eDeepRFID-IPS: Enhanced RFID Indoor Positioning with Deep Learning for Internet of Things.

In smart environments, indoor positioning systems provide several options for smart computing users, businesses, and industries, thereby dramatically enhancing human well-being and productivity. Smart homes and smart indoor environments are prominent emerging technologies in the Internet of Things era and future communications, with applications such as providing personalized healthcare to the elderly and those with impairments by connecting them to the world via high-speed wireless communication infrastructure. This study offers a new approach to real-time indoor positioning using passive RFID technology to estimate the real-time location of smart home users based on their movements in smart environment space. An experimental indoor positioning system technique intends to improve assisted living and identify daily activities in a smart environment. To demonstrate this, we conducted a case study on indoor positioning using RFID technology. The experimental investigation is based on a location-based system that leverages the creation of deep learning algorithms in conjunction with radio signal strength indicator (RSSI) measurements of passive RFID-tagged devices. The proposed architecture encourages more precise identification of smart home objects and the ability to precisely locate users in real-time with good measured precision while minimizing technical and technological barriers to the adoption of location-based technologies in the daily lives of smart environment inhabitants. This will eventually facilitate the realization of location-based Internet of Things (IoT) systems.