LDV dataset Ensemble Learning Based Effective Signal Processing for High Precision Laser Doppler Velocimetry

This dataset contains Laser Doppler Velocimetry (LDV) signals collected under various experimental conditions for the purpose of high-precision flow velocity measurement. Each sample includes raw Doppler waveforms alongside extracted time-frequency and wavelet features. The dataset is designed to support the development and evaluation of signal preprocessing and classification methods, particularly in the presence of noise. Labels are provided to distinguish valid signals from degraded ones, enabling supervised learning approaches. The dataset was used to train and validate an ensemble learning-based signal preprocessing framework, which demonstrated improved accuracy compared to traditional methods.本数据集包含在多种实验条件下采集的激光多普勒测速（Laser Doppler Velocimetry, LDV）信号，用于高精度流速测量任务。每个样本均包含原始多普勒波形，以及提取得到的时频特征与小波特征。本数据集旨在为信号预处理与分类方法的研发与评估提供支撑，尤其适配存在噪声的应用场景。数据集附带分类标签，用于区分有效信号与劣化信号，可支撑监督学习方法的落地应用。该数据集曾被用于训练并验证基于集成学习的信号预处理框架，该框架相较于传统方法展现出更优的精度表现。