Real-time classification method and device of spike signal, storage medium and electronic equipment

CN115186700BActive Publication Date: 2026-01-16GUANGDONG MEDICAL UNIV
View PDF -1 Cites 0 Cited by

Patent Information

Application Number
CN202210667464.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-06-13
Publication Date
2026-01-16
Estimated Expiration
2042-06-13

AI Technical Summary

Technical Problem

In existing technologies, the classification results of spike signals from high-density multi-channel electrode arrays suffer from redundancy and low classification efficiency, especially in the inability to effectively process real-time recorded spike signals.

Method used

The high-density multi-channel electrode array is divided into multiple electrode groups. Within a preset time window, sampling signals are collected through the electrode groups. Target sampling signals that meet the peak value or energy threshold are selected. Spike signals are intercepted with the peak position as the center. The signal collected by the middle electrode with the largest peak value is selected as the current signal for classification. Real-time classification is performed by combining the correlation coefficient.

Benefits of technology

This technology enables real-time signal classification of high-density multi-channel electrode arrays, reduces data volume, avoids redundancy in classification results, and improves classification efficiency, laying the foundation for portable, low-power brain signal analysis devices.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115186700B_ABST
    Figure CN115186700B_ABST
Patent Text Reader

Abstract

The embodiment of the application discloses a real-time classification method and device of a spike signal, a storage medium and an electronic device, and relates to the field of signal classification. The signal identification method of the application can collect the spike signal on the electrode closest to the neuron each time, provides the best spike signal to the subsequent classification process, avoids the redundancy of the classification result, reduces the data volume of the classification signal while ensuring the classification effect, and classifies the spike signal in real time through the data stream mode, thereby laying a foundation for the future development of a portable and low-power brain electrical signal analysis device.
Need to check novelty before this filing date? Find Prior Art