Mepco Schlenk Engineering College

About: Mepco Schlenk Engineering College is a based out in . It is known for research contribution in the topics: Wavelet & Wavelet transform. The organization has 1307 authors who have published 1665 publications receiving 18690 citations.

Ayurvedic Medicinal Plants Identification: A Comparative Study on Feature Extraction Methods

Abstract: Proper identification of medicinal plants is essential for agronomists, ayurvedic medicinal practitioners and for ayurvedic medicines industry. Even though many plant leaf databases are available publicly, no specific standardized database is available for Indian Ayurvedic Plant species. In this paper, we introduce a publicly available annotated database of Indian medicinal plant leaf images named as MepcoTropicLeaf. The research work also presents the preliminary results on recognizing the plant species based on the spatial, spectral and machine learnt features on the selected set of 50 species from the database. To attain the machine learnt features, we propose a six level convolutional neural network (CNN) and report an accuracy of 87.25% using machine learnt features.

Study on Energy Absorption Capacity of Steel–Polyester Hybrid Fiber Reinforced Concrete Under Uni-axial Compression

Abstract: This work presents the energy absorption capacity of hybrid fiber reinforced concrete made with hooked end steel fibers (0.5 and 0.75%) and straight polyester fibers (0.5, 0.8, 1.0 and 2.0%). Compressive toughness (energy absorption capacity) under uni-axial compression was evaluated on 100 × 200 mm size cylindrical specimens with varying steel and polyester fiber content. Efficiency of the hybrid fiber reinforcement is studied with respect to fiber type, size and volume fractions in this investigation. The vertical displacement under uni-axial compression was measured under the applied loads and the load–deformation curves were plotted. From these curves the toughness values were calculated and the results were compared with steel and polyester as individual fibers. The hybridization of 0.5% steel + 0.5% polyester performed well in post peak region due to the addition of polyester fibers with steel fibers and the energy absorption value was 23% greater than 0.5% steel FRC. Peak stress values were also higher in hybrid series than single fiber and based on the results it is concluded that hybrid fiber reinforcement improves the toughness characteristics of concrete without affecting workability.

Multiferroic Consequence of Porous (BiFeO3) x -(BiCrO3)1-x Composite Thin Films by Novel Sol-Gel Method

Abstract: In this work, we have presented a spin-coating method to produce thin films started with pure BiCrO3 (BCO) and ended up with BiFeO3 (BFO) by increasing x values in the (BiFeO3) x –(BiCrO3)1−x composites All the produced thin films have been crystallized at the annealing temperatures of 400 °C for 05 h The XRD and EDAX spectrums give insight that the two crystal phases related to BCO and BFO stayed together within the thin film matrices SEM analysis showed that the prepared composite had macroporous morphology with interconnected pores and its width (size) decreased with increasing x values The strong correlations are observed among the microstructure, dielectric, ferroelectric, ferromagnetic properties and Fe concentration Among all composites, the composition of 075 shows an attractive magnetization, polarization, switching and improved dielectric behaviors at room temperature Significant increase in the multiferroic characteristics of 075 composition is due to arise of lower leakage current by causing reduction in oxygen vacancy density, and enhancement of super-exchange magnetic interaction between Fe3+ and Cr3+ at BFO/BCO interface layers Our result shows that the thin layer on Pt (111)/Ti/SiO2/Si substrate possesses simultaneously improved ferroelectric and ferromagnetic properties which make an inaccessible potential application for nonvolatile ferroelectric memories

Online Fuzzy Supervised Learning of Radial Basis Function Neural Network Based Speed Controller for Brushless DC Motor

Abstract: In this paper, Online Fuzzy Logic Supervised Learning of Radial Basis Function Neural Network (RBFNN) based speed controller for Brushless DC (BLDC) motor is presented. The Fuzzy PID controller is acting as supervisor for RBFNN controller. Dynamic speed response is analyzed for BLDC motor with conventional PID controller and proposed controller. Rise time, peak overshoot, recovery time and steady state error are measured and analyzed for above controller. From the results, the proposed controller outperforms than PID controller.

Multispectral band image compression using adaptive wavelet transform - Tetrolet transform

Abstract: The proposed work develops an efficient multi spectral band imagery compression technique using adaptive haar wavelet transform, called tetrolet transform. Geometrical features are most important prominent factor in multispectral image processing. But existing compression algorithms are fail to preserve geometrical features at high compression ratio, which implicates the visual cognitive effects around features of reconstructed image. In tetrolet transform, the determined orthonormal basis functions are adapted to geometrical features of the image. By using the filter bank algorithm, the tetrolet transform coefficients of input image are obtained. Thresholding and encoding steps are used to achieve compression of an image. The reconstruction is done by using decoding and inverse tetrolet transform. This proposed method produces improved performance than existing extended shearlet based compression technique. The simulation results show that the proposed method produces better performance than extended shearlet based compression technique by the factors of peak signal to noise ratio (PSNR), compression ratio(CR) and bits per pixel (bpp).