Monira Islam

Human emotion recognition using frequency & statistical measures of EEG signal

The purpose of the research is to evaluate the different human emotions through Electroencephalogram (EEG) signal and to receive information about the internal changes of brain state. The paper presents the detection of human emotion based on some salient features of EEG signal. For this purpose, seven emotional states have been specified such as relax, thought, memory related, motor action, pleasant, fear, and enjoying music. Several EEG signals have been collected for these states and analyzed using frequency transform and statistical measures. Different significant features have been extracted from the analyzed signal. Among various statistical measures skewness and kurtosis are chosen which indicate the largest dispersion in different mental states and help to evaluate different human emotions. Frequency analysis shows how the ranges of magnitude vary with different frequency components. On the basis of magnitude ranges different emotional states are identified. EEG signal provides an effective way in the functioning of the brain to study of mental behavior.

Electronic energy meter with remote monitoring and billing system

Electronic energy meter is capable of taking readings and can store it into its memory. Taking energy meter reading is time consuming and an expensive task. The meter reader travels for a long distance and take the reading manually to prepare the bill. Consumers have to go to the billing office, stand in a long line and submit the bill. This is a boring job and time consuming also. It can be avoided by remote monitoring of electronic energy meter and prepaid billing system by the use of cash card. In this paper measurement of energy, remote monitoring, preparing of bill and billing system is presented. Low cost ATMEGA8L microcontroller is used here to control the whole system. Sampling of voltage and current is done by it. Then it processes data to achieve power in that instant. Then it stores the value of total energy consumed by the consumer and can calculate energy charge according to the tariff. LCD display is attached with this system to show total energy consumed, power factor and amount of charge etc. Communication between central energy distribution office and energy meter is done through power line. Complex tariff rate set up and cash card based billing is possible in this system. Electronic meter gives high accuracy for nonlinear loads than conventional rotating disc type electro-mechanical meter. Greater accuracy and stability can be maintained in this system.

Cognitive State Estimation by Effective Feature Extraction and Proper Channel Selection of EEG Signal

This paper presents a cognitive state estimation system focused on some effective feature extraction based on temporal and spectral analysis of electroencephalogram (EEG) signal and the proper channel selection of the BIOPAC automated EEG analysis system. In the proposed approach, different frequency components (i) real value; (ii) imaginary value; (iii) magnitude; (iv) phase angle and (v) power spectral density of the EEG data samples during different mental task performed to assess seven types of human cognitive states — relax, mental task, memory related task, motor action, pleasant, fear and enjoying music on the three channels of BIOPAC EEG data acquisition system — EEG, Alpha and Alpha RMS signal. Also the time and time-frequency-based features were extracted to compare the performance of the system. After feature extraction, the channel efficacy is evaluated by support vector machine (SVM) based on the classification rate in different cognitive states. From the experimental results and classification accuracy, it is determined that the overall accuracy for alpha channel shows much improved result for power spectral density than the other frequency based features and other channels. The classification rate is 69.17% for alpha channel whereas for EEG and alpha RMS channel it is found 47.22% and 32.21%, respectively. For statistical analysis standard deviation shows better result for alpha channel and it is found 65.4%. The time-frequency analysis shows much improved result for alpha channel also. For the mean value of DWT coefficients the accuracy is highest and it is 81.3%. Besides the classification accuracy, SVM shows better performance in compare with kNN classifier.

Refractive Index, Absorption Coefficient, and Photoelastic Constant: Key Parameters of InGaAs Material Relevant to InGaAs-Based Device Performance

A theoretical study has been carried out to evaluate key parameters of InxGa1-xAs material at energies below the direct band edge. The spectral dependence of refractive index, absorption coefficient, and photoelastic constants are evaluated for the whole composition range in InxGa1-xAs material on the basis of simplified models of the interband transitions. The results obtained from the present study are compared with the experimental results and found to be in good agreement. We have also evaluated refractive-index steps between InxGa1-xAs and GaAs materials for variety of waveguiding device applications.

Human emotion modeling based on salient global features of EEG signal

Feature extraction and accurate classification of the emotion-related EEG-characteristics have a key role in success of emotion recognition systems. This paper proposes an emotion modeling from EEG (Electroencephalogram) signals based on both time and frequency domain features by applying some statistical measures, Fourier and wavelet transform. After collecting the EEG signals, the various kinds of EEG features are investigated to build an emotion classification system. The main objective of this work is to compare the efficacy of the extracted features for classifying five types of emotional states relax, mental task, memory related task, pleasant, and fear. For this purpose support vector machine classifier was employed to classify the five emotional states by using salient global features. In case of statistical features the overall accuracy was obtained 54.2%, which is improved for FFT features 55.00% and the highest accuracy was obtained by DWT features 60.15%.

Wavelet based analysis of EEG signal for evaluating mental behavior

The purpose of the research is to evaluate the different human mental behavior through Electroencephalogram (EEG) signal with time-frequency analysis by receiving information from the internal changes of brain state. The paper presents the detection of human mental states based on some salient features of EEG signal. For this purpose seven emotional states have been specified such as relax, thought, memory related, motor action, pleasant, fear, and enjoying music. Several EEG signals have been collected for these states and analyzed using discrete wavelet transform. The discrete wavelet transform (DWT) is used to extract different significant features from the analyzed signal by computing the subband coefficients and applying statistical measures on them. Among various statistical measures maximum and minimum value, mean and standard deviation of wavelet coefficients in each subband are chosen which indicate the dispersion in different mental states and help to evaluate them. The analyzed results are compared with the spectrum analysis. It is found that wavelet analysis provides more effective way in the functioning of the brain to study of mental behavior in compare with Fourier analysis.

Mathematical modeling of human emotions using sub-band coefficients of wavelet analysis

Human emotion reflects on human behavior which plays a vital role in physiological research and real-time application. Mathematical modeling of emotional states plays a significant role in this scope which can correlate between human cognition, emotion and mental behavior. In this paper, we propose a new approach to model the emotional states with mathematical expressions based on wavelet analysis and trust region algorithm. The brain signals are collected using BIOPAC automated MP36 system and transformed on time-frequency domain using Daubechies4 wavelet function on different emotional states such as relax, memory, pleasant, fear, motor action, and enjoying music to extract the wavelet coefficients of these different states. The emotional states are modeled with different mathematical expressions which can be verified with these wavelet coefficients from the adjusted R-square percentage and the sum of square errors. The adjusted R- square percentage of the mathematical modeled states with the actual emotional states are 78.4% for relax, 77.18% for motor action and for memory, pleasant, enjoying music and fear they are 93%, 95.6%, 97.7% and 91.5% respectively. The main focus of this paper is to propose the mathematical modeling of these states which can be further applied for practical hardware implementation of human emotion based systems.

Projected Performance of InxGa1-xN-Based Multijunction Solar Cells

This paper reports the theoretical design and performance of In xGa1-xN-based multijunction solar cells for high efficiency. A simulation model is developed which optimizes the design of MJ solar cells for high efficiency. The efficiency was optimized by optimizing the band gap and thickness of different cells while keeping the current mismatch between different cells below 0.2%. The efficiency is found to be varied from 34.2% for two junctions to 45.22% for six junctions. Further increase in junction does not significantly increase the efficiency. An efficiency of about 46% is achievable for a seven junctions with a photocurrent density of 8.33 mA/cm2 and an open-circuit voltage of 6.26 V. The photocurrent density and open circuit voltage of each junction are calculated under AM 1.5 and it is assumed that each junction absorbs the solar photons that are not absorbed by the preceding one

An approach of cardiac disease prediction by analyzing ECG signal

Electrocardiogram (ECG) gives useful information about morphological and functional details of heart which is used to predict various cardiac diseases. In this paper a method of detecting cardiac diseases using support vector machine (SVM) is proposed. In this proposed method diseases are modeled using the time domain features of ECG signal which are extracted using BIOPAC AcqKnowledge software. Raw ECG signal contains these useful features which can be used to detect cardiac arrhythmia. The various ECG parameters like heart rate, QRS complex, PR interval, ST segment elevation, ST interval of ECG signal are used for analysis. Based on these parameters of ECG signal, different heart disease like atrial fibrillation, sinus tachycardia, myocardial infarction and apnea are detected. The individual accuracy of tachycardia arrhythmia, MI arrhythmia, atrial fibrillation arrhythmia and apnea proposed by SVM are 83.3%, 86.4%, 88% and 85.7% respectively.

Inherent features extraction for different colors stimulation of EEG signal

Inherent features of Electroencephalogram (EEG) signal acts a vital role to determine the human brain condition. The motivation of this paper is to extract the inherent features of EEG signal by visual stimulation of different colors such as green, red, blue, yellow. For stimulation Microsoft PowerPoint slide of different colors are shown to the subjects. Inherent features are extracted using statistical analysis, Fast Fourier Transform (FFT) and Power Spectral Density (PSD). In statistical measure, mean and maximum value of EEG signal indicate the largest dispersion and they so they are chosen as the prominent features for detection of different colors according to the stimulation of the brain signal. From the FFT and PSD analysis, the maximum frequency and power can be detected for specific color. So the focus of this study is to identify different colors according to the features of stimulated brain signal. In this analysis, human brain is more stimulated for green color than the other colors.