An Ensemble Learning Approach for Electrocardiogram Sensor Based Human Emotion Recognition

Abstract

Recently, researchers in the area of biosensor based human emotion recognition have used different types of machine learning models for recognizing human emotions. However, most of them still lack the ability to recognize human emotions with higher classification accuracy incorporating a limited number of bio-sensors. In the domain of machine learning, ensemble learning methods have been successfully applied to solve different types of real-world machine learning problems which require improved classification accuracies. Emphasising on that, this research suggests an ensemble learning approach for developing a machine learning model that can recognize four major human emotions namely: anger; sadness; joy; and pleasure incorporating electrocardiogram (ECG) signals. As feature extraction methods, this analysis combines four ECG signal based techniques, namely: heart rate variability; empirical mode decomposition; with-in beat analysis; and frequency spectrum analysis. The first three feature extraction methods are well-known ECG based feature extraction techniques mentioned in the literature, and the fourth technique is a novel method proposed in this study. The machine learning procedure of this investigation evaluates the performance of a set of well-known ensemble learners for emotion classification and further improves the classification results using feature selection as a prior step to ensemble model training. Compared to the best performing single biosensor based model in the literature, the developed ensemble learner has the accuracy gain of 10.77%. Furthermore, the developed model outperforms most of the multiple biosensor based emotion recognition models with a significantly higher classification accuracy gain.

Human Emotion Recognition: Review of Sensors and Methods

“…If the purpose is to evaluate an average level of valence and arousal or to detect the efficiency of applied stimulus, a fast Fourier transformation [48] or latency test can be used [49]. If the purpose is to identify a specific emotion and its strength, statistical methods [50] or machine learning techniques [51] can be implemented. A review of related works based on only EEG signals is provided in Table 2.…”

“…There are a huge number of researches available focused on different types of feature extraction methods. Some of those methods include heart rate variability (HRV), empirical mode decomposition (EMD) with-in beat analysis (WIB), FFT analysis, and various methods of wavelet transformations [51]. A detailed overview of various methods used for emotion recognition from ECG is presented in [76].…”

Emotion Assessment Using Feature Fusion and Decision Fusion Classification Based on Physiological Data: Are We There Yet?

“…Many physiological modalities and features have been evaluated for ER, namely Electroencephalography (EEG) [ 28 , 29 , 30 ], Electrocardiography (ECG) [ 31 , 32 , 33 ], Electrodermal Activity (EDA) [ 34 , 35 , 36 ], Respiration (RESP) [ 26 ], Blood Volume Pulse (BVP) [ 26 , 35 ] and Temperature (TEMP) [ 26 ]. Multi-modal approaches have prevailed; however, there is still no clear evidence of which feature combinations and physiological signals are the most relevant.…”

Continuous Vital Monitoring During Sleep and Light Activity Using Carbon-Black Elastomer Sensors

“…The respiratory period can be calculated by differentiating the peak position in time and converting to respiration per minute. Respiratory rate variability (RRV) can be presented as the root mean square of the successive differences (RMSSD) of respiratory rates, which is a similar metric that is commonly used in heart rate variability analysis [39]. RR and the corresponding successive differences were computed breath-to-breath for analysis followed by RMSSD calculation using a breath-to-breath RRV array.…”