Vignan University

About: Vignan University is a education organization based out in Guntur, Andhra Pradesh, India. It is known for research contribution in the topics: Computer science & Control theory. The organization has 1138 authors who have published 1381 publications receiving 7798 citations.

Design and implementation of automated flexible multisource charging system for hybrid electric vehicles

Abstract: The scarcity and cost of fossil fuels, combined with their greenhouse gas emissions, make the development of nonfossil fuel-based methods of transportation a high-priority task. This paper proposes the designing and sizing of a Multiple Input Hybrid Charging System (MIHCS) to be used in Hybrid Electric Vehicle (HEV) propulsion. It includes a fuel cell generator, solar cell charger, Internal Combustion Engine (ICE), flywheel storage system, on-board sources and a combined Energy Storage System (ESS) comprising a battery pack. Based on the speed range of the vehicle, multiple sources like solar energy, fuel cells and wind power are automatically selected for propulsion or charging purposes by using computer and interfacing circuits. To realise this logic, a program has been developed in 'C' language. This logic also helps in controlling the charging and discharging times of the batteries placed in the energy storage unit.

Modified self-training based statistical models for image classification and speaker identification

Abstract: Building a high precision statistical model requires ample amounts of supervised (labeled) data to train the models. In certain domains, it is difficult to acquire large amounts of labeled data, especially applications involving images, speech and video data. At the same time, lots of unlabeled data is available in such applications. Self-training is one of the semi-supervised approaches that enables the use of vast unlabeled data to boost the efficiency of the model along with minimal labeled data. In this work, we propose a variant of the self-training approach that embraces soft labeling of unlabeled examples rather than the hard labeling used in conventional self-training. As our work focuses on image and speaker recognition tasks, Gaussian Mixture Model (GMM) based Bayesian classifier is used as a wrapper in the self-training approach. Our experimental studies on STL10, CIFAR10, MIT (image recognition task) and NIST (speaker recognition task) benchmark datasets indicate that the proposed modified self-training approach offers enhanced efficiency over conventional self-training.

Augmented and Virtual Reality and Its Applications

Abstract: Augmented reality (AR) overlies manually made materials directly over the real-world materials. This chapter addresses the technological and design frameworks required to create realistic motion tracking environments, realistic audio, 3D graphical interactions, multimodal sensory integration, and user interfaces and games using virtual reality to augmented reality. Similarly, the portfolio required to build a personal VR or AR application is detailed. Virtual and augmented reality industry committed innovative technologies that can be explored in the field of entertainment, education, training, medical and industrial innovation, and the development are explored. Augmented reality (AR) allows the physical world to be enhanced by incorporating digital knowledge in real time created by virtual machine. Few applications that have used augmented and virtual reality in real-world applications are discussed.

Mechanistic models for prediction of cutting forces and power consumption considering chip geometry

Abstract: A novel approach for modeling and simulation of cutting force and power consumption in relation to chip geometry has been proposed in end milling‌ of AISI D2 steel. It is carried out in two stages:...