Ground-penetrating radar (GPR) is an essential tool for nondestructive subsurface exploration. However, electromagnetic wave propagation in underground environments is severely attenuated, leading to the loss of important geological information and limiting the resolution of underground imaging. To address this challenge, we propose an attention-enhanced U-Net (AEU-Net) model for GPR signal attenuation compensation. This model builds upon the 1-D U-Net architecture and integrates a feature fusion attention block (FFAB) to effectively capture both local and global features, thereby enhancing its capability to process complex datasets. In addition, to overcome dataset acquisition challenges, we use GprMax software to simulate realistic geological structures based on the relationship between conductivity and electromagnetic wave attenuation, thereby generating the training dataset. Experimental results with synthetic and field data demonstrate that the proposed method significantly improves noise robustness, restores fine subsurface details, and effectively compensates for GPR signal attenuation, thereby showing its potential for high-resolution underground imaging.

Deep neural networks (DNNs) are revolutionizing machine learning, with unprecedented accuracy on many AI tasks. Energy-efficient neural acceleration is crucial in broadening DNN applications in cloud and mobile end devices. However, power-hungry clock networks limit the energy-efficiency of DNN accelerators. In this work, we propose a novel DNN hardware accelerator, called the asynchronous neural network processor (AsNNP). At the heart of AsNNP is a scalable hierarchy matrix multiply unit, with bit-serial processing elements working in parallel. It replaces the global clock networks with asynchronous handshake protocols to realize the synchronization and communication between each part, minimizing the dynamic power. Meanwhile, a fine-grain asynchronous pipeline based on weak-conditioned half-buffer (WCHB) is introduced to pipe successive computations in a data-driven manner, i.e., once data arrives computation begins, maximizing the throughput. These techniques enable AsNNP to work in a fully data-driven asynchronous communication fashion with optimized energy-efficiency. The proposed accelerator is implemented with quasi-delay-insensitive (QDI) clockless logic family and evaluated in a 65 nm process. Compared with the synchronous baseline, simulation results show that AsNNP offers 2.2× higher equivalent frequency and 1.59× lower power. Compared with state-of-the-art DNN accelerators, AsNNP shows 1.17×-4.97× energy-efficiency improvement.