Wireless AI - AI/ML Empowered 5G/6G, Connected Car, and IoT

AI/ML for wireless communications Deep learning-based CSI feedback and channel estimation Deep learning-based resource allocation for 5G/6G and V2X networks Deep learning-based beam management - beam tracking, beam width selection AI/ML for emerging networks and simulations AI/ML for emerging networks, e.g., wireless powered networks, UAVs, URLLC, V2X, etc. AI/ML for network coexistence, e.g., HetNet, cognitive radio, device-to-device networks Testbed, experiments, and simulations of AI in communications and networking

Artificial Intelligence (AI) in wireless communications: AI, which learns from the perceived environment and can exploit the increasingly massive datasets available from wireless systems, can be used to solve complex and previously intractable problems. Many problems in wireless communication systems, such as decision making, resource optimization, and network management, can be cast in a form that is suitable to be solved by AI techniques. Hence, AI technologies have been applied to improve the performance of future wireless communication systems. We focus on the design of AI/ML empowered PHY, MAC, and network layers for 6G.
Deep learning (DL) for wireless resource allocation, CSI feedback, and interference mitigation: Resource management problems in systems and networking often manifest as difficult online decision making tasks where appropriate solutions depend on understanding the workload and environment. We apply recent DL technologies to wireless networks.
Deep reinforcement learning (DRL) for wireless and mobile networking: The integration of DRL into future wireless networks will revolutionize the conventional model-based network optimization to model-free approaches and meet various application demands. By interacting with the environment, DRL provides an autonomous decision-making mechanism for the network entities to solve non-convex, complex model-free problems, e.g., spectrum access, handover, scheduling, caching, data offloading, and resource allocation.

AI empowered 6G
RNN-based Solution for 5G Massive MIMO	Reconfigurable Deep Learning Framework for AI-aided 5G BS Systems
CNL's Machine Learning for Wireless Networks	CNL's Machine Learning Simulator (ongoing)

Wireless Connectivity - Radio access technologies for 5G/6G, V2X, and IoT

Integrated sensing and communication (ISAC) for B5G/6G, V2X, UAV networks Sensing-assisted predictive/fast beam management Machine learning/network intelligence for ISAC MIMO/Massive MIMO/intelligent reflecting surface (IRS)/Holographic MIMO surface for ISAC 5G/6G cellular connectivities NR Technologies for 5G Massive multiple-input multiple-output (MIMO) Interference cancellation, interference alignment, and interference mitigation Vehicle-to-everything (V2X) connectivities C-V2X (Cellular-V2X): LTE-based V2V, V2I/N, and V2P; 5G-V2X, NR V2X sidelink (SL) C-ITS (Cooperative Intelligent Transport Systems): Wireless access for vehicular environments (WAVE), IEEE 802.11p+IEEE 1609.x, ETSI C2C, etc. Network assisted autonomous driving, Network assisted Cooperative Adaptive Cruise Control (CACC) IoT connectivities: NB-IoT, LoRa, BT, Wi-Fi Massive connectivities and device discovery Power saving and low cost/complexity technologies Coexistence of Bluetooth and Wi-Fi

Integrated sensing and communication (ISAC) ISAC refers to the design paradigm and corresponding enabling technologies that combine sensing and communication systems to utilize resources efficiently and even to pursue mutual benefits. ISAC can acquire two main advantages over dedicated sensing and communication functionalities: 1) Integration gain to efficiently utilize congested resources for dual use of both communications and sensing, and even more interesting, 2) Coordination gain to balance dual-functional performance or/and perform mutual assistance. ISAC has been recently identified as an enabling technology for B5G/6G.
Applications of ISAC have been extended to numerous emerging areas, including vehicular networks, environmental monitoring, Internet of Things, as well as in-door services such as human activity recognition.
5G/6G cellular connectivities cover architectures and protocols for 5G/6G wiereless communications and networking. Research topics are learning-based radio resource management, NR technologies for 5G and beyond, multiple-input multiple-output (MIMO), device-to-device communications, etc.
Vehicle-to-everything (V2X) connectivities: C-V2X is a growing area of communications between vehicles and including roadside communication infrastructure. Advances in wireless communications are making possible sharing of information through real time communications between vehicles and infrastructure. This has led to applications to increase safety of vehicles and communication between passengers and the Internet.
Additionally, 3GPP Rel. 16 introduces 5G NR V2X communications including sidelink (SL) communications. NR V2X SL is to support enhanced V2X (eV2X) use cases related to connected and automated driving. Research topics are cellular-V2X and WAVE-based V2X (C-ITS) for autonomous driving and cooperative adaptive cruise control (CACC); and massive BDMA and radio resource management for vehicle communications.
IoT connectivities cover NB-IoT, LoRa, Wi-Fi, and Bluetooth. Research topics are response time and energy efficiency of IoT devices discovery; wireless access and communications technologies; conectivity and clustering; network platforms; coexistance of BT/Wi-Fi in the crowded 2.4GHz networks; and qalfication and improvement of audio chooping over bluetooth A2DP.

5G Radio Access Technologies		LTE/5G Simulator developed by CNL
Celluar-V2X and WAVE-V2X	SUMO-based Autonomous Driving Connectivity developed by CNL	BT DM App developed by CNL	Real Wi-Fi Traffic Generator App developed by CNL

Wireless Security - Security issues in Celluar, Connected Car, IoT, and Blockchain

Wireless and Vehicle securitiy Wireless security/vulnerability analysis in LTE/LTE-A and 5G/6G networks Protection for smart key and connected car security V2X security and IoT device authentication/security Blockchain and Cryptanalysis Blockchain consensus algorithm Blockchain Mining vulnerability Machine-learning based cryptanalysis

Wireless security covers securitiy issues in the wireless communications, e.g., LTE/LTE-A, 5G/6G, Bluetooth, Smart Home Remote Control, Wi-Fi, etc. LTE/5G is assumed to guarantee confidentiality and strong authentication. However, LTE/5G networks are vulnerable to wireless security. We study on the insecurity rationale behind celluar protocol exploits and rogue base stations.
Vehicle security covers security issues in Connected Car, Electric Vehicle Charging, V2X, Car Smart Key, etc. There is a potential risk to automotive security from cyber criminals. Security breaches can result in leaked personal data, threats to a vehicle's essential security and safety mechanisms and, in extreme cases, full remote control of the car. Moreover, passive keyless entry and start (PKES) systems unlocks or starts the car when the key is in the proximity of the car. However, the conventional schemes are vulnerable to relay attacks.
Blockchain and Cryptanalysis: Blockchain is a shared immutable ledger for recording the history of transactions. The blockchain isn't really as secure as we tend to think. For example, in the reward of the Bitcoin system, rogue miners can increase their rewards by using the block witholding attacks.
Recently, the cryptanalysis uses the machine-learning technologies to find the characteristics of block ciphers; or to classify encrypted traffic or to identify the cryptographic algorithm from ciphertexts.

Attacks scenarios of V2X with malicious and victim vehicles	Relay attack avoidance in smart key developed by CNL	Chrome password decryptor developed by CNL

#