Mohammadreza Amirian

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

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.

The S-transform using a new window to improve frequency and time resolutions

The S-transform presents arbitrary time series as localized invertible time–frequency spectra. This transformation improves the short-time Fourier transform and the wavelet transform by merging the multiresolution and frequency-dependent analysis properties of wavelet transform with the absolute phase retaining of Fourier transform. The generalized S-transform utilizes a combination of a Fourier transform kernel and a scalable-sliding window. The common S-transform applies a Gaussian window to provide appropriate time and frequency resolution and minimizes the product of these resolutions. However, the Gaussian S-transform is unable to obtain uniform time and frequency resolution for all frequency components. In this paper, a novel window based on the

Adaptive confidence learning for the personalization of pain intensity estimation systems

t

Support Vector Regression of Sparse Dictionary-Based Features for View-Independent Action Unit Intensity Estimation

t student distribution is proposed for the S-transform to achieve a more uniform resolution. Simulation results show that the S-transform with the proposed window provides in comparison with the Gaussian window a more uniform resolution for the entire time and frequency range. The result is suitable for applications such as spectrum sensing.

Using Radial Basis Function Neural Networks for Continuous and Discrete Pain Estimation from Bio-physiological Signals

In this work, a method is presented for the continuous estimation of pain intensity based on fusion of bio-physiological and video features. The focus of the paper is to analyse which modalities and feature sets are suited best for the task of recognizing pain levels in a person-independent setting. A large set of features is extracted from the available bio-physiological channels (ECG, EMG and skin conductivity) and the video stream. Experimental validation demonstrates which modalities contribute the most to a robust prediction and the effects when combining them to improve the continuous estimation given unseen persons.

Learning Neural Models for End-to-End Clustering

In this work, a method is presented for the continuous estimation of pain intensity based on fusion of bio-physiological and video features. Furthermore, a method is proposed for the adaptation of the system to unknown test persons based on unlabeled data. First, an analysis is presented that shows which modalities and feature sets are suited best for the task of recognizing pain levels in a person-independent setting. For this, a large set of features is extracted from the available bio-physiological channels (ECG, EMG and skin conductivity) and the video stream. We then propose a method to learn the confidence of a regression system using a multi-stage ensemble classifier. Based on the outcome of the classifier, which is realized by a neural network, confident samples are selected by the adaptation procedure. In various experiments, we show that the algorithm is able to detect highly confident samples which can be used to improve the overall performance. We furthermore discuss the current limitations of automatic pain intensity estimation—in light of the presented approach and beyond.

Deep Learning in the Wild

A continuous multimodal human affect recognition for both arousal and valence dimensions in a non-acted spontaneous scenario is investigated in this paper. Different regression models based on Random Forests and Echo State Networks are evaluated and compared in terms of robustness and accuracy. Moreover, an extension of Echo State Networks to a bi-directional model is introduced to improve the regression accuracy. A hybrid method using Random Forests, Echo State Networks and linear regression fusion is developed and applied on the test subset of the AVEC16 challenge. Finally, the label shift and prediction delay is discussed and an annotator specific regression model, as well as fusion architecture, is proposed for future work.

Classification of Mammograms Using Convolutional Neural Network Based Feature Extraction

In this paper, a robust system for viewindependent action unit intensity estimation is presented. Based on the theory of sparse coding, region-specific dictionaries are trained to approximate the characteristic of the individual action units. The system incorporates landmark detection, face alignment and contrast normalization to handle a large variety of different scenes. Coupled with head pose estimation, an ensemble of large margin classifiers is used to detect the individual action units. The experimental validation shows that our system is robust against pose variations and able to outperform the challenge baseline by more than 35%.