TY - GEN
T1 - Artificial Intelligence Enhanced Signal Processing for Large-scale Antenna Arrays via Memristor Crossbar Architectures
AU - Wang, Can
AU - Zhang, Yanming
AU - Liu, Wei
AU - Gao, Steven
N1 - Publisher Copyright:
© 2025 IEEE.
PY - 2025/11
Y1 - 2025/11
N2 - This paper presents a brain-like receiver architecture that utilizes memristor crossbar arrays for efficient direction of arrival (DoA) estimation. As a neuromorphic device, the memristor crossbar array leverages its capability of in-memory computing to replace analog-to-digital converters and digital signal processors in traditional receivers. Meanwhile, based on its bionic characteristics and its compatibility with neural networks, the brain-like receiver performs fast, efficient and accurate DoA estimation through neural network weight mapping. Numerical examples show that the proposed memristor-based neuromorphic architecture offers scalable, low-latency, and energy-efficient processing, making it well-suited for real-time DoA estimation in large-scale antenna arrays.
AB - This paper presents a brain-like receiver architecture that utilizes memristor crossbar arrays for efficient direction of arrival (DoA) estimation. As a neuromorphic device, the memristor crossbar array leverages its capability of in-memory computing to replace analog-to-digital converters and digital signal processors in traditional receivers. Meanwhile, based on its bionic characteristics and its compatibility with neural networks, the brain-like receiver performs fast, efficient and accurate DoA estimation through neural network weight mapping. Numerical examples show that the proposed memristor-based neuromorphic architecture offers scalable, low-latency, and energy-efficient processing, making it well-suited for real-time DoA estimation in large-scale antenna arrays.
KW - artificial intelligence
KW - DoA estimation
KW - memristor crossbar array
KW - neuromorphic computing
KW - Signal processing
UR - https://www.scopus.com/pages/publications/105031731688
U2 - 10.1109/SiPS66314.2025.11261269
DO - 10.1109/SiPS66314.2025.11261269
M3 - Conference article published in proceeding or book
AN - SCOPUS:105031731688
T3 - 2025 IEEE Workshop on Signal Processing Systems, SiPS 2025
SP - 1
EP - 5
BT - 2025 IEEE Workshop on Signal Processing Systems, SiPS 2025
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2025 IEEE Workshop on Signal Processing Systems, SiPS 2025
Y2 - 1 November 2025 through 4 November 2025
ER -