Department of Neurology, 3-18-15 Kuramotocho, Tokushima City, 770-8503, Japan.
Muscle Nerve. 2019 Feb;59(2):224-228. doi: 10.1002/mus.26363. Epub 2018 Dec 18.
The diagnostic importance of audio signal characteristics in needle electromyography (EMG) is well established. Given the recent advent of audio-sound identification by artificial intelligence, we hypothesized that the extraction of characteristic resting EMG signals and application of machine learning algorithms could help classify various EMG discharges.
Data files of 6 classes of resting EMG signals were divided into 2-s segments. Extraction of characteristic features (384 and 4,367 features each) was used to classify the 6 types of discharges using machine learning algorithms.
Across 841 audio files, the best overall accuracy of 90.4% was observed for the smaller feature set. Among the feature classes, mel-frequency cepstral coefficients (MFCC)-related features were useful in correct classification.
We showed that needle EMG resting signals were satisfactorily classifiable by the combination of feature extraction and machine learning, and this can be applied to clinical settings. Muscle Nerve 59:224-228, 2019.
音频信号特征在针极肌电图（EMG）中的诊断重要性已得到充分证实。鉴于人工智能最近在音频识别方面的出现，我们假设提取特征静息 EMG 信号并应用机器学习算法可以帮助对各种 EMG 放电进行分类。
将 6 类静息 EMG 信号的数据文件分为 2 秒段。使用机器学习算法提取特征（每个特征集分别为 384 和 4367 个特征）来对 6 种放电类型进行分类。
在 841 个音频文件中，使用较小特征集观察到的总体准确性最佳为 90.4%。在特征类别中，梅尔频率倒谱系数（MFCC）相关特征在正确分类中很有用。
我们表明，针极肌电图静息信号可以通过特征提取和机器学习的组合进行令人满意的分类，并且可以应用于临床环境。肌肉神经 59：224-228，2019 年。
