Cadence：一种实用的无标记IoT传感器流时间序列划分算法
Cadence: A Practical Time-series Partitioning Algorithm for Unlabeled IoT Sensor Streams
摘要：
时间序列分区是大多数机器学习驱动的基于传感器的物联网应用程序中的重要步骤。本文介绍了一种采样效率高、鲁棒性强的时间序列分割模型和算法。我们表明，通过学习一个表示，特别是基于最大平均差异（MMD）的分割目标，我们的算法可以鲁棒地检测跨不同应用程序的时间序列事件。我们的损失函数允许我们推断连续的样本序列是否来自相同的分布（零假设），并确定拒绝零假设的对之间的变点（即，来自不同的分布）。我们证明了它在现实世界的物联网部署环境感知为基础的活动识别的适用性。此外，虽然文献中存在许多关于变点检测的工作，但我们的模型要简单得多，平均可以在9-93秒内完成完全训练，不同应用程序的数据超参数变化很小。我们在四个流行的变化点检测（CPD）数据集上对Cadence进行了经验评估，其中Cadence匹配或优于现有的CPD技术。
英文摘要：
Timeseries partitioning is an essential step in most machine-learning driven, sensor-based IoT applications. This paper introduces a sample-efficient, robust, time-series segmentation model and algorithm. We show that by learning a representation specifically with the segmentation objective based on maximum mean discrepancy (MMD), our algorithm can robustly detect time-series events across different applications. Our loss function allows us to infer whether consecutive sequences of samples are drawn from the same distribution (null hypothesis) and determines the change-point between pairs that reject the null hypothesis (i.e., come from different distributions). We demonstrate its applicability in a real-world IoT deployment for ambient-sensing based activity recognition. Moreover, while many works on change-point detection exist in the literature, our model is significantly simpler and can be fully trained in 9-93 seconds on average with little variation in hyperparameters for data across different applications. We empirically evaluate Cadence on four popular change point detection (CPD) datasets where Cadence matches or outperforms existing CPD techniques.
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。
