This work follows the multi-label classification based paradigm for non-intrusive load monitoring (NILM). Power consumption signals used for NILM are inherently time varying. However prior multi-label classification techniques could not model this dynamical behaviour. They used off-the-shelf algorithms for classifying static signals on NILM problems. This is the first work that shows how to account for the temporal variability of input signals in a multi-label classification framework. Results on benchmark datasets like REDD and Pecan Street show considerable improvement over several state-of-the-art shallow and deep techniques.

中文翻译：

---

用于非侵入式设备负载监控的多标签 LSTM 自动编码器

这项工作遵循基于多标签分类的非侵入式负载监控 (NILM) 范式。用于 NILM 的功耗信号本质上是随时间变化的。然而，先前的多标签分类技术无法对这种动态行为进行建模。他们使用现成的算法对 NILM 问题上的静态信号进行分类。这是第一项展示如何在多标签分类框架中解释输入信号的时间可变性的工作。REDD 和 Pecan Street 等基准数据集的结果表明，与几种最先进的浅层和深层技术相比，有了相当大的改进。