UBiGTLoc: A Unified BiLSTM-Graph Transformer Localization Framework for IoT Sensor Networks

TL;DR

UBiGTLoc tackles IoT sensor localization under both anchor-free and anchor-present wireless sensor networks by leveraging RSSI data with temporal BiLSTM encoding and Graph Transformer-based spatial reasoning. The framework comprises four modules—Data Pre-Processing, Temporal Encoding, Spatial Attention, and Global Synthesis—feeding a centralized model that outputs 2D coordinates while relying solely on low-cost RSSI measurements. Empirical results show UBiGTLoc outperforms anchor-dependent baselines (GCN, AGNN, U-MLP) across dense and sparse networks, exhibits robustness to RSSI noise and interference, and maintains effectiveness as the anchor node percentage varies. The work demonstrates a practical, cost-efficient approach for scalable IoT deployments, with future directions toward multi-modal data integration and distributed processing.

Abstract

Sensor nodes localization in wireless Internet of Things (IoT) sensor networks is crucial for the effective operation of diverse applications, such as smart cities and smart agriculture. Existing sensor nodes localization approaches heavily rely on anchor nodes within wireless sensor networks (WSNs). Anchor nodes are sensor nodes equipped with global positioning system (GPS) receivers and thus, have known locations. These anchor nodes operate as references to localize other sensor nodes. However, the presence of anchor nodes may not always be feasible in real-world IoT scenarios. Additionally, localization accuracy can be compromised by fluctuations in Received Signal Strength Indicator (RSSI), particularly under non-line-of-sight (NLOS) conditions. To address these challenges, we propose UBiGTLoc, a Unified Bidirectional Long Short-Term Memory (BiLSTM)-Graph Transformer Localization framework. The proposed UBiGTLoc framework effectively localizes sensor nodes in both anchor-free and anchor-presence WSNs. The framework leverages BiLSTM networks to capture temporal variations in RSSI data and employs Graph Transformer layers to model spatial relationships between sensor nodes. Extensive simulations demonstrate that UBiGTLoc consistently outperforms existing methods and provides robust localization across both dense and sparse WSNs while relying solely on cost-effective RSSI data.

Figures (10)

• Figure 1: The system model of wireless IoT sensor networks with and without anchor nodes.
• Figure 2: The proposed unified BiLSTM-Graph Transformer Localization framework for wireless IoT sensor networks, namely UBiGTLoc.
• Figure 3: Computational graph of a single LSTM cell, i.e., $LSTM_t$.
• Figure 4: The computational graph of TransformerConv.
• Figure 5: CDF versus localization loss (in meters) for two network settings: (a) 500 sensor nodes, (b) 100 sensor nodes.