Indian Institute of Technology Indore

About: Indian Institute of Technology Indore is a education organization based out in Indore, Madhya Pradesh, India. It is known for research contribution in the topics: Fading & Support vector machine. The organization has 1606 authors who have published 4803 publications receiving 66500 citations.

Application of TQWT based filter-bank for sleep apnea screening using ECG signals

Abstract: The sleep apnea is a disease in which there is the absence of airflow during respiration for at least 10 s. It may occur several times during the night sleep. This disease can lead to many types of cardiovascular diseases. To detect this disease, signals obtained from many channels of polysomnography are to be observed visually by physicians for the long duration. This procedure is expensive, time-consuming, and subjective. Hence, it is required to build an automated system to detect the sleep apnea with few channels. This paper uses single-lead electrocardiogram (ECG) signal to detect apneic and non-apneic events. The proposed method uses tunable-Q wavelet transform (TQWT) based filter-bank instead of TQWT to decompose the segment of ECG signal into several constant bandwidth sub-band signals. Then centered correntropies are computed from the various sub-band signals. The obtained features are then fed to the various classifiers to select the optimum performing classifier. In this work, we have obtained the highest classification accuracy, specificity, and sensitivity of 92.78%, 93.91%, and 90.95% respectively using random forest classifier. Hence, our developed prototype is ready for validation with the huge database and clinical usage.

Event-shape engineering for inclusive spectra and elliptic flow in Pb-Pb collisions at √sNN = 2.76 TeV

Abstract: We report on results obtained with the event-shape engineering technique applied to Pb-Pb collisions at √sNN=2.76 TeV. By selecting events in the same centrality interval, but with very different average flow, different initial-state conditions can be studied. We find the effect of the event-shape selection on the elliptic flow coefficient v2 to be almost independent of transverse momentum pT, which is as expected if this effect is attributable to fluctuations in the initial geometry of the system. Charged-hadron, -pion, -kaon, and -proton transverse momentum distributions are found to be harder in events with higher-than-average elliptic flow, indicating an interplay between radial and elliptic flow.

EEG Signal Classification Using Empirical Mode Decomposition and Support Vector Machine

Abstract: In this paper, we present a new method based on empirical mode decomposition (EMD) for classification of seizure and seizure-free EEG signals. The EMD method decomposes the EEG signal into a set of narrow-band amplitude and frequency modulated (AM-FM) components known as intrinsic mode functions (IMFs). The method proposes the use of the area parameter and mean frequency estimation of IMFs in the classification of the seizure and seizure-free EEG signals. These parameters have been used as an input in least squares support vector machine (LS-SVM), which provides classification of seizure EEG signals from seizure-free EEG signals. The classification accuracy for classification of seizure and seizure-free EEG signals obtained by using proposed method is 98.33% for second IMF with radial basis function kernel of LS-SVM.