Origin and triggers of power quality (PQ) events must be identified in prior, in order to take preventive steps to enhance power quality. However it is important to identify, localize and classify the PQ events to determine the causes and origins of PQ disturbances. In this paper a novel algorithm is presented to classify voltage variations into six different PQ events considering the space phasor model (SPM) diagrams, dual tree complex wavelet transforms (DTCWT) sub bands and the convolution neural network (CNN) model. The input voltage data is converted into SPM data, the SPM data is transformed using 2D DTCWT into low pass and high pass sub bands which are simultaneously processed by the 2D CNN model to perform classification of PQ events. In the proposed method CNN model based on Google Net is trained to perform classification of PQ events with default configuration as in deep neural network designer in MATLAB environment. The proposed algorithm achieve higher accuracy with reduced training time in classification of events than compared with reported PQ event classification methods.

This paper presents experimental work on mammogram image analysis. Texture analysis is carried out using segmentation technique. Here, statistical method have been used to extract features from the segmented tumour area. The obtained features are classified using different classifiers such as Radial basis function, Main Feed forward and Main Fitnet method. The method was tested on 100 clinical data. The RBF classifier achieved anaccuracy of 91% Main fit net accuracy of 99. 20%Main Feed forward accuracy about 97%.

Wavelets are prominently used for Power Quality (PQ) signal analysis, the features that are computed from wavelet sub bands are informative for detection and classification. Energy levels of non-stationary events that occur in PQ signal computed considering wavelet sub bands suffer from shift variant property and hence use of dual tree complex wavelets that supports shift invariance property is used for PQ event analysis. In this paper, PQ event algorithm is developed considering dual tree wavelets and the results are compared with wavelets. Various PQ signals with non-stationary events are analyzed and the shift invariant property of dual tree wavelets is demonstrated to be advantageous in terms of event classification. Dual Tree Complexwavelet Transform (DTCWT) energy levels are capable of differentiating between multiple events as well as different types of sags, swells, harmonics, interrupts and flicker. The classification accuracy using DTCWT energy bands is improved by more than 90%. DTCWT filters selected in this paper are suitable for PQ event detection as well as classification.