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.

An experimental analysis of coal aluminium mixture in coal fired furnace

Abstract: Coal is an important fuel used in boiler furnaces. There are problems like unburnt coal and solid wastes like ash contain arsenic, selenium, chromium and cadmium while using it. In order to avoid all such difficulties, aluminium metal powder in various grain sizes mixed with pulverized coal and burned. aluminium metal powder is one of the pyrotechnics having higher calorific value and low ignition temperature. The thermal behavior of aluminium powder along with coal is recorded in DTA. The collected ashes were tested in Scanning Electron Microscope and X-Ray Diffraction meter. The SEM results show that coal ash is having granular and regular structure. All the particles have a size range from 5 to 8 μm. On the other hand, the aluminium coal mixture ash shows a fibrous matrix and the particles are irregular. In XRD graph, the peaks in the graph show orientation of atoms in particular plane and angle. The coal ash has a lot of peaks, but the maximum count value reaches only to 340.97. However the value of counts reaches a maximum of 1,539.06 for aluminium ash. This denotes high atom orientation in a single lattice plane.

FPGA Based Human Fatigue and Drowsiness Detection System Using Deep Neural Network for Vehicle Drivers in Road Accident Avoidance System

Abstract: Automobile Industry shares numerous accidents in our daily routine. Increasing rate of road accidents are due to driver distraction such as fatigue and lack of sleep. This work is intended solely for the implementation of fatigue and drowsiness detection system using the deep neural network in FPGA. In the proposed system, the image is preprocessed using median filtering and Viola Jones face detection algorithm for extracting the faces. Further, the features are extracted by using Local Binary Pattern analysis and the Max pooling is used to reduce the complexity level. These deep learning steps are followed by performing SVM classifier to define the status of the subject as drowsy or not. The system uses a camera to capture the real time image frames in addition with offline images of the system. The developed Vision-based driver fatigue and drowsiness detection system is a convenient technique for real time monitoring of driver’s vigilance.

Performance analysis of texture classification techniques using MRMRF and WSFS & WCFS

Abstract: Texture analysis plays an important role in many tasks, ranging from remote sensing to medical imaging and query by content in large image data bases. The main difficulty of texture analysis in the past was the lack of adequate tools to characterize different scales of textures effectively. The development in multi-resolution analysis such as Gabor and wavelet transform help to overcome this difficulty. This paper analyses the performance of texture classification techniques using (i) multi resolution Markov random field (MRMRF) features and (ii) a combination of wavelet statistical features (WSFs) and wavelet co-occurrence features (WCFs) with two different texture datasets.