Ramchandra Manthalkar

ECG Denoising by Modeling Wavelet Sub-Band Coefficients using Kernel Density Estimation

Discrete wavelet transforms are extensively preferred in biomedical signal processing for denoising, feature extraction, and compression. This paper presents a new denoising method based on the modeling of discrete wavelet coefficients of ECG in selected sub-bands with Kernel density estimation. The modeling provides a statistical distribution of information and noise. A Gaussian kernel with bounded support is used for modeling sub-band coefficients and thresholds and is estimated by placing a sliding window on a normalized cumulative density function. We evaluated this approach on offline noisy ECG records from the Cardiovascular Research Centre of the University of Glasgow and on records from the MIT-BIH Arrythmia database. Results show that our proposed technique has a more reliable physical basis and provides improvement in the Signal-to-Noise Ratio (SNR) and Percentage RMS Difference (PRD). The morphological information of ECG signals is found to be unaffected after employing denoising. This is quantified by calculating the mean square error between the feature vectors of original and denoised signal. MSE values are less than 0.05 for most of the cases.

Electroencephalography-Based Emotion Recognition Using Gray-Level Co-occurrence Matrix Features

Emotions are very essential for our day-to-day activities such as communication, decision-making and learning. Electroencephalography (EEG) is a non-invasive method to record electrical activity of the brain. To make Human–Machine Interaction (HMI) more natural, human emotion recognition is important. Over the past decade, various signal processing methods are used for analysing EEG-based emotion recognition (ER). This paper proposes a novel technique for ER using Gray-Level Co-occurrence Matrix (GLCM)-based features. The features are validated on benchmark DEAP database upto four emotions and classified using K-nearest neighbor (K-NN) classifier.

Joint Compression and Classification for Textures in the Wavelet and Ridgelet Domain

Image Compression is a widely addressed research area. Many compression standards are in place. There are many methods for image classification. But the joint compression and classification is a new research area wherein the classification is attempted in the compressed domain. The joint compression and classification (JCC) is explored in wavelet domain by some researchers. But it is not yet explored in Ridgelet domain. This paper discusses the performance of JCC for Wavelet and Ridgelet domain for Texture images. The experimentation is done with objective analysis and subjective analysis. Objective analysis is performed using the Compression metrics-RMSE, PSNR and classification metric- CCR. Subjective analysis is performed using Human Visual Perception. It is found that the Ridgelet Transform gives less Mean Squared Error (MSE) and is better for Joint Compression and Classification of Texture images. Extensive experimentation has been carried out to arrive at the conclusion.

Nonuniform Frequency Sampling Approach to FIR Filter Design

This paper investigates the new approach to FIR filter design based on nonuniform frequency sampling. This method generates the nonuniform samples in passband and stopband separately using Gaussian function. For the generated nonuniform sample, the desired frequency response values are generated using ideal filter characteristics. Then, taking its nonuniform IDFT gives the required filter coefficients. The proposed method is compared with existing methods like uniform frequency sampling and optimal filter design method and results show that the investigated approach has a better advantage over uniform frequency sampling and Parks–McClellan method with regard to the frequency response of designed filter.

The Detrended Fluctuation Analysis of EEG Signals: A Meditation-Based Study

The Detrended Fluctuation Analysis is a widely used method for analysis of non-stationary time series which has been applied to EEG signals. The Detrended Fluctuation Analysis (DFA) of the EEG signals in pre- and post-meditation (mindfulness) intervention are compared. It is observed that the EEG data obtained from 8 subjects out of total 11 subjects shows reduction in the DFA values. The reduction in DFA values represents the lower intrinsic fluctuations in the EEG time series, which is a measure of better (higher) complexity of these vital rhythms. The reduced DFA values after 8 weeks of Focused Attention (mindfulness) meditation practice in more number of subjects, indicates that the meditation practice enhances the ability to handle complexity. The reduced DFA values indicate improved neuronal functioning of these subjects.

Analyzing Effect of Meditation Using Higher Order Crossings and Functional Connectivity

People are experiencing difficulties in adapting to the rapid changes in work and social fabric due to the evolution of advanced technologies in everyday life. Health and well-being of an individual in the existing world is important for proper living. Meditation improves the adaptability of an individual to live a healthy and social life. To verify this, an experiment is designed with the simple meditation practice called Focused Attention for 8 weeks. The brain activity is recorded of 11 subjects using EMOTIV EPOC+ EEG device before (pre-meditation) and after (post-meditation) meditation. Features called Higher Order Crossings and Functional Connectivity are used to analyze the effect of meditation. The results indicated a decrease in HOC values for frontal, parietal, and occipital lobes and increase in HOC of temporal lobe. The interhemispheric connectivity increased after meditation practice.

Comparative Analysis of ICA, PCA-Based EASI and Wavelet-Based Unsupervised Denoising for EEG Signals

Electroencephalography (EEG) can be used to study various brain activities related to human responses and disorders. EEG signal is prone to noises which are caused due to eye movements, power-line interference, muscle movements, etc. Therefore, to obtain refined EEG signals for further processing, it should be denoised. There are several methods by which EEG signals can be denoised, among which we have used Independent Component Analysis (ICA), Principal Component Analysis (PCA)-based Equivariant Adaptive Separation by Independence (EASI), and Wavelet-based unsupervised denoising methods. The performance of these methods is compared using Signal-to-Noise Ratio (SNR) and Percentage Root-mean-square Difference (PRD).

Time series decomposition and predictive analytics using MapReduce framework

Abstract The recent development in precision agriculture, a large amount of data are generated by site-specific weather stations which will demand a platform for the processing and predictive weather analytics. The sophisticated methodology to solve large amount of data handling problem and process data in a small time is important. In this study, future conditions are predicted from weather stations large data by proposing the predictive approaches based on time series and neural network using MapReduce programming model. We have proposed predictive analytics approaches including the modules, i.e., analysis and decomposition, classification, and prediction. The time series based decomposition approach is proposed to decompose and find out the trend, regular and sophisticated components. The linear components are handled by time series MapReduce based Autoregressive Integrated Moving Average (M-ARIMA) model and nonlinear components are handled by M-K-Nearest Neighbors (M-KNN) model. In addition, the MapReduce-based Hybrid Model (M-HM) was proposed which will use the advantages of time series and neural network to increase prediction accuracy. The study verifies the effectiveness of proposed model over the regular and randomness component of the data. The performance measures and statistical test are performed to validate and check data consistency. In addition, excellent speed-up, scale-up, and size-up were tested by changing the size of data set. However, when the data size increases, the average execution time is reduced by using the MapReduce-based approach over the multiple-node workers.

Assessing effect of meditation on cognitive workload using EEG signals

Recent research suggests that meditation affects the structure and function of the brain. Cognitive load can be handled in effective way by the meditators. EEG signals are used to quantify cognitive load. The research of investigating effect of meditation on cognitive workload using EEG signals in pre and post-meditation is an open problem. The subjects for this study are young healthy 11 engineering students from our institute. The focused attention meditation practice is used for this study. EEG signals are recorded at the beginning of meditation and after four weeks of regular meditation using EMOTIV device. The subjects practiced meditation daily 20 minutes for 4 weeks. The 7 level arithmetic additions of single digit (low level) to three digits with carry (high level) are presented as cognitive load. The cognitive load indices such as arousal index, performance enhancement, neural activity, load index, engagement, and alertness are evaluated in pre and post meditation. The cognitive indices are improved in post meditation data. Power Spectral Density (PSD) feature is compared between pre and post-meditation across all subjects. The result hints that the subjects were handling cognitive load without stress (ease of cognitive functioning increased for the same load) after 4 weeks of meditation.

Recognition of vision-based activities of daily living using linear predictive coding of histogram of directional derivative

In this paper, we have introduced a novel approach for recognition of activities of daily living (ADL). These activities are the ones that the human beings perform in daily life. At the object level, we used computational color model for efficient object segmentation and tracking to handle dynamic background change in indoor environment. To make it computationally efficient, cosine of the angle between the expected image color vector and current image color vector is used. At feature level, we have presented a linear predictive coding of histogram of directional derivative as a spatio-temporal descriptor. Our proposed descriptor describes the local object shape and appearance within cuboids effectively and distinctively. A multiclass support vector machine has been used to classify the human activities. The proposed framework for recognition of indoor human activity has been extensively validated on the benchmark of ADL datasets, with a focus that this methodology is robust and attains more precise human activity recognition rate as compared to current methodologies available.