Manuscripts

Recent Papers

Effect of Environmental Parameters on Solar PV Performance with MPPT Techniques on Induction Motor Driven Water Pumping System

A photovoltaic cell produces electrical energy directly from visible light but their efficiency is fairly low and hence is expensive as compared to other available energy resources. Various factors affect pv system efficiency. This paper presents the important environmental factors which affect working of pv system by using MPPT techniques .These affects are solar Irradiation, temperature, humidity and wind speed . The variation of these factors at different condition has been studied to improve working of MPPT techniques for more reliable applications. In India there is a huge demand of energy due to various reasons like industrial development and increasing population. The main drawback in replacing conventional energy sources with new and more environmentally friendly alternative sources such as solar and wind energy, is how to capture them for maximum energy and how to deliver the maximum power at a minimum cost for a given load. The output power of photovoltaic cells or solar panels has nonlinear characteristics which are affected by temperature, light intensity and other environmental conditions and hence it is necessary to study them and rectify them for maximum and output.. To assess the overall performance with varying weather conditions, a PV model based on the Shockley diode equation has been used to predict the electrical characteristics of the cell with regard to changes in the environmental conditions of irradiation, temperature, humidity and wind speed.

Published by: Vishakha Garg

Author: Vishakha Garg

Paper ID: V3I3-1455

Paper Status: published

Published: June 5, 2017

Full Details

Monitoring Traffic Signal Destructions Using SVM Classifier

Typically vehicles are generally in movement so number plate detection from vehicles becomes very difficult problem due to possession of images, next to with that number plate may have other designs and some more additional stickers also. within this paper, we have taxing our process for number plate detection which includes many steps, the images of the vehicle’s number plate are composed from the car parking areas and from the network. Firstly, pre-processing of giving input sampled similes are done then feature drawing out of those pre-processed images by applying convolves Gabor and Zonal based algorithm. After that morphological operations are made to find the numbers and also to the segmentation of images, every single character is segmented parallel processing histogram. All the features of every number are designed using zonal based approach. The features are used as put in to the neural networks for quality identification.

Published by: Shruthi .U, Prof. Srinivasalu .G

Author: Shruthi .U

Paper ID: V3I3-1459

Paper Status: published

Published: June 5, 2017

Full Details
Research Paper

Under Water Image Enhancement by Color Convolution with Total variation

Due to concern about the current state of the world’s oceans, several large scale scientific projects have begun to investigate the condition of our oceans. These projects are making use of underwater video sequences to monitor marine species. The move to using underwater video monitoring introduces labor intensive manual processing techniques. This leads to the need for an automated system capable of processing the data at a much greater speed. This thesis investigated whether the development of suitable image processing techniques could be used for preprocessing underwater images which enhance the image. The main objective of this thesis reduce the noise ratio and increase the PSNR of image. In underwater situations, clarity of images are degraded by light absorption and scattering. This causes one color to dominate the image. In order to improve the perception of underwater images. Improve the color noise by convolution method which reduce the color blurriness and total variation (TV) improve the noise after blurriness we get the significance improvement in PSNR from existing method approximate multiple five increment of PSNR

Published by: Karamjit Kaur, Rajnish Kansal

Author: Karamjit Kaur

Paper ID: V3I3-1466

Paper Status: published

Published: June 5, 2017

Full Details

A Trinity Approach for Secure Image Access and Retrieval in Cloud

Images play an important role in human’s day to day life and it consumes much more space for storage rather than other formats. Hence, the need for cloud storage outsourcing arises. The Privacy of user and transfer of images in the network is the main concern. For privacy-preservation purposes, sensitive images, such as medical and personal images are needed to be encrypted before outsourcing, which makes the CBIR technique on plaintext realm to be inoperative. To ensure user privacy, a keyword based technique is introduced to provide individuality for the users. User validation for accessing their images from the cloud is provided by generating an OTP. The cryptography and segmentation techniques are upholding image security during transfer. Additionally, the illicit publication of user images is recognized with the help of watermark extraction.

Published by: T. E Bavisha, Ms. M. Madlin Asha

Author: T. E Bavisha

Paper ID: V3I3-1468

Paper Status: published

Published: June 5, 2017

Full Details

Fingerprint Based Universal Debit Card

We are designing the system which will read the AADHAR CARD number which will act as a UNIVERSALDEBIT CARD. Using this card automatically it will deduct the ticket charges from your account. So, the passenger doesn’t have to wait for long time in a long queue. Due to its transparency, we can keep tab on corruption. Using this system we can reduces human interference which effectively encourage corruption. It will make overall transaction digital and transparent. This transparency in money transaction will reduce scope of corruption. It will also help to eradicate. Exploitation which otherwise may occurs when transaction is through notes. Moreover this project can be major step towards success of Digital India drive of government.

Published by: Dhonddev Suhas, Gajanan Deshmukh, Vishal Joshi, Nitin Dawande

Author: Dhonddev Suhas

Paper ID: V3I3-1460

Paper Status: published

Published: June 3, 2017

Full Details

Study of Hopfield Neural Network for Noisy Random Patterns Using Evolutionary Approach

In this paper, a vigorous attempt has been made to study Hopfield neural network for storing and later recalling of random patterns using conventional hebbian learning rule and genetic algorithm. Storing of these patterns in the network is done using Hebbian learning rule followed by recalling of these patterns on presentation of distorted input patterns is done using both the methods i.e. Hebbian rule and genetic algorithm. The optimal weight matrix obtained is used to generate new weight matrices for the efficient recalling of prototype input patterns. Performance evaluation of the network is done on the basis of pattern recall with maximum noise present in patterns. The results thus obtained shows that the recall of these random patterns is more successful by using genetic algorithm.

Published by: Srishti Gangwar, T. P Singh

Author: Srishti Gangwar

Paper ID: V3I3-1451

Paper Status: published

Published: June 3, 2017

Full Details