Deep Quantum-Transformer Networks for Multimodal Beam Prediction in ISAC Systems

• Published in: IEEE internet of things journal Vol. 11; no. 18; pp. 29387 - 29401
• Main Authors: Tariq, Shehbaz, Arfeto, Brian Estadimas, Khalid, Uman, Kim, Sunghwan, Duong, Trung Q., Shin, Hyundong
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 15.09.2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: 6G mobile communication; Antenna arrays; Applications programs; Beam prediction; Deep learning; deepsense sixth generation (6G) data set; Global Positioning System; Headlamps; integrated sensing and communication (ISAC); Internet of Things; Laser radar; Millimeter wave communication; Millimeter waves; millimeter-wave (mmWave); Mobile computing; Position sensing; Quantum computing; quantum-transformer network (QTN); Radio equipment; Sensors; Situational awareness; Transformers; Vehicle-to-infrastructure; vehicle-to-infrastructure (V2I)
• ISSN: 2327-4662; 2327-4662
• DOI: 10.1109/JIOT.2024.3420455

In this article, we propose hybrid deep quantum-transformer networks (QTNs) to predict the optimal beam in integrated sensing and communication (ISAC) systems employing millimeter-wave (mmWave) band. In mobile applications, vehicle-to-infrastructure (V2I) communications at high frequency require large antenna arrays and narrow beams, which is associated with high-beam training overhead. In such a scenario, selecting an optimal beam to maximize the signal power at the receiver can be learned from the sensory data collected at the base station and guided by the position-based data provided by the user equipment. Such multimodal sensory data can be utilized by deep learning frameworks to create situational awareness for intelligently predicting optimal beams. We evaluate the proposed learning models in real-world V2I scenarios provided by the multimodal deepsense sixth generation data set and compare them with the existing works. The experimental results show a distance-based accuracy (DBA) score of 0.9124 for multimodal and 0.8832 for position-based data, respectively. Moreover, the hybrid QTN achieve the best DBA scores and the highest accuracy compared to other models on zero-shot testing. These QTN models exhibit low complexity and high performance, demonstrating their potential to address the challenges of beam management in mmWave ISAC systems.