Skip to main content
SpringerLink
Log in

LCSW: A Novel Indoor Localization System Based on CNN-SVM Model with WKNN in Wi-Fi Environments

  • Conference paper
  • First Online:
Neural Computing for Advanced Applications (NCAA 2022)

Part of the book series: Communications in Computer and Information Science ((CCIS,volume 1638))

Included in the following conference series:

  • 569 Accesses

Abstract

In this paper, we propose a novel indoor localization system, which fuses convolutional neural network (CNN) and support vector machine (SVM) model with an upgraded weighted K-nearest neighbor (WKNN) algorithm, called LCSW, to enhance the localization accuracy and robustness of the system. To this end, we propose a two-layer localization scheme. Specifically, in the first locating layer, we primarily partition the whole environment into certain subareas, then continuously collect the sequence data of RSSI in different time and reshape the data format as square matrix to serve as input of the modified CNN-SVM model to locate the target to a subarea. Then, in the second locating layer, the improved WKNN is used to calculate the precise location of the target in the corresponding subarea, which adopts the variance characteristic of Wi-Fi signal to assist the calculation of weights in measuring the distance and the cosine similarity to assist the assignment of weights in computing the coordinate, respectively. Finally, extensive real-world experiments are conducted to demonstrate the effectiveness of the proposed methods.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Pascacio, P., Casteleyn, S., Torres-Sospedra, J., Lohan, E.S., Nurmi, J.: Collaborative indoor localization systems: a systematic review. Sensors (Basel) 21(3), 1002 (2021). https://doi.org/10.3390/s21031002

  2. Zafari, F., Gkelias, A., Leung, K.K.: A survey of indoor localization systems and technologies. IEEE Commun. Surv. Tutorials 21(3), 2568–2599 (2019). https://doi.org/10.1109/COMST.2019.2911558

    Article  Google Scholar 

  3. Zhu, Q., Xiong, Q., Wang, K., Lu, W., Liu, T.: Accurate WiFi-based indoor localization by using fuzzy classifier and mlps ensemble in complex environment. J. Franklin Inst. 357(3), 1420–1436 (2020). https://doi.org/10.1016/j.jfranklin.2019.10.028

    Article  Google Scholar 

  4. Qwn, C.-M., Hou, J., Tao, W.: Signal fuse learning method With dual bands WiFi signal measurements in indoor localization. IEEE Access 7, 131805–131817 (2019). https://doi.org/10.1109/ACCESS.2019.2940054

    Article  Google Scholar 

  5. Yang, C., Shao, H.: WiFi-based indoor localization. IEEE Commun. Mag. 53(3), 150–157 (2015). https://doi.org/10.1109/MCOM.2015.7060497

    Article  Google Scholar 

  6. Wu, C., Yang, Z., Liu, Y.: Smartphones based crowdsourcing for indoor localization. IEEE Trans. Mobile Comput. 14(2), 444–457 (2015). https://doi.org/10.1109/TMC.2014.2320254

    Article  Google Scholar 

  7. Ma, Y., Wang, B., Pei, S., Zhang, Y., Zhang, S., Yu, J.: An indoor localization method based on AOA and PDOA using virtual stations in Multipath and NLOS environments for passive UHF RFID. IEEE Access 6, 31772–31782 (2018). https://doi.org/10.1109/CCESS.2018.2838590

    Article  Google Scholar 

  8. Bernardini, F., Buffi, A., Motroni, A., et al.: Particle swarm optimization in SAR-based method enabling real-time 3D localization of UHF-RFID tags. IEEE J. Radio Frequency Identif. 4(4), 300–313 (2020). https://doi.org/10.1109/JRFID.2020.3005351

    Article  Google Scholar 

  9. Kotrotsios, K., Orphanoudakis, T.: Accurate gridless indoor localization based on multiple bluetooth beacons and machine learning. In: 2021 7th International Conference on Automation, Robotics and Applications (ICARA), pp. 190–194 (2021). https://doi.org/10.1109/ICARA51699.2021.9376476

  10. Obreja, S.G., Vulpe, A.: Evaluation of an indoor localization solution based on bluetooth low energy Beacons. In: 2020 13th International Conference on Communications (COMM), pp. 227–231 (2020). https://doi.org/10.1109/COMM48946.2020.9141987

  11. Poulose, A., Han, D.S.: Feature-based deep LSTM network for indoor localization using UWB measurements. In: 2021 International Conference on Artificial Intelligence in Information and Communication (ICAIIC), pp. 298–301 (2021). https://doi.org/10.1109/ICAIIC51459.2021.9415277

  12. Zhang, S., Han, R., Huang, W., Wang, S., Hao, Q.: Linear bayesian filter based low-cost UWB systems for indoor mobile robot localization. In: 2018 IEEE SENSORS, pp. 1–4 (2018). https://doi.org/10.1109/ICSENS.2018.8589829

  13. You, Y., Wu, C.: Indoor localization system with cellular network assistance based on received signal strength indication of Beacon. IEEE Access 8, 6691–6703 (2020). https://doi.org/10.1109/ACCESS.2019.2963099

    Article  Google Scholar 

  14. Xue, W., Hua, X., Li, Q., Qiu, W., Peng, X.; Improved clustering algorithm of neighboring reference points based on KNN for indoor localization. In: 2018 Ubiquitous Localization, Indoor Navigation and Location-Based Services (UPINLBS), pp. 1–4 (2018). https://doi.org/10.1109/UPINLBS.2018.8559874

  15. Liu, W., Fu, X., Deng, Z., Xu, L., Jiao, J.: Smallest enclosing circle-based fingerprint clustering and modified-WKNN matching algorithm for indoor localization. In: 2016 International Conference on Indoor Localization and Indoor Navigation (IPIN), pp. 1–6 (2016). https://doi.org/10.1109/IPIN.2016.7743694

  16. Han, S., Zhao, C., Meng, W., Li C.: Cosine similarity based fingerprinting algorithm in WLAN indoor localization against device diversity. In: 2015 IEEE International Conference on Communications (ICC), pp. 2710–2714 (2015). https://doi.org/10.1109/ICC.2015.7248735

  17. Xue, W., et al.: A new weighted algorithm based on the Uneven spatial resolution of RSSI for Indoor localization. IEEE Access 6, 26588–26595 (2018). https://doi.org/10.1109/ACCESS.2018.2837018

    Article  Google Scholar 

  18. Han, X., Yang, G., Qu, S., Zhang, G., Chi, M.: A weighted algorithm based on physical distance and cosine similarity for Indoor localization. In: 2019 14th IEEE Conference on Industrial Electronics and Applications (ICIEA), pp. 179–183 (2019). https://doi.org/10.1109/ICIEA.2019.8833982

  19. Yang, B., Jia, X., Yang, F.: Variational bayesian adaptive unscented kalman filter for RSSI-based Indoor localization. Int. J. Control Autom. Syst. 19, 1183–1193 (2021). https://doi.org/10.1007/s12555-019-0973-9

    Article  Google Scholar 

  20. Guo, S., Niu, G., Wang, Z., Pun, M.-O., Yang, K.: An Indoor knowledge graph framework for efficient pedestrian localization. IEEE Sensors J. 21(4), 5151–5163 (2021). https://doi.org/10.1109/JSEN.2020.3029098

    Article  Google Scholar 

  21. Yang, H., Zhang, Y., Huang, Y., Fu, H., Wang, Z.: WKNN indoor location algorithm based on zone partition by spatial features and restriction of former location. Pervas. Mobile Comput. 60, 1192–1574 (2019). https://doi.org/10.1016/j.pmcj.2019.101085

    Article  Google Scholar 

  22. Chen, S., Zhu, Q., Li, Z., Long, Y.: Deep neural network based on feature fusion for Indoor wireless localization. In: 2018 International Conference on Microwave and Millimeter Wave Technology (ICMMT), pp. 1–3 (2018). https://doi.org/10.1109/ICMMT.2018.8563629

  23. Mittal, A., Tiku, S., Pasricha, S.: Adapting Convolutional Neural Networks for Indoor Localization with Smart Mobile Devices, pp. 117–122. Association for Computing Machinery (2018). https://doi.org/10.1145/3194554.3194594

  24. Tasaki, K., Takahashi, T., Ibi, S., Sampei, S.: 3D convolutional neural network-aided Indoor localization based on fingerprints of BLE RSSI. In: 2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), pp. 1483–1489 (2020)

    Google Scholar 

  25. Li, D., Xu, J., Yang, Z., Lu, Y., Zhang, Q., Zhang, X.: Train once, locate anytime for anyone: adversarial Learning based wireless localization. In: IEEE INFOCOM 2021 - IEEE Conference on Computer Communicatlons, pp. 1–10 (2021). https://doi.org/10.1109/INFOCOM42981.2021.9488693

  26. Qin, F., Zuo, T., Wang, X.: CCpos: WiFi fingerprint Indoor localization system based on CDAE-CNN. Sensors 21(4), 1114 (2021). https://doi.org/10.3390/s21041114

  27. Chen, H., Wang, B., Pei, Y., Zhang, L.: A WiFi Indoor localization method based on dilated CNN and support vector regression. In: 2020 Chinese Automation Congress (CAC), pp. 165–170 (2020) https://doi.org/10.1109/CAC51589.2020.9327326

  28. Qian, W., Lauri, F., Gechter, F.: Convolutional Mixture Density Recurrent Neural Network for Predicting User Location with WiFi Fingerprints. arXiv2019 (2019)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. College of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, 400065, China

    Xuhui Wang, Xin Deng & Hao Zhang

  2. College of Computer Science, Chongqing University, Chongqing, 400044, China

    Kai Liu

  3. School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, 611756, Sichuan, China

    Penglin Dai

Authors
  1. Xuhui Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Xin Deng
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Hao Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Kai Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Penglin Dai
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Hao Zhang .

Editor information

Editors and Affiliations

  1. Harbin Institute of Technology, Shenzhen, China

    Haijun Zhang

  2. University of Jinan, Jinan, China

    Yuehui Chen

  3. Shenzhen University, Shenzhen, China

    Xianghua Chu

  4. Hefei University of Technology, Hefei, China

    Zhao Zhang

  5. South China Normal University, Guangzhou, China

    Tianyong Hao

  6. Chongqing University, Chongqing, China

    Zhou Wu

  7. Western University, London, ON, Canada

    Yimin Yang

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Wang, X., Deng, X., Zhang, H., Liu, K., Dai, P. (2022). LCSW: A Novel Indoor Localization System Based on CNN-SVM Model with WKNN in Wi-Fi Environments. In: Zhang, H., et al. Neural Computing for Advanced Applications. NCAA 2022. Communications in Computer and Information Science, vol 1638. Springer, Singapore. https://doi.org/10.1007/978-981-19-6135-9_13

Download citation

  • DOI: https://doi.org/10.1007/978-981-19-6135-9_13

  • Published:

  • Publisher Name: Springer, Singapore

  • Print ISBN: 978-981-19-6134-2

  • Online ISBN: 978-981-19-6135-9

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation