Jeon Eun Som, Lohit Suhas, Anirudh Rushil, Turaga Pavan
Geometric Media Lab, Arizona State University, Tempe, AZ, USA.
Mitsubishi Electric Research Laboratories, Cambridge, MA, USA.
Proc IEEE Int Conf Acoust Speech Signal Process. 2023 Jun;2023. doi: 10.1109/icassp49357.2023.10096888. Epub 2023 May 5.
Time-series are commonly susceptible to various types of corruption due to sensor-level changes and defects which can result in missing samples, sensor and quantization noise, unknown calibration, unknown phase shifts etc. These corruptions cannot be easily corrected as the noise model may be unknown at the time of deployment. This also results in the inability to employ pre-trained classifiers, trained on (clean) source data. In this paper, we present a general framework and models for time-series that can make use of (unlabeled) test samples to estimate the noise model-entirely at test time. To this end, we use a coupled decoder model and an additional neural network which acts as a learned noise model simulator. We show that the framework is able to "clean" the data so as to match the source training data statistics and the cleaned data can be directly used with a pre-trained classifier for robust predictions. We perform empirical studies on diverse application domains with different types of sensors, clearly demonstrating the effectiveness and generality of this method.
由于传感器层面的变化和缺陷，时间序列通常容易受到各种类型的损坏，这可能导致样本缺失、传感器和量化噪声、未知校准、未知相位偏移等。这些损坏不容易纠正，因为在部署时噪声模型可能未知。这也导致无法使用在（干净的）源数据上训练的预训练分类器。在本文中，我们提出了一个用于时间序列的通用框架和模型，该框架和模型可以在测试时完全利用（未标记的）测试样本估计噪声模型。为此，我们使用一个耦合解码器模型和一个额外的神经网络，该神经网络充当学习到的噪声模型模拟器。我们表明，该框架能够“清理”数据，使其与源训练数据统计信息相匹配，并且清理后的数据可以直接与预训练分类器一起用于稳健预测。我们对使用不同类型传感器的各种应用领域进行了实证研究，清楚地证明了该方法的有效性和通用性。
