簡易檢索 / 詳目顯示

研究生: Akhmad Lutfi Rusidi
Akhmad Lutfi Rusidi
論文名稱: 基於神經網路解碼器和隨機森林進行室內定位
Combining Neural Network Decoder and Random Forest for Indoor Localization
指導教授: 林昌鴻
Chang-Hong Lin
口試委員: 陳維美
Wei-Mei Chen
吳晉賢
Chin-Hsien Wu
學位類別: 碩士
Master
系所名稱: 電資學院 - 電子工程系
Department of Electronic and Computer Engineering
論文出版年: 2022
畢業學年度: 111
語文別: 英文
論文頁數: 55
外文關鍵詞: Indoor Localization, Machine Learning, Wireless Sensor Network, Random Forest
相關次數: 點閱:174下載:3
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報


Indoor localization is one of the upcoming major research fields, which can be used in a wide variety of applications, such as indoor navigation and enterprise asset tracking. The original research on indoor localization dated back to 2000 when a group from Microsoft demonstrated RADAR, which used indoor localization with triangulation. Indoor localization with Wi-Fi used machine learning methods to effectively solve many limitations of conventional techniques, such as filtering, the fluctuation of RSSI signal, etc. This thesis proposes an indoor localization method using the Wi-Fi signals. We use two steps, which combines a Neural Network and a Random Forest. In the first step, we use a neural network decoder, which can generate more features. In the second step, we train the features acquired from the first step with the Random Forest to give the final prediction. We compare the proposed system using three datasets, and one of them is generated by collecting the dataset from an adlink-omnibot at the NTUST industry 4.0 research building. Comparing with existing methods in indoor localization, the proposed method gets the lowest average MSE for all three datasets.

ABSTRACT ..............................................I LIST OF CONTENTS..................................... II LIST OF FIGURES ......................................IV LIST OF TABLES........................................VI CHAPTER 1 INTRODUCTIONS .............................. 1 1.1 Motivation ....................................... 1 1.2 Contribution...................................... 3 1.3 Organization ..................................... 4 CHAPTER 2 RELATED WORKS .............................. 5 2.1 Traditional methods for indoor localization ...... 5 2.2 Machine Learning methods for indoor localization . 6 CHAPTER 3 PROPOSED METHODS............................ 8 3.1 Collecting dataset ............................... 8 3.2 Proposed model .................................. 12 3.2.1 Neural Network Architecture ....................13 3.3 Loss Function ................................... 15 3.4 Optimizer........................................ 15 3.5 Random Forest.................................... 17 3.5.1 Decision tree.................................. 19 CHAPTER 4 EXPERIMENTAL RESULTS ...................... 23 4.1 Experimental Environment......................... 23 4.2 Datasets......................................... 23 4.3 Experiments on Feature Extraction ............... 28 4.4 Evaluation Metric ............................... 32 4.4.1 Comparison of the Nexus 4 dataset.............. 32 4.4.2 Comparison of the Long-term fingerprint dataset 35 4.4.3 Comparison of the Our dataset.................. 38 CHAPTER 5 CONCLUSIONS and Future works .............. 40 5.1 Conclusions ..................................... 40 5.2 Future Works .................................... 41 REFERENCES .......................................... 42

[1] M. T. Hoang, Y. Zhu, B. Yuen, T. Reese, X. Dong, T. Luu, R. Westendorp and M. Xie,
“A soft range limited K-nearest neighbors algorithm for indoor localization
enhancement,” IEEE Sensors Journal, vol. 18, no. 24, pp.10208 -10216, 2001.
[2] P. Bahl and V. N. Padmanabhan, “RADAR: an in-building RF-based user location and
tracking system,” Conference on Computer and Communications, pp. 785-784, 2002.
[3] M. Nowicki and J. Wietrzykowski, “Low-effort place recognition with WiFi
fingerprints using deep learning,” International Conference on Automation, pp. 575-
584, 2017
[4] Z. Hyder and D. He, “Improved Wi-Fi indoor localization based on signal quality
parameters and RSSI smoothing algorithm,” International Conference on Information
and Automation for Sustainability, pp. 140-144, 2021.
[5] R. Ma, Q. Guo, C. Hu, and J. Xue, “An improved WiFi indoor positioning algorithm
by weighted fusion,” MDPI Sensors, vol. 15, no. 9, pp. 21824-21843, 2015.
[6] E. Jedari, Z. Wu, R. Rashidzadeh, and M. Saif, “Wi-Fi based indoor location
positioning employing random forest classifier," International Conference on Indoor
Positioning and Indoor Navigation, 2015.
[7] L. Zhao and L. Wang, “Improved indoor location algorithm based on Wi-Fi fingerprint
and random forest,” International Conference on Computer Information and Big Data
Applications, pp. 243-247, 2022.
[8] G. Mendoza-Silva, P. Richter, J. Torres-Sospedra, E. Lohan, and J. Huerta, “Long-term
WiFi fingerprinting dataset for research on robust indoor positioning,” MDPI Data, vol.
3, no.1:3, pp. 1-17, 2018.
[9] Z. Farid, R. Nordin, and M. Ismail, “Recent advances in wireless indoor localization
techniques and system," Journal of Compututer Networks and Communication, vol.
2013, pp. 1-12, 2013.
[10] M. Vossiek, L. Wiebking, P. Gulden, J. Wieghardt, and C. Hoffmann, “Wireless local
positioning - Concepts, solutions, applications,” Radio and Wireless Conference, pp.
219-224, 2003.
[11] Y. Tao, R. Yan and L. Zhao, “An Effective Fingerprint-Based Indoor Positioning
Algorithm Based on Extreme Values,” International Journal Geo-Information, vol. 11,
no. 2:81, pp. 1-21, 2022
[12] F. Seco, A. R. Jimenez, C. Prieto, J. Roa, and K. Koutsou, “A survey of mathematical
methods for indoor localization,” IEEE International Symposium on Intelligent Signal
Processing, pp. 4-14, 2009.
[13] T.-N. Lin and P.-C. Lin, “Performance comparison of indoor positioning techniques43
based on location fingerprinting in wireless networks,” International Conference on
Wireless Networks, Communications and Mobile Computing, pp. 1569-1574, 2005.
[14] M. A. Hearst, S. T. Dumais, E. Osuna, J. Platt, and B. Scholkopf, “Support vector
machines,” IEEE Intelligent Systems and their Applications, vol. 13, no. 4, pp.18-28
1998.
[15] B. Thomas and J. Anil, “A note on distance-weighted k-nearest neighbor rules,” IEEE
Transactions on Systems, Man, and Cybernetics, vol. 8, no. 4, pp.311-313, 1978.
[16] S. Hu, C. Shen, K. Zhang, and X. Huang, “Improved Wknn Indoor Positioning
Algorithm Based On C-Means And Chi-Square Distance,” International Conference on
Robots & Intelligent System, pp. 432-435, 2019.
[17] S. Amirisoori, S. M. Daud, N. A. Ahmad, S. Naatsaha, N. I. Mohd sa'at and N. Q. mohd
Noor, “Wi-Fi Based Indoor Positioning Using Fingerprinting Methods (KNN
Algorithm) in Real Environment,” International Journal of Future Generation
Communication and Networking, vol. 10, no. 9, pp.23-36, 2017.
[18] M. Heidari, F. O. Akgul, N. A. Alsindi, and K. Pahlavan, “Neural network assisted
identification of the absence of direct path in indoor localization,” IEEE Global
Telecommunications Conference, pp. 387-392, 2007.
[19] H. Dai, W.-H. Ying, and J. Xu, “Multi-layer neural network for received signal
strength-based indoor localization,” IET Communications, vol. 10, no. 6, pp.717-723,
2016.
[20] Y.-K. Cheng, H.-J. Chou, and R. Y. Chang, “Machine-learning indoor localization with
access point selection and signal strength reconstruction,” IEEE Vehicular Technology
Conference, 2016.
[21] A. H. Salamah, M. Tamazin, M. A. Sharkas, and M. Khedr, “An enhanced WiFi indoor
localization system based on machine learning,” International Conference on Indoor
Positioning and Indoor Navigation, 2016.
[22] R. Rong, Y. Fu, X. Zhang, J. Xu, and S. Xiong, “ANN Feature Scaling based k-Nearest
Neighbor Algorithm for Indoor Localization,” International Conference on Measuring
Technology and Mechatronics Automation, pp. 266-271, 2021.
[23] B. Soro and C. Lee, “Joint time-frequency RSSI features for convolutional neural
network-based indoor fingerprinting localization,” IEEE Access, vol. 7, pp.104892-
104899, 2019.
[24] X. Luo and N. Meratnia, “A geometric deep learning framework for accurate indoor
localization,” International Conference on Indoor Positioning and Indoor Navigation,
2022.
[25] “Neuron-OmniBot: A complete navigation package for ADLINK Neuron omnidirectionial robot.” Accessed: Nov. 08, 2022. [Online]. Available:
https://github.com/Adlink-ROS/Neuron-OmniBot44
[26] J. Guan, X. Zhi, H. Wang, and L. Yang, “Wi-Fi fingerprint positioning method based
on fusion of autoencoder and stacking mode,” International Conference on Cultureoriented Science & Technology, pp. 356-361, 2020.
[27] K. H. Tin, “Random decision forests," International Conference on Document Analysis
and Recognition, pp.278-282, 1995.
[28] F. Long, A. Behnad, and X. Wang, “Optimum reference node deployment for indoor
localization based on the average Mean Square Error minimization,” International
Performance Computing and Communications Conference, 2015,
[29] D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” International
Conference on Learning Representations, pp. 1-15, 2015.
[30] J. Duchi and H. Elad, “Adaptive subgradient methods for online learning and stochastic
optimization,” Journal of Machine Learning Research, vol. 12, pp. 2121-2159,2010.
[31] T. Takayama, T. Umezawa, N. Komuro, and N. Osawa, “An Indoor Positioning Method
Based on Regression Models with Compound Location Fingerprints,” Ubiquitous
Positioning, Indoor Navigation and Location-Based Service, 2018.
[32] Z. Wu, W. Lin, Z. Zhang, A. Wen, and L. Lin, “An Ensemble Random Forest Algorithm
for Insurance Big Data Analysis,” IEEE Access, vol. 5, pp. 16568 -16575, 2017.
[33] T. Peterek, P. Dohnalek, P. Gajdos, and M. Smondrk, “Performance evaluation of
Random Forest regression model in tracking Parkinson’s disease progress,”
International Conference on Hybrid Intelligent Systems, pp. 83-87, 2013.
[34] S. Saltykov, “Algorithm of Building Regression Decision Tree Using Complementary
Features,” International Conference Management of large-scale system development,
2020.
[35] ‘PyTorch’, Pytorch.org. [Online]. Available: https://pytorch.org/. [Accessed: 08-Nov-
2022].
[36] M. T. Hoang, B. Yuen, X. Dong, T. Lu, R. Westendorp, and K. Reddy Tarimala, “Semisequential probabilistic model for indoor localization enhancement,” IEEE Sensors
Journal, vol. 20, no. 11, pp.6160 - 6169, 2020.
[37] M. T. Hoang, B. Yuen, X. Dong, T. Lu, R. Westendorp, and K. Reddy, “Recurrent neural
networks for accurate RSSI indoor localization,” IEEE Internet of Things Journal, vol.
6, no. 6, pp. 10639 - 10651, 2019.
[38] H. Zou, M. Jin, H. Jiang, L. Xie, and C. J. Spanos, “WinIPS: Wi-Fi based non-intrusive
indoor positioning system with online radio map construction and adaptation,” IEEE
Transactions on Wireless Communications, vol. 16, no. 12, pp. 8118 - 8130, 2017.
[39] A. Kushki, K. N. Plataniotis, and A. N. Venetsanopoulos, “Kernel based positioning in
wireless local area networks,” IEEE Transactions on Wireless Communications, vol. 6,
no. 6, pp. 689 - 705, 2007.
[40] A. W. S. Au, C. Feng, S. Valaee, and S. Reyes, “Indoor tracking and navigation using45
received signal strength and compressive sensing on a mobile device,” IEEE
Transactions on Mobile Computing, vol. 12, no. 10, pp. 2050 - 2062, 2013.

QR CODE