通过基于xLSTM的深度学习与空间注意力和过器银行技术增强SSVEP生物拼写
Liuyuan Dong1, Chengzhi Xu1, Ruizhen Xie1
1Hubei Provincial Key Laboratory of Green Intelligent Computing Power Network, School of Computer, Hubei University of Technology, Wuhan 430068, China.
Biomimetics (Basel, Switzerland)
|August 27, 2025
概括
这项研究介绍了SED-xLSTM,一种用于大脑与计算机接口 (BCI) 的新型深度学习模型. 通过提高准确性和效率,它增强了失言症患者的稳定状态视觉唤起潜力 (SSVEPs) 沟通.
科学领域:
- 神经科学
- 计算机科学
- 生物医学工程
背景情况:
- 稳态视觉唤起潜力 (SSVEPs) 对于脑电脑接口 (BCI) 至关重要,特别是对于口音障碍患者.
- 现有的基于变压器的方法通常不充分利用SSVEP频率信息,并涉及冗余计算.
研究的目的:
- 提出一个新的深度学习架构,SED-xLSTM,用于增强SSVEP信号分析.
- 通过整合时间和频域信息来提高基于SSVEP的BCI的效率和准确性.
主要方法:
- 开发了一个堆叠的编码器-解码器 (SED) 网络架构,包含一个xLSTM模型和空间注意力机制 (SED-xLSTM).
- 使用低频谱作为输入,并应用过器银行技术来捕获波信息.
- 采用一个门机制来有效提取和融合高维空间通道的语义特征.
主要成果:
- 在三个公共数据集中,SED-xLSTM在分类准确性和信息传输速度方面表现出卓越的表现.
- 该模型的性能优于现有方法,特别是在不同时间尺度的交叉验证场景中.
- 从SSVEP信号中实现了空间通道语义特征的有效提取和融合.
结论:
- 在基于SSVEP的BCI拼写中,SED-xLSTM提供了显著的进步,特别是对于口音障碍患者.
- 拟议的架构有效地利用时间和频域信息来提高BCI性能.
- 这项研究强调了xLSTM和空间注意力在分析BCI应用中的复杂神经信号方面的潜力.
相关概念视频
01:35Long-term Potentiation
51.6K
Long-term potentiation, or LTP, is one of the ways by which synaptic plasticity—changes in the strength of chemical synapses—can occur in the brain. LTP is the process of synaptic strengthening that occurs over time between pre- and postsynaptic neuronal connections. The synaptic strengthening of LTP works in opposition to the synaptic weakening of long-term depression (LTD) and together are the main mechanisms that underlie learning and memory.
51.6K
01:25Long-term Potentiation
2.7K
Long-term potentiation, or LTP, is one of the ways by which synaptic plasticity—changes in the strength of chemical synapses—can occur in the brain. LTP is the process of synaptic strengthening that occurs over time between pre and postsynaptic neuronal connections. The synaptic strengthening of LTP works in opposition to the synaptic weakening of long-term depression (LTD) and together are the main mechanisms that underlie learning and memory.
Hebbian LTP
LTP can occur when...
Hebbian LTP
LTP can occur when...
2.7K