Facial-expression recognition: An emergent approach to the measurement of tourist satisfaction through emotions

Emotions provide valuable information regarding habits, health, mental activities, etc. Emotion recognition has attracted wide interests in affective computing, medical, brain-computer interface, and other relevant fields. Emotion recognition from EEG signals has facilitated to impaired peoples to intact with real world. Multi-components EEG signal need to decomposed into set of components to extract the hidden information, empirical selection of decomposition parameters can lead to loss of information due to mode mixing, generation of noisy modes, poor signal synthesis, etc. In this paper, optimized variational mode decomposition is proposed for emotion recognition using single-channel EEG signals. The Eigenvector centrality method (EVCM) is employed for dominant channel selection. An optimum number of modes ( ${K}_{\textit {opt}}$ ) and penalty factor ( $\alpha _{\textit {opt}}$ ) are selected adaptively for decomposition of non-stationary EEG signals. Time-domain features are elicited from the modes of EEG signals. The posthoc analysis are employed for significant features selection, these features are used as input to different classifiers for emotion classification. The overall accuracy of 97.24% is achieved with an extreme learning machine classifier for a four emotion classification. The performance of the proposed method is evaluated by five performance parameters. F-1 score, false-positive rate, Mathew’s correlation coefficient, and Cohen’s Kappa of 0.9454, 0.94%, 92.92%, and 0.9633 is obtained. In comparison with traditional variational mode decomposition and existing state-of-the-art using the same dataset, the proposed method shows improved performance of about 4% and 2%.

An Evolutionary Optimized Variational Mode Decomposition for Emotion Recognition

We present ProxEmo, a novel end-to-end emotion prediction algorithm for socially aware robot navigation among pedestrians. Our approach predicts the perceived emotions of a pedestrian from walking gaits, which is then used for emotion-guided navigation taking into account social and proxemic constraints. To classify emotions, we propose a multi-view skeleton graph convolution-based model that works on a commodity camera mounted onto a moving robot. Our emotion recognition is integrated into a mapless navigation scheme and makes no assumptions about the environment of pedestrian motion. It achieves a mean average emotion prediction precision of 82.47% on the Emotion-Gait benchmark dataset. We outperform current state-of-art algorithms for emotion recognition from 3D gaits. We highlight its benefits in terms of navigation in indoor scenes using a Clearpath Jackal robot.

ProxEmo: Gait-based Emotion Learning and Multi-view Proxemic Fusion for Socially-Aware Robot Navigation

The identification of facial expressions that reveal human emotions can help computers to better assess the human state of mind, so as to provide a more customized interaction. We explore the recognition of human facial expressions through a deep learning approach using a Convolutional Neural Network (CNN) algorithm. The system uses a labelled data set containing around 32,298 images with multiple facial expressions for training and testing. The pre-training phase involves a face detection subsystem with noise removal, including feature extraction. The generated classification model used for prediction can identify seven emotions of the Facial Action Coding System (FACS). Results of our work in progress demonstrate an accuracy of 79.8% for the recognition of all basic seven human emotions, without the application of optimization techniques.

Identifying Human Emotions from Facial Expressions with Deep Learning

Over the past few years, Generative Adversarial Networks (GANs) have been receiving attention from image and time series domain. In this work, we propose a novel sequence based generative model to generate ECG samples for enhancing emotion state classification. Firstly, emotional related features are extracted to represent emotion state in ECG record. Secondly, random forest and support vector machine are trained to classify arousal and valence states. Then proposed generative model is applied to generate ECG sample with the corresponding emotion state label. Finally, synthetic data is used to augment the original training set for another classification. Our proposed model classifying emotion state in both arousal and valence domain. With synthetic augmented dataset, the average classification accuracy increases around 5% compared with using only original data. The result demonstrates the notable effectiveness of our generative model for enhancing emotion state classification.

EmotionalGAN: Generating ECG to Enhance Emotion State Classification

This paper presents emotion recognition using facial expression. Emotion recognition is widely used in industrial applications where emotion of humans are used to derive conclusions on products and detection of suspective behaviour. In this project we have detected seven emotions of humans which are Happiness, Anger, Sadness, Disgust, Neutral, Surprise and fear. We have taken a set of still images, detected the facial region and the features are extracted. Features are extracted using Bag-Of-Features (BOF) and Histogram of Oriented Gradients (HOG). The feature vectors created by these techniques are used to train Support Vector Machines (SVM) and results are verified against a given test input. We have achieved satisfactory results for emotion recognition. We have found that HOG gives a better result the BOF

http://www.ijariie.com/AdminUploadPdf/Emotion_recognition_using_facial_expressions_ijariie10150.pdf

Emotion recognition using facial expressions

Introduction . Arrhythmia or irregular heartbeat occur when the heart’s electrical system is disorganized or out of sync, which may cause strokes, sudden cardiac death, and other complications. The introduction of an automated classification of arrhythmias based on deep learning could facilitate the decision-making process by saving time and labor resources. Aim . To study the performance of a modified arrhythmia classification improved by using binary images of segmented ECG signals with combinations of orthogonal and surface signals. Materials and methods . This article studies an arrhythmia classification based on binary images of surface and orthogonal ECG signals. The data labeling was automated using the Python programming language. Initially, all signals are subjected to preprocessing followed by their plotting and segmenting in 2-second windows. Next, those segments are saved as RGB images followed by their conversion into binary images, where the signal is white, and the background is black. Finally, the pre-trained Alexnet model is used to classify nine classes, where each surface ECG and orthogonal lead is classified separately. Results . The performance of the model is evaluated by the mean accuracy, precision, F1-score, and confusion matrix of all leads. The results of a parallel classification of 12 lead ECG are better than those for the orthogonal leads. All leads with accuracy, precision, and F1-score equal to 0.84, 0.78, and 0.71, respectively. Conclusion . The performance of the model was evaluated for three cases: 12 surface ECG leads, orthogonal leads, and all leads. The calculated mean values of accuracy, precision, and F1-score for each case confirmed the sufficiency of the 12-lead surface ECG for classifying nine different types of arrhythmia using binary images of ECG segments. 

/pdf/classification-of-arrhythmias-using-a-pre-trained-deep-2yfj1hlz.pdf

Shantanu Sali

Papers

Emotion recognition using facial expressions

Classification of Arrhythmias Using a Pre-trained Deep Learning Model with Binary Images of Segmented ECG