Stress Classification by Multimodal Physiological Signals Using Variational Mode Decomposition and Machine Learning

In this pandemic situation, importance and awareness about mental health are getting more attention. Stress recognition from multimodal sensor based physiological signals such as electroencephalogram (EEG) and electrocardiography (ECG) signals is a very cost-effective way due to its noninvasive nature. A dataset, recorded during the mental arithmetic task, consisting of EEG + ECG signals of 36 participants is used. It contains two categories of performance, namely, “Good” (nonstressed) and “Bad” (stressed) (Gupta et al. 2018 and Eraldeír et al. 2018). This paper presents an effective approach for the recognition of stress marker at frontal, temporal, central, and occipital lobes. It processes the multimodality physiological signals. The variational mode decomposition (VMD) strategy is used for data preprocessing and for the decomposition of signals into various oscillatory mode functions. Poincare plots (PP) are derived from the first eight variational modes and features from these plots have been extracted such as mean, area, and central tendency measure of the elliptical region. The statistical significance of the extracted features with p < 0.5 has been performed using the Wilcoxson test. The multilayer perceptron (MPLN) and Support Vector Machine (SVM) algorithms are used for the classification of stress and nonstress categories. MLPN has achieved the maximum accuracies of 100% for frontal and temporal lobes. The suggested method can be incorporated in noninvasive EEG signal processing based automated stress identification systems.

Influence of anxiety on the heart rate variability of patients in preoperative orthopedic surgery

Anxiety is a negative emotional response to situations that threaten the subject. Objective: The present study aims to verify the influence of anxiety on heart rate variability, considering two specific times: hospitalization and before surgery. In this analytical and cross-sectional study, the Hospital Anxiety and Depression Scale (HADS) was used to classify anxiety levels. Methodology: The time series of RR intervals were collected by Polar® monitor. Nonlinear methods and decision tree algorithm were combined with HADS scale to analyze the influence of the preoperative period on heart rate variability. The nonlinear methods used detrended fluctuation analysis (DFA), recurrence quantification analysis (RQA), and central tendency measure (CTM). Results: Among the 42 study participants, 13 (31%) were classified as anxious at hospital admission. The applied time domain methods found an increase in the heart rate variability (HRV) values in all features analyzed (p < 0.05). CTM method showed HRV reduction for the values considering radius between 6 and 20 milliseconds (p < 0.05). Conclusion: The anxiety identified at admission is directly related to the reduction in heart rate variability demonstrated by nonlinear methods, such as the central tendency measure.

Analysis of Normal and Adventitious Lung Sound Signals Using Empirical Mode Decomposition and Central Tendency Measure

Diagnosing chronic obstructive pulmonary disease (COPD) from lung sounds is time consuming, onerous, and subjective to the expertise of pulmonologists. The preliminary diagnosis of COPD is often based on adventitious lung sounds (ALS). This paper proposes to objectively analyze the lung sound signals associated with COPD. Specifically, empirical mode decomposition (EMD), a data adaptive signal decomposition technique suitable for analyzing non-stationary signals, was adopted to decompose non-stationary lung sound signals. The use of EMD on lung sound signal results in intrinsic mode functions (IMFs), which are symmetric and band limited. The analytic IMFs were then computed through the Hilbert transform, which reveals the instantaneous frequency content of each IMF. The Hilbert transformed signal is analytic, and has a complex representation containing real and imaginary parts. Next, the central tendency measure (CTM) was introduced to quantify the circular shape of the analytical IMF plot. The result was taken as a useful feature to distinguish normal lung sound signal with ALS. Simulation results show that the CTM of analytic IMFs has a strong ability to distinguish between normal lung sound signals and ALS.

Approximating the Normal Sample Median Distribution in Process Control

The present work aims to propose an approximation of the sample median distribution with a normal parent distribution. Although the mean is usually used as the central tendency measure for normal samples, the median has also been used in engineering, process control in particular. The proposed method approximates the normal sample median distribution only using the normal distribution function. It outperforms Castagliola’s method for small samples and serves as an alternative approximation for trading off accuracy against computational complexity for large samples.

Depression Detection Based on Geometrical Features Extracted from SODP Shape of EEG Signals and Binary PSO

Late detection of depression is having detrimental consequences including suicide thus there is a serious need for an accurate computer-aided system for early diagnosis of depression. In this research, we suggested a novel strategy for the diagnosis of depression based on several geometric features derived from the Electroencephalography (EEG) signal shape of the second-order differential plot (SODP). First, various geometrical features of normal and depression EEG signals were derived from SODP including standard descriptors, a summation of the angles between consecutive vectors, a summation of distances to coordinate, a summation of the triangle area using three successive points, a summation of the shortest distance from each point relative to the 45-degree line, a summation of the centroids to centroid distance of successive triangles, central tendency measure and summation of successive vector lengths. Second, Binary Particle Swarm Optimization was utilized for the selection of suitable features. At last, the features were fed to support vector machine and k-nearest neighbor (KNN) classifiers for the identification of normal and depressed signals. The performance of the proposed framework was evaluated by the recorded bipolar EEG signals from 22 normal and 22 depressed subjects. The results provide an average classification accuracy of 98.79% with the KNN classifier using city-block distance in a ten-fold cross-validation strategy. The proposed system is accurate and can be used for the early diagnosis of depression. We showed that the proposed geometrical features are better than extracted features in the time, frequency, time-frequency domains as it helps in visual inspection and provide up to 17.56% improvement in classification accuracy in contrast to those features.

Guidelines for the prevention of secondary lymphedema following breast cancer treatment: adhesion and associated factors

Introduction: Lymphedema is the most feared complication that may take place after breast cancer treatment. With treatment progression, doubts have arisen regarding the real benefits of lymphedema prevention care, as well as of patient adherence to guidelines. Objective: In this context, the aim of this study was to assess patient adherence to preventive lymphedema guidelines and the distribution of sociodemographic, clinical, and treatment variables according to adherence to treatment. Methods: A cross-sectional study conducted at the Cancer Hospital III/INCA, Rio de Janeiro, Brazil, concerning patients with breast cancer undergoing surgical treatment with an axillary approach. Participants were questioned about assistance care performance, exercise-related care, and limb ipsilateral to surgery care. A descriptive analysis of patient demographic, clinical, treatments, postoperative complications variables, and main outcomes (adherence to the guidelines) was performed through a central tendency measure and data dispersion and frequency measures analyses. Differences between means were assessed using the Student’s t-test, while differences between proportions were evaluated using the chi-square test. A significance level of 5% was considered for all assessments. Results: Of the 103 women included in this study, 89.3% adhered to assistance care, 61.2% adhered to limb care, and 42.7% performed exercise-related care. Women undergoing chemotherapy (p = 0.030) and axillary lymphadenectomy (AL) (p = 0.017) exhibited greater adherence to care. Non-white patients (p = 0.048) and those who underwent AL (p = 0.025) adhered to limb care more frequently. Finally, patients displaying lower education levels (p = 0.013) and those who underwent AL (p = 0.009) adhered more frequently to limb exercises. Conclusion: Patients adhered the most to assistance care and limb care compared to exercise practice. Patients undergoing chemotherapy displayed greater adherence to care and non-white patients adhered the most to limb care. Women who underwent AL displayed greater adherence to all types of care and those presenting lower education levels adhered more frequently to exercise guidelines.

The Robustness of the Modified H-Statistic in the Test of Comparing Independent Groups

The H-statistic is a robust test statistic in comparing the equality of two and more than two independent groups. This statistic is one of a good alternative to the F-statistic in the analysis of variance (ANOVA). The F-statistic is good only when the distribution of data is normal with homogeneous variances. If there is a violation of at least one of these assumptions, it affects the Type I error rate of the test. The main weakness of the F-statistic is its calculation based on the mean. The mean is well-known as a very sensitive central tendency measure with 0 breakdown point, whereas the H-statistic provides a test with fewer assumptions yet powerful. This statistic is readily adaptable to any measure of central tendency, and it appears to give reasonably good results. Hence, this paper provides a detailed study on the robustness of the H-statistic and its performance using different robust central tendency measures such that the modified one-step M (MOM) estimator and Winsorized MOM estimator. Based on the simulation study, this paper also investigates the performance of the H-statistic under various data conditions. The findings reveal that this statistic performs as well as the F-statistic under normal and homogeneous variance, yet it provides better control of Type I error rate under non-normal data or heterogeneous variances or both. Keywords: H-statistic; robust test; mean; modified one-step M-estimator

Winsorized Modified One Step M-Estimator As a Measure of the Central Tendency in the Alexander-Govern Test

This research dealt with making comparison of the independent group tests with the use of parametric technique. This test used mean as its central tendency measure. It was a better alternative to the ANOVA, the Welch test and the James test, because it gave a good control of Type I error rates and high power with ease in its calculation, for variance heterogeneity under a normal data. But the test was found not to be robust to non-normal data. Trimmed mean was used on the test as its central tendency measure under non-normality for two group condition, but as the number of groups increased above two, the test failed to give a good control of Type I error rates. As a result of this, the MOM estimator was applied on the test as its central tendency measure and is not influenced by the number of groups. However, under extreme condition of skewness and kurtosis, the MOM estimator could no longer control the Type I error rates. In this study, the Winsorized MOM estimator was used in the AG test, as a measure of its central tendency under non-normality. 5,000 data sets were simulated and analysed for each of the test in the research design with the use of Statistical Analysis Software (SAS) package. The results of the analysis shows that the Winsorized modified one step M-estimator in the Alexander-Govern (AGWMOM) test, gave the best control of Type I error rates under non-normality compared to the AG test, the AGMOM test, and the ANOVA, with the highest number of conditions for both lenient and stringent criteria of robustness.