Performance Evaluation of Machine Learning for Recognizing Human Facial Emotions

2021 ◽  
Vol 17 (3) ◽  
pp. 63-79
Author(s):  
Alti Adel ◽  
Ayeche Farid
Keyword(s):  
Machine Learning ◽  
Feature Selection ◽  
Recognition Rate ◽  
Classification Problem ◽  
Expression Recognition ◽  
Emotion Classification ◽  
Feature Classification ◽  
Shape Model ◽  
Classification Feature ◽  
Human Emotions

Facial expression recognition is a human emotion classification problem attracting much attention from scientific research. Classifying human emotions can be a challenging task for machines. However, more accurate results and less execution time are still the issues when extracting features of human emotions. To cope with these challenges, the authors propose an automatic system that provides users with a well-adopted classifier for recognizing facial expressions in a more accurate manner. The system is based on two fundamental machine learning stages, namely feature selection and feature classification. Feature selection is realized by active shape model (ASM) composed of landmarks while the feature classification algorithm is based on seven well-known classifiers. The authors have used CK+ dataset, implemented and tested seven classifiers to find the best classifier. The experimental results show that quadratic classifier (DA) provides excellent performance, and it outperforms the other classifiers with the highest recognition rate of 100% for the same dataset.

scholarly journals Effect on speech emotion classification of a feature selection approach using a convolutional neural network

2021 ◽  
Vol 7 ◽  
pp. e766
Author(s):  
Ammar Amjad ◽  
Lal Khan ◽  
Hsien-Tsung Chang
Keyword(s):  
Neural Network ◽  
Feature Selection ◽  
Convolutional Neural Network ◽  
Feature Selection Method ◽  
Classification Problem ◽  
Speech Emotion Recognition ◽  
Support Vector ◽  
Emotion Classification ◽  
K Nearest Neighbors ◽  
Feature Selection Technique

Speech emotion recognition (SER) is a challenging issue because it is not clear which features are effective for classification. Emotionally related features are always extracted from speech signals for emotional classification. Handcrafted features are mainly used for emotional identification from audio signals. However, these features are not sufficient to correctly identify the emotional state of the speaker. The advantages of a deep convolutional neural network (DCNN) are investigated in the proposed work. A pretrained framework is used to extract the features from speech emotion databases. In this work, we adopt the feature selection (FS) approach to find the discriminative and most important features for SER. Many algorithms are used for the emotion classification problem. We use the random forest (RF), decision tree (DT), support vector machine (SVM), multilayer perceptron classifier (MLP), and k-nearest neighbors (KNN) to classify seven emotions. All experiments are performed by utilizing four different publicly accessible databases. Our method obtains accuracies of 92.02%, 88.77%, 93.61%, and 77.23% for Emo-DB, SAVEE, RAVDESS, and IEMOCAP, respectively, for speaker-dependent (SD) recognition with the feature selection method. Furthermore, compared to current handcrafted feature-based SER methods, the proposed method shows the best results for speaker-independent SER. For EMO-DB, all classifiers attain an accuracy of more than 80% with or without the feature selection technique.

scholarly journals Facial Expressions Recognition Based on Delaunay Triangulation of Landmark and Machine Learning

2021 ◽  
Vol 38 (6) ◽  
pp. 1575-1586
Author(s):  
Farid Ayeche ◽  
Adel Alti
Keyword(s):  
Machine Learning ◽  
Facial Expressions ◽  
Delaunay Triangulation ◽  
Connected Graph ◽  
Recognition Rate ◽  
Machine Learning Techniques ◽  
Expression Recognition ◽  
Technological Advances ◽  
Learning Techniques ◽  
Machine Learning Approach

Facial expressions can tell a lot about an individual’s emotional state. Recent technological advances opening avenues for automatic Facial Expression Recognition (FER) based on machine learning techniques. Many works have been done on FER for the classification of facial expressions. However, the applicability to more naturalistic facial expressions remains unclear. This paper intends to develop a machine learning approach based on the Delaunay triangulation to extract the relevant facial features allowing classifying facial expressions. Initially, from the given facial image, a set of discriminative landmarks are extracted. Along with this, a minimal landmark connected graph is also extracted. Thereby, from the connected graph, the expression is represented by a one-dimensional feature vector. Finally, the obtained vector is subject for classification by six well-known classifiers (KNN, NB, DT, QDA, RF and SVM). The experiments are conducted on four standard databases (CK+, KDEF, JAFFE and MUG) to evaluate the performance of the proposed approach and find out which classifier is better suited to our system. The QDA approach based on the Delaunay triangulation has a high accuracy of 96.94% since it only supports non-zero pixels, which increases the recognition rate.

Intelligent Feature Subset Selection with Machine Learning based Risk Management for DAS Prediction

2021 ◽  
pp. 08-16
Author(s):  
Mohamed Abdel Abdel-Basset ◽  
◽  
◽  
Mohamed Elhoseny
Keyword(s):  
Machine Learning ◽  
Risk Management ◽  
Feature Selection ◽  
Subset Selection ◽  
Classification Problem ◽  
Feature Subset Selection ◽  
Feature Subset ◽  
Time Machine ◽  
Primary Level ◽  
Stage Process

In the current epidemic situations, people are facing several mental disorders related to Depression, Anxiety, and Stress (DAS). Numerous scales are developed for computing the levels for DAS, and DAS-21 is one among them. At the same time, machine learning (ML) models are applied widely to resolve the classification problem efficiently, and feature selection (FS) approaches can be designed to improve the classifier results. In this aspect, this paper develops an intelligent feature selection with ML-based risk management (IFSML-RM) for DAS prediction. The IFSML-RM technique follows a two-stage process: quantum elephant herd optimization-based FS (QEHO-FS) and decision tree (DT) based classification. The QEHO algorithm utilizes the input data to select a valuable subset of features at the primary level. Then, the chosen features are fed into the DT classifier to determine the existence or non-existence of DAS. A detailed experimentation process is carried out on the benchmark dataset, and the experimental results showcased the betterment of the IFSML-RM technique in terms of different performance measures.

Review on Feature Selection and Classification using Neuro-Fuzzy Approaches

2016 ◽  
Vol 7 (4) ◽  
pp. 28-44 ◽  
Author(s):  
Saroj Biswas ◽  
Monali Bordoloi ◽  
Biswajit Purkayastha
Keyword(s):  
Machine Learning ◽  
Feature Selection ◽  
Computation Time ◽  
Recent Survey ◽  
Learning Problems ◽  
Fuzzy Approach ◽  
Redundant Data ◽  
Classification Feature ◽  
Research Article ◽  
Neuro Fuzzy

This research article attempts to provide a recent survey on neuro-fuzzy approaches for feature selection and classification. Feature selection acts as a catalyst in reducing computation time and dimensionality, enhancing prediction performance or accuracy and curtailing irrelevant or redundant data. The neuro-fuzzy approach is used for feature selection and for providing some insight to the user about the symbolic knowledge embedded within the network. The neuro–fuzzy approach combines the merits of neural network and fuzzy logic to solve many complex machine learning problems. The objective of this article is to provide a generic introduction and a recent survey to neuro-fuzzy approaches for feature selection and classification in a wide area of machine learning problems. Some of the existing neuro-fuzzy models are also applied on standard datasets to demonstrate the applicability of neuro-fuzzy approaches.

scholarly journals Emotion Classification through Nonlinear EEG Analysis Using Machine Learning Methods

2018 ◽  
Vol 5 (4) ◽  
pp. 135-149 ◽  
Author(s):  
Morteza Zangeneh Soroush ◽  
Keivan Maghooli ◽  
Seyed Kamaledin Setarehdan ◽  
Ali Motie Nasrabadi
Keyword(s):  
Machine Learning ◽  
Emotion Recognition ◽  
Chaotic Behavior ◽  
Recognition Rate ◽  
Emotion Classification ◽  
Learning Methods ◽  
Suggested Approach ◽  
Machine Learning Methods ◽  
Combination Of Classifiers ◽  
Nonlinear Features

Background: Emotion recognition, as a subset of affective computing, has received considerable attention in recent years. Emotions are key to human-computer interactions. Electroencephalogram (EEG) is considered a valuable physiological source of information for classifying emotions. However, it has complex and chaotic behavior. Methods: In this study, an attempt is made to extract important nonlinear features from EEGs with the aim of emotion recognition. We also take advantage of machine learning methods such as evolutionary feature selection methods and committee machines to enhance the classification performance. Classification performed concerning both arousal and valence factors. Results: Results suggest that the proposed method is successful and comparable to the previous works. A recognition rate equal to 90% achieved, and the most significant features reported. We apply the final classification scheme to 2 different databases including our recorded EEGs and a benchmark dataset to evaluate the suggested approach. Conclusion: Our findings approve of the effectiveness of using nonlinear features and a combination of classifiers. Results are also discussed from different points of view to understand brain dynamics better while emotion changes. This study reveals useful insights about emotion classification and brain-behavior related to emotion elicitation.

scholarly journals Heart Disease Prediction Based on an Optimal Feature Selection Method using Autoencoder

2020 ◽  
pp. 25-38
Author(s):  
Azhar M. A. ◽  
Princy Ann Thomas
Keyword(s):  
Machine Learning ◽  
Feature Selection ◽  
Feature Selection Method ◽  
Classification Problem ◽  
Machine Learning Techniques ◽  
Classification Problems ◽  
Process Data ◽  
Integration Algorithm ◽  
Learning Techniques ◽  
Hybrid Classification

Heart Failure is one of the common diseases that can lead to dangerous situations. There are several data available within the healthcare systems. However, there was an absence of successful analysis methods to find connections and patterns in health care data. Some Machine learning methods can help us remedy this circumstance. This helps in getting a better insight into the concept of a classification problem. In many classification problems, it is difficult to learn good classifiers before removing these unwanted features due to the huge size of the data. In my work, we have used an artificial neural network-based autoencoder for effective feature selection The aim of feature selection is improving prediction performance and providing a better understanding of the process data. Hybrid Classification method with a dynamic integration algorithm for classification that aims at finding optimal features by applying machine learning techniques resulting in improving the performance in the prediction of cardiovascular disease.

scholarly journals Implementation of Rule based Classifiers for Wind Turbine Blade Fault Diagnosis using Vibration Signals

2019 ◽  
Vol 8 (2S11) ◽  
pp. 320-331
Keyword(s):  
Machine Learning ◽  
Feature Extraction ◽  
Feature Selection ◽  
Fault Diagnosis ◽  
Wind Turbine ◽  
Turbine Blade ◽  
Learning Approach ◽  
Feature Classification ◽  
Rule Based ◽  
Machine Learning Approach

The fast developing wind industry has revealed a requirement for more multifaceted fault diagnosis system in the segments of a wind turbine. “Present wind turbine researches concentrate on enhancing their dependability quality and decreasing the cost of energy production, especially when wind turbines are worked in off-shore places. Wind turbine blades are ought to be an important component among the other basic segments in the wind turbine framework since they transform dynamic energy of wind into useable power and due to environmental conditions, it get damage often and cause lack in productivity. The main objective of this study is to carry out a fault identification model for wind turbine blade using a machine learning approach through vibration data to classify the blade condition. Here five faults namely, blade bend, hub-blade loose connection, blade cracks, blade erosion and pitch angle twist have been considered. Machine learning approach has three steps namely feature extraction, feature selection and feature classification. Feature extraction was carried out by statistical analysis followed by feature selection using J48 decision tree algorithm. Feature classification was done using twelve rule based classifiers using WEKA. The results were compared with respect to the classification accuracy and the computational time of the classifier.”

scholarly journals Machine Learning Techniques for Brain Signal Analysis

2020 ◽  
Author(s):  
Charlie Dondapati ◽  
Arakkal Fahad ◽  
Jinan Fiaidhi
Keyword(s):  
Machine Learning ◽  
Signal Analysis ◽  
Brain Activity ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Human Cognition ◽  
Emotion Classification ◽  
Learning Models ◽  
Human Emotions ◽  
High Level

<p>Brain signal analysis has revolutionized the research on human-computer interaction. Analyzing brain activity of the human emotions opens greater avenues to advance the research on Brain signal analysis. Human emotions play a significant role in social intercourse, human cognition, and decision making.[1] In this project, Differential Entropy (DE) features of EEG are used to perform emotion classification. The DE features are more suited for emotion recognition than Energy spectrum (ES) features which are used traditionally [2]. We have applied machine learning algorithms to discriminate three categories of human emotion: 1) positive 2) neutral and 3) negative. Feature extraction and dimensionality reduction are performed on the EEG dataset to obtain high-level features which helped to increase the accuracy and efficiency of the classification models. We have performed numerous machine learning models on the EEG data and compared the results of deep learning models and shallow models. .</p><br>

scholarly journals Decoding the Neural Signatures of Valence and Arousal From Portable EEG Headset

2021 ◽  
Author(s):  
Nikhil Garg ◽  
Rohit Garg ◽  
Parrivesh NS ◽  
Apoorv Anand ◽  
V.A.S. Abhinav ◽  
...  
Keyword(s):  
Machine Learning ◽  
Feature Extraction ◽  
Feature Selection ◽  
Emotion Recognition ◽  
Machine Learning Techniques ◽  
Emotion Classification ◽  
Learning Techniques ◽  
Eeg Data ◽  
Valence And Arousal ◽  
Mean Square Errors

This paper focuses on classifying emotions on the valence-arousal plane using various feature extraction, feature selection and machine learning techniques. Emotion classification using EEG data and machine learning techniques has been on the rise in the recent past. We evaluate different feature extraction techniques, feature selection techniques and propose the optimal set of features and electrodes for emotion recognition. The images from the OASIS image dataset were used for eliciting the Valence and Arousal emotions, and the EEG data was recorded using the Emotiv Epoc X mobile EEG headset. The analysis is additionally carried out on publicly available datasets: DEAP and DREAMER. We propose a novel feature ranking technique and incremental learning approach to analyze the dependence of performance on the number of participants. Leave one out cross-validation was carried out to identify subject bias in emotion elicitation patterns. The importance of different electrode locations was calculated, which could be used for designing a headset for emotion recognition. Our study achieved root mean square errors of less than 0.75 on DREAMER, 1.76 on DEAP, and 2.39 on our dataset.

Sign in / Sign up

Export Citation Format

Share Document