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

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Nilima Salankar ◽  
Deepika Koundal ◽  
Saeed Mian Qaisar
Keyword(s):  
Mental Arithmetic ◽  
Statistical Significance ◽  
Cost Effective ◽  
Physiological Signals ◽  
Support Vector ◽  
Variational Mode Decomposition ◽  
Arithmetic Task ◽  
Central Tendency Measure ◽  
Ecg Signals ◽  
Mode Decomposition

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.

Estimation of Cognitive Distraction from Driver Gazing

2017 ◽  
Vol 9 (2) ◽  
pp. 50-60 ◽  
Author(s):  
Akira Yoshizama ◽  
Hiroyuki Nishiyama ◽  
Hirotoshi Iwasaki ◽  
Fumio Mizoguchi
Keyword(s):  
Qualitative Data ◽  
Mental Arithmetic ◽  
Support Vector ◽  
Simulation Environment ◽  
Time Intervals ◽  
Arithmetic Task ◽  
Task Load ◽  
Cognitive Distraction ◽  
Mental Arithmetic Task ◽  
Using Data

In their study, the authors sought to generate rules for cognitive distractions of car drivers using data from a driving simulation environment. They collected drivers' eye-movement and driving data from 18 research participants using a simulator. Each driver drove the same 15-minute course two times. The first drive was normal driving (no-load driving), and the second drive was driving with a mental arithmetic task (load driving), which the authors defined as cognitive-distraction driving. To generate rules of distraction driving using a machine-learning tool, they transformed the data at constant time intervals to generate qualitative data for learning. Finally, the authors generated rules using a Support Vector Machine (SVM).

scholarly journals Analysis of Different Classification Techniques for Two-Class Functional Near-Infrared Spectroscopy-Based Brain-Computer Interface

2016 ◽  
Vol 2016 ◽  
pp. 1-11 ◽  
Author(s):  
Noman Naseer ◽  
Nauman Khalid Qureshi ◽  
Farzan Majeed Noori ◽  
Keum-Shik Hong
Keyword(s):  
Infrared Spectroscopy ◽  
Discriminant Analysis ◽  
Near Infrared Spectroscopy ◽  
Near Infrared ◽  
Continuous Wave ◽  
Mental Arithmetic ◽  
Statistical Significance ◽  
Support Vector ◽  
Functional Near Infrared Spectroscopy ◽  
Linear Discriminant

We analyse and compare the classification accuracies of six different classifiers for a two-class mental task (mental arithmetic and rest) using functional near-infrared spectroscopy (fNIRS) signals. The signals of the mental arithmetic and rest tasks from the prefrontal cortex region of the brain for seven healthy subjects were acquired using a multichannel continuous-wave imaging system. After removal of the physiological noises, six features were extracted from the oxygenated hemoglobin (HbO) signals. Two- and three-dimensional combinations of those features were used for classification of mental tasks. In the classification, six different modalities, linear discriminant analysis (LDA), quadratic discriminant analysis (QDA),k-nearest neighbour (kNN), the Naïve Bayes approach, support vector machine (SVM), and artificial neural networks (ANN), were utilized. With these classifiers, the average classification accuracies among the seven subjects for the 2- and 3-dimensional combinations of features were 71.6, 90.0, 69.7, 89.8, 89.5, and 91.4% and 79.6, 95.2, 64.5, 94.8, 95.2, and 96.3%, respectively. ANN showed the maximum classification accuracies: 91.4 and 96.3%. In order to validate the results, a statistical significance test was performed, which confirmed that thepvalues were statistically significant relative to all of the other classifiers (p< 0.005) using HbO signals.

Modified Variational Mode Decomposition for Power Line Interference Removal in ECG Signals

2016 ◽  
Vol 6 (1) ◽  
pp. 151 ◽  
Author(s):  
Neethu Mohan ◽  
Sachin Kumar S ◽  
Prabaharan Poornachandran ◽  
Soman K.P
Keyword(s):  
Interference Cancellation ◽  
Linear Time ◽  
Power Line ◽  
Variational Mode Decomposition ◽  
Ecg Signals ◽  
Mode Decomposition ◽  
Signal Characteristics ◽  
Actual Signal ◽  
Notch Filtering ◽  
Power Line Interference

Power line interferences (PLI) occurring at 50/60 Hz can corrupt the biomedical recordings like ECG signals and which leads to an improper diagnosis of disease conditions. Proper interference cancellation techniques are therefore required for the removal of these power line disturbances from biomedical recordings. The non-linear time varying characteristics of biomedical signals make the<strong> </strong>interference removal a difficult task without compromising the actual signal characteristics. In this paper, a modified variational mode decomposition based approach is proposed for PLI removal from the ECG signals. In this approach, the central frequency of an intrinsic mode function is fixed corresponding to the normalized power line disturbance frequency. The experimental results show that the PLI interference is exactly captured both in magnitude and phase and are removed. The proposed approach is experimented with ECG signal records from MIT-BIH Arrhythmia database and compared with traditional notch filtering.

scholarly journals Identification of Cutting Chatter through Deep Learning and Classification

2020 ◽  
Vol 19 (4) ◽  
pp. 667-677
Author(s):  
H. N. Gao ◽  
D. H. Shen ◽  
L. Yu ◽  
W. C. Zhang
Keyword(s):  
Vibration Signal ◽  
Identification Accuracy ◽  
Support Vector ◽  
Identification Algorithm ◽  
Variational Mode Decomposition ◽  
Time Frequency ◽  
Chatter Identification ◽  
Mode Decomposition ◽  
Cutting Chatter ◽  
Cutting Vibration

The traditional analytical method has difficulty in accurately modelling cutting chatter. This paper constructs the vibration datasets of different chatter states and establishes a machine learning (ML) model for chatter identification, treating physical vibration signal as the input. Specifically, the cutting vibration signal was converted into the time-frequency spectrum, which was then classified by a self-designed deep residual convolutional neural network (DR-CNN). After that, the cutting vibration signal was broken down into chatter bands through variational mode decomposition (VMD). The information entropies of the chatter bands were calculated as cutting chatter features. Next, support vector machine (SVM) was introduced to classify the extracted features and used to create an online cutting chatter identification algorithm. The proposed method achieved a much higher mean identification accuracy (92.57 %) than the traditional identification method.

scholarly journals Application of Variational Mode Decomposition and Permutation Entropy for Rolling Bearing Fault Diagnosis

2019 ◽  
Vol 24 (2) ◽  
pp. 303-311 ◽  
Author(s):  
Xiaoxia Zheng ◽  
Guowang Zhou ◽  
Dongdong Li ◽  
Haohan Ren
Keyword(s):  
Vibration Signal ◽  
Rolling Bearing ◽  
Permutation Entropy ◽  
Support Vector ◽  
Variational Mode Decomposition ◽  
Intrinsic Mode Functions ◽  
Bearing Fault Diagnosis ◽  
Multi Scale ◽  
Mode Decomposition ◽  
Bearing Vibration

Rolling bearings are the key components of rotating machinery. However, the incipient fault characteristics of a rolling bearing vibration signal are weak and difficult to extract. To solve this problem, this paper presents a novel rolling bearing vibration signal fault feature extraction and fault pattern recognition method based on variational mode decomposition (VMD), permutation entropy (PE) and support vector machines (SVM). In the proposed method, the bearing vibration signal is decomposed by VMD, and the intrinsic mode functions (IMFs) are obtained in different scales. Then, the PE values of each IMF are calculated to uncover the multi-scale intrinsic characteristics of the vibration signal. Finally, PE values of IMFs are fed into SVM to automatically accomplish the bearing condition identifications. The proposed method is evaluated by rolling bearing vibration signals. The results indicate that the proposed method is superior and can diagnose rolling bearing faults accurately.

Sign in / Sign up

Export Citation Format

Share Document