Privacy-Preserving Non-Wearable Occupancy Monitoring System Exploiting Wi-Fi Imaging for Next-Generation Body Centric...

Area of Science:

• Wireless sensing and communication systems
• Artificial intelligence in smart environments
• Cybersecurity for data privacy

Background:

• Next-generation technologies rely on nano-scaled structures, wireless sensing, and wearable devices.
• Radio-Frequency (RF) sensing systems are increasingly used in consumer electronics, healthcare, and smart buildings.
• Current systems often require wearable devices, raising privacy concerns.

Purpose of the Study:

• To propose a novel, non-wearable, device-free, and privacy-preserving Wi-Fi imaging-based occupancy detection system.
• To enable the identification of human presence and daily living activities within smart buildings without body-worn sensors.
• To develop a secure method for storing and analyzing occupancy data.

Main Methods:

• Utilized off-the-shelf non-wearable devices (Wi-Fi router, NIC, antenna) for Wi-Fi signal reception.
• Converted received Wi-Fi signals into time-frequency scalograms for image-based analysis.
• Employed an auto-encoder neural network for classifying scalogram images to detect occupancy and identify activities.
• Implemented a novel encryption algorithm based on Chirikov and Intertwining maps for data security.

Main Results:

• Achieved a classification accuracy of 91.1% for occupancy detection and activity recognition.
• Demonstrated the system's capability to detect human presence and activities without requiring any wearable devices.
• Successfully developed and integrated a privacy-preserving encryption algorithm for scalogram images.

Conclusions:

• The proposed Wi-Fi imaging system offers a promising solution for device-free occupancy detection in smart buildings.
• The system enhances privacy by being non-wearable and incorporating a robust encryption mechanism.
• Future applications include advanced human-centric communication and monitoring in smart environments.