Feature extraction and classification of electrocardiogram (ECG) signals are necessary for the automatic diagnosis of cardiac diseases. In this study, a novel method based on genetic algorithm-back propagation neural network (GA-BPNN) for classifying ECG signals with feature extraction using wavelet packet decomposition (WPD) is proposed. WPD combined with the statistical method is utilized to extract the effective features of ECG signals. The statistical features of the wavelet packet coefficients are calculated as the feature sets. GA is employed to decrease the dimensions of the feature sets and to optimize the weights and biases of the back propagation neural network (BPNN). Thereafter, the optimized BPNN classifier is applied to classify six types of ECG signals. In addition, an experimental platform is constructed for ECG signal acquisition to supply the ECG data for verifying the effectiveness of the proposed method. The GA-BPNN method with the MIT-BIH arrhythmia database achieved a dimension reduction of nearly 50% and produced good classification results with an accuracy of 97.78%. The experimental results based on the established acquisition platform indicated that the GA-BPNN method achieved a high classification accuracy of 99.33% and could be efficiently applied in the automatic identification of cardiac arrhythmias.
Automatic recognition of arrhythmias is particularly important in the diagnosis of heart diseases. This study presents an electrocardiogram (ECG) recognition system based on multi-domain feature extraction to classify ECG beats. An improved wavelet threshold method for ECG signal pre-processing is applied to remove noise interference. A novel multi-domain feature extraction method is proposed; this method employs kernel-independent component analysis in nonlinear feature extraction and uses discrete wavelet transform to extract frequency domain features. The proposed system utilises a support vector machine classifier optimized with a genetic algorithm to recognize different types of heartbeats. An ECG acquisition experimental platform, in which ECG beats are collected as ECG data for classification, is constructed to demonstrate the effectiveness of the system in ECG beat classification. The presented system, when applied to the MIT-BIH arrhythmia database, achieves a high classification accuracy of 98.8%. Experimental results based on the ECG acquisition experimental platform show that the system obtains a satisfactory classification accuracy of 97.3% and is able to classify ECG beats efficiently for the automatic identification of cardiac arrhythmias.
Aims. Sarcopenia is a common condition in older individuals, especially in the elderly with type 2 diabetes mellitus (T2DM). The aim of the present study was to examine the risk factors for sarcopenia in elderly individuals with T2DM and the effects of metformin. Methods. A total of 1732 elderly with T2DM were recruited to this cross-sectional observational study, and we analyzed the data using logistic regression analyses. Skeletal muscle mass, grip strength, and usual gait speed were measured to diagnose sarcopenia according to the criteria of the Asian Working Group for Sarcopenia, combined with expert consensus on sarcopenia in China. Results. The overall prevalence of sarcopenia was 10.37% of the participants. In the multivariate analysis, sex, age, educational level, and BMI were risk factors for sarcopenia, with women more likely to develop sarcopenia relative to men ( OR = 2.539 , 95% CI = 1.475 –4.371; P < 0.05 ). We observed that sarcopenia increased with age and decreased with increasing BMI and educational level ( P < 0.05 ). Participants who took metformin alone or combined with other drugs exhibited a lower risk for sarcopenia than those who took no medication ( OR = 0.510 , 95% CI = 0.288 –0.904 and OR = 0.398 , 95% CI = 0.225 –0.702, respectively; P < 0.05 ). Conclusions. We showed that being female and at an older age, lower educational level, and lower BMI were risk factors for sarcopenia in elderly T2DM and that metformin acted as a protective agent against sarcopenia in these patients.
Highlights Polyimide-based flexible microneedle array (PI-MNA) electrodes realize high electrical/mechanical performance and are compatible with wearable wireless recording systems. The normalized electrode–skin interface impedance (EII) of the PI-MNA electrodes reaches 0.98 kΩ cm2 at 1 kHz and 1.50 kΩ cm2 at 10 Hz, approximately 1/250 of clinical standard electrodes. This is the first report on the clinical study of microneedle electrodes. The PI-MNA electrodes are applied to clinical long-term continuous monitoring for polysomnography. Abstract Microneedle array (MNA) electrodes are an effective solution to achieve high-quality surface biopotential recording without the coordination of conductive gel and are thus very suitable for long-term wearable applications. Existing schemes are limited by flexibility, biosafety, and manufacturing costs, which create large barriers for wider applications. Here, we present a novel flexible MNA electrode that can simultaneously achieve flexibility of the substrate to fit a curved body surface, robustness of microneedles to penetrate the skin without fracture, and a simplified process to allow mass production. The compatibility with wearable wireless systems and the short preparation time of the electrodes significantly improves the comfort and convenience of electrophysiological recording. The normalized electrode–skin contact impedance reaches 0.98 kΩ cm2 at 1 kHz and 1.50 kΩ cm2 at 10 Hz, a record low value compared to previous reports and approximately 1/250 of the standard electrodes. The morphology, biosafety, and electrical/mechanical properties are fully characterized, and wearable recordings with a high signal-to-noise ratio and low motion artifacts are realized. The first reported clinical study of microneedle electrodes for surface electrophysiological monitoring was conducted in tens of healthy and sleep-disordered subjects with 44 nights of recording (over 8 h per night), providing substantial evidence that the electrodes can be leveraged to substitute for clinical standard electrodes.
Electrocardiogram (ECG) signal feature extraction is important in diagnosing cardiovascular diseases. This paper presents a new method for nonlinear feature extraction of ECG signals by combining principal component analysis (PCA) and kernel independent component analysis (KICA). The proposed method first uses PCA to decrease the dimensions of the ECG signal training set and then employs KICA to cal-B Hongqiang Li Circuits Syst Signal Process culate the feature space for extracting the nonlinear features. Support vector machine (SVM) is utilized to determine the nonlinear features of the ECG signal classification. Genetic algorithm is also used to optimize the SVM parameters. The proposed method is advantageous because it does not require a huge amount of sampling data, and this technique is better than traditional strategies to select optimal features in the multi-domain feature space. Computer simulations reveal that the proposed method yields more satisfactory classification results on the MIT-BIH arrhythmia database, reaching an overall accuracy of 97.78 %.
Although the mechanisms of steady-state visual evoked potentials (SSVEPs) have been well studied, none of them have been implemented with strictly experimental conditions. Our objective was to create an ideal observer condition to exploit the features of SSVEPs. We present here an electroencephalographic (EEG) eye tracking experimental paradigm that provides biofeedback for gaze restriction during the visual stimulation. Specifically, we designed an EEG eye tracking synchronous data recording system for successful trial selection. Forty-six periodic flickers within a visual field of 11.5° were successively presented to evoke SSVEP responses, and online biofeedback based on an eye tracker was provided for gaze restriction. For eight participants, SSVEP responses in the visual field and topographic maps from full-brain EEG were plotted and analyzed. The experimental results indicated that the optimal visual flicking arrangement to boost SSVEPs should include the features of circular stimuli within a 4–6° spatial distance and increased stimulus area below the fixation point. These findings provide a basis for determining stimulus parameters for neural engineering studies, e.g. SSVEP-based brain-computer interface (BCI) designs. The proposed experimental paradigm could also provide a precise framework for future SSVEP-related studies.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.