Identification of Depression-Related Electroencephalographic Patterns Using Astrocyte Spiking Neural Network

Real-time electroencephalography (EEG) offers a more objective foundation for diagnosing depression compared to alternative methodologies. Our research introduces AstrocyteSNN (Astrocyte Spiking Neural Network), an innovative approach that enhances EEG signal recognition by leveraging astrocytic calcium waves to establish long-range connections. AstrocyteSNN demonstrates superior performance in managing long-range dependencies and integrating global information compared to conventional spiking neural networks (SNNs), while maintaining low energy consumption. The model shows promise for early depression diagnosis and monitoring.