Dr. Babasaheb Ambedkar Technological University

About: Dr. Babasaheb Ambedkar Technological University is a education organization based out in Goregaon, India. It is known for research contribution in the topics: Machining & Surface roughness. The organization has 389 authors who have published 485 publications receiving 6027 citations.

Iris recognition: an emerging biometric technology

Abstract: In this paper, iris recognition as one of the important method of biometrics-based identification systems and iris recognition algorithm is described. As technology advances and information and intellectual properties are wanted by many unauthorized personnel. As a result many organizations have being searching ways for more secure authentication methods for the user access. In network security there is a vital emphasis on the automatic personal identification. Due to its inherent advantages biometric based verification especially iris identification is gaining a lot of attention. Iris recognition uses iris patterns for personnel identification. The system steps are capturing iris patterns; determining the location of iris boundaries; converting the iris boundary to the stretched polar coordinate system; extracting iris code based on texture analysis. The system has been implemented and tested using dataset of number of samples of iris data with different contrast quality. The developed algorithm performs satisfactorily on the images, provides 93% accuracy. Experimental results show that the proposed method has an encouraging performance.

Deep convolutional neural network based medical image classification for disease diagnosis

Abstract: Medical image classification plays an essential role in clinical treatment and teaching tasks. However, the traditional method has reached its ceiling on performance. Moreover, by using them, much time and effort need to be spent on extracting and selecting classification features. The deep neural network is an emerging machine learning method that has proven its potential for different classification tasks. Notably, the convolutional neural network dominates with the best results on varying image classification tasks. However, medical image datasets are hard to collect because it needs a lot of professional expertise to label them. Therefore, this paper researches how to apply the convolutional neural network (CNN) based algorithm on a chest X-ray dataset to classify pneumonia. Three techniques are evaluated through experiments. These are linear support vector machine classifier with local rotation and orientation free features, transfer learning on two convolutional neural network models: Visual Geometry Group i.e., VGG16 and InceptionV3, and a capsule network training from scratch. Data augmentation is a data preprocessing method applied to all three methods. The results of the experiments show that data augmentation generally is an effective way for all three algorithms to improve performance. Also, Transfer learning is a more useful classification method on a small dataset compared to a support vector machine with oriented fast and rotated binary (ORB) robust independent elementary features and capsule network. In transfer learning, retraining specific features on a new target dataset is essential to improve performance. And, the second important factor is a proper network complexity that matches the scale of the dataset.

Technological development in the stirling cycle engines

Abstract: The performance of Stirling engines meets the demands of the efficient use of energy and environmental security and therefore they are the subject of much current interest. Hence, the development and investigation of Stirling engine have come to the attention of many scientific institutes and commercial companies. The Stirling engine is both practically and theoretically a significant device, its practical virtue is simple, reliable and safe which was recognized for a full century following its invention by Robert Stirling in 1816. The engine operates on a closed thermodynamic cycle, which is reversible. Today Stirling cycle-based systems are in commercial use as a heat pump, cryogenic refrigeration and air liquefaction. As a prime mover, Stirling cycles remain the subject of research and development efforts. The objective of this paper is to provide fundamental information and present a detailed review of the past efforts taken for the development of the Stirling cycle engine and techniques used for engine analysis. A number of attempts have been made by researches to build and improve the performance of Stirling engines. It is seen that for successful operation of engine system with good efficiency a careful design of heat exchangers, proper selection of drive mechanism and engine configuration is essential. The study indicates that a Stirling cycle engine working with relatively low temperature with air of helium as working fluid is potentially attractive engines of the future, especially solar-powered low-temperature differential Stirling engines with vertical, double acting, and gamma configuration.

Effect of machining parameters and cutting edge geometry on surface integrity of high-speed turned Inconel 718

Abstract: Stringent control on the quality of machined surface and sub-surface during high-speed machining of Inconel 718 is necessary so as to achieve components with greater reliability and longevity. This paper extends the present trend prevailing in the literature on surface integrity analysis of superalloys by performing a comprehensive investigation to analyze the nature of deformation beneath the machined surface and arrive at the thickness of machining affected zone (MAZ). The residual stress analysis, microhardness measurements and degree of work hardening in the machined sub-surfaces were used as criteria to obtain the optimum machining conditions that give machined surfaces with high integrity. It is observed that the highest cutting speed, the lowest feedrate, and the moderate depth of cut coupled with the use of honed cutting edge can ensure induction of compressive residual stresses in the machined surfaces, which in turn were found to be free of smeared areas and adhered chip particles.