Broadband Diffraction-Encoded and Electron-Decoded Neural Networks for Single-Pixel Arrival Information Sensing
- 19 June 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Antennas and Propagation
- Vol. 73 (10) , 8201-8215
Abstract
With the rapid growth of the Internet of Things and wireless technologies, rapid, low-cost, intelligent arrival information sensing (AIS) devices have emerged as an urgent demand. Traditional array antenna-based AIS technologies usually encounter high costs and slow processing speeds due to complicated hardware architecture and post-processing algorithms. Programmable metasurfaces, as an alternative solution, often suffer from design complexity and time consumption for state switching. As a promising optical computing architecture, diffractive deep neural networks (D2NNs) present opportunities for designing rapid, simple, high-performance AIS devices. However, available D2NNs-based AIS sensing works employ the multi-pixel reception scheme, which is time-consuming and complicated for the microwave or terahertz band, owing to the limited accessibility of mature detectors that allow simultaneous sensing in multiple locations. To address these issues, we utilized broadband diffraction-encoded and electron-decoded neural networks for single-pixel arrival information sensing. It only requires a passive metasurface and a single-pixel intensity-only detector in terms of hardware architecture and fully connected neural networks at the software level. Leveraging this approach, we realized far-field angle-of-arrival and near-field three-dimensional spatial position estimation tasks. Furthermore, we also provided an adaptive learning strategy to enhance the robustness and enable intelligent machine vision meta-devices. The proposed method allows for a simple and low-cost AIS scheme, potentially facilitating the advancement of AIS meta-devices.Keywords
Funding Information
- National Natural Science Foundation of China (61671178, 62271170)
- National Key Laboratory of Laser Spatial Information Foundation (LSI2025ZZKY03)
- Fundamental Research Funds for the Central Universities (HIT.DZJJ.2025010)
This publication has 59 references indexed in Scilit:
- Non‐Interleaved Shared‐Aperture Full‐Stokes Metalens via Prior‐Knowledge‐Driven Inverse DesignAdvanced Materials, 2024
- Electromagnetic Manipulation Evolution from Stacked Meta‐Atoms to Spatially Cascaded MetasurfacesAnnalen der Physik, 2024
- Matrix Diffractive Deep Neural Networks Merging Polarization into Meta‐Devices (Laser Photonics Rev. 18(2)/2024)Laser & Photonics Reviews, 2024
- 3D Reconfigurable Vectorial Holography via a Dual‐Layer Hybrid Metasurface DeviceLaser & Photonics Reviews, 2023
- Diffraction Neural Network for Multi‐Source Information of Arrival SensingLaser & Photonics Reviews, 2023
- Artificial Neural Network for Direction‐of‐Arrival Estimation and Secure Wireless Communications Via Space‐Time‐Coding Digital MetasurfacesAdvanced Optical Materials, 2022
- Metasurface Micro/Nano-Optical Sensors: Principles and ApplicationsACS Nano, 2022
- All‐Dielectric Trifunctional Metasurface Capable of Independent Amplitude and Phase ModulationLaser & Photonics Reviews, 2022
- A framework for spatial map generation using acoustic echoes for robotic platformsRobotics and Autonomous Systems, 2022
- A high-efficiency acquisition method of LED-multispectral images based on frequency-division modulation and RGB cameraOptics Communications, 2021