Sample Entropy Values Research Articles

Development and validation of a sample entropy-based method to identify complex patient-ventilator interactions during mechanical ventilation

Patient-ventilator asynchronies can be detected by close monitoring of ventilator screens by clinicians or through automated algorithms. However, detecting complex patient-ventilator interactions (CP-VI), consisting of changes in the respiratory rate and/or clusters of asynchronies, is a challenge. Sample Entropy (SE) of airway flow (SE-Flow) and airway pressure (SE-Paw) waveforms obtained from 27 critically ill patients was used to develop and validate an automated algorithm for detecting CP-VI. The algorithm’s performance was compared versus the gold standard (the ventilator’s waveform recordings for CP-VI were scored visually by three experts; Fleiss’ kappa = 0.90 (0.87–0.93)). A repeated holdout cross-validation procedure using the Matthews correlation coefficient (MCC) as a measure of effectiveness was used for optimization of different combinations of SE settings (embedding dimension, m, and tolerance value, r), derived SE features (mean and maximum values), and the thresholds of change (Th) from patient’s own baseline SE value. The most accurate results were obtained using the maximum values of SE-Flow (m = 2, r = 0.2, Th = 25%) and SE-Paw (m = 4, r = 0.2, Th = 30%) which report MCCs of 0.85 (0.78–0.86) and 0.78 (0.78–0.85), and accuracies of 0.93 (0.89–0.93) and 0.89 (0.89–0.93), respectively. This approach promises an improvement in the accurate detection of CP-VI, and future study of their clinical implications.

Fall-related measures in elderly individuals and Parkinson's disease subjects.

Falls pose a serious problem in elderly and clinical populations. Most often, they lead to a loss of mobility and independence. They might also be an indirect cause of death. The aim of this study was to determine an objective predictor of the fear of falling and falls in elderly subjects (ESs) and Parkinson's disease (PD) subjects. Thirty-two ESs were examined in this study, of whom sixteen were diagnosed with PD. The testing procedures comprised force plate measurements (limit of stability test-LOS test) and clinical tests (Berg Balance Scale, Functional Reach Test, Timed Up and Go test, Tinetti test). The Falls Efficacy Scale International (FES-I) was used to evaluate the fear of falling. The range of the maximum forward lean was normalized to the length from the ankle joint to the head of the first metatarsal bone and was named the functional forward stability indicator (FFSI). The FFSI, derived from the LOS test, allowed us to demonstrate the real deficit in functional stability and individual safety margins. Moreover, the FFSI was highly correlated with the FES-I score and almost all clinical test results in elderly subjects (r>0,6; p<0.05). In PD subjects, the FFSI was poorly correlated with the fear of falling, the BBS score and the FR distance; however, a high correlation with the Tinetii test (r>0,6, p<0.05) was noted. The PD subjects presented a different balance strategy when close to their stability limits, which was also reflected in the lower values of sample entropy (t = (-2.40); p<0.05; d = 0.87). The FFSI might be a good predictor of the fear of falling in the group of elderly people. Additionally, the FFSI allows us to show real balance deficits both in PD subjects and in their healthy peers without the need for a reference group and norms. In conclusion, it is postulated that the popular clinical assessments of postural balance in PD subjects should be accompanied by reliable posturography measurements.

Sample Entropy Analysis of Horses with and without Lameness at Trot before and after Sedation

The horses were trotted in a straight line, and the acceleration data were recorded from the movement of the horse’s head. Inertial sensors were used to collect the information. The sample entropy was used to characterize the dynamics of horse gait. The gait of sound and lame horses was compared, and the sound horses had smaller values of the sample entropy. The effects of sedative detomidine on the gait of lame horses were also examined. The values of sample entropy for sedated horses were smaller than the values of the sample entropy for untreated horses. The sample entropy can provide important information about the dynamics of the equine gait.

Dual-Mass MEMS Gyroscope Parallel Denoising and Temperature Compensation Processing Based on WLMP and CS-SVR

For the sake of decreasing the effects of noise and temperature error on the measurement accuracy of micro-electro-mechanical system (MEMS) gyroscopes, a denoising and temperature drift compensation parallel model method based on wavelet transform and forward linear prediction (WFLP) and support vector regression based on the cuckoo search algorithm (CS-SVR) is proposed in this paper. First, variational mode decomposition (VMD) is proposed in this paper, which is aimed at dividing the output signal of the gyroscope into intrinsic mode functions (IMFs); then, the IMFs are classified into three features—drift, mixed, and pure noise features—by the sample entropy (SE) value. Second, a wavelet transform and forward linear prediction (WFLP) are combined to remove the noise from the mixed features. Meanwhile, the drift feature is compensated by support vector regression based on the cuckoo search algorithm (CS-SVR). Finally, through reconstruction, the final signal is obtained. Experimental results demonstrate that the VMD-SE-WFLP-CS-SVR method proposed in this paper can decrease noise and compensate the temperature error effectively (angular random walking value is optimized from 1.667°/√h to 0.0667°/√h and the bias stability is reduced from 30°/h to 4°/h). In terms of denoising, the performance of the WFLP algorithm is superior to the wavelet threshold and FLP, as it combines their advantages; furthermore, in terms of temperature compensation, the proposed CS-SVR algorithm uses the cuckoo search algorithm to find the optimal parameters of SVR, improving the accuracy of the model.

Schizophrenia detection using MultivariateEmpirical Mode Decomposition and entropy measures from multichannel EEG signal

Multivariate analysis of the EEG signal for the detection of Schizophrenia condition is proposed here. Multivariate Empirical Mode Decomposition (MEMD) is used to decompose the EEG signal into Intrinsic Mode Functions (IMF) signal. The randomness measure of the IMF signal is determined by computing the entropy of the signal. Five entropy measures such as Approximate entropy, Sample entropy, Permutation entropy, Spectral entropy, and Singular Value Decomposition entropy are measured from the IMF signal. These entropy measures showed a significant difference (p<0.01) between the healthy controls (HC) and Schizophrenia (SZ) subjects. Many state-of-the-art (SoA) machine learning classifiers are trained on the feature matrix obtained from entropy values of the IMF signal, amongst them Support Vector Machine based on Radial Basis Function (SVM-RBF) provided the highest accuracy and F1-score of 93% for the 95 features. The area under the curve (AUC) value of 0.9831 was obtained using this classifier. These performance metrics suggests that computation of randomness measure such as entropy in the multivariate IMF domain provided better discriminating power in detection of Schizophrenia condition from the multichannel EEG signal.

Lithium-ion batteries fault diagnostic for electric vehicles using sample entropy analysis method

Abstract Fault detection plays a vital role in the operation of lithium-ion batteries in electric vehicles. Typically, during the operation of battery systems, voltage signals are susceptible to noise interference. In this paper, a novel fault detection method based on the Empirical Mode Decomposition and Sample Entropy is proposed to identify battery faults under various operating conditions. Firstly, effective fault features are extracted through the proposed Empirical Mode Decomposition method by decomposing battery voltage signals and removing the noise interference during the voltage sampling process. Experiments are conducted to quantitatively illustrate the fault features extracted by the Empirical Mode Decomposition. Then, based on these extracted fault features, the Sample Entropy values are calculated to help accurately detect and locate the battery faults. Moreover, an evaluation strategy of the detected faults is designed to indicate the battery fault level. Finally, the effectiveness of the proposed approach is verified against real-world data measured from electric vehicles in the presence of regular and sudden faults.

Postural Control at Hospital Discharge after Spine Surgery–The Influence of the Type of Surgery, Pain Level, Radiculopathy and Stance Parameters

Information on postural control has gained recognition as an objective outcome measure after spine surgery. Insights on the patterns of posture and movement exhibited by patients using nonlinear tools can provide useful information on the structure of sway variability, adding value to the traditional quantification of its magnitude. The results should guide efficient therapeutic strategies to promote early recovery. To date, no clinical trial used this protocol at the time of hospital discharge. This study aims to analyse postural control under the acute effect of spine surgery. Thirty-seven patients submitted to decompressive or fusion spine surgery to treat degenerative pathologies or correct severe deformities were recruited (21 male, 16 female; mean age: 53,4 ± 18,1 y, range 14-80). Thirty-seven matching healthy volunteers included the control group. All participants performed a standard stabilometric test on a force platform for 180 seconds, patients being tested at the hospital on discharge day. Six more trials were randomly performed in different stance conditions: 1) eyes closed; 2) feet together; 3) performing a mental task; 4) on a high-density foam; 5) on a low-density foam; 6) holding a box. Values of sway range, mean velocity, elliptic area, and sample entropy, were extracted from centre-of-pressure displacement time-series and analysed using parametric statistical methods. Comparisons were made between control values and the effects of surgery, type of surgical procedure, level of back or leg pain, and residual radiculopathy. During the baseline task (eyes open) patients increased their total area of oscillation (p=0,016), mainly its range in the anteroposterior (AP) direction (p=0,010); the structure of that variability has less complexity and more regularity compared to control participants, showing lower sample entropy values (p=0,031 / AP direction). Differences were not significant in the mediolateral (ML) direction, and the mean velocity did not discriminate participants. Eyes closed condition, being on a high- density foam, or holding a box, exhibited the most robust cumulative significance. Interactions between all the parameters (the type of surgery, level of pain, presence of radiculopathy) may reveal more significant determinants to the postural patterns adopted. However, present data should be interpreted cautiously, being necessary broader samples for each sub-group in future studies, the replication of these measures in later follow-ups, and consider the effects of rehabilitation programs tailored in concordance to the main findings. At hospital discharge, patients having surgery for spine conditions show a significant increase in the magnitude of body sway and a postural pattern markedly regular with low complexity. Stabilometric trials performed with eyes closed, on high-density foam, or holding a box, demonstrate superior ability to discriminate patients from controls and should be used preferentially in future trials. Further studies using nonlinear measures after spine surgery are needed to clarify the underlying motor behaviour. Early intervention is recommended to correct postural impairments and facilitate optimal movement variability.

Detection and Classification of Alcoholics Using Electroencephalogram Signal and Support Vector Machine

Alcoholism may be recognized with the use of (EEG) analyzing signals. None-the-less, the analysis of the multi-channel signals of EEG is a complicated issue that usually needs performing complex computation operations and takes quite a long time to execute. The presented research will propose 13 optimal channel to feature extraction. In this research, an innovative horizontal visibility graph entropy (HVGE) method has been proposed for evaluating signals of EEG from controlled drinkers and alcoholic subjects and comparing against an approach of sample entropy (SaE). Values of HVGE and SaE have been obtained from 1200 records of bio-medical signals. While in classification step using SVM as classifier.

Vocal fold oscillation pattern changes related to loudness in patients with vocal fold mass lesions

IntroductionVocal fold mass lesions can affect vocal fold oscillation patterns and therefore voice production. It has been previously observed that perturbation values from audio signals were lower with increased loudness. However, how much the oscillation patterns change with gradual alteration of loudness is not yet fully understood.Material and methodsEight patients with vocal fold mass lesions were asked to perform a glide from minimum to maximum loudness on the vowel /i/, ƒo of 125 Hz for male or 250 Hz for female voices. During phonation the subjects were simultaneously recorded with transnasal high speed videoendoscopy (HSV, 20,000 fps), electroglottography (EGG), and an audio recording. Based on the HSV material the Glottal Area Waveform (GAW) was segmented and GAW parameters were computed.ResultsThe greatest vocal fold irregularities were observed at different values between minimum and maximum sound pressure level. There was a relevant discrepancy between the HSV and EGG derived open quotients. Furthermore, the EGG derived sample entropy and GAW values also evidenced different behavior.ConclusionsThe amount of vocal fold irregularity changes with varying loudness. Therefore, any evaluation of the voice should be performed under different loudness conditions. The discrepancy between EGG and GAW values appears to be much stronger in patients with vocal fold mass lesions than those with normal physiological conditions.Level of evidence4.

Nonlinear measures in posturography compared to linear measures based on yoga poses performance

Yoga is known as a type of exercise that combines physical, mental and spiritual aspects. There has not been much research on the postural control in various yoga poses. The aim of this study was to examine CoP regularity in both yoga instructors and novices during the performance of four yoga poses, and to verify the sensitivity of linear and nonlinear methods for assessing postural stability. The dynamic characteristics of CoP fluctuations were examined using linear and nonlinear methods on a group of 22 yoga instructors (Y) and 18 age-matched non-practitioners of yoga (NY). The study involved maintaining a balance for 20 seconds while performing four yoga poses. Conventional analysis of CoP trajectories showed that NY and Y exhibited similar control of postural sway, as indicated by similar CoP path-length and area values observed in both groups. These results suggest that the special balance yoga training received by Y may not have an impact on less challenging balance conditions, such as the poses used in this experiment. Interestingly, nonlinear dynamical analysis of CoP showed that Y exhibited less CoP regularity and more complex signal than NY, as evidenced by higher values of sample entropy and fractal dimension. The results shed light on the surplus values of CoP trajectories in the nonlinear dynamical analysis to gain further insight into the mechanisms involved in posture control.

Threshold determination method of Duffing chaotic system based on multi-scale entropy

Entropy is one of the parameters describing the state of matter in thermodynamics, it can be used to measure the degree of confusion. The entropy of the signal can be used to express the complexity of the signal. The threshold for the transition of the Duffing chaotic system from the critical chaotic state to the large-scale periodic state is called the transition threshold. It is an important parameter for the analysis of chaotic systems, and its solution method is one of the problems urgently to be solved in chaos theory. If the jump threshold is smaller than the real threshold of the system, it will affect its detection signal-to-noise ratio. If the jump threshold is larger than the real threshold, it will cause incorrect detection results, so it is very important to accurately determine the jump threshold. In this study, we found that the multiscale sample entropy value of the Duffing system is significantly different when the system is in the chaotic state and the periodic state, when the system is in a chaotic state, the entropy value is larger, when the system is in a periodic state, the entropy value is smaller, and when the system enters the periodic state, the multiscale entropy value tends to be stable, this paper proposes to use this phenomenon to determine the transition threshold by analyzing the relationship between the entropy of the system and the amplitude of the driving force. When the entropy value is obviously smaller and tends to be stable, the corresponding driving force amplitude is the jump threshold. using this method, the jump threshold of the sinusoidal signal and square wave signal detection system is calculated, the results show that the method is fast, accurate and simple to calculate. However, this method may have a problem that the calculated threshold value is smaller than the real threshold value, our analysis is that the random selection of the subsequence used for calculation causes the calculation threshold value to be too small, so the method is improved in conjunction with genetic algorithm, using genetic algorithm to find the most complicated subsequence in the whole sequence, then this subsequence is used to solve the threshold, Through a large number of calculations and analysis, it can be seen that the problem of a small threshold is no longer present, and the improved method can obtain the jump threshold of the Duffing system very accurately.

Gear Fault Diagnosis Based on Genetic Mutation Particle Swarm Optimization VMD and Probabilistic Neural Network Algorithm

The decomposition number $K$ and penalty factor $\alpha $ in the variational mode decomposition (VMD) algorithm have a great influence on the decomposition effect and the accuracy of subsequent fault diagnosis. Therefore, a gear fault diagnosis method based on genetic mutation particle swarm optimization VMD and probabilistic neural network (GMPSO-VMD-PNN) algorithm is proposed in this paper. Firstly, the GMPSO algorithm is used to optimize the $[K,\alpha]$ parameter combination in the VMD algorithm, and the optimal $[K,\alpha]$ parameter combination of each gear fault vibration signal to be decomposed is selected. Then, the gear fault vibration signal is decomposed into several intrinsic mode functions (IMFs) by VMD, and the sample entropy value of each IMFs is extracted to form the feature vector of subsequent fault diagnosis. Finally, the characteristic vector of gear fault vibration signal is input into PNN model, and gear fault is accurately classified. By comparing with fixed parameter VMD algorithm, empirical mode decomposition (EMD) and complete ensemble empirical mode decomposition adaptive noise (CEEMDAN) algorithm, the superiority of this method in gear fault diagnosis is verified. Therefore, the GMPSO-VMD-PNN algorithm proposed in this paper has certain application value for gear fault diagnosis.

Short-term wind speed prediction model based on GA-ANN improved by VMD

Wind power, as a potential new energy generation technology, is gradually developing towards to the mainstream energy in the world. However, the inherent random volatility of wind brings severe challenges to the safe operation of the grid and the reliability of power supply, one of the effective ways to solve the problem is to improve the accuracy of wind speed prediction. However, most of wind speed prediction model cannot well mine the inherent regularity of wind speed data. Therefore, this paper introduces variational mode decomposition (VMD) algorithm. And the Short-term Wind Speed Prediction Model based on GA-ANN improved by VMD is proposed, which can effectively improve the accuracy of wind speed prediction. Firstly, hierarchical cluster method in this paper is employed to extract the historical data with high similarity to the predicted day. And then the appropriate number of decompositions K is selected by judging the value of sample entropy, so that the extracted historical data is decomposed into K subsequences by the variational mode decomposition. Next, with the global optimization ability of genetic algorithm, the artificial neural network is optimized to improve the forecasting performance. Finally, the short-term wind speed forecasting model based on GA-ANN improved by VMD is employed to predict the wind speed of each subsequence and superimposed them to obtain the final wind speed prediction sequence. The results in this paper show that (1) the model can find the periodic fluctuation of wind speed through historical data by hierarchical cluster method, so that significantly improving the accuracy of short-term wind speed prediction; (2) for the wind speed prediction, the error value of GA-ANN model is smaller than that of BP neural network; (3) in view of the inherent nature of the wind, the model proposed in this paper can use VMD to decompose the wind speed signal to obtain different scale fluctuations or trends, so as to fully exploit the potential information of wind speed, and obtain more accurate prediction results. The research work can help the relevant departments of the power system to accurately assess the risk of power grid operation, make a reasonable generation plan, effectively reduce the cost of power operation, and then greatly promote the development of green energy.

Effects of Nonstationarity on Muscle Force Signals Regularity During a Fatiguing Motor Task.

Physiological signals present fluctuations that can be assessed from their temporal structure, also termed complexity. The complexity of a physiological signal is usually quantified using entropy estimators, such as Sample Entropy. Recent studies have shown a loss of force signal complexity with the development of neuromuscular fatigue. However, these studies did not consider the stationarity of the force signals which is an important prerequisite of Sample Entropy measurements. Here, we investigated the effect of the potential nonstationarity of force signals on the kinetics of neuromuscular fatigue-induced change in force signal's complexity. Eleven men performed submaximal intermittent isometric contractions of knee extensors until exhaustion. Neuromuscular fatigue was assessed from changes in voluntary and electrically evoked contractions. Sample Entropy values were computed from submaximal force signals throughout the fatiguing task. The Dickey-Fuller test was used to statistically investigate the stationarity of force signals and the Empirical Mode Decomposition was applied to detrend these signals. Maximal voluntary force, central voluntary activation and muscle twitch decreased throughout the task (all ), indicating the development of global, central and peripheral fatigue, respectively. We found an increase in Sample Entropy with fatigue ( p = 0.024 ) when not considering the nonstationarity of force signals (i.e., 43% of nonstationary signals). After applying the Empirical Mode Decomposition, we found a decrease in Sample Entropy with fatigue ( p = 0.002 ). These findings confirm the presence of nonstationarity in force signals during submaximal isometric contractions which influences the kinetics of Sample Entropy with neuromuscular fatigue.

Percussion-based bolt looseness monitoring using intrinsic multiscale entropy analysis and BP neural network

In this paper, a novel percussion-based bolt looseness monitoring approach using intrinsic multiscale entropy analysis and back propagation (BP) neural network is proposed. The percussion-caused audio signals of bolt connection are decomposed by complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) to obtain intrinsic mode functions (IMFs). The IMFs are in order of high-to-low instantaneous frequencies and contain underlying dynamical characteristics of audio signals. Multiscale sample entropy (MSE) is improved by smoothed coarse graining process, and the proposed improved multiscale sample entropy (IMSE) values of certain IMFs are adopted as condition indicators in bolt looseness monitoring. The intrinsic multiscale entropy analysis consisting of CEEDMAN and IMSE extracts underlying dynamical characteristics during percussion-caused audio signal processing to identify bolt looseness conditions. The condition indicators, namely IMSE values at smallest scale factors, are employed as input of BP neural network for training and testing, to achieve accurate and stable bolt looseness condition monitoring. The effectiveness and superiority of the proposed approach have been validated by theoretical derivation and practical experimental researches, and the adaptivity and robustness of the proposed approach are also illustrated. The results of the research in this paper demonstrate the proposed approach is promising in practical applications of bolt looseness monitoring.

Altered movement strategy of chronic ankle instability individuals with postural instability classified based on Nyquist and Bode analyses

BackgroundThe aim of the current study was to assess movement strategies during a single leg balance in chronic ankle instability individuals with unstable postural control strategy identified by Nyquist and Bode analyses in conjunction with sample entropy. MethodsThirty-three participants with self-reported chronic ankle instability and 22 healthy controls performed single-leg eyes closed static balance trials. The sagittal and frontal plane kinematics in the lower extremity and trunk as well as center of pressure trajectories were recorded during three, 20-second trials. The Nyquist and Bode stability analyses, which classify center of pressure waveforms as stable based on the resulting gain and phase margins, were performed to identify the presence of postural control deficits. Sample entropy was implemented to analyze movement strategies during the task. FindingsBased on the Nyquist and Bode stability analyses, we included 19 out of 33 chronic ankle instability participants with unstable postural control strategy and 16 out of 22 controls with stable postural control strategy in the final analyses. Chronic ankle instability participants demonstrated a significantly lower sample entropy value in sagittal and frontal plane trunk kinematics and sagittal plane hip kinematics compared to the controls. No between-group differences existed in other kinematic measures. InterpretationThe lower sample entropy values in participants with chronic ankle instability indicates that those with postural control deficits may increase reliance on the trunk and hip joint contributions to the maintenance of postural control, reflecting changes in the sensorimotor constraints on movement patterns during the task.

Renyi Distribution Entropy Analysis of Short-Term Heart Rate Variability Signals and Its Application in Coronary Artery Disease Detection.

Coronary artery disease (CAD) is a life-threatening condition that, unless treated at an early stage, can lead to congestive heart failure, ischemic heart disease, and myocardial infarction. Early detection of diagnostic features underlying electrocardiography signals is crucial for the identification and treatment of CAD. In the present work, we proposed novel entropy called Renyi Distribution Entropy (RdisEn) for the analysis of short-term heart rate variability (HRV) signals and the detection of CAD. Our simulation experiment with synthetic, physiological, and pathological signals demonstrated that RdisEn could distinguish effectively among different subject groups. Compared to the values of sample entropy or approximation entropy, the RdisEn value was less affected by the parameter choice, and it remained stable even in short-term HRV. We have developed a combined CAD detection scheme with RdisEn and wavelet packet decomposition (WPD): (1) Normal and CAD HRV beats obtained were divided into two equal parts. (2) Feature acquisition: RdisEn and WPD-based statistical features were calculated from one part of HRV beats, and student’s t-test was performed to select clinically significant features. (3) Classification: selected features were computed from the remaining part of HRV beats and fed into K-nearest neighbor and support vector machine, to separate CAD from normal subjects. The proposed scheme automatically detected CAD with 97.5% accuracy, 100% sensitivity and 95% specificity and performed better than most of the existing schemes.

Arrhythmia classification based on multi-domain feature extraction

Arrhythmia is a common abnormality of cardiac electrical activity. Arrhythmia classification has enormous significance for the clinical diagnosis of cardiovascular diseases. In this study, a method of multi-domain electrocardiogram feature extraction was put forward as to classify arrhythmia precisely. The RR intervals were extracted as time domain feature. The fifth level approximation coefficients of wavelet decomposition were adopted to represent frequency domain feature. Besides, the sample entropy values of six wavelet coefficients were employed as nonlinear feature. These three features were fed to classifier for automated diagnosis. Furthermore, ten-fold cross-validation scheme was adopted to train and test classifier whose parameters were optimized by genetic algorithm. In this study, eight classes of the most frequently occurring arrhythmia from MIT-BIH arrhythmia database were validated. The result turned out that the SVM classifier yields an average accuracy of 99.70%. Compared with the existing methods, the proposed method shows better results.

Brain Complexity in Children with Mild and Severe Autism Spectrum Disorders: Analysis of Multiscale Entropy in EEG.

Multiscale entropy (MSE) model quantifies the complexity of brain functions by measuring the entropy across multiple time-scales. Although MSE model has been applied in children with Autism spectrum disorders (ASD) in previous studies, they were limited to distinguish children with ASD from those normally developed without corresponding severity level of their autistic features. Therefore, we aims toexplore and to identify the MSE features and patterns in children with mild and severe ASD by using a high dense 64-channel array EEG system. Thisstudy is a cross-sectional study, where 36 children with ASD were recruited and classified into two groups: mild and severe ASD (18 children in each). Three calculated outcomes identified brain complexity of mild and severe ASD groups: averaged MSE values, MSE topographical cortical representation, and MSE curve plotting. Averaged MSE values of children with mild ASD were higher than averaged MSE value in children with severe ASD in right frontal (0.37 vs. 0.22, respectively, p=0.022), right parietal (0.31 vs. 0.13, respectively, p=0.017), left parietal (0.37 vs. 0.17, respectively, p=0.018), and central cortical area (0.36 vs. 0.21, respectively, p=0.026). In addition, children with mild ASD showed a clear and more increase in sample entropy values over increasing values of scale factors than children with severe ASD. Obtained data showed different brain complexity (MSE) features, values and topographical representations in children with mild ASD compared with those with severe ASD. As a result of this, MSE could serve as a sensitive method for identifying the severity level of ASD.

ECG arrhythmia classification using artificial intelligence and nonlinear and nonstationary decomposition

ECG signals reflect all the electrical activities of the heart. Consequently, it plays a key role in the diagnosis of the cardiac disorder and arrhythmia detection. Based on tiny alterations in the amplitude, duration and morphology of the ECG, computer-aided diagnosis has become a recognized approach to classifying the heartbeats of different types of arrhythmia. In this study, a classification approach was developed based on the non-linearity and nonstationary decomposition methods due to the nature of the ECG signal. Complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) was used to obtain intrinsic mode functions (IMFs). Established on those IMFs, four parameters have been computed to construct the feature vector. Average power, coefficient of dispersion, sample entropy and singular values have been calculated as parameters from the first six IMFs. Then, ANN has been adopted to apply the feature vector using them and classify five different arrhythmia heartbeats downloaded from Physionet in the MIT–BIH database. To evaluate the performance of the proposed method and compare it with previous algorithms, confusion matrix, sensitivity (SEN), specificity (SPE), accuracy (ACC) and ROC have been used. It has been found that performance from the CEEMDAN and ANN is better than all existing methods, where the SEN is 99.7%, SPE is 99.9%, ACC is 99.9%, and ROC is 01.0%.