Deep Learning for 3D Indoor Localization: A CNN Approach with 802.11az Fingerprinting

International Journal of Electronics and Communication Engineering

© 2025 by SSRG - IJECE Journal

Volume 12 Issue 9

Year of Publication : 2025

Authors : Bharti Masram, Sonam Chopade, Vinita Kakani, Minal Patil, Monali Gulhane, Nitin Rakesh, Roshan Umate

10.14445/23488549/IJECE-V12I9P107

How to Cite?

Bharti Masram, Sonam Chopade, Vinita Kakani, Minal Patil, Monali Gulhane, Nitin Rakesh, Roshan Umate, "Deep Learning for 3D Indoor Localization: A CNN Approach with 802.11az Fingerprinting," SSRG International Journal of Electronics and Communication Engineering, vol. 12,  no. 9, pp. 84-97, 2025. Crossref, https://doi.org/10.14445/23488549/IJECE-V12I9P107

Abstract:

Vehicle Indoor location tracking is a crucial technology for various applications, including intelligent buildings, robotics, and the Internet of Things (IoT). This research presents a deep learning method that employs Convolutional Neural Networks (CNNs) for Three-Dimensional (3D) indoor positioning, using 802.11az Wi-Fi fingerprinting. The proposed technique utilizes Channel Impulse Response (CIR) fingerprints generated through ray-tracing methods to gather detailed features of the wireless channel. In our method, CIR fingerprints are collected from multiple Access Points (APs) and enhanced through techniques like data augmentation, outlier removal, and normalization to boost model generalization. A sophisticated CNN architecture is designed to extract spatial information from Wi-Fi fingerprints, establishing strong connections between the received signals and their 3D location coordinates. The model is trained on both synthetic and real-world datasets and evaluated using cross-validation techniques. Our experimental results indicate that positioning based on CNNs significantly outperforms traditional machine learning approaches. Specifically, increasing Wi-Fi bandwidth (from CBW20 MHz to CBW180 MHz) and implementing MIMO configurations reduce positioning errors from 2.5 meters to 0.6 meters, achieving sub-meter localization accuracy in over 90% of cases. The analysis of the Cumulative Distribution Function (CDF) further corroborates that enhanced bandwidth and multiple antennas improve localization accuracy. Additionally, a comparative evaluation of 1×1 and 4×4 MIMO configurations highlights the performance gains achieved through spatial diversity. In conclusion, the proposed CNN-based system demonstrates that deep learning can significantly enhance Wi-Fi fingerprinting for indoor positioning, making it a viable solution for accurate localization in complex indoor environments. Future research may focus on optimizing neural architectures, facilitating real-time adjustments, and integrating beam-forming techniques to further elevate positioning efficacy.

Keywords:

Indoor Positioning, Wi-Fi Fingerprinting, 802.11az, (CNN), Channel Impulse Response (CIR), Ray-Tracing, Localization Accuracy, MIMO, Bandwidth Expansion.

References:

[1] IEEE P802.11az™/D2.6 Draft Standard for Information Technology-Telecommunications and Information Exchange between Systems Local and Metropolitan Area Networks-Specific Requirements - Amendment 3: Enhancements for Positioning, IEEE, pp. 1-269, 2021. [Google Scholar]
[2] Akis Kokkinis et al., “RSS Indoor Localization Based on a Single Access Point,” Sensors, vol. 19, no. 17, pp. 1-14, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Xuyu Wang et al., “CSI-Based Fingerprinting for Indoor Localization: A Deep Learning Approach,” IEEE Transactions on Vehicular Technology, vol. 66, no. 1, pp. 763-776, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Zhanpeng Zhang et al., “3D Indoor Localization via Universal Signal Fingerprinting Powered by LSTM,” 2024 14th International Conference on Indoor Positioning and Indoor Navigation (IPIN), Kowloon, Hong Kong, pp. 1-5, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Dongfang Mao, Haojie Lin, and Xuyang Lou, “Fingerprinting Indoor Positioning Based on Improved Sequential Deep Learning,” Algorithms, vol. 18, no. 1, pp. 1-17, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Muhammad Izzuddin Mahali et al., “DeepFuzzLoc Positioning: A Unified Fusion of Fuzzy Clustering and Deep Learning for Scalable Indoor Localization Using Wi-Fi RSSI,” 2024 Joint 13th International Conference on Soft Computing and Intelligent Systems and 25th International Symposium on Advanced Intelligent Systems (SCIS&ISIS), Himeji, Japan, pp. 1-6, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Zhuoyi Yu, “A WiFi Indoor Localization System Based on Robot Data Acquisition and Deep Learning Model,” 2024 6th International Conference on Internet of Things, Automation and Artificial Intelligence (IoTAAI), Guangzhou, China, pp. 367-371, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Hera Neyaz, Muhammad Inamullah, and M.M. Sufyan Beg, “Machine Learning Based Indoor Positioning System Using Wi-Fi Fingerprinting Dataset,” 2024 International Conference on Electrical, Computer and Energy Technologies (ICECET), Sydney, Australia, pp. 1-5, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Jae-Hyeon Park, Dongdeok Kim, and Young-Joo Suh, “WKNN-Based Wi-Fi Fingerprinting with Deep Distance Metric Learning via Siamese Triplet Network for Indoor Positioning,” Electronics, vol. 13, no. 22, pp. 1-19, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Yong Deng, and Chuanhao Li, “Research on Indoor Localization Method based on Deep Learning and Wireless Sensing,” Academic Journal of Science and Technology, vol. 11, no. 3, pp. 97-101, 2024.
[CrossRef] [Publisher Link]
[11] Yifan Yang et al., “MLTL: Manifold-Based Long-Term Learning for Indoor Positioning using WiFi Fingerprinting,” 2024 International Joint Conference on Neural Networks (IJCNN), Yokohama, Japan, pp. 1-8, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Jaspreet Kaur et al., “Fingerprinting-based Indoor Localization in a 3x3 Meter Grid Using OFDM Signals at Sub-6 GHz,” Applied AI Letters, vol. 6, no. 1, pp. 1-13, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Xuechen Chen et al., “Wi-Fi Fingerprint based Indoor Localization using Few Shot Regression,” 2024 27th International Conference on Computer Supported Cooperative Work in Design (CSCWD), Tianjin, China, pp. 2704-2709, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Farid Yuli Martin Adiyatma et al., “Hierarchical KNN for Smartphone-Based 3D Indoor Positioning,” 2024 International Technical Conference on Circuits/Systems, Computers, and Communications (ITC-CSCC), Okinawa, Japan, pp. 1-5, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Xinghang Zhan, and Zhenhua Wu, “Indoor Positioning based on Channel State Information and Deep Learning Domain Adaptation,” International Conference on Computer Graphics, Artificial Intelligence, and Data Processing, Qingdao, China, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Xiaofei Kang, Xian Liang, and Tian Wang, “Indoor Localization Algorithm based on Geometric Deep Learning,” Fifteenth International Conference on Signal Processing Systems (ICSPS 2023), Xi’an, China, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Fujun Pei, Mingjie Shi, and Xiangfei Kong, “Multi-Level Feature Extraction and Autoregressive Prediction Based Wi-Fi Indoor Fingerprint Localization,” 2023 China Automation Congress (CAC), Chongqing, China, pp. 1424-1428, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Lila Rana et al., “Indoor Positioning using DNN and RF Method Fingerprinting-based on Calibrated Wi-Fi RTT,” 2023 13th International Conference on Indoor Positioning and Indoor Navigation (IPIN), Nuremberg, Germany, pp. 1-6, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Kyounghyun Park et al., “Study on WiFi-based Indoor Positioning Prediction using Machine Learning Techniques,” 2023 14th International Conference on Information and Communication Technology Convergence (ICTC), Jeju Island, Korea, pp. 1471-1474, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Qianqian Ren et al., “FSTNet: Learning Spatial–Temporal Correlations from Fingerprints for Indoor Positioning,” Ad Hoc Networks, vol. 149, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Yinhuan Dong, Tughrul Arslan, and Yunjie Yang, “A Multimodal Graph Fingerprinting Method for Indoor Positioning Systems,” 2023 13th International Conference on Indoor Positioning and Indoor Navigation (IPIN), Nuremberg, Germany, pp. 1-6, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Farid Yuli Martin Adiyatma, Dwi Joko Suroso, and Panarat Cherntanomwong, “Machine Learning-Based Multi-Room Indoor Localization Using Fingerprint Technique,” 2023 15th International Conference on Information Technology and Electrical Engineering (ICITEE), Chiang Mai, Thailand, pp. 258-263, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Hui Zhu et al., “Neural-Network-Based Localization Method for Wi-Fi Fingerprint Indoor Localization,” Sensors, vol. 23, no. 15, pp. 1-19, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Xu Feng, Khuong An Nguyen, and Zhiyuan Luo, “A Dynamic Model Switching Algorithm for WiFi Fingerprinting Indoor Positioning,” 2023 13th International Conference on Indoor Positioning and Indoor Navigation (IPIN), Nuremberg, Germany, pp. 1-6, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Irene Cappelli et al., “Embedded Machine Learning for 3D Indoor Visible Light Positioning via Optimized Fingerprinting,” 2023 IEEE International Workshop on Metrology for Industry 4.0 & IoT (MetroInd4.0&IoT), Brescia, Italy, pp. 13-18, 2023. [CrossRef] [Google Scholar] [Publisher Link]