Second-order Difference Plot Research Articles

Automatic detection of Alzheimer's disease from EEG signals using an improved AFS-GA hybrid algorithm.

Alzheimer's Disease (AD) is a neurodegenerative disorder characterized by energy diffusion and partial disconnection in the brain, with its main feature being an insidious onset and subtle clinical symptoms. Electroencephalogram (EEG) as a primary tool for assessing and aiding in the diagnosis of brain diseases has been widely used in AD detection. Accurate diagnosis is crucial for preventing the transition from early cognitive impairment to AD and providing early treatment for AD patients. This study aims to establish a hybrid model based on the Improved Artificial Fish Swarm Algorithm (IAFS) and Genetic Algorithm (GA)-IAFS-GA, to determine the optimal channel combination for AD detection under multiple EEG signals. Geometric features and complexity features of AD EEG signals were extracted using Second Order Difference Plot (SODP) and entropy analysis across the full frequency band. Subsequently, Pearson correlation was used for feature ranking, selecting the six least correlated features for each channel. The Relief algorithm was then used to fuse these selected features, with one fused feature representing one channel. Based on this, a feature selection optimization algorithm, IAFS-GA, combining the improved artificial fish swarm algorithm and genetic algorithm, was proposed. Finally, the feature combination was input into a Naive Bayes classifier for the identification of AD patients and normal controls. The feature combination was input into a Naive Bayes classifier for the identification of AD patients and normal controls. Using a five-fold cross-validation strategy across the entire frequency band, the classification accuracy reached 93.53%, with a sensitivity of 98.74%, specificity of 98.25%, and an AUC area of 97.82%. This framework can quickly select appropriate brain channels to enhance the efficiency of detecting AD and other neurological diseases. Moreover, it is the first time that an improved artificial fish swarm genetic combination algorithm and SODP features has been used for channel selection in EEG, proving to be an effective method for AD detection. It is based on SODP analysis, entropy analysis, and intelligent algorithms, which can assist clinicians in rapidly diagnosing AD, reducing the misdiagnosis rate of false positives, and expanding our understanding of brain function in patients with neurological diseases.

Epileptic Seizure Detection from Decomposed EEG Signal through 1D and 2D Feature Representation and Convolutional Neural Network

Electroencephalogram (EEG) has emerged as the most favorable source for recognizing brain disorders like epileptic seizure (ES) using deep learning (DL) methods. This study investigated the well-performed EEG-based ES detection method by decomposing EEG signals. Specifically, empirical mode decomposition (EMD) decomposes EEG signals into six intrinsic mode functions (IMFs). Three distinct features, namely, fluctuation index, variance, and ellipse area of the second order difference plot (SODP), were extracted from each of the IMFs. The feature values from all EEG channels were arranged in two composite feature forms: a 1D (i.e., unidimensional) form and a 2D image-like form. For ES recognition, the convolutional neural network (CNN), the most prominent DL model for 2D input, was considered for the 2D feature form, and a 1D version of CNN was employed for the 1D feature form. The experiment was conducted on a benchmark CHB-MIT dataset as well as a dataset prepared from the EEG signals of ES patients from Prince Hospital Khulna (PHK), Bangladesh. The 2D feature-based CNN model outperformed the other 1D feature-based models, showing an accuracy of 99.78% for CHB-MIT and 95.26% for PHK. Furthermore, the cross-dataset evaluations also showed favorable outcomes. Therefore, the proposed method with 2D composite feature form can be a promising ES detection method.

Unravelling COVID-19 waves in Rio de Janeiro city: Qualitative insights from nonlinear dynamic analysis

Since the COVID-19 pandemic was first reported in 2019, it has rapidly spread around the world. Many countries implemented several measures to try to control the virus spreading. The healthcare system and consequently the general quality of life population in the cities have all been significantly impacted by the Coronavirus pandemic. The different waves of contagious were responsible for the increase in the number of cases that, unfortunately, many times lead to death. In this paper, we aim to characterize the dynamics of the six waves of cases and deaths caused by COVID-19 in Rio de Janeiro city using techniques such as the Poincaré plot, approximate entropy, second-order difference plot, and central tendency measures. Our results reveal that by examining the structure and patterns of the time series, using a set of non-linear techniques we can gain a better understanding of the role of multiple waves of COVID-19, also, we can identify underlying dynamics of disease spreading and extract meaningful information about the dynamical behavior of epidemiological time series. Such findings can help to closely approximate the dynamics of virus spread and obtain a correlation between the different stages of the disease, allowing us to identify and categorize the stages due to different virus variants that are reflected in the time series.

The Use of Empirical Mode Decomposition on Heart Rate Variability Signals to Assess Autonomic Neuropathy Progression in Type 2 Diabetes

In this study, we investigated the use of empirical mode decomposition (EMD)-based features extracted from electrocardiogram (ECG) RR interval signals to differentiate between different levels of cardiovascular autonomic neuropathy (CAN) in patients with type 2 diabetes mellitus (T2DM). This study involved 60 participants divided into three groups: no CAN, subclinical CAN, and established CAN. Six EMD features (area of analytic signal representation—ASRarea; area of the ellipse evaluated from the second-order difference plot—SODParea; central tendency measure of SODP—SODPCTM; power spectral density (PSD) peak amplitude—PSDpkamp; PSD band power—PSDbpow; and PSD mean frequency—PSDmfreq) were extracted from the RR interval signals and compared between groups. The results revealed significant differences between the noCAN and estCAN individuals for all EMD features and their components, except for the PSDmfreq. However, only some EMD components of each feature showed significant differences between individuals with noCAN or estCAN and those with subCAN. This study found a pattern of decreasing ASRarea and SODParea values, an increasing SODPCTM value, and a reduction in PSDbpow and PSDpkamp values as the CAN progressed. These findings suggest that the EMD outcome measures could contribute to characterizing changes associated with CAN manifestation in individuals with T2DM.

Classification of focal and non-focal EEG signals using optimal geometrical features derived from a second-order difference plot of FBSE-EWT rhythms

Background/introduction:Manual detection and localization of the brain’s epileptogenic areas using electroencephalogram (EEG) signals is time-intensive and error-prone. An automated detection system is, thus, highly desirable for support in clinical diagnosis. A set of relevant and significant non-linear features plays a major role in developing a reliable, automated focal detection system. Methods:A new feature extraction method is designed to classify focal EEG signals using eleven non-linear geometrical attributes derived from the Fourier–Bessel series expansion-based empirical wavelet transform (FBSE-EWT) segmented rhythm’s second-order difference plot (SODP). A total of 132 features (2 channels × 6 rhythms × 11 geometrical attributes) were computed. However, some of the obtained features might be non-significant and redundant features. Hence, to acquire an optimal set of relevant non-linear features, a new hybridization of ‘Kruskal–Wallis statistical test (KWS)’ with ‘VlseKriterijuska Optimizacija I Komoromisno Resenje’ termed as the KWS-VIKOR approach was adopted. The KWS-VIKOR has a two-fold operational feature. First, the significant features are selected using the KWS test with a p-value lesser than 0.05. Next, the multi-attribute decision-making (MADM) based VIKOR method ranks the selected features. Several classification methods further validate the efficacy of the features of the selected top n%. Results:The proposed framework has been evaluated using the Bern-Barcelona dataset. The highest classification accuracy of 98.7% was achieved using the top 35% ranked features in classifying the focal and non-focal EEG signals with the least-squares support vector machine (LS-SVM) classifier. Conclusions:The achieved results exceeded those reported through other methods. Hence, the proposed framework will more effectively assist the clinician in localizing the epileptogenic areas.

Epileptic Seizure Detection Using Geometric Features Extracted from SODP Shape of EEG Signals and AsyLnCPSO-GA.

Epilepsy is a neurological disorder that is characterized by transient and unexpected electrical disturbance of the brain. Seizure detection by electroencephalogram (EEG) is associated with the primary interest of the evaluation and auxiliary diagnosis of epileptic patients. The aim of this study is to establish a hybrid model with improved particle swarm optimization (PSO) and a genetic algorithm (GA) to determine the optimal combination of features for epileptic seizure detection. First, the second-order difference plot (SODP) method was applied, and ten geometric features of epileptic EEG signals were derived in each frequency band (δ, θ, α and β), forming a high-dimensional feature vector. Secondly, an optimization algorithm, AsyLnCPSO-GA, combining a modified PSO with asynchronous learning factor (AsyLnCPSO) and the genetic algorithm (GA) was proposed for feature selection. Finally, the feature combinations were fed to a naïve Bayesian classifier for epileptic seizure and seizure-free identification. The method proposed in this paper achieved 95.35% classification accuracy with a tenfold cross-validation strategy when the interfrequency bands were crossed, serving as an effective method for epilepsy detection, which could help clinicians to expeditiously diagnose epilepsy based on SODP analysis and an optimization algorithm for feature selection.

Epileptic seizure detection in EEG using mutual information-based best individual feature selection

Epilepsy is a group of neurological disorders that affect normal brain activities and human behavior. Electroencephalogram based automatic epileptic seizure detection has significant applications in epilepsy treatment and medical diagnosis. In this study, a novel epileptic seizure detection method is proposed with a combination of empirical mode decomposition, mutual information-based best individual feature (MIBIF) selection algorithm and multi-layer perceptron neural network. Initially, fixed length EEG epochs are decomposed into amplitude and frequency-modulated components called intrinsic mode functions (IMFs). Three features named ellipse area of second-order difference plot, variance and fluctuation index are calculated from first few IMFs. The most significant features are then selected from the calculated features using the MIBIF algorithm to produce a final feature set. Later, the generated feature set is fed into the multi-layer perceptron neural network (MLPNN) classifier. Two well-known benchmark epileptic EEG datasets are used in this study for experimental evaluations. The result of proposed approach shows a significant performance improvement compared to the recent state-of-the-art methods.

Graphical representation and variability quantification of handwriting signals: New tools for Parkinson’s disease detection

A reliable computer-aided method for Parkinson’s disease (PD) detection can slow down its progression and improve the life quality of patients. In this study, a new non-invasive and cost-effective method based on the online analysis of handwriting signals has been proposed. First, the dynamic handwriting signals have been converted into two graphical representations of the variability rate. Then, two new feasible features, including area of the analytic signal representation and area of the second-order difference plot, have been used to quantify the variability rate of handwriting signals. A statistical test and support vector machine classifier have been applied in a comparative study to test the impact of each variability feature, writing task, and time sequence on the detection performance, separately.The obtained results on PaHaW database with 35 Parkinson’s disease patients and 36 healthy controls have shown that the proposed method of handwriting variability feature extraction has effective performance and the capability for the PD detection. It has achieved an average sensitivity of 86.26% with only two types of features, providing a trade-off between the performance, the computational complexity, and interpretability of the motor patterns from the point of view of clinicians and neuropsychologists. X-coordinate time-series and writing a sentence can achieve superior accuracy and robustness in the presence of individual differences. The experimental results have demonstrated that extracting the variability features that used graphical representations of the global changes in oscillatory mode has the ability to clinically describe the pathological dynamics of the handwriting signals for the PD identification.

Integrating old and new complexity measures toward automated seizure detection from long-term video EEG recordings

SummaryAutomated seizure detection in long-term video-EEG recordings is far from being integrated into common clinical practice. Here, we leverage classical and state-of-the-art complexity measures to robustly and automatically detect seizures from scalp recordings. Brain activity is scored through eight features, encompassing traditional time domain and novel measures of recurrence. A binary classification algorithm tailored to treat unbalanced dataset is used to determine whether a time window is ictal or non-ictal from its features. The application of the algorithm on a cohort of ten adult patients with focal refractory epilepsy indicates sensitivity, specificity, and accuracy of 90%, along with a true alarm rate of 95% and less than four false alarms per day. The proposed approach emphasizes ictal patterns against noisy background without the need of data preprocessing. Finally, we benchmark our approach against previous studies on two publicly available datasets, demonstrating the good performance of our algorithm.

Emotion recognition from EEG signals using empirical mode decomposition and second-order difference plot

Emotion recognition from electroencephalography (EEG) signals is a very cost-effective method to monitor the general well-being of an individual, an employee of an organization, or to cater to mental health patients. But it is a challenging task owing to the non-stationarity of the EEG signals. Extracting relevant features through signal processing techniques that can be used to classify patterns in the EEG signal leading to different emotions is a difficult task. A dataset for emotion analysis with physiological signals DEAP [1] consists of EEG signals of 32 participants are categorized on the quadrant of valence, arousal, dominance, and liking, which signifies how they are associated with different emotions. In this paper, an efficient classifier for emotion/quadrant recognition from EEG signals with exceptional accuracy is presented. The data preprocessing strategy adapted is Empirical Mode Decomposition (EMD), which decomposes the signals into several oscillatory Intrinsic Mode Functions (IMF). Features are extracted from Second order difference plots (SODP) are area, mean, and central tendency measure of the elliptical region. Wilcoxson Test was performed to ensure the statistical significance of the extracted features with p < 0.05. Support Vector Machine (SVM) and 2-hidden layer Multilayer Perceptron is used for binary and multi-class classification of emotions in the quadrant of valence, arousal, dominance, and liking. The performance of the models is evaluated by statistical parameters- sensitivity, specificity, and accuracy. The classification results from Multilayer Perceptron outperformed that of SVM, and the maximum accuracy achieved, is 100 % in the binary classification of High and Low Arousal space.

Phase entropy: a new complexity measure for heart rate variability

Objective: Information entropy is generally employed for analysing the complexity of physiological signals. However, most definitions of entropy estimate the degree of compressibility and thus quantify the randomness. Physiological signals are very complex because of nonlinear relationships and interactions between various systems and subsystems of the body. Therefore, analysis of randomness may not be sufficient to describe this complexity. To analyse the complexity of heart rate variability (HRV), a new entropy method, phase entropy (PhEn), has been proposed as a quantification of two-dimensional phase space. Approach: The second-order difference plot (SODP), a two-dimensional phase space, provides a visual summary of the rate of variability. The distribution of scatter points in a SODP provides information about the dynamics of the underlying system. PhEn estimates the Shannon entropy of the weighted distribution in a coarse-grained SODP. Main results: The performance of PhEn has been evaluated using simulated signals, synthetic HRV signals and real HRV signals. PhEn shows a better discriminating power and stability than other entropy measures. It is computationally efficient. Moreover, it has the ability to assess temporal asymmetry of physiological signals. Significance: PhEn quantifies the multiplicity and rate of variability associated with physiological signals. It is sensitive to time irreversibility. Therefore, it appears to be a promising tool for analysing physiological signals such as HRV.

Automated identification for autism severity level: EEG analysis using empirical mode decomposition and second order difference plot

BackgroundPrevious automated EEG-based diagnosis of autism spectrum disorders (ASD) using various nonlinear EEG analysis methods were limited to distinguish only children with ASD from those normally developed without approaching their autistic features severity. ObjectivesIdentifying potential differences between children with mild and sever ASD based on EEG analysis using empirical mode decomposition (EMD) and second-order difference plot (SODP) models, and determining the accuracy of such model outcome measures to distinguish ASD severity levels. MethodsResting-state EEG data recorded for 36 children, who divided equally into two matched groups of mild and sever ASD. EMD analysis was applied to their EEG data to identify intrinsic mode functions (IMFs) features, SODP patterns, elliptical area and central tendency measure (CTM) values. Artificial neural network then used to determine the accuracy of this models outcome measures in distinguishing between the two ASD groups. ResultsChildren with sever ASD showed smaller, less twitches and oscillation of IMFs features, more stochastic SODP plotting, less CTM values, and higher ellipse area values compared to the children with mild ASD, which indicates their greater EEG variabilities and their greater inability to suppress their improper behavior. ANN ended with model sensitivity and specificity of 100% and 94.7%, respectively, and 97.2% overall accuracy of distinguishing between ASD groups. ConclusionChildren with sever and mild ASD had different IMFs features, SODP plotting, elliptical area and CTM values. In addition, these EMD outcome measures could serve as a sensitive automated tool to distinguish different severity levels in children with ASD.

Psychological stress detection using phonocardiography signal: An empirical mode decomposition approach

Psychological stress is a part of the modern day lifestyle and affects human cognitive abilities. The well-established relation between stress and a host of behavioural and somatic pathological conditions emphasizes the need for timely detection of psychological stress. The purpose of this research work is to present a novel framework for psychological stress detection using Phonocardiography (PCG) signal based on Empirical Mode Decomposition (EMD) technique. The methods like Electroencephalography (EEG) and Electrocardiography (ECG) provide important biophysical measures for psychological stress detection but are expensive or require a proper clinical setup. Whereas, the acoustic heart sound or PCG signals carry significant information and can be easily acquired. In this research, pre-competitive (or exam related) psychological stress is detected from the S1-S1 interval of PCG signal referred as Inter-beat Interval (IBI). The IBI signal is decomposed to Intrinsic Mode Functions (IMF) using EMD technique which is suitable for non-linear and non-stationary signal analysis. The non-linear features namely Area of Analytic Signal Representation (AASR), Log of Area of ellipse from Second-order Difference Plot (LASODP), Root Mean Square value of IMF (RmsIMF), Shannon Entropy (ShEnt) and Fuzzy Entropy (FzEnt) were evaluated from IMFs of IBI signals. The first set of experiments comprises of deviation analysis in stressed signals from mean baseline values of the features in non-stressed signals. Thereafter, in the second set of experiments, Kruskal-Wallis statistical test has been used to check the significance and discrimination ability of the features. Then the features which showed maximum deviation and are statistically significant have been selected and fed to least-square support vector machine (LS-SVM) classifier. The 10-fold cross-validation has been used to make the system more reliable and robust. In this work, the average accuracy of 93.14% in classifying stressed and non-stressed signals has been achieved using Radial Basis Function (RBF) kernel. The results indicate that the proposed features provide better discrimination ability than well-known low-frequency to high-frequency power ratio (LF/HF) parameter of the ECG signal. The novelty of this study is the use of PCG signals for psychological stress detection and the use of subject-specific baseline template to incorporate the individual cardiovascular characteristic behaviour and stress responses. The proposed novel methodology of using PCG signals for psychological stress detection is cost-effective and is suitable for home-care, telemedicine and in rural health care centres especially in developing countries.

Computer-aided autism diagnosis via second-order difference plot area applied to EEG empirical mode decomposition

Autism spectrum disorder (ASD) is a name for a group of neurodevelopmental conditions that are characterized by some degree of impairment in social interaction, verbal and non-verbal communication, and difficulty in symbolic capacity and repetitive behaviors. The only protocol followed currently for ASD diagnosis is the qualitative behavioral assessment by experts through internationally established descriptive scaling standards. The assessment can, therefore, be affected by the degree of the evaluator experience as well as by the level of the descriptive standard robustness. This paper presents an EEG-based quantitative approach intended for automatic discrimination between children with typical neurodevelopment and children with ASD. The suggested work relies on second-order difference plot (SODP) area as a discriminative feature: First, every EEG channel in a 64 electrode cap—for every volunteer—is decomposed into intrinsic mode functions (IMFs) by empirical mode decomposition (EMD). Next, the second-order difference plot for the first ten intrinsic mode functions—of every channel—is sketched. Third, the value of the elliptical area —for every plot—is calculated. The 95% confidence ellipse area is used as the discriminative feature. Fourth, paired t-student test is applied to the vectors consisting of discriminative feature values for counterpart channels/IMFs (e.g., channel FPz/IMF7 in autistic and neurotypical) for all volunteers. Finally, principal component analysis (PCA) and neural network (NN) are applied to the SODP area feature matrix for two-class classification (ASD and neurotypical). Moreover, the 3D mapping of EEG SODP area values was implemented and analyzed. The obtained results show that the conducted t-student tests yield values of less than 0.05, and that the NN two-class classification based on SODP features leads to a 94.4% accuracy, which indicates significant differences between SODP area values of children with neurotypical development and those diagnosed with ASD. The obtained results have also been emphasized by the analysis of the findings of the performed 3D mapping.

Deep learning with 3D-second order difference plot on respiratory sounds

Abstract The second order difference plot (SODP) is a nonlinear signal analysis method that visualizes two consecutive data points for many types of biomedical signals. The proposed method is based on analysing quantization of 3D-space which is originated using three consecutive data points in signal. The obtained 3D-SODP space was segmented into 3–10 spaces using octants, spheres and cuboid polyhedrons of which centroids are at the origin. Lung sound is an indispensable tool for respiratory and cardiac diseases. The study is focused on classifying the lung sounds from at risk level and the interior level of chronic obstructive pulmonary disease (COPD). The COPD is one of the most deadliest and common respiratory diseases which come into existence as a consequence of smoking. The smokers for a few years are qualified as at risk level of COPD (COPD-0). The 12 channels of lung sounds from the RespiratoryDatabase@TR were utilized in the analysis of the proposed 3D-SODP quantization method. The lung sounds are auscultated synchronously from posterior and anterior sides of subjects using two digital stethoscopes by a pulmonologist clinician in Antakya State Hospital, Turkey. Deep Belief Networks (DBN) algorithm was preferred in the classification stage. It has a greedy layer-wise pre-training which is based on restricted Boltzmann machines and optimizes the pre-trained weights using supervised iterations. The proposed DBN model had 2 hidden layers with 270 and 580 neurons, respectively. The conjunction usage of 3D-SODP quantization features with the DBN separated the lung sounds from different levels of COPD with high classification performance rates of 95.84%, 93.34% and 93.65% for accuracy, sensitivity and specificity, respectively. The results indicate that the 3D-SODP quantization on respiratory sounds has ability to diagnose the levels of the COPD using the deep learning model. Especially, the octant-based quantization is effective on lung sounds with high generalization capability using a small number of feature set dimension.

An Emotion Recognition Approach based on Wavelet Transform and Second-Order Difference Plot of ECG

Emotion, as a psychophysiological state, plays an important role in human communications and daily life. Emotion studies related to the physiological signals are recently the subject of many researches. In This study a hybrid feature based approach was proposed to examine affective states. To this effect, Electrocardiogram (ECG) signals of 47 students were recorded using pictorial emotion elicitation paradigm. Affective pictures were selected from the International Affective Picture System and assigned into four different emotion classes. After extracting approximate and detail coefficients of Wavelet Transform (WT / Daubechies 4 at level 8), two measures of the second-order difference plot (CTM and D) were calculated for each wavelet coefficient. Subsequently, Least Squares Support Vector Machine (LS-SVM) was applied to discriminate between affective states and the rest. The statistical analysis indicated that the density of CTM in the rest is distinctive from the emotional categories. In addition, the second-order difference plot measurements at the last level of WT coefficients showed significant differences between the rest and emotion categories. Applying LS-SVM, the maximum classification rate of 80.24 % was reached for discrimination between rest and fear. The results of this study indicate the usefulness of the WT in combination with nonlinear technique in characterizing emotional states.

Depth of anaesthesia assessment using interval second‐order difference plot and permutation entropy techniques

This study presents a new method to apply the interval second-order difference plot (ISODP) and interval permutation entropy (IPE) techniques to assess the depth of anaesthesia (DoA). First, the denoised electroencephalograph signals are decomposed into 13 different frequency bands. The second-order difference plot (SODP) and permutation entropy (PE) values of each frequency band are calculated. The SODP and PE values of high-frequency bands (21.5-47 Hz) show the highest linear relationship with the anaesthesia states, therefore they are selected to form the parameter set. Then the SODP and PE parameters are fine tuned using the interval feature technique. Finally, a new index is designed using the ISODP and IPE. The new index is evaluated and compared with measured bispectral (BIS). The results show that there is a very close correlation between the proposed index and the BIS during different anaesthetic states. The new index also shows an earlier time response (3.1–59.7 s) than BIS during the change of anaesthetic states. In addition, the proposed index is able to continuously assess the DoA of patients when the quality of signal is poor and the BIS does not have any valid outputs.

A Multistage Deep Belief Networks Application on Arrhythmia Classification

An electrocardiogram (ECG) is a biomedical signal type that determines the normality and abnormality of heart beats using the electrical activity of the heart and has a great importance for cardiac disorders. The computer-aided analysis of biomedical signals has become a fabulous utilization method over the last years. This study introduces a multistage deep learning classification model for automatic arrhythmia classification. The proposed model includes a multi-stage classification system that uses ECG waveforms and the Second Order Difference Plot (SODP) features using a Deep Belief Network (DBN) classifier which has a greedy layer wise training with Restricted Boltzmann Machines algorithm. The multistage DBN model classified the MIT-BIH Arrhythmia Database heartbeats into 5 main groups defined by ANSI/AAMI standards. All ECG signals are filtered with median filters to remove the baseline wander. ECG waveforms were segmented from long-term ECG signals using a window with a length of 501 data points (R wave centered). The extracted waveforms and elliptical features from the SODP are utilized as the input of the model. The proposed DBN-based multistage arrhythmia classification model has discriminated five types of heartbeats with a high accuracy rate of 96.10%.

Patient Specific Congestive Heart Failure Detection From Raw ECG signal

In this study; in order to diagnose congestive heart failure (CHF) patients, non-linear second-order difference plot (SODP) obtained from raw 256 Hz sampled frequency and windowed record with different time of ECG records are used. All of the data rows are labelled with their belongings to classify much more realistically. SODPs are divided into different radius of quadrant regions and numbers of the points fall in the quadrants are computed in order to extract feature vectors. Fisher's linear discriminant, Naive Bayes, Radial basis function, and artificial neural network are used as classifier. The results are considered in two step validation methods as general k-fold cross-validation and patient based cross-validation. As a result, it is shown that using neural network classifier with features obtained from SODP, the constructed system could distinguish normal and CHF patients with 100% accuracy rate.

APPLICATION OF EMPIRICAL MODE DECOMPOSITION–BASED FEATURES FOR ANALYSIS OF NORMAL AND CAD HEART RATE SIGNALS

Coronary Artery Disease (CAD) is a heart disease caused due to insufficient supply of nutrients and oxygen to the heart muscles. Hence, reduced supply of nutrients and oxygen causes heart attack or stroke and may cause death. Also significant number of people are suffering from CAD around the world so timely diagnosis of CAD can save the life of patients. In this work, we have proposed computer assisted diagnosis of CAD using Heart Rate (HR) signals obtained from Electrocardiogram (ECG) signals. We have used the Empirical Mode Decomposition (EMD) technique to process the HR signals. The features namely: Second-Order Difference Plot (SODP) area, Analytic Signal Representation (ASR) area, Amplitude Modulation (AM) bandwidth, Frequency Modulation (FM) bandwidth and Fourier–Bessel expansion (FBE)- based mean frequency computed from the Intrinsic Mode Functions (IMFs) are extracted to discriminate normal and CAD subjects. Thereafter, Kruskal–Wallis statistical test is performed on these features. The features having p-value less than 0.05 are considered to be significant. Our results show that three features namely: AM bandwidth, FM bandwidth and FBE-based mean frequency are more suitable than ASR area and SODP area features for discrimination of normal and CAD subjects.