SDM College of Engineering and Technology

About: SDM College of Engineering and Technology is a based out in . It is known for research contribution in the topics: Diesel fuel & Combustion. The organization has 350 authors who have published 351 publications receiving 2399 citations.

Polymorphic donor–acceptor substituted chalcone: structural, spectral, dielectric and nonlinear optical properties for optical limiting applications

Abstract: Herein, we report the third-order nonlinear absorption and optical limiting property of fluorinated polymorphic nonlinear optical (NLO) material 1-(3,4-dimethoxyphenyl)-3-(4-fluorophenyl) prop-2-en-1-one (abbreviated as PDPFO) based on reverse saturable absorption The FTIR studies of optically transparent PDPFO single crystals confirm the presence of various functional groups PDPFO is optically transparent in the visible wavelength region The open aperture Z-scan technique showed the intensity-dependent nonlinear absorption A decrease in normalized transmittance with input intensity indicated the optical limiting behavior at the wavelength 532 nm The excited-state absorption cross-section value ( $${\sigma }_{ex}=$$ 172 × 10–16 cm2) is much greater than ground-state absorption cross-section value $$({\sigma }_{g}=$$ 249 × 10–22 cm2), suggesting that optical limiting phenomena are due to RSA

Wind Speed Assessment and Techno-Economic Analysis of a Community Microgrid in Warm and Humid Climate Zone of India

Abstract: In this paper, wind speed assessment of a wind site located in BELAGAVI under warm humid climatic zone is proposed. Weibull and Rayleigh models were used for the statistical analysis and typical meteorological year (TMY) data was considered. Rayleigh model was found to be suitable compared to Weibull model for BELAGAVI site. The techno-economic analysis of a community microgrid in the same location was carried out considering hybrid renewable energy system for grid connected and off grid system. Promising results were obtained in terms of model and cost.

An approach for face detection using artificial intelligence

Abstract: This paper proposes a method for detecting faces in a given image by combining Gabor filter and Neural network. The first phase uses gabor filter which generates a fetaure set. Face and non face templates is taken and processed with gabor filter.The face images are present in spatial (time) domain. The conversion of images into frequency domain is processed through inverse fast fourier transform. The subsequent frquency domain images is conjugated with gabor filter bank and feature vector is generated. The second phase involves a method where all the features are given as input to neural network of 2 hidden layer with scaled conjugate training. Thus this approach being deployed, is a convolution of Gabor filter with frequency domain of training and test images provided a fetaure vector that was sourced to neural network. Proposed system was tested and the results indicated the efficient performance.

Efficiency Comparison of Supervised and Unsupervised Classifier on Content Based Classification using Shape, Color, Texture

Abstract: The field of machine learning is growing in modern times, computational models are able to go beyond the performance of previous forms of artificial intelligence. The use of evaluation model ,selection of model and algorithm selecting techniques play an major role in machine learning study and also in field of industries. In this work, we made evaluation of various supervised, unsupervised machine learning classifiers for flower datasets. We made use of local features such as Histogram of gradient , Kaze, Local binary pattern(LBP) ,Oriented Fast and Rotated Brief( ORB), global features like Color Histograms, Haralick Textures , Hu Moments , fusion of both and Bag of visual words(BOVW) using Vocabulary builder K-Means clustering which represents color ,texture, shape features of image. Experiment is carried out on 20 classes of flower datasets with 100 images each. .Flower datasets have many characteristic in common like sunflower will be similar to daffodil in terms of color and texture .Hence to quantify the image we need to combine different feature descriptors like color, texture and shape features. We develop a Content based classification system to find efficiency comparison of different machine learning algorithms for classification and retrieval problems. Eleven classifiers mainly Support Vector Machine, K Nearest Neighbor, Gaussian Naive Bayes , CART, Kmeans, Linear Discriminant Analysis, Adaboost ,Logistic Regression, MLP, Random Forest, CNN are analyzed on the shape, color ,texture features. Experimentation are carried out and results are recorded using CPU as well as GPU on google cobalatory platform.