2026· IEEE Transactions on Reliability· Vol 75, pp. 2486-2498· 0 citations· 49 references
Computer Science
Abstract
Spiking neural network (SNN) has drawn substantial research focus due to its high biological interpretability, low energy consumption and effectiveness in time-dependent data processing. However, existing methods fail to fully integrate the biological interpretability of SNN with the physical interpretability of time-frequency transform methods in machinery fault diagnosis. To this end, we propose a spiking time-frequency patching (STFP) spiking neural network model, in which a STFP module is designed for time-frequency feature extraction inside the network, and a spiking temporal–spatial attention module is designed to focus on important features of temporal–spatial dimensions. In addition, the spiking residual network used in the model is also improved in neurons. Extensive experimental results on two datasets of rotating machinery parts demonstrate that, the proposed model achieves superior diagnostic performance benefiting from the designed modules, furnishing an end-to-end fault diagnosis method excelling in accuracy, stability, and interpretability.
This work proposes Burst Spiking Neural Networks (BuSNNs), built upon Burst-enhanced Spiking Neurons and a Dynamic Weight Constraint (DWC) mechanism, which mitigates perturbation-induced transitions in activation states and thereby enhances robustness.
Jiahong Zhang, Sijun Shen, Man Yao et al.· 0 citations
This work proposes a noisy group neuron (NGN) model, which incorporates population-level synchronous resetting and neural stochasticity as fundamental computational mechanisms, and develops the NGN method as a framework that combines the NGN model with backpropagation learning based on mean-field dynamics.
Yajie Zhai, Yanmei Kang, Meng Li et al.· 0 citations
A Spiking Neural Network (SNN) is a kind of brain-inspired and event-driven network, which is becoming a promising energy-efficient alternative to Artificial Neural Networks (ANNs). In recent years, SNN methods have been successfully applied in the fields of electromagnetic signal processing and image signal processing, particularly in application scenarios that require low energy consumption. However, the performance of SNNs by direct training is far from satisfactory. In this paper, we study a novel learning method named SAD-SNN (Spatial-Activation Distillation for Spiking Neural Networks), which utilizes the ANN model to guide the SNN model learning. Unlike prior works that rely on element-wise feature alignment approaches, SAD-SNN aligns spatial-activation maps at different resolutions of the teacher and student networks. Specifically, we introduce a direct alignment approach, which defines a spatial-activation loss and normalizes the representation vectors of ANN and SNN, to alleviate the unexpected precision loss. This enables the knowledge of teacher ANNs to be effectively transferred to train student SNNs. On three image classification datasets, our proposed SAD-SNN outperforms other SNN training methods no matter whether homogeneous or heterogeneous teacher ANNs are used. Furthermore, we apply SAD-SNN to the electromagnetic signal detection task, demonstrating strong generalization ability and superior performance. In conclusion, the experimental results on various tasks and SNN architectures demonstrate that our method is a general and effective solution that significantly improves the learning of student SNNs with only two time steps.
Chongxiao Qu, Qian Zhang, Chenxiao Dou et al.· Italian National Conference...· 0 citations
Spiking neural networks (SNNs) have garnered significant attention in reinforcement learning tasks for their low power consumption. However, traditional spiking reinforcement learning (SRL) methods, which rely on local-connected encoding and fixed-threshold learning, struggle to capture the inter-dimensional correlations of input information within short timesteps, limiting the network’s expressive capacity at low timesteps. While increasing timesteps can significantly enhance performance, excessive timesteps result in substantial delays. To address this contradiction and enhance the expressive and decision-making capabilities of SNNs within short timesteps, we propose Mask-Adaptive Global Connection (MAGC), a novel encoding method that efficiently captures long-range dependencies via sparse, adaptively masked connections—enabling global feature interaction in a single timestep. Additionally, dynamic-threshold spiking neurons are introduced to effectively capture and distinguish subtle changes in input signals at each timestep, thereby enhancing the spatial-temporal state representation during spike information transmission. Extensive experimental results demonstrate that the proposed method achieves performance comparable to state-of-the-art algorithms using only a single timestep, while significantly reducing inference latency and energy consumption. When extended to multiple timesteps, our approach consistently outperforms existing methods, showing substantial improvements across eight continuous control tasks from OpenAI Gym.
Rong Xiao, Zhiyuan Hu, Ping He et al.· IEEE Transactions on Image P...· 0 citations
Spiking neural networks (SNNs) hold great potential to realize brain-inspired, energy-efficient computational systems. However, current SNNs still fall short in terms of multiscale temporal processing compared to their biological counterparts. This limitation has resulted in poor performance in many pattern recognition tasks with information that varies across different timescales. To address this issue, we put forward a novel spiking neuron model called the parallel multi-compartment spiking neuron (PMSN). The PMSN emulates biological neurons by incorporating multiple interacting substructures and allows for flexible adjustment of the substructure counts to effectively represent temporal information across diverse timescales. In addition, to address the computational burden associated with the increased complexity of the proposed model, we introduce two parallelization techniques that decouple the temporal dependencies of neuronal updates, enabling parallelized training across different time steps. Our experiments across a wide range of pattern recognition tasks demonstrate that PMSN outperforms state-of-the-art (SOTA) spiking neuron models in temporal processing capacity and training speed. Specifically, compared with the commonly used leaky integrate-and-fire (LIF) neuron, PMSN offers more than $10\times $ acceleration and a 30% accuracy improvement on the Sequential CIFAR-10 dataset while maintaining comparable computational cost. Our implementation on neuromorphic hardware further demonstrates the deployability of PMSN and highlights its favorable tradeoff between effectiveness and efficiency. Therefore, the proposed PMSN presents a promising solution to harness the computational advantages of detailed biological neurons, enabling high-performance and efficient temporal processing on neuromorphic computing systems. Code is available at https://github.com/xychen-comp/PMSN.
Xinyi Chen, Jibin Wu, Chenxiang Ma et al.· IEEE Transactions on Neural...· 16 citations· ⚡4
Physiological signals, such as electroencephalograms (EEG), electrocardiograms (ECG), and electromyograms (EMG) play a critical role in modern clinical diagnosis, monitoring, and rehabilitation. While deep artificial neural networks (ANNs) have achieved strong performance in analyzing these signals, their high computational cost and energy demands limit deployment in real-time, wearable, and edge-based healthcare systems. Spiking Neural Networks (SNNs), inspired by biological neural computation, offer an event-driven alternative that naturally captures temporal dynamics and enables energy-efficient inference. This article provides a comprehensive review of SNN-based methods for physiological signal analysis across EEG, ECG, and EMG modalities. We survey neuron models, network architectures, encoding schemes, and training methodologies, and systematically review recent state-of-the-art applications in medical diagnosis and rehabilitation. Through analysis, we identify recurring architectural and methodological trends that indicate the dominance of convolution-based spiking architectures, the critical role of encoding strategies in determining energy efficiency, and the task-dependent nature of SNN training approaches. Despite demonstrating performance comparable to conventional deep learning models, often at significantly reduced computational cost, SNN research remains challenged by inconsistent evaluation protocols, limited benchmark standardization, and restricted clinical validation. We conclude by outlining key open challenges and future research directions, emphasizing the need for standardized benchmarks, encoding-aware training, and hybrid ANN–SNN systems. As neuromorphic hardware and event-driven learning methods continue to mature, SNNs are well-positioned to introduce scalable, low-power physiological signal processing for next-generation intelligent healthcare systems.