Navas-Olive, Rubio, et al. (2023). Figure 6 - data

Figure 6. Extending sharp-wave ripple detection to non-human primates. c) Significant differences between SWR recorded in mice and monkey. d) The best model of each architecture trained in mouse data, and the best filter configuration for mouse data, were applied to detect SWRs on the macaque data. We evaluated all models by computing F1-score against the ground truth (GT). Note relatively good results from non-retrained ML models and filter. e) Results of model re-training using macaque data. Data were split into a training and validation dataset (50% and 20% respectively), used to train the ML models; and a test set (30%), used to compute the F1 (left panel). Filter was not re-trained. f) F1-scores for the maximal performance of each model before and after re-training.

图6。将尖波涟漪（sharp-wave ripple, SWR）检测方法拓展至非人类灵长类动物。c) 小鼠与猕猴所记录的尖波涟漪之间存在显著差异。d) 将基于小鼠数据训练得到的各架构最优模型，以及适配小鼠数据的最优滤波器配置，应用于猕猴数据以检测尖波涟漪。我们通过与真实标注（ground truth, GT）对比计算F1分数，对所有模型进行了性能评估。请注意，未重新训练的机器学习（Machine Learning, ML）模型与滤波器即可获得较为优异的检测结果。e) 基于猕猴数据进行模型重新训练的实验结果。数据被划分为训练集与验证集（占比分别为50%与20%，用于训练机器学习模型），以及测试集（占比30%，用于计算F1分数，对应左侧面板）。滤波器未进行重新训练。f) 各模型在重新训练前后的最优F1分数表现。