No abstract

In this study, a single-phase pulse-width modulation rectifier with regenerative capability has been presented. Here, the main purpose is to achieve unity power factor with least harmonics on AC-side source current while having regulated DC voltage at output. It is very difficult to achieve aforementioned goals with commonly used proportionalintegral (PI) regulators due to their limited control bandwidth, especially under rapidly varying input AC and dynamic load conditions. The disturbances on DC side are mainly due to double frequency ripple components, which are periodic in nature and are very much prominent in single-phase rectification. The problem may be further exaggerated due to the presence of periodic noise/disturbances in input AC supply. Hence, a repetitive controller (RC) is designed, which is well known for its capabilities in tracking periodic disturbances. The systematic design and modelling of stable RC controller based on internal model principle theory has been presented. The proposed control technique has been developed and simulated in MATLAB/SimPower System. The experimental results have been presented and analysed in detail to validate the performance of the proposed RC control technique in comparison with its PI counterpart.

Content-based image retrieval (CBIR) is a methodology used to search indistinguishable images across any vast repository. Texture, Color and Shape are among the most prominent features of any CBIR system. Two texture descriptors namely Gray level Co-occurence matrix (GLCM) and Discrete wavelet transform (DWT) have been utilized here for the formation of a hybrid texture descriptor, denoted as (Co-DGLCM). To enhance the retrieval accuracy of the proposed system, a framework of an Extreme learning machine (ELM) with Relevance feedback (RF) has also been used. This technique provides simultaneously spatial relationship and information related to frequency in co-occuring local patterns of an image. Two benchmark texture databases namely Brodatz and MIT-Vistex have been tested and results are obtained in terms of accuracy, total average recall and total average precision which is 96.35% and 97.34% respectively on the two databases.

No abstract

Many encryption and searching techniques have been used, but they did not prove effective to support smart devices in order to provide input image. Therefore, based on these facts, an effective and novel system has been developed in this paper which is based on content-based search concentrated on encrypted images. Four type of features, namely color moment (CM), Gray level co-occurrence matrix (GLCM), hybrid of CM and GLCM, and lastly, a deep belief network (DBN) has been used here. This deep neural network is based on clustering in combination with indexing and the developed model is called as cluster-based deep belief network (CBDBN) in the present work. A web based application has also been developed using Apache Tomcat server and MATLAB engine. Analysis of many parameters like precision, recall, entropy, correlation coefficient, and time has been done here on benchmark datasets, namely WANG and COIL.