SMORE: Similarity-based Hyperdimensional Domain Adaptation for Multi-Sensor Time Series Classification (2402.13233v2)
Abstract: Many real-world applications of the Internet of Things (IoT) employ 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.
- Huihui Qiao et al. A time-distributed spatiotemporal feature learning method for machine health monitoring with multi-sensor time series. Sensors, 2018.
- Ishaan Gulrajani et al. In search of lost domain generalization. In International Conference on Learning Representations, 2021.
- Samuel Wilson et al. Hyperdimensional feature fusion for out-of-distribution detection. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2023.
- Dequan Wang et al. Tent: Fully test-time adaptation by entropy minimization. In International Conference on Learning Representations, 2020.
- Han Zhao et al. Multiple source domain adaptation with adversarial learning. In 6th International Conference on Learning Representations, ICLR 2018, 2018.
- Xin Qin et al. Generalizable low-resource activity recognition with diverse and discriminative representation learning. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, page 1943–1953, 2023.
- Shiori Sagawa et al. Distributionally robust neural networks. In International Conference on Learning Representations, 2019.
- Junyao Wang et al. Domino: Domain-invariant hyperdimensional classification for multi-sensor time series data. In 2023 IEEE/ACM International Conference on Computer Aided Design (ICCAD), pages 1–9. IEEE, 2023.
- Yao Qin et al. A dual-stage attention-based recurrent neural network for time series prediction. In Proceedings of the 26th International Joint Conference on Artificial Intelligence, 2017.
- Sepp Hochreiter et al. Long short-term memory. Neural computation, 1997.
- Junyao Wang et al. Disthd: A learner-aware dynamic encoding method for hyperdimensional classification. arXiv preprint arXiv:2304.05503, 2023.
- Junyao Wang et al. Hyperdetect: A real-time hyperdimensional solution for intrusion detection in iot networks. IEEE Internet of Things Journal, 2023.
- Mi Zhang et al. Usc-had: A daily activity dataset for ubiquitous activity recognition using wearable sensors. In Proceedings of the 2012 ACM conference on ubiquitous computing, 2012.
- Qi Dou et al. Domain generalization via model-agnostic learning of semantic features. Advances in Neural Information Processing Systems, 2019.
- Yaroslav Ganin et al. Domain-adversarial training of neural networks. The journal of machine learning research, 2016.
- Abbas Rahimi et al. Hyperdimensional biosignal processing: A case study for emg-based hand gesture recognition. In ICRC. IEEE, 2016.
- Ali Moin et al. A wearable biosensing system with in-sensor adaptive machine learning for hand gesture recognition. Nature Electronics, 2021.
- Junyao Wang et al. Robust and scalable hyperdimensional computing with brain-like neural adaptations. arXiv preprint arXiv:2311.07705, 2023.
- Billur Barshan et al. Recognizing daily and sports activities in two open source machine learning environments using body-worn sensor units. The Computer Journal, 2014.
- Attila Reiss et al. Introducing a new benchmarked dataset for activity monitoring. In 16th international symposium on wearable computers. IEEE, 2012.
- Alejandro Hernández-Cano et al. Onlinehd: Robust, efficient, and single-pass online learning using hyperdimensional system. In DATE. IEEE, 2021.
- Junyao Wang (9 papers)
- Mohammad Abdullah Al Faruque (51 papers)