Combining Deep and Hand-Crafted Features for Audio-Based Pain Intensity Classification

Author(s):  
Patrick Thiam ◽  
Friedhelm Schwenker
2019 ◽  
Author(s):  
Patrick Thiam ◽  
Peter Bellmann ◽  
Hans A. Kestler ◽  
Friedhelm Schwenker

AbstractStandard feature engineering involves manually designing and assessing measurable descriptors based on some expert knowledge in the domain of application, followed by the selection of the best performing set of designed features in order to optimize an inference model. Several studies have shown that this whole manual process can be efficiently replaced by deep learning approaches which are characterized by the integration of feature engineering, feature selection and inference model optimization into a single learning process. Such techniques have proven to be very successful in the domain of image processing and have been able to attain state-of-the-art performances while significantly outperforming traditional approaches based on hand-crafted features. In the following work, we explore deep learning approaches for the analysis of physiological signals. More precisely, deep learning architectures are designed for the assessment of measurable physiological channels in order to perform an accurate classification of different levels of artificially induced nociceptive pain. Most of the previous works related to pain intensity classification based on physiological signals rely on a carefully designed set of hand-crafted features in order to achieve a relatively good classification performance. Therefore, the current work aims at building competitive pain intensity classification models without the need of domain specific expert knowledge for the generation of relevant features. The assessment of the designed deep learning architectures is based on the BioVid Heat Pain Database (Part A) and experimental validation demonstrates that the proposed uni-modal architecture for the electrodermal activity (EDA) and the deep fusion approaches significantly outperform previous classification methods reported in the literature, with respective average performances of 85.03% and 83.76% for the binary classification experiment consisting of the discrimination between the baseline level and the pain tolerance level (T0vs.T4) in a Leave-One-Subject-Out (LOSO) cross-validation evaluation setting.


2020 ◽  
Vol 146 (5) ◽  
pp. 411-450 ◽  
Author(s):  
Tobias Markfelder ◽  
Paul Pauli

2001 ◽  
Vol 10 (2) ◽  
pp. 73-77
Author(s):  
Ariel J. Raigrodski ◽  
Shawky E. Mohamed ◽  
Diana M. Gardiner
Keyword(s):  

2005 ◽  
Vol 24 (07) ◽  
pp. 626-639 ◽  
Author(s):  
V. Pfaffenrath ◽  
L. Pageler ◽  
H. Peil ◽  
B. Aicher ◽  
H. C. Diener

ZusammenfassungDie Wirksamkeit, Sicherheit und Verträglichkeit einer Einzelgabe von zwei Tabletten der fixen Dreierkombination mit 250 mg Azetylsalizylsäure (ASS) plus 200 mg Paracetamol plus 50 mg Koffein (Thomapyrin®) gegenüber zwei Tabletten mit 500 mg ASS, oder zwei Tabletten mit 500 mg Paracetamol, oder zwei Tabletten mit 50 mg Koffein beziehungsweise Plazebo wurde in einer klinischen Studie an 1 743 Patienten geprüft, die ihre episodischen Kopfschmerzen vom Spannungstyp oder ihre Migräne mit und ohne Aura üblicherweise erfolgreich mit verschreibungsfreien Analgetika behandeln. Die Dreierkombination war im a priori definierten primären Endpunkt “Zeit bis zu 50% Schmerzreduktion” sowohl der Zweierkombination aus ASS plus Paracetamol (p = 0,0181), als auch den Monoanalgetika ASS (p = 0,0398) und Paracetamol (p = 0,0016), sowie auch der Monotherapie mit Koffein (p < 0,0001) und Plazebo (p < 0,0001) überlegen. Alle Behandlungen außer der Koffein-Monotherapie waren der Plazebobehandlung überlegen (p < 0,0001). Die überlegene Wirksamkeit der Dreierkombination gilt auch für alle sekundären Endpunkte wie beispielsweise der “Verringerung der Kopfschmerzen auf 10 mm VAS (visual analog scale = visuelle Analogskala zur Schmerzmessung), dem gewichteten % SPID (sum of pain intensity difference = aufsummierte Schmerzintensitätsdifferenz gegenüber dem Ausgangsschmerz in Prozent), dem Ausmaß der Beeinträchtigung der alltäglichen Aktivitäten und der globalen Beurteilung der Wirksamkeit durch die Patienten. Alle Behandlungen waren gut verträglich, die Inzidenz von unerwünschten Begleiterscheinungen war gering.


2020 ◽  
Vol 3 (3) ◽  
pp. 42-50
Author(s):  
Theresa Rahmadhani ◽  
Nyimas Fatimah ◽  
Eka Febri Zulissetiana

The effect of hydrotherapy on pain intensity and functional ability in lumbar disk herniation (LDH) patients thatundergo non-operative procedure; pre-experimental study at medical rehabilitation installation of RSUPdr. Mohammad Hoesin Palembang. Lumbar disk herniation (LDH) is the most common disease that becaused low backpain and functional disability. Some studies mentioned that hydrotherapy is an effective treatment for low back pain.Therefore, this study was conducted to determine the effect of hydrotherapy on reducing pain intensity and improvingfunctional ability in LDH patients. This study was a pre-experimental study with one group pretest-posttest design. Datawas collected by direct interviews to the patients using visual analogue scale (VAS) to measure pain intensity andModified Oswestry Low Back Pain Disability Questionnaire to assess functional ability before and after underwenthydrotherapy once a week for 4 weeks. The data then undergo Shapiro-Wilk normality test and continue with Paired t-Test or Wilcoxon test. From 30 subjects, it was found that there are effects of hydrotherapy on reducing pain intensity(p<0,001) and improving functional ability (p<0,001) in LDH patients that undergo non-operative procedure at theMedical Rehabilitation Installation of RSUP Dr. Mohammad Hoesin Palembang. There are effects of hydrotherapy onpain intensity and functional ability in LDH patients that undergo non-operative procedure.


Sign in / Sign up

Export Citation Format

Share Document