Author's Name: Krishna Nanduri, P. Samba Rao, Ratna Sadhu
Abstract—The acknowledgment and order of the assorted variety of materials that exist in the earth around us are a key visual capability that PC vision frameworks center around lately. Understanding the recognizable proof of materials in unmistakable pictures includes a profound procedure that has gained use of the ongoing ground in neural systems which has carried the possibility to prepare models to extricate highlights for this difficult assignment. This venture utilizes best in class Convolution Neural Network (CNN) methods and Support Vector Machine (SVM) classifiers so as to order materials and investigate the outcomes. Expanding on different broadly utilized material databases gathered, a determination of CNN structures is assessed to comprehend which is the best way to deal with extricate includes so as to accomplish remarkable outcomes for the errand. The outcomes assembled more than four material datasets and nine CNNs diagram that the best in general execution of a CNN utilizing a straight SVM can accomplish up to ~92.5% mean normal exactness, while applying another applicable heading in PC vision, move learning. By restricting the measure of data extricated from the layer before the last completely associated layer, move learning targets dissecting the commitment of concealing data and reflectance to recognize which fundamental qualities choose the material classification the picture has a place with. Notwithstanding the primary subject of my venture, the assessment of the nine distinctive CNN designs, it is addressed if, by utilizing the exchange learning as opposed to extricating the data from the last convolution layer, the all out exactness of the framework made improves. The aftereffects of the examination accentuate the way that the precision and execution of the framework improves, particularly in the datasets which comprise of an enormous number of pictures.
Author's Name: R. Navlesh, S. Patil
Abstract— This makes motion planning extremely complicated and difficult. Further, these systems also have restrictions such as time and to do real-world tasks in an unstructured environment. Thus, incorporating these restrictions in existing motion planners is complex and computationally expensive. So, real-time calculation i.e. very fast computation of inverse kinematics (IK) in complex robotics systems with dynamically stable configuration is of high priority .as they are very vulnerable to do tasks in an unstructured environment. In this thesis, a methodology to motion planning for complex robotics manipulators using Deep Reinforcement Learning (RL) is proposed. Where the robotics manipulator autonomously learns the optimal behavior through a series of trial-and-error interactions with the environment. It is based on the Markov Decision Process (MDP), Bellman’s Equation, Q learning, Deep Deterministic Policy Gradient (DDPG), and Hindsight Experience Replay (HER). The proposed strategy was developed for various motion planning tasks in Robotics. Our goal is to develop ways to train different kinds of complex Robotics Manipulator (gripers).To learn to interact with different objects, especially to grasp, perform some maneuvers to these objects. Achieving this would open up the possibility of the robot agent learning to interact with the environment without prior knowledge
Author's Name: Aadhithya Sharma and E. Ravira Varma
Abstract— — IoT’s Internet of Things. The basic set of protocols followed for data transmission and data handling in a secured and safe mode, between various computational devices is known as IOT’s. Network interoperability is the continuous receiving and transmitting data which is linked with each other for data transmission and network managements. In this context the paper is all about implementation of Network Interoperability in the fields of telecommunications for wide access areas via Interoperability of IoTs in the fields of telecommunications by zigbee, ARM controllers and SIP, VOIP, IPV4 protocols, IMS packet switch networks.
Author's Name: Anand D. G, Ashwini K., Anusha A
Abstract—Cloud Computing is an emerging paradigm in the advanced network arena that facilitates the users to access shared computing resources through internet-on-demand. Cloud Computing has been widely used since it brings tremendous improvements in business. Cloud users are expected to grow exponentially in the future. In order to meet the demands of future cloud users, a full-fledged survey analyzing the various issues is the need of the hour. The different classifications presently available do not present the issues at micro levels. Amongst the various issues, the ones at design and implementation levels are of utmost importance since they directly affect the performance of the applications. Hence the cloud issues at those levels are presented in this paper from the available literature. This paper also attempts to outline a few possible solutions for some of the issues. Innovation is necessary to ride the inevitable tide of change and one such hot recent area of research in Information Technology (IT) is cloud computing. Cloud computing is a distributed computing technology offering required software and hardware through Internet. It also provides storage, computational platform and infrastructure which are demanded by the user according to their requirement. Due to the growing need of infrastructure educational institutes, organizations have to spend a large amount on their infrastructure to fulfill the needs and demands of the users. Cloud computing is a next generation platform that allows institutions and organizations with a dynamic pools of resource and to reduce cost through improved utilization. In the present scenario, many education institutions are facing the problems with the growing need of IT and infrastructure. Cloud computing which is an emerging technology and which relies on existing technology such as Internet, virtualization, grid computing etc. can be a solution to such problems by providing required infrastructure, software and storage. In this paper a basic research has been carried out to show how cloud computing can be introduced in the education to improve teaching, agility and have a cost-effective infrastructure which can bring a revolution in the field of education. It also tries to bring out its benefits and limitations.
Author's Name: Babasaheb S, Ravindra R., Shrikant D
Abstract— If vapour compression system are to be used for the production of low temperatures, the best alternative to stage compression is the cascade system. If very low temperature is desired, then the corresponding evaporator pressure is also low and this results in a higher pressure ratio, there is a reduction in volumetric efficiency. In order to avoid this problem, cascade refrigeration system is used. Again question was of energy. In day to day life, the challenge was to save electrical energy along with the increasing performance of the system. So the development was done by using the Phase Change Material (PCM). In this paper the experimentation was done on cascade refrigeration system with PCM and without PCM. Also calculated the energy efficiency of the system using different PCMs and different size and shape of the PCM boxes. For this experimentation, the PCM box was made of aluminium sheet having a 2cm and 3cm thickness, whereas ethylene glycol-water solution and NaCl solution was used as a PCM
