Many real-world applications of the Internet of Things (IoT) employ machine learning (ML) algorithms to analyze time series information collected by interconnected sensors. However, distribution shift, a fundamental challenge in data-driven ML, arises when a model is deployed on a data distribution different from the training data and can substantially degrade model performance. Additionally, increasingly sophisticated deep neural networks (DNNs) are required to capture intricate spatial and temporal dependencies in multi-sensor time series data, often exceeding the capabilities of today's edge devices. In this paper, we propose SMORE, a novel resource-efficient domain adaptation (DA) algorithm for multi-sensor time series classification, leveraging the efficient and parallel operations of hyperdimensional computing. SMORE dynamically customizes test-time models with explicit consideration of the domain context of each sample to mitigate the negative impacts of domain shifts. Our evaluation on a variety of multi-sensor time series classification tasks shows that SMORE achieves on average 1.98% higher accuracy than state-of-the-art (SOTA) DNN-based DA algorithms with 18.81x faster training and 4.63x faster inference.

翻译：许多物联网（IoT）实际应用采用机器学习（ML）算法分析互联传感器收集的时间序列信息。然而，数据分布偏移——数据驱动型ML的基本挑战——会在模型部署到与训练数据不同的数据分布时出现，并显著降低模型性能。此外，捕捉多传感器时间序列数据中复杂的时空依赖关系需要日益复杂的深度神经网络（DNN），这往往超出当前边缘设备的能力。本文提出SMORE，一种新颖的资源高效的域自适应（DA）算法，用于多传感器时间序列分类，其利用高维计算的高效并行操作。SMORE通过显式考虑每个样本的域上下文动态定制测试时模型，以减轻域偏移的负面影响。我们在多种多传感器时间序列分类任务上的评估表明，SMORE相比最先进的基于DNN的DA算法平均准确率提升1.98%，同时训练速度提升18.81倍，推理速度提升4.63倍。