Multimodal prediction of trait emotional intelligence–Through affective changes measured using non-contact based physiological measures

Abstract

Inability to efficiently deal with emotionally laden situations, often leads to poor interpersonal interactions. This adversely affects the individual’s psychological functioning. A higher trait emotional intelligence (EI) is not only associated with psychological wellbeing, educational attainment, and job-related success, but also with willingness to seek professional and non-professional help for personal-emotional problems, depression and suicidal ideation. Thus, it is important to identify low (EI) individuals who are more prone to mental health problems than their high EI counterparts, and give them the appropriate EI training, which will aid in preventing the onset of various mood related disorders. Since people may be unaware of their level of EI/emotional skills or may tend to fake responses in self-report questionnaires in high stake situations, a system that assesses EI using physiological measures can prove affective. We present a multimodal method for detecting the level of trait Emotional intelligence using non-contact based autonomic sensors. To our knowledge, this is the first work to predict emotional intelligence level from physiological/autonomic (cardiac and respiratory) response patterns to emotions. Trait EI of 50 users was measured using Schutte Self Report Emotional Intelligence Test (SSEIT) along with their cardiovascular and respiratory data, which was recorded using FMCW radar sensor both at baseline and while viewing affective movie clips. We first examine relationships between users’ Trait EI scores and autonomic response and reactivity to the clips. Our analysis suggests a significant relationship between EI and autonomic response and reactivity. We finally attempt binary EI level detection using linear SVM. We also attempt to classify each sub factor of EI, namely–perception of emotion, managing own emotions, managing other’s emotions, and utilization of emotions. The proposed method achieves an EI classification accuracy of 84%, while accuracies ranging from 58 to 76% is achieved for recognition of the sub factors. This is the first step towards identifying EI of an individual purely through physiological responses. Limitation and future directions are discussed.

Machine Learning in RADAR-based Physiological Signals Sensing: A Scoping Review of the Models, Datasets and Metrics

“…Two papers state directly the use of valence-arousal theory [202], [209]. Regarding machine learning or deep learning choice, we observe both simpler alternatives, with SVM [204], [205], KNN [205]- [207], Random Forest (RF) or DT [205], [206], and deeper models with MLP [206], CNN [202], [206] and CNN + RNN [208], [209]. The size of the dataset of the included papers ranges from 5 subjects [207] to 72 subjects [201], with the subjects involved in a static condition.…”

“…We classified 9 papers in the area of RADAR-based affective computing. 7 papers [201], [202], [205]- [209] deal with emotion recognition, one paper with emotional intelligence classification [204] and one paper deals with lie detection based on the emotional response [203]. It can be noticed that all the papers dealing with emotion recognition classify only a small subset of possible emotions, with up to four classes, due to the clear complexity of the topic.…”

A contactless monitoring system for accurately predicting energy expenditure during treadmill walking based on an ensemble neural network

“… 44 Compared with contact-based sensors (e.g., airflow sensor, smart bracelet Mi 3) and electrocardiograms, the accuracy of HR measurement via radar is up to 93% and > 80%, respectively. 62 The AWR1642BOOST integrates RF/analog system, radio processor subsystem, data processing system, and main control system, operates in 76-81 GHz band, and can detect heart rate waveforms with a sampling rate of 20 Hz. A micro-USB cable was included in the AWR1642 package to communicate with the computer and a 5 V/2.5 A power cable was used to power the sensor.…”

Cluster Ensemble Method and Convolution Neural Network Model for Predicting Mental Illness

“…CNN is used for building predictive modeling [8], [9], [10]. The study also explores the potential benefits that improve effective classifications of true or false mental illness.…”