菜单
In-ear EEG monitoring platform methodology for simultaneous EEG sensing and auditory stimulation. Covers personalized IEEM device design, closed-loop neuromodulation, and in-ear electrode validation.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/hiyenwong/ai_collection --skill earable-eeg-auditory-platform命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
基于 SOC 职业分类
正在显示 SKILL.md
| name | earable-eeg-auditory-platform |
| description | In-ear EEG monitoring platform methodology for simultaneous EEG sensing and auditory stimulation. Covers personalized IEEM device design, closed-loop neuromodulation, and in-ear electrode validation. |
| version | 1.0.0 |
| author | Research Synthesis |
| license | MIT |
| metadata | {"hermes":{"tags":["eeg","earable","neuromodulation","auditory","hardware","closed-loop"],"source_paper":"Earable Platform with Integrated Simultaneous EEG Sensing and Auditory Stimulation (arXiv:2604.22137)","citations":0}} |
Methodology for personalized in-ear EEG monitors (IEEM) that simultaneously capture EEG signals from the outer ear while delivering audio playback through the same device. Enables closed-loop neuromodulation where brain activity is monitored in real-time and corresponding acoustic stimulation is delivered adaptively, all within the ear.
Based on: Earable Platform with Integrated Simultaneous EEG Sensing and Auditory Stimulation (arXiv:2604.22137) by Min Suk Lee et al., accepted at IEEE NER 2025.
The platform successfully detects multiple physiological signals:
# IEEM Signal Processing Pipeline
import numpy as np
from scipy.signal import butter, filtfilt
class IEEMProcessor:
"""Process simultaneous EEG + auditory signals from in-ear device."""
def __init__(self, fs=500):
self.fs = fs
def bandpass_filter(self, signal, low=0.5, high=45):
"""Bandpass filter for EEG signals."""
nyq = self.fs / 2
b, a = butter(4, [low/nyq, high/nyq], btype='band')
return filtfilt(b, a, signal)
def detect_alpha_power(self, eeg_signal, window_sec=2):
"""Extract alpha band power (8-13 Hz) from EEG."""
nfft = int(window_sec * self.fs)
freqs, psd = self._compute_psd(eeg_signal, nfft)
alpha_mask = (freqs >= 8) & (freqs <= 13)
return np.trapz(psd[alpha_mask], freqs[alpha_mask])
def detect_assr(self, eeg_signal, stim_freq=40):
"""Detect Auditory Steady-State Response at stimulation frequency."""
nfft = len(eeg_signal)
freqs, psd = self._compute_psd(eeg_signal, nfft)
freq_idx = np.argmin(np.(freqs - stim_freq))
signal_power = psd[freq_idx]
noise_power = np.mean(np.concatenate([
psd[freq_idx-:freq_idx],
psd[freq_idx+:freq_idx+]
]))
* np.log10(signal_power / noise_power)
():
alpha = .detect_alpha_power(eeg_signal)
alpha > threshold:
:
():
freqs = np.fft.rfftfreq(nfft, /.fs)
psd = np.(np.fft.rfft(signal, n=nfft))** / nfft
freqs, psd
| Metric | Target | Method |
|---|---|---|
| Electrode impedance | < 100 kOhm | EIS measurement |
| ASSR detection | SNR > 3 dB | Frequency-domain analysis |
| Alpha detection | Correlation with scalp EEG > 0.7 | Cross-validation |
| EOG/blink detection | Sensitivity > 90% | Amplitude thresholding |