轻量级Transformer融合脑部信号，实时识别疼痛
A Lightweight Transformer for Pain Recognition from Brain Activity
- 统一令牌化融合多源fNIRS数据，无需模态适配
- 在AI4Pain数据集上达良好识别精度，计算量小
- 适合部署在CPU/GPU端，适合临床实时应用
疼痛是一种复杂且普遍的现象，具有重大临床与社会负担，实现可靠的自动化评估至关重要。本文提出一种轻量级Transformer架构，通过统一的令牌化机制融合多种fNIRS表征，实现互补信号视图的联合建模，无需模态特异性调整且不增加结构复杂度。所提令牌混合策略通过将异构输入投影到共享隐空间，保留空间、时间及时间-频率特性，并采用结构化分割方案控制局部聚合与全局交互的粒度。模型在AI4Pain数据集上基于堆叠的原始波形与功率谱密度表示进行评估。实验结果表明，该方法在保持计算紧凑的同时实现了具有竞争力的疼痛识别性能，适用于在GPU和CPU硬件上进行实时推理。
原文摘要 · Abstract (English)
Pain is a multifaceted and widespread phenomenon with substantial clinical and societal burden, making reliable automated assessment a critical objective. This paper presents a lightweight transformer architecture that fuses multiple fNIRS representations through a unified tokenization mechanism, enabling joint modeling of complementary signal views without requiring modality-specific adaptations or increasing architectural complexity. The proposed token-mixing strategy preserves spatial, temporal, and time-frequency characteristics by projecting heterogeneous inputs onto a shared latent representation, using a structured segmentation scheme to control the granularity of local aggregation and global interaction. The model is evaluated on the AI4Pain dataset using stacked raw waveform and power spectral density representations of fNIRS inputs. Experimental results demonstrate competitive pain recognition performance while remaining computationally compact, making the approach suitable for real-time inference on both GPU and CPU hardware.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。