基于条件生成对抗网络的动物行为传感器分类算法
Improved Sensor-Based Animal Behavior Classification Performance through Conditional Generative Adversarial Network
摘要:
许多活动分类将数据分割成固定的窗口大小,用于特征提取和分类。然而,动物行为具有与预定窗口大小不匹配的各种持续时间。密集标记和密集预测方法通过预测每个点的标签来解决这个限制。因此,通过追踪活动的起点和终点,我们可以知道所有活动发生的时间、地点和持续时间。尽管如此,密集的预测可能是嘈杂的错位问题。我们修改了U-Net和条件生成对抗网络(cGAN),使用自定义的损失函数作为训练策略,以减少碎片化和其他失调。在cGAN中,训练器和生成器像对抗性竞争一样相互训练。生成器生成密集的预测。在我们的例子中,该工具作为一个高级一致性检查,推动生成器预测具有合理持续时间的活动。使用cGAN训练的模型在牛、猪和UCI HAPT数据集中表现出更好或相当的性能。与之前的密集预测工作相比,cGAN训练的修改后的U-Net对于UCI HAPT数据集从92.17%提高到94.66%,对于猪数据从90.85%提高到93.18%。
英文摘要:
Many activity classifications segments data into fixed window size for feature extraction and classification. However, animal behaviors have various durations that do not match the predetermined window size. The dense labeling and dense prediction methods address this limitation by predicting labels for every point. Thus, by tracing the starting and ending points, we could know the time location and duration of all occurring activities. Still, the dense prediction could be noisy with misalignments problems. We modified the U-Net and Conditional Generative Adversarial Network (cGAN) with customized loss functions as a training strategy to reduce fragmentation and other misalignments. In cGAN, the discriminator and generator trained against each other like an adversarial competition. The generator produces dense predictions. The discriminator works as a high-level consistency check, in our case, pushing the generator to predict activities with reasonable duration. The model trained with cGAN shows better or comparable performance in the cow, pig, and UCI HAPT dataset. The cGAN-trained modified U-Net improved from 92.17% to 94.66% for the UCI HAPT dataset and from 90.85% to 93.18% for pig data compared to previous dense prediction work.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。