The Promise of Spiking Neural Networks for Ubiquitous Computing: A Survey and New Perspectives

2025-06-02

AI Summary

To address the limited adoption of Spiking Neural Networks (SNNs) in ubiquitous computing, this paper systematically reviews 76 works applying SNNs to temporal sensor data analysis across six ubiquitous computing scenarios. We propose the first full-stack SNN knowledge graph tailored for ubiquitous computing, establishing a cross-domain taxonomy of common challenges and a scenario-driven hardware-software co-design guideline. The survey covers core components—including LIF and Izhikevich neuron models, spatio-temporal backpropagation and surrogate gradient training methods, frameworks such as SpyTorch and BindsNET, and neuromorphic hardware including Intel Loihi and SynSense Dynap-SE. We introduce the first ubiquitous-computing-oriented SNN application classification framework and release a reproducible hardware-software evaluation matrix. This work significantly advances the practical deployment of SNNs for energy-efficient, edge-based temporal perception.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Hardware-aware ML

Application Category

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

Abstract

Spiking neural networks (SNNs) have emerged as a class of bio -inspired networks that leverage sparse, event-driven signaling to achieve low-power computation while inherently modeling temporal dynamics. Such characteristics align closely with the demands of ubiquitous computing systems, which often operate on resource-constrained devices while continuously monitoring and processing time-series sensor data. Despite their unique and promising features, SNNs have received limited attention and remain underexplored (or at least, under-adopted) within the ubiquitous computing community. To address this gap, this paper first introduces the core components of SNNs, both in terms of models and training mechanisms. It then presents a systematic survey of 76 SNN-based studies focused on time-series data analysis, categorizing them into six key application domains. For each domain, we summarize relevant works and subsequent advancements, distill core insights, and highlight key takeaways for researchers and practitioners. To facilitate hands-on experimentation, we also provide a comprehensive review of current software frameworks and neuromorphic hardware platforms, detailing their capabilities and specifications, and then offering tailored recommendations for selecting development tools based on specific application needs. Finally, we identify prevailing challenges within each application domain and propose future research directions that need be explored in ubiquitous community. Our survey highlights the transformative potential of SNNs in enabling energy-efficient ubiquitous sensing across diverse application domains, while also serving as an essential introduction for researchers looking to enter this emerging field.

Problem

• Exploring SNNs' potential for low-power ubiquitous computing systems
• Surveying SNN applications in time-series data analysis across domains
• Addressing SNN adoption gaps with tools and research directions

Innovation

• Bio-inspired SNNs for low-power computation
• Survey of 76 SNN-based time-series studies
• Review of SNN frameworks and hardware