Sazali Yaacob

A new hybrid PSO assisted biogeography-based optimization for emotion and stress recognition from speech signal

Abstract Speech signals and glottal signals convey speakers’ emotional state along with linguistic information. To recognize speakers’ emotions and respond to it expressively is very much important for human-machine interaction. To develop a subject independent speech emotion/stress recognition system, by identifying speakers emotion from their voices, features from OpenSmile toolbox, higher order spectral features and feature selection algorithm, is proposed in this work. Feature selection plays an important role in overcoming the challenge of dimensionality in several applications. This paper proposes a new particle swarm optimization assisted Biogeography-based algorithm for feature selection. The simulations were conducted using Berlin Emotional Speech Database (BES), Surrey Audio-Visual Expressed Emotion Database (SAVEE), Speech under Simulated and Actual Stress (SUSAS) and also validated using eight benchmark datasets. These datasets are of different dimensions and classes. Totally eight different experiments were conducted and obtained the recognition rates in range of 90.31%–99.47% (BES database), 62.50%–78.44% (SAVEE database) and 85.83%–98.70% (SUSAS database). The obtained results convincingly prove the effectiveness of the proposed feature selection algorithm when compared to the previous works and other metaheuristic algorithms (BBO and PSO).

Particle swarm optimization based feature enhancement and feature selection for improved emotion recognition in speech and glottal signals.

In the recent years, many research works have been published using speech related features for speech emotion recognition, however, recent studies show that there is a strong correlation between emotional states and glottal features. In this work, Mel-frequency cepstralcoefficients (MFCCs), linear predictive cepstral coefficients (LPCCs), perceptual linear predictive (PLP) features, gammatone filter outputs, timbral texture features, stationary wavelet transform based timbral texture features and relative wavelet packet energy and entropy features were extracted from the emotional speech (ES) signals and its glottal waveforms(GW). Particle swarm optimization based clustering (PSOC) and wrapper based particle swarm optimization (WPSO) were proposed to enhance the discerning ability of the features and to select the discriminating features respectively. Three different emotional speech databases were utilized to gauge the proposed method. Extreme learning machine (ELM) was employed to classify the different types of emotions. Different experiments were conducted and the results show that the proposed method significantly improves the speech emotion recognition performance compared to previous works published in the literature.

Mental tasks classifications using S-transform for BCI applications

The classification of different types of mental tasks is an active area of research that seems to be ever expanding. This field is gaining interest from researchers all over the world. This study is intended to utilize the Stockwell transform (ST) to investigate the classification accuracy of five different types of mental tasks. A well known electroencephalogram (EEG) database (Keirn and Aunon database) has been used in this study. Two subjects from the database were considered for the study. k-means nearest neighborhood (k-NN) and Linear Discriminant Analysis (LDA) based classifiers were used to perform a pair-wise classification of the 10 combinations of mental tasks. Two different discriminant functions such as linear and quadratic were used in LDA classifier and their effects on the classification performance are presented. The effect of different ‘k’ values (1 to 10) was also studied in kNN algorithm. Conventional and k-fold cross validation methods were used to investigate the reliability of the classification results of the classifiers. The experimental results show that the proposed method gives promising pair-wise classification accuracy from 78.80% to 100%.

Black-box modelling of the induction motor

This paper is concerned with the black-box modelling of the induction motor from test data. Data obtained using a computer-based data acquisition card, the aim of the work described in this paper is to obtain linear model of the induction motor directly from test data. A pseudo random binary sequence (PRBS) was chosen as the test input signal. Data once collected was downloaded to the PC. The process of modelling and validation is then carried out using a MATLAB package. In this application a noise/disturbance free model structure (ARMAX) was assumed.

Recognition of motor imagery of hand movements for a BMI using PCA features

Motor imagery is the mental simulation of a motor act that includes preparation for movement and mental operations of motor representations implicitly or explicitly. The ability of an individual to control his EEG through imaginary mental tasks enables him to control devices through a brain machine interfaces (BMI). In other words a BMI can be used to rehabilitate people suffering from neuromuscular disorders as a means of communication or control. This paper presents a novel approach in the design of a four state BMI using two electrodes. The BMI is designed using Neural Network Classifiers. The performance of the BMI is evaluated using two network architectures. The performance of the proposed algorithm has an average classification efficiency of 93.5%.

Online self-tuning controller for induction motor based on generalized minimum variance method

The implicit or direct GMV regulator combined with the recursive least squares parameter estimation method was applied to regulate the speed of the induction motor under the influence of load variations. To obtain good tracking and control characteristics, a GMV self-tuning regulator is adopted and a design procedure is developed. The performance of the self-tuning GMV regulator depends a great deal on the specification of weighting polynomials for output, input and the reference point.

Hybrid BBO_PSO and higher order spectral features for emotion and stress recognition from natural speech

Display Omitted We proposed higher order spectral based Bispectral and Bicoherence features for multi-class emotion/stress recognition from speech signal.Utterances from three speech emotional databases namely BES, SAVEE and SUSAS have been used in this work.Multi-cluster feature selection, Hybrid Bio-geographical based optimization and particle swarm optimization (HBBO_PSO) are used for feature selection.Experiment results show the effectiveness and efficiency of the proposed method by yielding higher emotion/stress recognition rates. The aim of the present study is to select a set of higher order spectral features for emotion/stress recognition system. 50 Bispectral (28 features) and Bicoherence (22 features) based higher order spectral features were extracted from speech signal and its glottal waveform. These features were combined with Inter-Speech 2010 features to further improve the recognition rates. Feature subset selection (FSS) was carried out in this proposed work with the objective of maximizing emotion recognition rate for subject independent with minimum features. The FSS contains two stages: Multi-cluster feature selection was adopted in Stage 1 to reduce feature space and identify relevant feature subset from Interspeech 2010 features. In Stage 2, Biogeography based optimization (BBO), Particle swarm optimization (PSO) and proposed BBO_PSO Hybrid optimization were performed to further reduce the dimension of feature space and identify the most relevant feature subset, which has higher discrimination ability to distinguish different emotional states. The proposed method was tested in three different databases: Berlin emotional speech database (BES), Surrey audio-visual expressed emotion database (SAVEE) and Speech under simulated and actual stress (SUSAS) simulated domain. The proposed feature set was evaluated with subject independent (SI), subject dependent (SD), gender dependent male (GD-male), gender dependent female (GD-female), text independent pairwise speech (TIDPS), and text independent multi-style speech (TIDMSS) experiments by using SVM and ELM classifiers. From the results obtained, it is evident that the proposed method attained accuracies of 93.25% (SI), 100% (SD), 93.75% (GD-male), and 97.58% (GD-female) for BES; 62.38% (SI) and 76.19% (SD) for SAVEE; and 90.09% (TIDMSS), 97.04% (TIDPS Angry vs. Neutral), 98.89% (TIDPS Lombard vs. Neutral), 99.07% (TIDPS Loud vs. Neutral) for SUSAS.

Real time self tuning controller for induction motor based on PI method

The self-tuning speed control of induction motor drives is presented using proportional plus integral (PI) method combined with the recursive least squares parameter estimation method to regulate the motor speed and load variation. To obtain good tracking and control characteristics, a PI self-tuning controller is adopted and the design procedure is developed for systematically finding its parameters according to the recursive least square method. The performance of the PI self-tuning controller greatly improves due to the integral action which eliminate the disturbance and the steady-state error. In addition, the RLS identification minimizes the error between the actual plant parameter and the recently estimated plant parameter.

A novel indoor mobile robot mapping with USB-16 ultrasonic sensor bank and NWA optimization algorithm

This paper highlights on the development of a Ultrasonic Sensor Bank with sixteen pieces 40 kHz ultrasonic sensor (USB-16) mounted on hexadecagon-based plate on a mobile robot to perform real time 2D and 3D mapping. The purpose of this research is to evaluate the capability of USB-16 in providing an accurate map in terms of the walls perimeter and its shape, where the robot is located. Each wall will be scanned with USB-16 sensor bank to measure the distance between the center of sensor bank and the wall. The Homogeneous Transformation Matrix (HTM) and trigonometrically algorithm is utilized in this research as a wall mapping algorithm and is clearly explained in this paper. An optimum wall mapping algorithm was introduced to minimize measurement error. The optimum wall mapping technique named a Nominal Wall Angle (NWA) using trigonometric approach was introduced to improve the mapping accuracy. This algorithm has the capability to improve the ultrasonic mapping accuracy during the scanning process and is different from data manipulation technique like most of similar researches currently adapted. The comparison of experimental results before and after implementation of the optimization technique in different wall shape (Curve, Square, Rectangle, Triangle and Laboratory environment) will be presented in this paper. The results are very impressive, where the implementation of NWA algorithm is able to produce an accurate wall mapping compared with the actual wall size. LabVIEW software, Basic Atom and BASIC Stamp microcontroller are fully utilized to produce the real time 2D and 3D graph during the USB-16 mapping.

Real time self tuning controller for induction motor based on pole assignment method

In this paper, a self-tuning speed control of induction motor drives is presented using pole placement method combined with recursive least squares parameter estimation method to regulate the induction motor speed under load variation. To obtain good tracking and control characteristics, a pole placement self-tuning controller is adopted and design procedure is developed for systematically finding its parameters according to recursive least square method. The performance of the self-tuning pole assignment controller depends a great deal on the specification of the tailoring polynomial. Thus the poles of the tailoring polynomial should be chosen carefully.