Prevent Over-fitting and Redundancy in Physiological Signal Analyses for Stress Detection

Fang, Ruijie; Zhang, Ruoyu; Hosseini, Elahe; Parenteau, Anna; Hang, Sally; Rafatirad, Setareh; Hostinar, Camelia E.; Orooji, Mahdi; Homayoun, Houman

doi:10.1109/bibm55620.2022.9995121

Cited by 9 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, LASSO is effective in excluding insignificant variables by selecting an optimal subset of predictors [191] , [192] . For ROC curves, regularisation can be used to prevent the model from over-fitting the training data, ensuring that the performance, as measured by the area under the curve (AUC), is realistic and reproducible on new datasets [194] . This can be achieved by implementing cross-validation techniques during the training process to evaluate the effectiveness of the model on different subsets of the dataset, ensuring that the model is well-trained and generalizable [195] , [196] .…”

Section: Limitationsmentioning

confidence: 99%

Differential gene expression analysis pipelines and bioinformatic tools for the identification of specific biomarkers: A review

Rosati,

Palmieri,

Brunelli

et al. 2024

Computational and Structural Biotechnology Journal

View full text Add to dashboard Cite

Section: Limitationsmentioning

confidence: 99%

Differential gene expression analysis pipelines and bioinformatic tools for the identification of specific biomarkers: A review

Rosati,

Palmieri,

Brunelli

et al. 2024

Computational and Structural Biotechnology Journal

View full text Add to dashboard Cite

“…They achieved an accuracy of 96.6% when dealing only with two classes (stress-no stress). The same dataset has been extensively used, in combination with machine learning 13,14 or deep learning 15,16 algorithms in the context of the stress detection problem.…”

Section: Physiological Signals-based Stress Detectionmentioning

confidence: 99%

Stress detection based on physiological sensor and audio signals, and a late fusion framework: An experimental study and public dataset

Xefteris,

Dominguez,

Grivolla

et al. 2023

Preprint

View full text Add to dashboard Cite

Stress can be considered a mental/physiological reaction in conditions of high discomfort and challenging situations. The levels of stress can be reflected in both the physiological responses and speech signals of a person. In this work, we introduce a novel decision-level fusion framework for multimodal stress level detection based on physiological signals from wearable devices and user speech audio recordings. The physiological signals include Electrocardiograph (ECG), Respiration (RSP), and InertialMeasurement Unit (IMU) sensors equipped in a smart vest. A data collection protocol was introduced to receive data for the training of both the sensor-based and audio-based stress detection modules. Five subjects participated in the data collection, where both their physiological and audio signals were recorded. The analysis of physiological signals includes a massive feature extraction along with various fusion and feature selection methods. The audio analysis comprises a state-of-the-art feature extraction fed to a classifier to predict stress levels. Results from the analysis of audio and physiological signals are fused at a decision level for the final stress level detection, utilizing a machine learning algorithm. The whole framework was also tested in a pilot scenario as part of the XR4DRAMA project. We also made the training dataset publicly available.

show abstract

“…They achieved an accuracy of 96.6% when dealing only with two classes (stress-no stress). The same dataset has been extensively used in combination with machine learning [14,15] or deep learning [16,17] algorithms in the context of the stress detection problem.…”

Section: Physiological Signal-based Stress Detectionmentioning

confidence: 99%

A Multimodal Late Fusion Framework for Physiological Sensor and Audio-Signal-Based Stress Detection: An Experimental Study and Public Dataset

Xefteris,

Dominguez,

Grivolla

et al. 2023

Electronics

View full text Add to dashboard Cite

Stress can be considered a mental/physiological reaction in conditions of high discomfort and challenging situations. The levels of stress can be reflected in both the physiological responses and speech signals of a person. Therefore the study of the fusion of the two modalities is of great interest. For this cause, public datasets are necessary so that the different proposed solutions can be comparable. In this work, a publicly available multimodal dataset for stress detection is introduced, including physiological signals and speech cues data. The physiological signals include electrocardiograph (ECG), respiration (RSP), and inertial measurement unit (IMU) sensors equipped in a smart vest. A data collection protocol was introduced to receive physiological and audio data based on alterations between well-known stressors and relaxation moments. Five subjects participated in the data collection, where both their physiological and audio signals were recorded by utilizing the developed smart vest and audio recording application. In addition, an analysis of the data and a decision-level fusion scheme is proposed. The analysis of physiological signals includes a massive feature extraction along with various fusion and feature selection methods. The audio analysis comprises a state-of-the-art feature extraction fed to a classifier to predict stress levels. Results from the analysis of audio and physiological signals are fused at a decision level for the final stress level detection, utilizing a machine learning algorithm. The whole framework was also tested in a real-life pilot scenario of disaster management, where users were acting as first responders while their stress was monitored in real time.

show abstract

Prevent Over-fitting and Redundancy in Physiological Signal Analyses for Stress Detection

Cited by 9 publications

References 13 publications

Differential gene expression analysis pipelines and bioinformatic tools for the identification of specific biomarkers: A review

Differential gene expression analysis pipelines and bioinformatic tools for the identification of specific biomarkers: A review

Stress detection based on physiological sensor and audio signals, and a late fusion framework: An experimental study and public dataset

A Multimodal Late Fusion Framework for Physiological Sensor and Audio-Signal-Based Stress Detection: An Experimental Study and Public Dataset

Contact Info

Product

Resources

About