Exploring Spiking Neural Networks for Binary Classification in Multivariate Time Series at the Edge

2025-10-23

AI Summary

This work addresses binary classification of multivariate time series on resource-constrained edge devices, specifically under stringent low-false-alarm-rate requirements for incremental prediction. Method: We propose a lightweight spiking neural network (SNN) framework optimized via the Evolutionary Optimization of Neural Spiking (EONS) algorithm, jointly evolving both architecture and parameters to yield an ultra-sparse, stateful SNN with only 49 neurons. Input is encoded via spike-based representation, and classification employs a single-neuron spike-count decision mechanism, enhanced by simple voting-based ensemble for robustness. Contribution/Results: To our knowledge, this is the first efficient deployment of an SNN on the microCaspian neuromorphic platform. On gamma-ray spectroscopy data, it achieves 67.1% true positive rate (TPR) at a false alarm rate of 1/hr—substantially outperforming PCA- and deep learning–based baselines. For EEG-based epileptic seizure detection, it attains 95% TPR while reducing parameter count by over 90%.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Learning on the Edge & Model Compression
• Search and Optimization: Evolutionary Computation

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

We present a general framework for training spiking neural networks (SNNs) to perform binary classification on multivariate time series, with a focus on step-wise prediction and high precision at low false alarm rates. The approach uses the Evolutionary Optimization of Neuromorphic Systems (EONS) algorithm to evolve sparse, stateful SNNs by jointly optimizing their architectures and parameters. Inputs are encoded into spike trains, and predictions are made by thresholding a single output neuron's spike counts. We also incorporate simple voting ensemble methods to improve performance and robustness. To evaluate the framework, we apply it with application-specific optimizations to the task of detecting low signal-to-noise ratio radioactive sources in gamma-ray spectral data. The resulting SNNs, with as few as 49 neurons and 66 synapses, achieve a 51.8% true positive rate (TPR) at a false alarm rate of 1/hr, outperforming PCA (42.7%) and deep learning (49.8%) baselines. A three-model any-vote ensemble increases TPR to 67.1% at the same false alarm rate. Hardware deployment on the microCaspian neuromorphic platform demonstrates 2mW power consumption and 20.2ms inference latency. We also demonstrate generalizability by applying the same framework, without domain-specific modification, to seizure detection in EEG recordings. An ensemble achieves 95% TPR with a 16% false positive rate, comparable to recent deep learning approaches with significant reduction in parameter count.

Problem

• Training spiking neural networks for binary classification on time series
• Optimizing SNN architectures and parameters for low false alarm rates
• Deploying energy-efficient SNNs for edge-based multivariate signal detection

Innovation

• EONS algorithm evolves sparse spiking neural networks
• Input encoding into spike trains for binary classification
• Voting ensemble methods enhance performance and robustness