ABSTRACT
In recent years, exploring the physiological and pathological mechanisms of brain functional integration from the neural network level has become one of the focuses of neuroscience research. Due to the non-stationary and nonlinear characteristics of neural signals, its linear characteristics are not sufficient to fully explain the potential neurophysiological activity mechanism in the implementation of complex brain functions. In order to overcome the limitation that the linear algorithm cannot effectively analyze the nonlinear characteristics of signals, researchers proposed the transfer entropy (TE) algorithm. In recent years, with the introduction of the concept of brain functional network, TE has been continuously optimized as a powerful tool for nonlinear time series multivariate analysis. This paper first introduces the principle of TE algorithm and the research progress of related improved algorithms, discusses and compares their respective characteristics, and then summarizes the application of TE algorithm in the field of electrophysiological signal analysis. Finally, combined with the research progress in recent years, the existing problems of TE are discussed, and the future development direction is prospected.
Subject(s)
Algorithms , Brain/physiology , Entropy , Neural Networks, Computer , Nonlinear DynamicsABSTRACT
Changes in the intrinsic characteristics of brain neural activities can reflect the normality of brain functions. Therefore, reliable and effective signal feature analysis methods play an important role in brain dysfunction and relative diseases early stage diagnosis. Recently, studies have shown that neural signals have nonlinear and multi-scale characteristics. Based on this, researchers have developed the multi-scale entropy (MSE) algorithm, which is considered more effective when analyzing multi-scale nonlinear signals, and is generally used in neuroinformatics. The principles and characteristics of MSE and several improved algorithms base on disadvantages of MSE were introduced in the article. Then, the applications of the MSE algorithm in disease diagnosis, brain function analysis and brain-computer interface were introduced. Finally, the challenges of these algorithms in neural signal analysis will face to and the possible further investigation interests were discussed.
ABSTRACT
The paper proposes a new approach to heart activity diagnosis based on Gram polynomials and probabilistic neural networks (PNN). Heart disease recognition is based on the analysis of phonocardiogram (PCG) digital sequences. The PNN provides a powerful tool for proper classification of the input data set. The novelty of the proposed approach lies in a powerful feature extraction based on Gram polynomials and the Fourier transform. The proposed system presents good performance obtaining overall sensitivity of 93%, specificity of 91% and accuracy of 94%, using a public database of over 3000 heart beat sound recordings, classified as normal and abnormal heart sounds. Thus, it can be concluded that Gram polynomials and PNN prove to be a very efficient technique using the PCG signal for characterizing heart diseases.
Subject(s)
Classification , Dataset , Diagnosis , Fourier Analysis , Heart Diseases , Heart Sounds , Heart , Sensitivity and SpecificityABSTRACT
The paper dilates upon epileptic EEG data treatment and analysis methods based on machine learning,including supervised learning,unsupervised learning,semi-supervised learning,reinforcement learning and machine learning methods of other types,and evaluates the application effects of the methods on inspection of epileptic EEG data.
ABSTRACT
Este artículo reporta el desarrollo de la etapa de procesamiento de la señal electrocardiográfica implementada en el prototipo DIGICARDIAC. El prototipo DIGICARDIAC es un instrumento de uso médico que permite la adquisición simultánea de las doce derivaciones del electrocardiograma (ECG) estándar, con características de alta resolución (ECGAR). El software desarrollado, pretende agrupar algunos de los criterios expuestos por los investigadores e implementar algunas técnicas novedosas, en la detección del latido cardiaco y la medición de los intervalos QT y ST en la señal ECGAR adquirida con el sistema. En las pruebas de funcionamiento se comprobó la eficiencia del algoritmo. Los errores obtenidos en la detección del complejo QRS son inferiores al 0,1 % y en la medición del intervalo QT se obtuvo un error promedio del 1,89 % en las señales ECG de los pacientes control.
This paper reports the development stage of the electrocardiographic signal processing implemented at the prototype DIGICARDIAC. The DIGICARDIAC prototype is a medical instrument that allows the simultaneous acquisition of the twelve-lead electrocardiogram (ECG) standard, which features high resolution (HRECG). The software developed, aims to bring together some of the criteria set up by the researchers and implement some new techniques, in heartbeat detection and measurement of QT and ST intervals in the HRECG signal acquired with the system. The algorithm efficient was proved through tests of perfomance. The errors obtained in QRS complex detection are lower than 0,1% and measuring QT interval averaging 1.89% error in the ECG signals of the control patients was obtained.
Subject(s)
Humans , Male , Female , Algorithms , Signal Processing, Computer-Assisted/instrumentation , Cardiovascular Diseases/diagnostic imaging , Electrocardiography , Heart Diseases/pathology , Systems Analysis , Software , Public HealthABSTRACT
Objective To make a quantitative research on the vertical force homogeneity of Yizhichan manipulation and look for the quantitative index and reference value which can describe the force homogeneity of Yizhichan manipulation effectively. Methods After the force homogeneity was described mathematically, the vertical force signals from Yizhichan manipulation operated by 5 experts, 5 skilled doctors and 5 beginners were measured and analyzed, respectively. Results The period homogeneities and the waveform homogeneities were obtained. No significant differences were found in the period homogeneities among the three groups, but significant differences appeared in waveform homogeneities between the beginner and expert group or the beginner and skilled doctor group. Conclusions The waveform homogeneities are more suitable for evaluating the vertical force homogeneity of Yizhichan manipulation by different operators, and 0.927 can be used as a reference value to evaluate the vertical force homogeneity of the operator.
ABSTRACT
Objective A surface feedback-stimulation gastric-pacing device was designed to extract gastric surface information,determine the status of gastric and surface stimulation.Methods The characteristic parameters of gastric electrical formed by processing signal and extracting parameter.By that,the state of stomach could be confirmed,and stimulus signal of stomach pace-making in different frequency and intensity could be decided as needed.During the processes of the stimulation,the variations of gastric electrical parameters can be analyzed in real-time and the stimulation parameters could be modified to achieve the self-feedback mode.Results Self-feedback model in different gastric motility analog environment could be realized.Conclusion The preliminary validation of experimental results proved the effectiveness of self-feedback of gastric pacing devices and its application prospects in some areas.
ABSTRACT
Objective To raise a quantitative indicator for the waveform similarity between different signals of the same kind and apply it to the analysis on the vertical force signals from the rolling manipulation. Method After two signals of the same kind were normalized and their waveform errors were analyzed, the waveform similarity, which was to be utilized to describe the extent to which two signals were similar to each other, was defined. Then, the vertical force signals of the rolling manipulation operated by several experts, graduates who have learned the manipulation for some time and beginners were measured, respectively. Subsequently, the values of the waveform similarity between the three different groups of signals were calculated. Results The similarity between the experts’ signals was relatively high, so it was reasonable to be used as a template for other operators’ signals to be compared with. Further calculation revealed that the waveform similarity between the experts’ signals and the graduates’ was generally lower than that between the experts’, and the similarity between the experts’ and the beginners’ was the lowest. There was significant difference between the three groups. Conclusions The waveform similarity raised in this paper could serve as a quantitative indicator for the similarity between different vertical force signals from the rolling manipulation, and this method was also applicable to the similarity evaluation between other approximate periodic signals.
ABSTRACT
One of the main goals in ultrasonic Doppler blood flow assessment in the estimation of the mean speed. The aim of this work is focused in Carotid artery blood flow signals...
Subject(s)
Algorithms , Carotid Arteries , Echocardiography, Doppler , Normal Distribution , Signal Processing, Computer-AssistedABSTRACT
Phonocardiogram contains a lot of information on the physiological and pathological cardiac function, so it can improve the diagnosis and treatment of cardiovascular disease to effectively diagnose cardiac sounds. This paper presents the design of a computer-based measurement and real-time analysis system of heart sounds. Applying computers to the analysis and auxiliary diagnosis of cardiac sounds, the system is real-time and intelligent.