Automatic Pain Recognition from Video and Biomedical Signals

Werner, Philipp; Al-Hamadi, Ayoub; Niese, Robert; Walter, Steffen; Gruss, Sascha; Traue, Harald C.

doi:10.1109/icpr.2014.784

Cited by 120 publications

(144 citation statements)

References 26 publications

Supporting

Mentioning

127

Contrasting

Order By: Relevance

“…The next best thing however is a classifier that has been trained on as much data as possible, in this case the 86 persons in the training set. This approach is inspired and supported by the relatively high classification accuracies of such classifiers in earlier studies on the same dataset [9], [10]. Concretely, a Random Forest classifier is trained on each available person (besides the test person) and it is then used to assign proxy labels to the data of the test person.…”

Section: ) Machine Learning Based Measuresmentioning

confidence: 99%

See 1 more Smart Citation

Methods for Person-Centered Continuous Pain Intensity Assessment From Bio-Physiological Channels

Kächele

Thiam

Amirian

et al. 2016

IEEE J. Sel. Top. Signal Process.

View full text Add to dashboard Cite

In this work, we present methods for the personalization of a system for the continuous estimation of pain intensity from bio-physiological channels. We investigate various ways to estimate the similarity of persons and to retrieve the most informative ones using meta information, personality traits and machine learning techniques. Given this information, specialized classifiers can be created that are both, more efficient in terms of complexity and training times and also more accurate than classifiers trained on the complete data. To capture the most information in the different bio-physiological channels, we cover a broad spectrum of different feature extraction algorithms. Furthermore, we show that the system is capable of running in real-time and discuss issues that arise when dealing with incremental data processing. In extensive experiments we verify the validity of our approach.

show abstract

Section: ) Machine Learning Based Measuresmentioning

confidence: 99%

“…heart rate, electrodermal activity) [8], linguistic and paralinguistic measures or video signals, into complex classification systems. Pain recognition based on multi-modal signals has recently been proven to be very effective, most often outperforming unimodal systems significantly [9], [10].…”

Section: Introductionmentioning

confidence: 99%

Methods for Person-Centered Continuous Pain Intensity Assessment From Bio-Physiological Channels

Kächele

Thiam

Amirian

et al. 2016

IEEE J. Sel. Top. Signal Process.

View full text Add to dashboard Cite

show abstract

“…Pain recognition is generally based on the analysis of pain indicators such as cry characteristics [5,16], facial expressions [2,4,21,23], body posture, [3] physiological signals [13,28] or in combination [38]. Depending on the pain indicators and pain metric employed, previous work on automatic pain recognition can be classified into two categories: PSPI based and non-PSPI based pain recognition.…”

Section: Automatic Pain Recognitionmentioning

confidence: 99%

“…However, capturing these signals commonly involves invasive procedures where sensors have to be directly connected to the patient's body. Werner et al [38] combine bio and visual signals for pain estimation. Evaluating on the BioVid database, they show that the combination performs better than the individual features.…”

Section: Automatic Pain Recognitionmentioning

confidence: 99%

Cumulative attributes for pain intensity estimation

Egede

Valstar

2017

Proceedings of the 19th ACM International Conference on Multimodal Interaction

View full text Add to dashboard Cite

Pain estimation from face video is a hard problem in automatic behaviour understanding. One major obstacle is the difficulty of collecting sufficient amounts of data, with balanced amounts of data for all pain intensity levels. To overcome this, we propose to adopt Cumulative Attributes, which assume that attributes for high pain levels with few examples are a superset of all attributes of lower pain levels. Experimental results show a consistent relative performance increase in the order of 20% regardless of features used. Our final system significantly outperforms the state of the art on the UNBC McMaster Shoulder Pain database by using cumulative attributes with Relevance Vector Regression on a combination of features, including appearance, geometric, and deep learned features.

show abstract

“…Martinéz et al [12] were able to 28 significantly outperform standard approaches built upon hand-crafted features by using 29 a deep learning algorithm for affect modelling based on physiological signals (two 30 physiological signals consisting of Skin Conductance (SC) and Blood Volume Pulse 31 (BVP) were used in this specific work). The designed approach consisted of a 32 multi-layer Convolutional Neural Network (CNN) [13] combined with a single-layer 33 perceptron (SLP). The parameters of the CNN were trained in an unsupervised manner 34 using denoising auto-encoders [14].…”

mentioning

confidence: 99%

Exploring Deep Physiological Models for Nociceptive Pain Recognition

Thiam

Bellmann

Kestler³

et al. 2019

Preprint

View full text Add to dashboard Cite

Standard 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 (T 0 vs.T 4 ) in a Leave-One-Subject-Out (LOSO) cross-validation evaluation setting.

show abstract

Automatic Pain Recognition from Video and Biomedical Signals

Cited by 120 publications

References 26 publications

Methods for Person-Centered Continuous Pain Intensity Assessment From Bio-Physiological Channels

Methods for Person-Centered Continuous Pain Intensity Assessment From Bio-Physiological Channels

Cumulative attributes for pain intensity estimation

Exploring Deep Physiological Models for Nociceptive Pain Recognition

Contact Info

Product

Resources

About