Aneesh C

This paper presents the effective exploitation of Graphical ProcessingUnit (GPU) in Raspberry Pi for fast Fourier transform (FFT) computation. Very fast computation of FFT is found useful in computer vision based navigation system,Global Positioning System (GPS), HAM radio and on Raspberry Pi. A comparisonis performed over the speed of FFT computation on BCM2835 GPU with that of 700 MHz ARM processor available in Raspberry Pi and also with intel-COREi5processors. The FFT is computed for any one… Show more

This paper presents the effective exploitation of Graphical ProcessingUnit (GPU) in Raspberry Pi for fast Fourier transform (FFT) computation. Very fast computation of FFT is found useful in computer vision based navigation system,Global Positioning System (GPS), HAM radio and on Raspberry Pi. A comparisonis performed over the speed of FFT computation on BCM2835 GPU with that of 700 MHz ARM processor available in Raspberry Pi and also with intel-COREi5processors. The FFT is computed for any one dimensional input signal and itsanalysis is done on different processors with varying signal lengths. The GNU radiois installed on Raspberry Pi, and the FFT computation done on GNU radiois accelerated using GPU of Raspberry Pi. Even though the Raspberry Pi GPU isprimarily built for video enhancement, the parallel computational ability of GPU isutilized in this paper for accelerated FFT computation. Show less

his paper discusses the methodology to recognize printed Malayalam characters in document images using Singular Value Decomposition (SVD) and Euclidean Distance Measure. Optical character recognition (OCR) task is challenging for Malayalam language characters as there exist similarity among many characters. The present work utilizes Active Contour based segmentation technique for character segmentation and performs Singular Value Decomposition operation to represent the character in a low… Show more

his paper discusses the methodology to recognize printed Malayalam characters in document images using Singular Value Decomposition (SVD) and Euclidean Distance Measure. Optical character recognition (OCR) task is challenging for Malayalam language characters as there exist similarity among many characters. The present work utilizes Active Contour based segmentation technique for character segmentation and performs Singular Value Decomposition operation to represent the character in a low dimensional feature space.
In this feature space, the recognition task is performed using Euclidean Distance Measure. The identied character is then represented in
UTF-8 encoding scheme to get displayed in notepad. Show less

This work considers the classification of power quality disturbances based on VMD (Variational Mode Decomposition) and EWT (Empirical Wavelet Transform) using SVM (Support Vector Machine). Performance comparison of VMD over EWT is done for producing feature vectors that can extract salient and unique nature of these disturbances. In this paper, these two adaptive signal processing methods are used to produce three Intrinsic Mode Function (IMF) components of power quality signals. Feature… Show more

This work considers the classification of power quality disturbances based on VMD (Variational Mode Decomposition) and EWT (Empirical Wavelet Transform) using SVM (Support Vector Machine). Performance comparison of VMD over EWT is done for producing feature vectors that can extract salient and unique nature of these disturbances. In this paper, these two adaptive signal processing methods are used to produce three Intrinsic Mode Function (IMF) components of power quality signals. Feature vectors produced by finding sines and cosines of statistical parameter vector of three different IMF candidates are used for training SVM. Validation for six different classes of power qualities including normal sinusoidal signal, sag, swell, harmonics, sag with harmonics, swell with harmonics is performed using synthetic data in MATLAB. Classification results using SVM shows that VMD outperforms over EWT for feature extraction process and the classification accuracy is tabled. Show less