 정부 (교육부)의 재원으로 한국연구재단의 지원을 받아 수행된 기초연구사업임 (No. 2020R1I1A3052733). 이 성과는 정부 (과학기술정보통신부)의 재원으로 한국연구재단의 지원을 받아 수행된 연구임 (No. 2021R1C1C2095696).

References

  1. E.Heidari, A.Gladisch, B.Moshiri, and D.Tavangarian, "Survey on location information services for Vehicular Communication Networks," Wireless networks, Vol.20, No.5, pp.1085-1105, 2014. https://doi.org/10.1007/s11276-013-0666-x
  2. S.K.Prasad, J.Rachna, O.I.Khalaf, and D.N.Le, "Map matching algorithm: real time location tracking for smart security application," Telecommunications and Radio Engineering, Vol.79, No.13, pp.1189-1203, 2020. https://doi.org/10.1615/TelecomRadEng.v79.i13.80
  3. A.Poulose, and D.S.Han, "UWB indoor localization using deep learning LSTM networks," Applied Sciences-Basel, Vol. 10, No.18, pp.6290:1-6290:23, 2020. https://doi.org/10.3390/app10186290
  4. G.Li, E.Geng, Z.Ye, Y.Xu, J.Lin, and Y.Pang, "Indoor positioning algorithm based on the improved RSSI distance model," Sensors, Vol.18, No.9, pp.2820:1-2820:15, 2018. https://doi.org/10.3390/s18092820
  5. E.Hatem, B.El-Hassan, M.J.Laheurte, S.Abou-Chakra, E.Colin, and C.Marechal, "Study the estimated distance error in indoor localization using UHF-RFID," in Proceedings of IEEE Middle East and North Africa Communications Conference (MENACOMM), pp.1-5, 2018.
  6. N.Chuku and A.Nasipuri, "RSSI-Based localization schemes for wireless sensor networks using outlier detection," Journal of Sensor and Actuator Networks, Vol.10, No.1, pp.10:1-10:22, 2021. https://doi.org/10.3390/jsan10010010
  7. M.I.M.Ismail, R.A.Dzyauddin, S.Samsul, N.A.Azmi, Y.Yamada, M.F.M.Yakub, and N.A.B.A.Salleh, "An RSSI-based wireless sensor node localisation using trilateration and multilateration methods for outdoor environment," 2019, arXiv:1912.07801. [Online]. Available: https://arxiv.org/abs/1912.07801
  8. Z.Wu, E.Jedari, R.Muscedere, and R.Rashidzadeh, "Improved particle filter based on WLAN RSSI fingerprinting and smart sensors for indoor localization," Computer Communications, Vol.83, pp.64-71, 2016.
  9. S.B.LEE, J.H.Kwon, and E.J.Kim, "Linear Regression-Based Distance Estimation Model for Preventing Safety Accidents in School Vehicles," in Proceedings of the Korean Institute of Communication Sciences Conference, pp.1219-1220, 2021.
  10. Y.H.Kwon and I.B.Jung, "A Location Compensation Method for Smart Mobile Objectsusing Multilateral Machine Learning," KIISE Transactions on Computing Practices, Vol.26, No. 7, pp.312-321, 2020. https://doi.org/10.5626/KTCP.2020.26.7.312
  11. M. Abadi, A. Agarwal, P. Barham, E. Brevdo, Z. Chen, C. Citro, G. S. Corrado, A. Davis, J. Dean, M. Devin et al., "Tensorflow: Large-scale machine learning on heterogeneous distributed systems," 2016, arXiv:1603.04467. [Online]. Available: https://arxiv.org/abs/1603.04467
  12. D.C.LEE. "Comparison of Reinforcement Learning Activation Functions to Maximize Rewards in Autonomous Highway Driving," The Journal of the Institute of Internet, Broadcasting and Communication, Vol.22, No.5, pp. 63-68, 2022.
  13. C.T.Chen, and G.X.Gu, "Generative deep neural networks for inverse materials design using backpropagation and active learning," Advanced Science, Vol.7, No.5, pp.1902607:1-1902607:10, 2020.
  14. L.Li, M.Doroslovacki, and M.H.Loew, "Approximating the gradient of cross-entropy loss function," IEEE Access, Vol.8, pp.111626-111635, 2020.
  15. Beafon, BLE Beacon of Beafon [Online]. Available: http://www.beafon.co.kr
  16. Raspberry Pi, Teach, Learn, and Make with Raspberry Pi [Online]. Available: https://www.raspberrypi.org