Manuscripts

Recent Papers

Detection and Analysis of Microanuerysm in Diabetic Retinopathy Using Fundus Image Processing

Diabetic-related eye disease is a major cause of blindness in the world. It is a complication of diabetes which can also affect various parts of the body. When the small blood vessels have a high level of glucose in the retina, the vision will be blurred and can cause blindness eventually, which is known as diabetic retinopathy.Detection of the disease at an early stage enables the patient to get treatment by advanced methods like laser treatment to prevent total blindness. The paper deals with detecting the diabetic retinopathy retinal changes. The retinal images are first subjected to pre-processing techniques like colour normalization and enhancement process. There may exist different kinds of lesions caused by diabetic retinopathy in a diabetic patient’s eye such as micro aneurysm, hard exudates, soft exudates, hemorrhage etc. Automated analysis of the fundus (retinal image) image is very much essential and will be of help to facilitate the clinical diagnosis.

Published by: Nirav Gori, Hardik Kadakia, Vinayak Kashid, Mrs. Pranali Hatode

Author: Nirav Gori

Paper ID: V3I2-1508

Paper Status: published

Published: April 17, 2017

Full Details
Research Paper

Glimpse of Cloud Computing

In this paper, the concept of cloud computing has been studied. The service provider must ensure that the infrastructure and applications are protected and must take actions to reinforce user’s application and use strong passwords and authentication measures. In the first part, a brief introduction to the cloud computing has been given. It includes a definition of cloud computing given by NIST and other scholars. In the next section, the architecture and various service models, as well as deployment models provided by cloud computing, has been discussed. This is followed by the working of the cloud which includes the concept of virtualization. Then the light has been put on its major application areas. In the next part, its advantages and disadvantages have been highlighted.

Published by: Anushka Gaur, Anurag Jain

Author: Anushka Gaur

Paper ID: V3I2-1510

Paper Status: published

Published: April 17, 2017

Full Details
Review Paper

Review Paper on Shifted Histogram Using Optimal Shift Distance for Images with Entropy Value & Wavelet Decomposition Images

A histogram is a graphical representation of the brightness values that comprise an image. The brightness values (i.e. 0-255) are displayed along the x-axis of the graph. The frequency of occurrence of each of these values in the image is shown on the y-axis. Histogram of a digital image with intensity level in the range of [0, L-1 ] is a discrete function h(rk) = nk where rk is the kth intensity level and nk is no of a pixel in the image with intensity rk. Histogram equalization is a method in image processing of contrast adjustment using the image's histogram. Histogram equalization automatically determines a transformation function that seeks to produce output images that have a uniform histogram. When the automatic enhancement is desired that is the good approach because result from this technique are predictable and method is simple to implement. The method used to generate a processed image that has a specified histogram is called histogram matching or histogram specification. In this thesis we will use the advanced algorithm to enhance the quality of an image and we succeeded and also got the entropy value of image by changing the scaling factor K we got different value and also got different shifted histogram image. In our research work, we will work on the different level to analyze the effect of an algorithm. By changing scaling factor we analyze different EME and image enhanced significantly from which a lot of important information can be recovered.

Published by: Rekha, Vijay Nandal

Author: Rekha

Paper ID: V3I2-1491

Paper Status: published

Published: April 14, 2017

Full Details
Research Paper

Taxonomy of Load Balancing

Cloud computing is one of an emerging technology in the computer world these days. Virtualization is the concept behind cloud computing that allows sharing of resources like software, infrastructure, and platform. Different people share different views regarding cloud computing. Some enterprises take a lot of advantages from cloud computing while other considers it being an unsafe place for storing critical information. Load balancing is one of an important issue in cloud computing. This paper is for those who want to understand the basics of load balancing.

Published by: Divya Garg, Er. Anurag Jain

Author: Divya Garg

Paper ID: V3I2-1509

Paper Status: published

Published: April 14, 2017

Full Details

Manufacturing Of Eco-Friendly Parking Tiles

In this project, we have manufactured parking tiles by using Electronic Waste. We use recycled Electronic Waste as a raw material in the manufacturing of parking tiles & it is one of the alternative methods for disposal of Electronic Waste. We have replaced Silica & Crush by Electronic Waste in a small amount. We have used Electronic Waste in powder form after recycling it. Electronic Waste does not contain metals. After manufacturing of “Eco-friendly Tiles,” we get the results as per conventional tiles. Due to the use of recycled Electronic Waste cost of tiles increases. Because now a day Electronic Waste recycling plants are minimum or negligible so that cost of parking tiles increases but after some years it becomes minimum due to an increase of Electronic Waste recycling plants.

Published by: Supriya Sunil More, Poonam C. Ombale, Jyoti A. Dalavi, Trupti B. Dalavi, Prajkta D. Ghadge, Prof. S. S. Lembhe

Author: Supriya Sunil More

Paper ID: V3I2-1506

Paper Status: published

Published: April 14, 2017

Full Details

A Hybrid System for Chemical Named Entity Simplification

One explicit challenge in medicine named entity recognition (NER) and normalization is that the identification and resolution of composite named entities, wherever one span refers to over one idea (e.g., compositeBRCA1/2). Previous Named Entity Recognition (NER) and normalization studies have either neglected composite mentions, used straight forward rules or solely handled coordination omission, making a strong approach for handling composites mentions greatly required to the present finish, we tend to propose a hybrid technique integrating a machine-learning model with a pattern identification strategy to spot the individual elements of every composite mention. Our method , that we’ve named SimConcept is the first to consistently handle many sorts of composite mentions. The technique achieves high performance in distinguishing and resolving composite mentions for three key biological entities: genes (90.42% in F-measure), diseases (86.47% in F-measure), and chemicals (86.05% in F-measure).The proposed SimConcept technique will later improve the performance of gene, disease chemicals concept recognition and normalization. We observe that in our datasets, approximately 10% of gene, disease, and chemical mentions are composite mentions, hence, it is important to handle them properly. This study presents a new method for bio-concept mention simplification in a systematic fashion.

Published by: Gunjal Sonali Vishram, Prof. N. B. Kadu

Author: Gunjal Sonali Vishram

Paper ID: V3I2-1504

Paper Status: published

Published: April 14, 2017

Full Details