Comparison of Feature Extraction Methods for Physiological Signals for Heat-Based Pain Recognition

Gouverneur, Philip; Li, Frédéric; Adamczyk, Wacław M.; Szikszay, Tibor M.; Luedtke, Kerstin; Grzegorzek, Marcin

doi:10.3390/s21144838

Cited by 24 publications

(29 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Overall the results of this study are similar to what was reported in related works [ 2 , 3 , 4 , 14 , 15 , 18 , 19 , 20 , 21 ]. Nonetheless, this investigation goes further than previous literature, since it uses a higher number of physiological data, and, thus, a deep analysis of the effects of pain in the body.…”

Section: Discussionsupporting

confidence: 92%

“…Overall, the results for the EMG features validate the previous research in the area [ 15 , 19 ]: firstly, the RMSA, where both muscles showed a well-marked of value boxplots for the CPT epoch, thus corroborating the premise of reaction on the ANS due to the presence of pain. The statistical analysis shows that the Baseline presents significant differences with all the remaining epochs, indicating that, during the Rest, the muscle did not recover to the original state, whereas the triceps show differences between the baseline and the remaining epochs, except for the Rest period, indicating that it was able to recover.…”

Section: Discussionsupporting

confidence: 86%

“…Ref. [ 15 ] goes beyond the analysis of machine learning recognition models for pain assessment based on physiological and behavioral data. It also proposes a framework for feature extraction methods that allows a fair comparison of the performances of feature extraction and feature learning approaches.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Analysis of Physiological Responses during Pain Induction

Sebastião

Bento

Brás

2022

Sensors

View full text Add to dashboard Cite

Pain is a complex phenomenon that arises from the interaction of multiple neuroanatomic and neurochemical systems with several cognitive and affective processes. Nowadays, the assessment of pain intensity still relies on the use of self-reports. However, recent research has shown a connection between the perception of pain and exacerbated stress response in the Autonomic Nervous System. As a result, there has been an increasing analysis of the use of autonomic reactivity with the objective to assess pain. In the present study, the methods include pre-processing, feature extraction, and feature analysis. For the purpose of understanding and characterizing physiological responses of pain, different physiological signals were, simultaneously, recorded while a pain-inducing protocol was performed. The obtained results, for the electrocardiogram (ECG), showed a statistically significant increase in the heart rate, during the painful period compared to non-painful periods. Additionally, heart rate variability features demonstrated a decrease in the Parasympathetic Nervous System influence. The features from the electromyogram (EMG) showed an increase in power and contraction force of the muscle during the pain induction task. Lastly, the electrodermal activity (EDA) showed an adjustment of the sudomotor activity, implying an increase in the Sympathetic Nervous System activity during the experience of pain.

show abstract

Section: Discussionsupporting

confidence: 92%

Section: Discussionsupporting

confidence: 86%

See 1 more Smart Citation

Analysis of Physiological Responses during Pain Induction

Sebastião

Bento

Brás

2022

Sensors

View full text Add to dashboard Cite

show abstract

“…During each repetitive paradigm, the respiBAN Professional (Plux; a chest‐worn device that registers various physiological modalities at a sampling rate of 1000 Hz) was used to collect physiological data derived from the OpenSignals software (PLUX Wireless Biosignals S.A). EDA was measured using two Ag/AgCl hydrogel electrodes (Covidien/Kendall) at the medial phalanx of index and middle fingers of the non‐dominant arm (Gouverneur et al, 2021; Posada‐Quintero & Chon, 2020). Participants were asked to wash their hands with ordinary soap immediately before attaching the electrodes.…”

Section: Methodsmentioning

confidence: 99%

Temporal properties of pain contrast enhancement using repetitive stimulation

Szikszay

Adamczyk

Lévénez

et al. 2022

European Journal of Pain

Self Cite

View full text Add to dashboard Cite

Background Offset analgesia (OA) is characterized by a disproportionately large reduction in pain following a small decrease in noxious stimulation and is based on temporal pain contrast enhancement (TPCE). The underlying mechanisms of this phenomenon are still poorly understood. This study is aiming to investigate whether TPCE can also be induced by repetitive stimulation, i.e., by stimuli clearly separated in time. Methods A repetitive TPCE paradigm was induced in healthy, pain‐free subjects (n = 33) using heat stimuli. Three different interstimulus intervals (ISIs) were used: 5, 15, and 25 s. All paradigms were contrasted with a control paradigm without temperature change. Participants continuously rated perceived pain intensity. In addition, electrodermal activity (EDA) was recorded as a surrogate measure of autonomic arousal. Results Temporal pain contrast enhancement was confirmed for ISI 5 s (p < 0.001) and ISI 15 s (p = 0.005) but not for ISI 25 s (p = 0.07), however, the magnitude of TPCE did not differ between ISIs (p = 0.11). A TPCE‐like effect was also detected with increased EDA values. Conclusions TPCE can be induced by repetitive stimulation. This finding may be explained by a combination of the mechanisms underlying the OA and a facilitated pain habituation. Significance This experiment shows for the first time that temporal contrast enhancement of pain can be elicited by stimuli that are clearly separated in time with an interstimulus interval below 25 s.

show abstract

“…Support vector machine (SVM) [ 59 ], random forest (RF) [ 60 ], k-nearest neighbors (KNN) [ 61 ], decision tree [ 62 ], etc., are among the most popular classifiers used in the past literature. In this paper, a soft-margin SVM (known as a C-SVM) with a radial basis function (RBF) kernel and a RF classifier are the two chosen classifiers due to their high performance and ability to overcome overfitting in the case of high dimensional data [ 14 , 63 , 64 ].…”

Section: Methodsmentioning

confidence: 99%

A Machine Learning Framework for Automated Accident Detection Based on Multimodal Sensors in Cars

Pour

Wegmeth

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

Identifying accident patterns is one of the most vital research foci of driving analysis. Environmental or safety applications and the growing area of fleet management all benefit from accident detection contributions by minimizing the risk vehicles and drivers are subject to, improving their service and reducing overhead costs. Some solutions have been proposed in the past literature for automated accident detection that are mainly based on traffic data or external sensors. However, traffic data can be difficult to access, while external sensors can end up being difficult to set up and unreliable, depending on how they are used. Additionally, the scarcity of accident detection data has limited the type of approaches used in the past, leaving in particular, machine learning (ML) relatively unexplored. Thus, in this paper, we propose a ML framework for automated car accident detection based on mutimodal in-car sensors. Our work is a unique and innovative study on detecting real-world driving accidents by applying state-of-the-art feature extraction methods using basic sensors in cars . In total, five different feature extraction approaches, including techniques based on feature engineering and feature learning with deep learning are evaluated on the strategic highway research program (SHRP2) naturalistic driving study (NDS) crash data set. The main observations of this study are as follows: (1) CNN features with a SVM classifier obtain very promising results, outperforming all other tested approaches. (2) Feature engineering and feature learning approaches were finding different best performing features. Therefore, our fusion experiment indicates that these two feature sets can be efficiently combined. (3) Unsupervised feature extraction remarkably achieves a notable performance score.

show abstract

Comparison of Feature Extraction Methods for Physiological Signals for Heat-Based Pain Recognition

Cited by 24 publications

References 51 publications

Analysis of Physiological Responses during Pain Induction

Analysis of Physiological Responses during Pain Induction

Temporal properties of pain contrast enhancement using repetitive stimulation

A Machine Learning Framework for Automated Accident Detection Based on Multimodal Sensors in Cars

Contact Info

Product

Resources

About