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.

Tunable-Q Wavelet Transform and Dual Multiclass SVM for Online Automatic Detection of Power Quality Disturbances

Abstract: A new automated recognition approach based on tunable-Q wavelet transform (TQWT) and a dual multiclass support vector machines (MSVM) has been proposed for detection of power quality disturbances. The proposed approach first investigates the presence of low-frequency interharmonics and then tunes the wavelet for decomposition of signal into fundamental and harmonic components. The tuning of Q-factor and redundancy makes the filter design to accurately extract the fundamental frequency component from a distorted input signal. Then, a unique set of features, which clearly reveal the characteristics of disturbances, are extracted. The power quality disturbances are broadly categorized into two groups based on the pre-obtained information of low-frequency interharmonics. Therefore, multiple disturbances are recognized by employing a dual MSVM, one for each group. Results demonstrate the applicability, strength, and accuracy of the proposed approach for classification of single and combined disturbances under different noisy conditions. Moreover, to illustrate the prominence of the features extracted from TQWT, two more classifiers based on decision tree and feedforward neural network have been employed for classification of power quality disturbances.

Human Activity Classification in Smartphones Using Accelerometer and Gyroscope Sensors

Abstract: Activity classification in smartphones helps us to monitor and analyze the physical activities of the user in daily life and has potential applications in healthcare systems. This paper proposes a descriptor-based approach for activity classification using built-in sensors of smartphones. Accelerometer and gyroscope sensor signals are acquired to identify the activities performed by the user. In addition, time and frequency domain signals are derived using the collected signals. In the proposed approach, two descriptors, namely, histogram of gradient and centroid signature-based Fourier descriptor, are employed to extract feature sets from these signals. Feature and score level fusion are explored for information fusion. For classification, we have studied the performance of multiclass support vector machine and $k$ -nearest neighbor classifiers. The proposed approach is evaluated on two publicly available data sets, namely, UCI HAR data set and physical activity sensor data. Our experimental results show that the feature level fusion provides better performance than the score level fusion. In addition, our approach provides considerable improvement in classifying different activities as compared with the existing works. The average activity classification accuracy achieved using the proposed method is 97.12% as against the existing work, which provided 96.33% on UCI HAR data set. On the second data set, the proposed approach attained 96.83% classification accuracy, whereas the existing work achieved 90.2%.

Measurement of prompt D -meson production in p-Pb collisions at sNN =5.02TeV

Abstract: The p_{T}-differential production cross sections of the prompt charmed mesons D^{0}, D^{+}, D^{*+}, and D_{s}^{+} and their charge conjugate in the rapidity interval -0.96