Manuscripts

Recent Papers

Research Paper

Characteristic study in optimization of Biomethanation process for high TDS spent wash from Distilleries

Acidic in nature, dark brown colored rich source of salts, a highly thick and viscous by-product of the sugar industry is known as Molasses. This molasses also contains sugar which could not be crystallized. It is one of the strongest organic industrial waste and even complex troublesome having extremely very high Chemical Oxygen Demand and Biological Oxygen Demand values. Due to the high concentration of organic contents in distillery spent wash which acts as a potential source of renewable energy. In a developing country like India, distilleries have become a major source of pollution as 88% of its raw materials are converted into waste and discharged into the distillery for every liter of ethanol produced.

Published by: Lalitha Devaraju, Dr. Manju B., Dr. Sathisha N. S., Dr. Kiran B. M.

Author: Lalitha Devaraju

Paper ID: V7I4-1261

Paper Status: published

Published: July 19, 2021

Full Details
Research Paper

Effective video retrieval system using Adaptive Shot Detection and Feature Vector Algorithm

In the current situation, around 150 million hours of video are uploaded to the Internet (i.e., YouTube, Netflix, Dailymotion, Vimeo, etc.). It becomes very difficult to extract the required relevant videos from such a large data set. Semantic / context-based matching is fast but highly dependent on the correct tags assigned to the video. On the other hand, due to the large number of frames involved in the video, it is difficult to apply a context-based search to the video. We have developed a novel video retrieval system that can extract the required videos from large sets of video data. The algorithm consists of content-based adaptive shot detection and feature vector extraction from each video from the dataset. The user only needs to provide an image similar to the system input to search for any video in the dataset.

Published by: J. Abhishek Paul, Dr. Sowmyarani C. N.

Author: J. Abhishek Paul

Paper ID: V7I4-1441

Paper Status: withdrawn

Submitted: July 19, 2021

Full Details Track Status
Research Paper

Comparative study of industrial steel structure (pre-engineered building) and residential RCC structure

Industrial steel structure (PEB) constructions are very popular to their advantages over conventional RCC construction. RCC structures are bulky and impart more seismic weight and less deflection whereas Steel structures instruct more deflections and ductility to the structure, which are advantages to resisting earthquake forces. Industrial steel structure Construction the better properties of both steel and concrete along with lesser cost, speedy construction, better quality control, sustainability, etc. Hence the aim of the present study is to compare a G+2 story residential RCC structure and an industrial steel structure. Both structures are designed for the same loading condition. Beam and column sections are made of either RCC, Steel (PEB) sections. STAAD PRO software is used for analysis and design and analysis results are compared. Cost-effectiveness based on material cost for Steel structure and RCC structure determined. The study concludes that industrial steel structures (PEB) are the best-suited types of constructions in terms of material cost.

Published by: Mahesh Nivrutti Ghumare, S. N. Daule

Author: Mahesh Nivrutti Ghumare

Paper ID: V7I4-1440

Paper Status: published

Published: July 19, 2021

Full Details
Research Paper

Credit Card Fraud Prediction

Fraud detection by credit companies is essential in this digital era where the majority of financial transactions are made online. Fraudsters use loopholes in the payment systems to their benefit. Such problems can be solved to a large extent if the companies add an extra layer of security before confirming the transactions using machine learning algorithms. This project intends to use the Isolation Forest algorithm to enhance the security of credit card transactions by predicting the credibility of the transaction before authorization. Detecting 100% of the fraudulent transaction, minimizing the incorrect fraud classifications, and making the process automated is our objective.

Published by: Yash Rajesh, Thyagaraj Tanjavur

Author: Yash Rajesh

Paper ID: V7I4-1435

Paper Status: published

Published: July 19, 2021

Full Details
Research Paper

Used car price prediction

This research paper is the combination of datasets collected by cardekho.com and we have used ML to predict the price of a used car by creating a model using python, flask, and HTML the algorithm that we have used is Random Forest Regression. The price of the car is determined by the manufacturer and not everyone can afford it so they look for some low-cost alternative such as used car and this helps to build a big and evergreen used car market but due to the price irregularities this market is facing lots of problems so we have used machine learning to develop a new model that will predict the price and help consumers to buy the used car at a perfect price.

Published by: Abhishek Jha, Dr. Ramveer Singh, Manish, Imran Saifi, Shipra Srivastava

Author: Abhishek Jha

Paper ID: V7I4-1434

Paper Status: published

Published: July 19, 2021

Full Details
Research Paper

implementation and analysis of credit card fraud detection using a Machine Learning Technique

Due to rapid growth in the field of various cashless transactions or digital transactions, credit cards are widely used in almost every work and hence there are more chances of fraudulent transactions. Depending on the type of fraud faced by banks or credit card companies, various measures can be adopted and implemented. Here the credit card fraud detection is based on fraudulent transactions. Generally, credit card fraud activities can happen both offline and online. But in today’s world online fraud transaction activities are increasing day by day. So in order to find online fraud transactions, various methods have been proposed and implemented by various organizations. This project proposes a machine learning technique for credit card fraud detection. Machine learning is the currently used technique implemented in various sectors. It is prioritized due to its ongoing advancements making our lives easier. In the proposed system, we use Random Forest Algorithm (RFA) for finding the fraudulent transactions and the accuracy of the transactions. The main aim is to detect fraud while making a transaction and alert the user if his/her account was accessed by an intruder. Credit card fraud detection using Machine learning is done by using classification and regression techniques. We use the Random Forest algorithm which is a supervised learning algorithm to classify the fraud card transaction into fraud or genuine transactions. This algorithm uses decision trees for classifying the data set. After classifying the dataset a confusion matrix is obtained. The performance of the Random Forest Algorithm is evaluated based on the confusion matrix. The results obtained from the processing data set to give an accuracy of about 70%. The random forest has better efficiency and accuracy than any other machine learning algorithm. This model is implemented by Python and SQL programming languages.

Published by: Sanka Reshmi, Saripalli V. R .Manasa, Siramdas Shyamala, Sreerama Usha Ramya, B. Esther Sunanda, D. Sowjanya

Author: Sanka Reshmi

Paper ID: V7I4-1432

Paper Status: published

Published: July 19, 2021

Full Details