Multivariate Time Series Classification Using Spiking Neural Networks
This work addresses the need for low-power time series classification in embedded IoT and CPS devices, representing an incremental improvement by adapting SNNs to a new domain.
The paper tackled the problem of processing multivariate time series in energy-limited scenarios by developing an encoding scheme and training algorithm for spiking neural networks, achieving performance comparable to deep neural networks on UCR repository datasets.
There is an increasing demand to process streams of temporal data in energy-limited scenarios such as embedded devices, driven by the advancement and expansion of Internet of Things (IoT) and Cyber-Physical Systems (CPS). Spiking neural network has drawn attention as it enables low power consumption by encoding and processing information as sparse spike events, which can be exploited for event-driven computation. Recent works also show SNNs' capability to process spatial temporal information. Such advantages can be exploited by power-limited devices to process real-time sensor data. However, most existing SNN training algorithms focus on vision tasks and temporal credit assignment is not addressed. Furthermore, widely adopted rate encoding ignores temporal information, hence it's not suitable for representing time series. In this work, we present an encoding scheme to convert time series into sparse spatial temporal spike patterns. A training algorithm to classify spatial temporal patterns is also proposed. Proposed approach is evaluated on multiple time series datasets in the UCR repository and achieved performance comparable to deep neural networks.