Study of Emotion Recognition Based on Surface Electromyography and Improved Least Squares Support Vector Machine

Abstract

In order to improve human-computer interaction (HCI), computers need to recognize and respond properly to their user’s emotional state. This paper introduces emotional pattern recognition method of Least Squares Support Vector Machine (LS_SVM). The experiment introduces wavelet transform to analyze the Surface Electromyography (EMG) signal, and extracts maximum and minimum of the wavelet coefficients in every level. Then we construct the coefficients as eigenvectors and input them into improved Least Squares Support Vector Machines. The result of experiment shows that recognition rate of four emotional signals (joy, anger, sadness and pleasure) are all more than 80%. The results of experiment also show that the wavelet coefficients as the eigenvector can be effective characterization of EMG. The experimental results demonstrate that compared with classical L_M BP neural network and RBF neural network, LS_SVM has a better recognition rate for emotional pattern recognition.<a href="/index.php/jcp/author/saveSubmit/3#_ftn1"> </a&gt

Robust Facial Expression Recognition for MuCI: A Comprehensive Neuromuscular Signal Analysis

“…In this method, equality constraints are used to find the optimal solution by solving a set of linear equations instead of solving a quadratic optimization problem [81]. This classifier has already been examined for facial EMG classification and promising results were reported in [34], [39] and [42]. The LS-SVM model used in this paper is formed using RBF kernel where the regularization    and smoothing    2 parameters are set at 10 and 0.2 respectively while the multiclass LS-SVM is trained and encoded by the one-versus-all scheme.…”

Emotion Recognition Based on Various Physiological Signals - A Review

“…BP neural network was employed for solving linear equations used to achieve the classification makes the training time greatly reduced and the recognition rate can reach more than 83.33%. In [35], the author proposed emotional pattern recognition using Least Squares Support Vector Machine (LSSVM). For this, wavelet transform is used which has multi scale decomposition level.…”

A Fast and Stable Cluster Labeling Method for Support Vector Clustering

“…That is to say the distance from any data point lies in the profile to α is always lower than R. Following closely the derivation of [22]- [24], [26], to obtain the solution of the minimal hypersphere approximate covering with an appropriate width q of the kernel function, a gradient dynamical system which is associated with the trained kernel function R 2 (x) can be constructed as follows. 2 (1)…”

“…Input: the dataset X , Gaussian kernel width q and the penalty term C Output: labels for all the data points 1 collect V for q by solving dual problem 2 To analyze the time complexity of the proposed method, let N be the number of data points in a dataset, N SV be the number of SVs, l be the average number of iterations for each data point to locate its corresponding local minimum via the steepest decent process [22], N SEV is the number of SEVs and m be the sample rate. Apparently, the time cost by the three phases are O(lN SV ), mN 2 SEV and O((N − N SV )N SEV ) respectively. Therefore, the time complexity of FSCL is O(lN SV + N N SEV ).…”

“…Clustering, focusing on forming natural grouping of data points that maximize intro-cluster similarity and minimize inter-cluster similarity, has been extensively employed in image processing, pattern recognition, data analysis and instance-based learning, etc. Among the previous studies [1], [2], support vector clustering (SVC) [3]- [7], a boundary-based clustering algorithm inspired by the support vector machines (SVM) [8] whose advantage is to generate cluster boundaries of arbitrary shape, is recently emerged algorithm to characterize the support of a highdimensional distribution.…”