ECG-Based Subject Identification Using Statistical Features and Random Forest

Abstract

In this work, a nonfiducial electrocardiogram (ECG) identification algorithm based on statistical features and random forest classifier is presented. Two feature extraction approaches are investigated: direct and band-based approaches. In the former, eleven simple statistical features are directly extracted from a single-lead ECG signal segment. In the latter, the single-lead ECG signal is first decomposed into bands, and the statistical features are extracted from each segment of a given band and concatenated to form the feature vector. Nonoverlapping segments of different lengths (i.e., 1, 3, 5, 7, 10, or 15 sec) are examined. The extracted feature vectors are applied to a random forest classifier, for the purpose of identification. This study considers 290 reference subjects from the ECG database of the Physikalisch-Technische Bundesanstalt (PTB). The proposed identification algorithm achieved an accuracy rate of 99.61% utilizing the single limb lead (I) with the band-based approach. A single chest lead (V1), augmented limb lead (aVF), and Frank’s lead (Vx) achieved an accuracy rate of 99.37%, 99.76%, and 99.76%, respectively, using the same approach.

ELEKTRA: ELEKTRokardiomatrix application to biometric identification with convolutional neural networks

“…Many proposals can also be found that use Machine Learning (ML) or DL algorithms to perform user identification and classification. Some of the most promising algorithms tested for user identification could be some of the ML algorithms such as Support Vectors Machine (SVM) [72,102,103], a Random Forest [104,105] or Logistic Regression [106,107], other deep learning algorithms as a k-Nearest Neighbour (k-NN) [108,109,110] or any Neural Network (NN) [93,111,112,113,114].…”

An Intraoral Non-Occlusal MEMS Sensor for Bruxism Detection

“…Next, calculations were applied to the baseline removed pressure signal to create sixty-four features for each 250 ms epoch of the recordings. The 64 features were created using an ensemble of time domain statistical measures across different size windows, peak detection information and frequency domain measures [24,25]. The 64 features are split into 8 groups each with 8 features each to make it easier to describe in table II.…”

Application of Fourier-Bessel expansion and LSTM on multi-lead ECG for cardiac abnormalities identification

“…Statistical measures such as variance, skewness, and kurtosis of ECG signals are extracted as statistical features. The kurtosis measures the sharpness of the peak, whereas skewness is used to measure the asymmetry of the ECG signal's amplitude distribution (Alotaiby et al 2019). Depending on heart activity, sample distribution in ECG signal may vary.…”