My Account Log in

1 option

An Integrated and Miniaturized Multi-Channel Distributed Cooperative Spectrum Sensing Technology Based on Zynq Nanjing University of Science and Technology, School of Elec

SAE Technical Papers (1906-current) Available online

View online
Format:
Book
Conference/Event
Author/Creator:
Chen, Wangjie, author.
Contributor:
Fan, Zhenhong
Shi, Songhua
Yang, Jian
Zhou, Mingyu
Zhu, Weiqiang
Conference Name:
SAE 2024 Intelligent and Connected Vehicles Symposium (2024-09-22 : Shanghai, China)
Language:
English
Physical Description:
1 online resource cm
Place of Publication:
Warrendale, PA SAE International 2024
Summary:
In response to the escalating demand for high-performance, miniaturized, and integrated radio frequency (RF) systems, this research explores the application of the Zynq UltraScale+ RFSoC XCZU47DR chip in the realm of integrated RF transceiver technology. An 8-channel, 4.8Gsps multi-channel distributed collaborative spectrum sensing architecture has been designed, incorporating lightweight IQ neural network, which comprises a convolutional layer, three Bottleneck Units (BNU), a Global Average Pooling (GAP) layer, and a Fully Connected (FC) layer. Notably, each BNU encapsulates one or two inverted bottleneck residual blocks that integrate the concepts of inverted residual blocks and linear bottlenecks. The parameter counts and computational complexity associated with the convolution operation are significantly reduced to merely 11.89% of those required by traditional networks. The performance metrics of the hardware circuit were validated through a constructed test system. Within a 2GHz instantaneous bandwidth, the amplitude consistency between Analog-to-Digital Converter (ADC) channels is less than 1dB, and the effective number of bits exceeds 7.3 bits. Simulation results demonstrate that, at a Signal-to-Noise Ratio (SNR) of -10dB with a false alarm probability of 0.5%, the detection probability of the collaborative spectrum sensing algorithm reaches 91.13%, marking a 6dB enhancement over conventional energy detection methods. This achievement underscores the technology's substantial advantage in boosting spectrum sensing capabilities, providing novel perspectives for the design of RF systems and the evolution of wireless communication technologies
Notes:
Vendor supplied data
Publisher Number:
2024-01-7041
Access Restriction:
Restricted for use by site license

The Penn Libraries is committed to describing library materials using current, accurate, and responsible language. If you discover outdated or inaccurate language, please fill out this feedback form to report it and suggest alternative language.

Find

Home Release notes

My Account

Shelf Request an item Bookmarks Fines and fees Settings

Guides

Using the Find catalog Using Articles+ Using your account