Research on Adaptive SVR Indoor Location Based on GA Optimization
- 144 Downloads
Indoor positioning based on the received signal strength index of ZigBee has received more and more attention due to its low cost, low hardware power consumption and easy implementation. However, due to the existence of multi-path and shadow effects, traditional positioning algorithms often cannot achieve better positioning results. Support vector regression can use these relative errors as the characteristics of the fingerprint database to establish a regression map between the RSSI values and the positioning coordinates. Based on this, this paper proposes a genetic algorithm optimization support vector regression (GA-SVR) method to solve the problem of low ZigBee positioning accuracy. The penalty vector \(C\), RBF kernel width \(\sigma\), and loss function variable \(\in\) of support vector regression are optimized by genetic algorithm in the proposed method, so that support vector regression achieves the best position prediction performance. Firstly, the training data is clustered by Gaussian hybrid clustering algorithm to establish a fingerprint database. Then the GA-SVM classifier is used to classify the test points. Finally, the coordinates of the test points are regressed and predicted by the GA-SVR model. The simulation and experiment in the actual scene prove the effectiveness of the proposed method. The experimental results show that compared with PSO-SVR, GS-SVR, PLS-SVR, SVR and WKNN algorithms, the GA-SVR algorithm has higher positioning accuracy.
KeywordsFingerprint database Genetic algorithm (GA) RSSI Support vector regression (SVR) ZigBee
This work was funded by North University of China of Key Laboratory Open Research Fund (No. DXMBJJ2018-08).
- 3.Kjærgaard, M. B., Blunck, H., & Godsk, T. (2010). Indoor positioning using GPS revisited. In Proceedings international conference on pervasive computing (pp. 38–56).Google Scholar
- 5.Gikas, V., Dimitratos, A., & Perakis, H. (2016). Full-scale testing and performance evaluation of an active RFID system for position and personal mobility. In Proceedings international conference on IPIN (pp. 1–8), Alcalá de Henares, Spain, October 2016.Google Scholar
- 6.Seco, F., Plagemann, C., & Jiménez, A. (2010). Improving RFID-based indoor positioning accuracy using gaussian processes. In Proceedings international conference on IPIN (pp. 1–8), Zurich, Switzerland, September 2010.Google Scholar
- 10.Yuan, Y., Pei, L., & Xu, C. (2014). Efficient WiFi fingerprint training using semi-supervised learning. In Proceedings UPINLBS (pp. 148–155), Corpus Christ, USA, November 2014.Google Scholar
- 11.Reddy, H., Chandra, M. G., & Balamuralidhar, P. (2007). An improved time-of-arrival estimation for WLAN-based local positioning. In Proceedings of 2nd international conference COMSWARE, Bangalore, India, January 2007.Google Scholar
- 15.Yang, L., Chen, H., & Cui, Q. (2015). Probabilistic-KNN: A novel algorithm for passive indoor-localization scenario. In Proceedings 81st IEEE VTC, Glasgow, UK, May 2015.Google Scholar
- 16.Youssef, M. A., Agrawala, A., & Shankar, A. U. (2003). WLAN location determination via clustering and probability distributions. In Proceedings 1st IEEE international conference on pervasive computing and communications (pp. 143–150), Dallas-Fort Worth, USA, March 2003.Google Scholar
- 19.Laoudias, C., Panayiotou, C. G., & Kemppi, P. (2010). On the RBF-based positioning using WLAN signal strength fingerprints. In Proceedings 7th WPNC (pp. 93–98), Dresden, Germany, March 2010.Google Scholar
- 22.Haeberlen, A., Flannery, E., & Ladd, A. M. (2004). Practical robust localization overlarge-scale 802.11 wireless networks. In Proceedings 10th annual international conference on mobile computing and networking (pp. 70–84), Philadelphia, USA, 26 September through 1 October 2004.Google Scholar
- 26.Kuo, R. J., Chen, C. M., Liao, T. W., et al. (2013). Hybrid of artificial immune system and particle swarm optimization-based support vector machine for radio frequency identification-based positioning system. Computers and Industrial Engineering, 64, 333–341. https://doi.org/10.1016/j.cie.2012.10.007.CrossRefGoogle Scholar
- 30.Drucker, H., Burges, C. J. C., & Kaufman, L., et al. (1996). Support vector regression machines. [Online] http://papers.nips.cc/paper/1238-support-vector-regression-machines.pdf. Accessed 13 Feb 2019.