C-MEL: Consensus-Based Multiple Ensemble Learning for Indoor Device-Free Localization Through Fingerprinting

• Published in: IEEE access 2024, Vol.12, p.166381-166392
• Main Authors: Suroso, Dwi Joko, Adiyatma, Farid Yuli Martin
• Format: Article
• Language: English
• Subjects: Accuracy; Boosting; Buildings; C-MEL; Classification algorithms; consensus strategy; Ensemble learning; ensemble learning algorithm; Fingerprint recognition; fingerprinting; Indoor device-free localization; Location awareness; Random forests; Wireless communication; Wireless fidelity
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2024.3493889

The rise of location-aware services is enhancing the effectiveness of our daily tasks, especially within indoor environments where most activities take place. Wireless indoor localization systems are the predominant method for estimating locations indoors. These systems utilize two primary approaches: device-based and device-free. Device-based techniques are attracting considerable research attention due to their ability to offer highly accurate localization in most scenarios. Conversely, device-free techniques are increasingly popular because they can determine a target's location without the target carrying a device. This capability makes them suitable for certain applications such as elderly monitoring and intruder tracking. The most popular technique for both approaches is fingerprinting, which uses the uniqueness of spatial information to predict a target's location. This spatial information is stored in a fingerprint database, containing locations and their associated parameters. However, in device-free methods, the fingerprint technique encounters challenges in accurately recognizing the complexity of each parameter combination pattern, thus impacting the accuracy of the estimation. To overcome this issue, we introduce a novel indoor device-free localization (IDFL) pattern matching algorithm named Consensus-based Multiple Ensemble Learning (C-MEL). This algorithm incorporates consensus strategies, i.e., majority voting and average strategy, to integrate outputs from various ensemble learning algorithms, such as Random Forest, Gradient Boosting, XGBoost, and LightGBM. We validate our algorithm in an 18 m2 office space featuring stainless steel partitions, tables, chairs, and cabinets. Experimental results show that C-MEL using the average strategy (C-MEL-AV) enhances accuracy by up to 44.51%, 11.26%, and 37.85%, while C-MEL with majority voting (C-MEL-MV) improves by up to 40.56%, 4.95%, and 33.44% compared to Decision Tree, Gradient Boosting, and 1D CNN-BLSTM, respectively. Based on these results, C-MEL-AV emerges as a reliable approach for accurate IDFL based on the fingerprint technique, while C-MEL-MV remains a viable alternative for IDFL systems.