Classifiers For Emotion Recognition Research Articles

BiTCAN: A emotion recognition network based on saliency in brain cognition.

In recent years, with the continuous development of artificial intelligence and brain-computer interfaces, emotion recognition based on electroencephalogram (EEG) signals has become a prosperous research direction. Due to saliency in brain cognition, we construct a new spatio-temporal convolutional attention network for emotion recognition named BiTCAN. First, in the proposed method, the original EEG signals are de-baselined, and the two-dimensional mapping matrix sequence of EEG signals is constructed by combining the electrode position. Second, on the basis of the two-dimensional mapping matrix sequence, the features of saliency in brain cognition are extracted by using the Bi-hemisphere discrepancy module, and the spatio-temporal features of EEG signals are captured by using the 3-D convolution module. Finally, the saliency features and spatio-temporal features are fused into the attention module to further obtain the internal spatial relationships between brain regions, and which are input into the classifier for emotion recognition. Many experiments on DEAP and SEED (two public datasets) show that the accuracies of the proposed algorithm on both are higher than 97%, which is superior to most existing emotion recognition algorithms.

Multimodal Emotion Recognition From EEG Signals and Facial Expressions

Emotion recognition has attracted a lot of attention in recent years. It is widely used in health care, teaching, human-computer interaction, and other fields. Various human emotional features are often used to recognize different emotions. Currently, there is more and more research on multimodal emotion recognition based on the fusion of multiple features. This paper proposes a deep learning model of multimodal emotion recognition based on the fusion of electroencephalogram (EEG) signals and facial expressions to achieve an excellent classification effect. First, the pre-trained convolution neural network (CNN) is used to extract the facial features from the facial expressions. Next, the attention mechanism is introduced to extract more critical facial frame features. Then, we apply CNNs to extract spatial features from original EEG signals, which use a local convolution kernel and a global convolution kernel to learn the features of left and right hemispheres channels and all EEG channels. After feature-level fusion, the fusion features of the facial expression features and EEG features are fed into the classifier for emotion recognition. This paper conducted experiments on the DEAP and MAHNOB-HCI datasets to evaluate the performance of the proposed model. The accuracy of valence dimension classification is 96.63%, and arousal dimension classification is 97.15% on the DEAP dataset, while 96.69% and 96.26% on the MAHNOB-HCI dataset. The experimental results show that the proposed model can effectively carry out emotion recognition.

Voice Emotion Recognition using CNN and Decision Tree

This paper presents the use of decision tree and CNN as classifier to classify the emotions from the English and Kannada audio data. The performance of CNN and DT are potential for various emotions. Comparative study of the classifiers using various parameters is presented. The performance of CNN has been identified as the best classifier for emotion recognition. Emotions are recognized with 72% and 63% accuracy using CNN and Decision Tree algorithms respectively. MFCC features are extracted from the audio signals and Model is trained, tested and evaluated accordingly by changing the parameters. Speech Emotion Recognition system is useful in psychiatric diagnosis, lie detection, call centre conversations, customer voice review, voice messages.

Emotion recognition from single-channel EEG signals using a two-stage correlation and instantaneous frequency-based filtering method

Background and objective:The recognition of emotional states is a crucial step in the development of a brain-computer interface (BCI) system. Emotion recognition system finds applications in medical science for the impaired and disabled people. Electroencephalography assesses the neurophysiology of the brain for recognition of different emotional states.Methods: The audio-video stimulus based experimental setup is arranged for the electroencephalogram (EEG) recordings of happy, fear, sad, and relax emotions and a two-stage filtering method is proposed for the recognition of emotion EEG signals. At the first stage, a correlation-criterion is suggested for removal of noisy intrinsic mode functions (IMFs) from the IMFs obtained by applying the empirical mode decomposition on the raw EEG signal. The noise-free IMFs are used to reconstruct the denoised EEG signal with improved stationarity characteristics. The denoised EEG signal is further decomposed into modes using the variational mode decomposition (VMD). At the second stage, the instantaneous-frequency based filtering of VMD modes is performed and filtered modes are retained for the reconstruction of denoised EEG signal with the desired frequency range. After two-stage filtering, the non-linear measures of filtered EEG signals are used as input features to multi-class least squares support vector machine (MC-LS-SVM) classifier for emotion recognition.Results:The different kernel functions are tested in MC-LS-SVM classifier for emotion recognition. The Morlet wavelet (MW) kernel function provides the best individual classification accuracies for happy, fear, sad, and relax emotions as 92.79%, 87.62%, 88.98%, and 93.13%, respectively. The MW-kernel function also obtained the best overall accuracy of 90.63%, F1-score 0.9064, and kappa value 0.8751.Conclusions: The Audio-video stimulus based emotion EEG-dataset is recorded. A new filtering method is proposed for EEG signals. The proposed method provides better emotion recognition performance as compared to the state-of-the-art methods and classifies emotions using single-bipolar EEG channel, which can greatly reduce the complexity of emotion-recognition based BCI systems.

EEG based patient emotion monitoring using relative wavelet energy feature and Back Propagation Neural Network.

In EEG-based emotion recognition, feature extraction is as important as the classification algorithm. A good choice of features results in higher recognition rate. However, there is no standard method for feature extraction in EEG-based emotion recognition, especially for real time monitoring, where speed of computation is crucial. In this work, we assess the use of relative wavelet energy as features and Back Propagation Neural Network (BPNN) as classifier for emotion recognition. This method was implemented in simulated real time emotion recognition by using a publicly accessible database. The results showed that relative wavelet energy and BPNN achieved an average recognition rate of 92.03%. The highest average recognition rate was achieved when the time window was 30s.

Features and classifiers for emotion recognition from speech: a survey from 2000 to 2011

Speaker emotion recognition is achieved through processing methods that include isolation of the speech signal and extraction of selected features for the final classification. In terms of acoustics, speech processing techniques offer extremely valuable paralinguistic information derived mainly from prosodic and spectral features. In some cases, the process is assisted by speech recognition systems, which contribute to the classification using linguistic information. Both frameworks deal with a very challenging problem, as emotional states do not have clear-cut boundaries and often differ from person to person. In this article, research papers that investigate emotion recognition from audio channels are surveyed and classified, based mostly on extracted and selected features and their classification methodology. Important topics from different classification techniques, such as databases available for experimentation, appropriate feature extraction and selection methods, classifiers and performance issues are discussed, with emphasis on research published in the last decade. This survey also provides a discussion on open trends, along with directions for future research on this topic.

Visuo-auditory Multimodal Emotional Structure to Improve Human-Robot-Interaction

We propose an approach to analyze and synthesize a set of human facial and vocal expressions, and then use the classified expressions to decide the robot’s response in a human-robot-interaction. During a human-to-human conversation, a person senses the interlocutor’s face and voice, perceives her/his emotional expressions, and processes this information in order to decide which response to give. Moreover, observed emotions are taken into account and the response may be aggressive, funny (henceforth meaning humorous) or just neutral according to not only the observed emotions, but also the personality of the person. The purpose of our proposed structure is to endow robots with the capability to model human emotions, and thus several subproblems need to be solved: feature extraction, classification, decision and synthesis. In the proposed approach we integrate two classifiers for emotion recognition from audio and video, and then use a new method for fusion with the social behavior profile. To keep the person engaged in the interaction, after each iterance of analysis, the robot synthesizes human voice with both lips synchronization and facial expressions. The social behavior profile conducts the personality of the robot. The structure and work flow of the synthesis and decision are addressed, and the Bayesian networks are discussed. We also studied how to analyze and synthesize the emotion from the facial expression and vocal expression. A new probabilistic structure that enables a higher level of interaction between a human and a robot is proposed.