Researchs
collaborative threat detection framework for massive iot in industrial applications
The heterogeneous connectivity of the massive Internet of Things (IoT) in 6G networks offers significant advantages by generating a vast amount of real-time data for various intelligent IoT services. However, this capability is vulnerable to sophisticated cyber-attacks and malicious network activities. This research provides a trusted and verifiable collaborative threat detection (CTD) framework by utilizing blockchain, federated learning, and efficient digital signature for securing massive IoT services in industrial applications.
edge learning-assisted interactive avatar creation platform in metaverse
Avatars are essential in the metaverse platform development to visually represent the players. Edge learning-assisted interactive avatar creation framework can address the limited movement capability in the existing metaverse environments. This research provides a human-like avatar creation framework by employing IoT-based human activity recognition (HAR) with distributed and collaborative learning mechanisms. A reliable communication module is developed to integrate the HAR framework and metaverse platform.
Related Publications: [Paper 1]
Related Publications: [Paper 1]
trusted and decentralized automatic modulation classification (AMC) for next-generation wireless networks
Automatic modulation classification (AMC) is essential to dynamic spectrum access in B5G and 6G networks for refarming the spectrum resources. However, the recent deep learning (DL)-based AMC framework has communication overhead, requires more computing resources, and poses security issues. Next-generation wireless networks allow distributed collaborative scenarios to provide ultra-reliable and low-latency communications (URLLC) services. This study proposes a blockchain-assisted decentralized collaborative AMC framework with a lightweight model to provide a trusted and decentralized AMC framework for next-generation wireless networks.