College of Engineering, Pune

About: College of Engineering, Pune is a based out in . It is known for research contribution in the topics: Computer science & Sliding mode control. The organization has 4264 authors who have published 3492 publications receiving 19371 citations. The organization is also known as: COEP.

Ranking of sites for power plant installation using soft computing techniques - A thought beyond EIA

Abstract: Research on decision making in an imprecise environment has gained and will continue to gain overriding importance in recent years. In this context, decision making on the location of hazardous plant installations is an issue of relevance. The authors believe that there is a need of a standard model to overcome the discrepancies in Environmental Impact Assessment (EIA) for rationalization of site selection. An inappropriate choice of a site for an upcoming hazardous industrial plant may lead to further degradation of existing environment thus resulting in hazardous effects on mankind as well as all other living organisms. It could be argued that there exists quantifiable (measurable parameters) and epistemic (non measurable parameters) uncertainties in the scoping phase and the overall EIA process. The uncertainties could be modeled using soft computing techniques in ranking the sites for upcoming hazardous industry and justify the results in linguistic terms. The case study in the paper relates to the application of Back propagation Artificial Neural Network (BP-ANN), Learning Vector Quantization (LVQ-ANN), Ant Colony optimization with Fuzzy Soft Sets (FSS) and Fuzzy Indexing (FI), in ranking the existing/upcoming power plant locations in India. Comparative evaluation of these methods is also an integral part of the paper.

On a methodology for detecting diabetic presence from iris image analysis

Abstract: Iris image analysis for clinical diagnosis is one of the most efficient non-invasive diagnosis methods for determining health status of organs. Correct and timely diagnosis is a critical, yet essential requirement of medical science. From the literature, it is found that modern technology also fails in lot of cases to diagnose disease correctly. The attempt is being made to explore the area of diagnosis from different perspectives. The approach used is a combination of ancestor's technology Iridodiagnosis with modern technology. Iridodiagnosis is an alternative branch of medical science, which can be used for diagnostic purposes. To begin with a database is created of eye images with clinical history of subject's emphasis on diabetic (type II) disease in pathological laboratory. The various algorithms are developed for image quality assessment, segmentation of iris, iris normalization and clinical feature classification for clinical diagnosis. The artificial neural network is used for training and classification purpose. The entire process shows classification accuracy of 90 ∼ 92 percent between diabetic and non-diabetic subjects. A significant improvement is demonstrated in classification performance over the existing approaches. This approach will be useful in the diagnosis field which is faster, user friendly and less time consuming.

Numerical analysis of multiphase flow in hydrodynamic journal bearing using CFD coupled Fluid Structure interaction with cavitation

Abstract: In this work, hydrodynamic journal bearing are simulated considering the realistic deformations of the bearing with fluid structure interactions (FSI) coupled with CFD. Mixture model is used model cavitation in the bearing. Parametric modeling is used to modify the flow domain due to deformation. Both systems are coupled and multi objective genetic algorithm (MOGA) is used to get optimized solution of the attitude angle and eccentricity for the combination of operating speed and load. Bearings with and without cavitation are studied. It is observed that maximum pressure values drop when cavitation is considered in the bearing. The oil vapour distribution goes on increasing with the increase in shaft speed thus lowering the magnitude of the pressure build up in the bearing. The experimental data obtained showed very good agreements with numerical results. Considerable reduction in computation time is observed.

Image Retrieval using Weighted Fusion of GLCM and TSBTC Features

Abstract: Innovation in imaging technology, the widespread use of smartphones and social media, along with the boost in networking and storage technology has resulted in huge image databases. Exploring and searching similar visual images has become a key topic of research. This research article presents weighted feature fusion of gray level co-occurrence matrix (GLCM) based texture features and n-ary Thepade's Sorted Block Truncation Coding (TSBTC) based color features for image retrieval. Query image feature vector is compared with dataset image feature vector. Related images having a minimum mean squared error (MSE) are retrieved. The experimental results demonstrate that the weighted fusion of GLCM and TSBTC 8-ary features with weights 0.3 and 0.7, respectively give an Average Retrieval Accuracy (ARA) of 44.74% for augmented Wang dataset and, the weighted fusion of GLCM and TSBTC 4-ary features with 0.4 and 0.6 weights, respectively gives an ARA of 74.36% for modified COIL dataset. The proposed technique performs better as compared to the existing techniques studied and proved through statistical evaluations.