Shih-Chin Fang

Human identification by quantifying similarity and dissimilarity in electrocardiogram phase space

Specific patterns of electrocardiogram (ECG), along with other biometrics, have recently been used to recognize a person. Most ECG-based human identification methods rely on the reduced features derived from ECG characteristic points and supervised classification. However, detecting characteristic points is an arduous procedure, particularly at low signal-to-noise ratios. The supervised classifier requires retraining when a new person is included in the group. In the present study, we propose a novel unsupervised ECG-based identification method based on phase space reconstruction of one-lead or three-lead ECG, saving from picking up characteristic points. Identification is performed by inspecting similarity or dissimilarity measure between ECG phase space portraits. Our results in a 100-subject group showed that one-lead ECG reached identification rate at 93% accuracy and three-lead ECG acquired 99% accuracy.

Heart rate variability characterization in daily physical activities using wavelet analysis and multilayer fuzzy activity clustering

A portable data recorder was developed to parallel measure the electrocardiogram and body accelerations. A multilayer fuzzy clustering algorithm was proposed to classify the physical activity based on body accelerations. Discrete wavelet transform was incorporated to retrieve time-varying characteristics of heart rate variability under different physical activities. Nine healthy subjects were included to investigate activity-related heart rate variability during 24 h. The results showed that the heartbeat fluctuations in high frequencies were the greatest during lying and the smallest during standing. Moreover, very-low-frequency heartbeat fluctuations during low activity level (lying) were greater than during high activity level (nonlying).

Classification of neuronal spikes over the reconstructed phase space.

Spike information is beneficial to correlate neuronal activity to various stimuli or determine target neural area for deep brain stimulation. Data clustering based on neuronal spike features provides a way to separate spikes generated from different neurons. Nevertheless, some spikes are aligned incorrectly due to spike deformation or noise interference, thereby reducing the accuracy of spike classification. In the present study, we proposed unsupervised spike classification over the reconstructed phase spaces of neuronal spikes in which the derived phase space portraits are less affected by alignment deviations. Principal component analysis was used to extract major principal components of the portrait features and k-means clustering was used to distribute neuronal spikes into various clusters. Finally, similar clusters were iteratively merged based upon inter-cluster portrait differences.

Heartbeat Detection Using Energy Thresholding and Template Match

Heartbeat detection is very important for retrieving the vital signs of heart functions. The morphologies and inter-beat intervals of heartbeats can reveal the condition of heart contraction. In this paper, we developed a heartbeat information integration scheme to deal with the information yielded by the energy thresholding and template match methods, which are usually used to detect the heartbeats and match the QRS, respectively. The proposed method are developed in SIMULINK 2.0 and assessed by the MIT/BIH arrhythmia database. The result demonstrated excellent sensitivity of detecting QRS and ventricular premature contraction in the proposed method

Recognition of Ventricular Extrasystoles Over the Reconstructed Phase Space of Electrocardiogram

Distinguishing ventricular extrasystoles from normal heartbeats is crucial to cardiac arrhythmia analysis. This paper proposes novel morphological descriptors, the major portrait partition area (MPPA) and point distribution percentage (PDP), which are extracted from the reconstructed phase space of the QRS complex. These measures can be linked to QRS width and prolonged ventricular contraction, and offer several advantages over traditional characterization of the QRS structure: it does not require QRS boundary detection, is robust under R-peak misalignment, and including some information from nearby points. The first four principal components of MPPA variables and PDPs in the first and the third quadrants of the phase space diagram were used as inputs of neural networks. The performance of networks in distinguishing premature ventricular contraction events from normal heartbeats were evaluated under a series of 50 cross-validations based on the electrocardiogram data taken from the MIT/BIH arrhythmia database. The sensitivity and specificity obtained using the aforementioned MPPA principal components and PDPs as inputs were similar to those obtained using wavelet features and Hermite coefficients. However, the phase space information performed better in situations of noise contaminations and waveform deformations.

Linear and Nonlinear EEG Indexes in Relation to the Severity of Coma

Glascows coma scale (GCS) is a clinical standard for assessing the severity of coma in intensive care units (ICUs). The EEG monitoring can be on-line work, soon responds to the change in the brain wave, and allows long-term continuous monitoring of brain activity. In this paper, several EEG parameters, including spectral possession distribution and nonlinear description (approximate entropy and Lempel-Ziv complexity) were used to assess the capability of EEG indexes for the severity of coma. Our results demonstrated that all EEG parameters are moderately related to the GCS, with the Spearman statistical correlation of 0.62-0.71 between the spectral possession distribution and the GCS and 0.62-0.66 between nonlinear measures and the GCS. The moderate correlation between EEG parameters and the GCS implies the possibility of the EEG-derived index to reveal the neurological status of patients in coma

Phase-space Reconstruction of Electrocardiogram for Heartbeat Classification

Heartbeat classification is crucial for cardiac arrhythmia analysis. QRS complex presents important characteristics which are beneficial to distinguish abnormal beats from normal beats. In the present study we propose a novel descriptor for QRS complex. The waveform is transformed to a two-dimensional phase space and then mapped to a onedimensional portrait partition area (PPA). The proposed morphological descriptor has advantages of no need to detect Q and S characteristic points, tolerating R-peak misalignment and taking into account temporal relation of data samples. On the basis of 32 records from the MIT/BIH arrhythmia database, normal QRS and premature ventricular contraction (PVC) beats show different phase space portraits and PPA. An artificial neuronal network using PPA as the input feature was built for heartbeat classification. Our results showed that the sensitivity and specificity of distinguishing PVC from normal QRS achieved 0.9699 and 0.9651 in the testing sets, respectively.

Nonlinear characteristics of heart rate variability during unsupervised and steady physical activities.

The heart rate (HR) exhibits various behavior patterns in different postures and during physical activities, whereas a conventional long-term analysis of HR variability has the confounding effect whether the subject was physically active or immobilized. A specially designed ambulatory recorder that simultaneously measures the electrocardiogram and body accelerations was used to study the short-term (< or =11 beats, alpha1) fractal correlation property and the approximate entropy (ApEn) of RR interval data during sleep, sitting and standing (passive standing or mild walking) levels and immediately after rising in the morning in 15 healthy subjects. The alpha1 exponent that increased from sleep to sitting to standing implies an increased correlation of HR dynamics, which is concomitant with an increased ratio of low-frequency power to high-frequency power (LF/HF) that is usually linked with an increased sympathetic activity. A lower ApEn value during standing and after rising implies a reduced complexity of HR dynamics. Compared to the HR measures during the standing level, the LF/HF ratio showed a quick autonomic shift and alpha1 showed a rapid recruitment of fractal HR behavior after rising, whereas the ApEn value had a slower recovery of HR complexity. In conclusion, both linear and nonlinear HR behaviors during different unsupervised physical activities can be better interpreted with the aid of the recorded movement data.

Linear and nonlinear analysis of electroencephalogram of the coma

The coma is common in intensive care units. The bedside physical examination provides a means to measuring the neurological status, but it cannot be a continuous evaluation, whereas electroencephalogram (EEG) can reflect the immediate electrical activities of the brain. In this paper, we investigate the spectral parameters, complexity and irregular measures, and spectral entropy in the coma. Compared to the normal subject, the EEG of the coma has a dominance of slow wave, low complexity, less irregularity, and low spectral entropy. This result demonstrates the possibility to use EEG analysis for the monitoring of neurological function.

Approximate entropy analysis of electroencephalogram in vasovagal syncope on tilt table test

Thirty vasovagal attacks on sublingual nitroglycerin stressed tilting test were selected. By the method of shifting window along the continuous EEG signals the linear (spectral power and coherence) and nonlinear (approximate entropy) EEG features of the whole course in the tilt table test were demonstrated. Of all the EEG parameters approximate entropy is a more sensitive index in clarifying stages of various degree of tilting stress and in identifying the syncopal transient.