PRISM: Lightweight Multivariate Time-Series Classification through Symmetric Multi-Resolution Convolutional Layers
By: Federico Zucchi, Thomas Lampert
Potential Business Impact:
Makes computers understand body signals better, faster.
Multivariate time-series classification is pivotal in domains ranging from wearable sensing to biomedical monitoring. Despite recent advances, Transformer- and CNN-based models often remain computationally heavy, offer limited frequency diversity, and require extensive parameter budgets. We propose PRISM (Per-channel Resolution-Informed Symmetric Module), a convolutional-based feature extractor that applies symmetric finite-impulse-response (FIR) filters at multiple temporal scales, independently per channel. This multi-resolution, per-channel design yields highly frequency-selective embeddings without any inter-channel convolutions, greatly reducing model size and complexity. Across human-activity, sleep-stage and biomedical benchmarks, PRISM, paired with lightweight classification heads, matches or outperforms leading CNN and Transformer baselines, while using roughly an order of magnitude fewer parameters and FLOPs. By uniting classical signal processing insights with modern deep learning, PRISM offers an accurate, resource-efficient solution for multivariate time-series classification.
Similar Papers
PRISM: Periodic Representation with multIscale and Similarity graph Modelling for enhanced crystal structure property prediction
Machine Learning (CS)
Helps predict material traits from crystal patterns.
PRISM: Diversifying Dataset Distillation by Decoupling Architectural Priors
Machine Learning (CS)
Creates better fake data for training computers.
PRISM: Probabilistic Runtime Insights and Scalable Performance Modeling for Large-Scale Distributed Training
Distributed, Parallel, and Cluster Computing
Predicts training time for giant computer jobs.