发表机构
University of Oxford; National Centre for Radio Astrophysics (NCRA)（牛津大学; 国家射电天体物理学中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出LeoNet卷积神经网络，利用十个可学习滤波器提取多普勒频移信号特征，在500秒模拟观测中使漏报率平均降低55.5%，处理速度较PRESTO提升约499倍，可用于实时双星脉冲星搜索。
AI 中文摘要
双星脉冲星为检验引力理论提供了宝贵的实验室，但轨道多普勒频移使其探测变得复杂。傅里叶域加速度和急动度搜索通过匹配滤波应对这一挑战，但计算成本高昂。我们提出了LeoNet，一种卷积神经网络，使用十个可学习滤波器来提取受多普勒频移影响的信号特征。由此产生的十通道特征图提供了一种紧凑、低维的替代方案，替代显式采样的加速度-急动度响应网格，并由卷积分类器分析以识别候选信号。对于持续500秒的模拟观测，与所评估的PRESTO加速度搜索配置相比，LeoNet在五个采样间隔上的平均相对漏报率降低了55.5%。经TensorRT优化的LeoNet在NVIDIA H100 PCIe GPU上以FP32格式处理每次500秒观测耗时3.44-4.37毫秒，涵盖八个采样间隔，包括预处理、推理和后处理。在128微秒的采样间隔下，其平均处理时间为3.54毫秒，而PRESTO FDAS在AMD EPYC 9825 CPU上、搜索频率限制为96-1000赫兹时的处理时间为1.767秒，对应实测处理时间约499倍的加速。这些结果表明，LeoNet有潜力提高探测性能，而其毫秒级的处理时间支持其作为实时双星脉冲星搜索流水线中候选识别阶段的应用。
英文摘要
Binary pulsars provide valuable laboratories for testing theories of gravity, but orbital Doppler shifts complicate their detection. Fourier-domain acceleration and jerk searches address this challenge via matched filtering, but at substantial computational cost. We present LeoNet, a convolutional neural network that uses ten learnable filters to extract features of signals affected by Doppler shifts. The resulting ten-channel feature map provides a compact, lower-dimensional alternative to an explicitly sampled acceleration-jerk response grid and is analysed by a convolutional classifier to identify candidate signals. For simulated observations lasting 500 s, LeoNet achieves a mean relative reduction in false negative rate of 55.5% across five sampling intervals compared with the evaluated PRESTO acceleration-search configuration. TensorRT-optimised LeoNet processes each 500 s observation in 3.44-4.37 ms in FP32 on an NVIDIA H100 PCIe GPU across eight sampling intervals, including preprocessing, inference, and postprocessing. At a sampling interval of 128 microseconds, its mean processing time is 3.54 ms, compared with 1.767 s for PRESTO FDAS on an AMD EPYC 9825 CPU with search-frequency limits of 96-1000 Hz, corresponding to an approximately 499-fold speedup in the measured processing time. These results suggest that LeoNet has the potential to improve detection performance, while its millisecond-scale processing time supports its use as a candidate-identification stage in real-time binary pulsar search pipelines.
