AI-Enhanced Wide Range Fingerprinting Localization for Low-Energy Wireless Sensor Networks

Localization is now a popular topic in research and development. It uses various methods to locate objects in space, whether these objects are moving or static. The researchers aim to find the most accurate way to position or track these objects. GPS and similar systems provide global precision, but cannot be depended upon in indoor environments due to signal attenuation and obstacle loss, causing erroneous and poor data for the localization system. Wireless Sensor Networks (WSNs) have enhanced techniques by employing internal signal strength in indoor environments. However, challenges remain, such as nonline-of-sight, signal variability, and energy consumption. It is important to explore other link quality metrics from the used hardware. In this paper, we intend to solve these problems using advanced Link Quality Metrics (LQM) AI-Fingerprinting based on revolutionized ML techniques, taking into consideration low energy consumption for extending the overall WSN lifetime.