Manuscripts

Recent Papers

Review Paper

Management and utilization of Keratin Waste– A review

Keratin is a major complex structural protein present in hair, wool, home, hoops, feathers and nails of animals. It is considered as an environmental pollutant because of its slow degradation and produced mostly at both domestic and industrial levels. So beneficial utilisation and management go these keratin based waste has a significant importance. Out of many traditional and new approaches to breakdown keratin, the use of natural soil keratinophilic microbes is widely studied because of nontoxic and useful byproducts produced. These keratin based products have a widespread application in medical, animal feed, fertiliser, biomedical uses and many other type of industries. In the present review various strategies for hydrolysis of keratin from the organic waste have been described and use of natural keratin in different industries have also been explored.

Published by: Sruthi Menon, Bhairavi Savur, Deepakshi Kasat, Urja Mavani, Shailja Singh, Mayuri Rane

Author: Sruthi Menon

Paper ID: V6I3-1446

Paper Status: published

Published: June 6, 2020

Full Details
Research Paper

Surgical site infections in a tertiary care center in Rajasthan

Surgical site infections are the 3rd most common nosocomial infections in a hospital setting. It is a menace to both patients and surgeons, as it accounts for 1-3% of all surgical procedures, decreasing the success rate of surgeries. The study was conducted on 90 consecutive patients of Surgical site infection occurring after various surgical procedures within the same surgical team in the National Institute of Medical Sciences and Research, Jaipur, from 1st January 2018 till 30th June 2019. The objectives of this study were to assess the etiological factors of surgical site infection, the relationship of these factors with the type of surgical site infection, and to isolate the bacteria and the choice of antibiotic therapy suited for such patients. The rate of surgical site infections in our study was 6.99%. This value is relatively low when considering that the majority of the patients that were taken for surgery were in an emergency condition. A relationship was seen between co-morbidities in the form of diabetes mellitus, immunosuppressed patients, and patients who smoke, as all of them made up the majority of the patients who developed surgical site infection. As per treatment modalities, patients who had drains placed intra-operatively made up a larger majority of the total patients who had developed surgical site infections compared to those patients who did not have a drain placed. The most common bacteria isolated was Staphylococcus aureus which showed high sensitivity to piperacillin, vancomycin, linezolid, and amikacin.

Published by: Dr. Sankalp Goel, Dr. N. S. Shekhawat

Author: Dr. Sankalp Goel

Paper ID: V6I3-1435

Paper Status: published

Published: June 6, 2020

Full Details
Research Paper

Duration of an actor in a video using Keras

This research is mainly based on automating the process of calculating the time taken for any actor to appear on the screen. It is one of the main factors for determining the remuneration to be given to actors for appearing on the screen for a particular time period. By automating this process, we can accurately determine the screen time of an actor with minimum error. This proposed idea can be implemented using the knowledge related to image processing with the help of CNN architecture. The major part of the research lies in determining the hyperparameters and the right model that fits the given video appropriately and gives the best results for the model evaluation. The major findings of this paper lie on analyzing the right activation function, the number of layers for the neural network, finding the drop-out rate for the trained neural network, deciding upon the weight sharing of the input attributes, and of the hidden layers. The final outcome of this performed experiment is a neural network that can be used for deciding the duration of an actor on the screen.

Published by: Puja Kedia, Saurabh Singh, Lakshmi Saai Rasazna Konagalla, Shantha H. Biradar

Author: Puja Kedia

Paper ID: V6I3-1425

Paper Status: published

Published: June 6, 2020

Full Details
Research Paper

Drowsiness detection using feature extraction

Drowsiness detection system is a visual based system which will detect the eyes of the driver and classify it as awake or asleep in real time. The targeted customers predominately consist of commercial land transport companies, and is also available to general public. Since long distance transportations exhausts a lot of drivers which can lead to driver unexpectedly falling asleep can cause fatal accidents. In order to prevent this the Drowsiness detection system will immediately detect the state of the driver, if the driver falls asleep the system will immediately raise an alarm to alert the driver. The system’s interface will be through a web app which will display the camera feed and the status of the driver in real time. The system uses HOG [Histogram Oriented Gradient] for feature extraction of facial points recognition. Though there will some delay between the real time feed and the processed feed Our project aims in making it as fast as possible with minimum compute resources. This project is done using openCV, python, Dlib, boot.python.

Published by: Nagasai Shanmuka Sreenivas, Ankit Bando, Ariyan Chowdhury, Imad Ahmad, Thenmozhi T.

Author: Nagasai Shanmuka Sreenivas

Paper ID: V6I3-1424

Paper Status: published

Published: June 6, 2020

Full Details
Survey Report

An alert to focus on self development for post COVID world

The work world is profoundly affected by the global pandemic COVID-19.It is impacting not only the health of millions, but also their livelihood and well-being are in stake. It has presented unique challenges for all forms of learning’s to skill development processes. It has stimulated the need to accelerate all form of online learning and skilling. In this context to the need to explore innovative, upgrading methodologies and skills in workplace

Published by: Swarna Devesh Keswani

Author: Swarna Devesh Keswani

Paper ID: V6I3-1421

Paper Status: published

Published: June 6, 2020

Full Details
Research Paper

Comparative analysis on vehicle insurances fraud detection using machine learning

Now-a-days frauds have become a serious threat to the society. Fraud is an illegal way of gaining more money. Frauds are posing problems to so many people. So, fraud detection becomes very important in this current world. Fraud detection can be implemented in various fields like banking, insurance, financial sectors and information security systems. And in the field of insurance, we have different types of insurances- health, vehicle and even life insurances. Frauds occur in each of these types of insurances. There are many approaches using which fraud can be detected. Machine learning, artificial intelligence, data mining and other methods are used to detect frauds. The well-known methods used in machine learning to detect frauds are Bayesian Network, Decision trees and back propagation techniques. Many algorithms are also used to detect frauds like Naïve Bayes, KNN, Random forest. In this paper, the different techniques used for vehicle insurance fraud detection are presented along with comparative analysis.

Published by: Sheethal H. D., P. Sai Pranavi, Sharanya S. Kumar, Sonika Kariappa, Swathi B. H., Gururaj H. L.

Author: Sheethal H. D.

Paper ID: V6I3-1419

Paper Status: published

Published: June 6, 2020

Full Details