Manuscripts

Recent Papers

Research Paper

Credit card fraud identification using machine learning

Today technology is increasing at a very rapid pace, which can be used for good as well as for bad purposes. So with this growing technology e-commerce and online transactions grew up which mostly contain transactions through credit cards. Credit cards help People to enjoy buy now and pay later for both online and offline purchases. It provides cashless shopping at every shop in all countries. As the usage of credit cards is increasing more, the chances of credit card frauds are also increasing dramatically. The credit card system is most vulnerable to frauds. These credit card frauds cost financial companies and consumers a very huge amount of money annually, fraudsters always try to find new methods and tricks to commit these illegal and outlaw actions. Online transaction fraud detection is the most challenging issue for banks and financial companies. So it is much essential for banks and financial companies to have efficient fraud detection systems to reduce their losses due to these credit card fraud transactions. Various approaches have been found by many researchers to date to detect these frauds and to reduce them. Comparison of Local Outlier Factor and Isolation Factor algorithms using python and their detailed experimental results are proposed in this paper. After the analysis of the dataset, we got an accuracy of 97% by the Local Outlier Factor and 76% by Isolation Forest.

Published by: Aishwarya Shirole, Riya Thakur, Yash Singh, Harsh Singh

Author: Aishwarya Shirole

Paper ID: V7I3-2083

Paper Status: published

Published: June 24, 2021

Full Details
Research Paper

An efficient optimized multi-kernel support vector machine-based brain tumor classification and segmentation in MRI

Magnetic resonance (MR) imaging has been playing a vital role in neuroscience research to examine brain conditions related to normal and abnormal brain structures and functions in vivo. In previous years, MRI is observed to play an important role in brain abnormalities research in determining the size and location of affected tissues. MRI Image segmentation and classification refers to a process of assigning labels to a set of pixels or multiple regions. It plays a major role in the field of biomedical applications as it is widely used by radiologists to segment the medical images input into meaningful regions. Thus, various segmentation techniques in medical imaging depending on the region of interest had been proposed. Medical image segmentation problems have been approached with several solution methods by different ranges of applicability such as Region Growing, Self-Organizing Map (SOM), and Fuzzy c-Means (FCM). Some recent progress has been made to create semi-supervised (based on user interaction) or supervised variational methods. In the last decades, many methods have been proposed to segment the brain tumor of MR images, such as neural networks, finite Gaussian mixture model, knowledge-based methods, atlas-based method, active contour model, level set methods, and outlier detection. However, the segmentation of medical imagery remains a challenging problem due to the complexity of the images. Brain tissue is a particularly complex structure and its segmentation is an important step for studies in temporal change detection of morphology. The success of MRI in the detection of brain pathologies is very encouraging. However, diagnosis and locations of abnormality are made manually by radiologists. It consumes valuable human resources, is error sensitive, and makes it prone to error.

Published by: P. Harshavardhan, M. Rishika Reddy

Author: P. Harshavardhan

Paper ID: V7I3-2103

Paper Status: published

Published: June 24, 2021

Full Details
Research Paper

Urban underground drainage monitoring system using IoT

The additional volume of wastewater entering the pipes, can cause backups which can lead to the sewer system to overflow. The Monitoring of urban underground infrastructure, it is important to control the current flow from the external water is in the pipe line. By wireless to connect underground communication, and sensor solutions, you can follow the development of the urban underground IoT applications, such as for the monitoring of wastewater and stormwater overflow in real-time with the help of Flow sensors with respect to Arduino and NodeMCU. This paper presents an analysis of the loss of a wireless underground utility services in the urban underground IoT for waste water monitoring and control. It is shown that the communication range is4 km away and can be reached from an underground channel of communication by means of a 10 cm-thick layer of asphalt. The urban waste water and is responsible for the collection and the treatment of wastewater in the waste water treatment plants, treatment of the many millions of litres of water per day. Cities and towns in the need for the monitoring of the quantity and quality of wastewater discharged into the system the collection and the achievement of these structures. The volume of water in the pipes and could cause back-ups, which in turn can lead to sewer overflows.

Published by: D. Deepak Kumar, N. Indrajith, R. Bhavya, Dr. V. Jayaprakasan

Author: D. Deepak Kumar

Paper ID: V7I3-1968

Paper Status: published

Published: June 24, 2021

Full Details
Research Paper

3-Dimensional visualization and animation of a construction schedule of a single storey building – 2021

Construction sector needs proper scheduling, planning and management procedure for any project which leads to improve the general optimization of the time, cost and resources. The planner utilizes the 2- dimensional drafting tools and follows the contents of the illustrations with respect to exercises of the construction schedule for which Primavera and Microsoft Project for the scheduling process and AutoCAD for drafting plan and to visualize ,decision making of various construction activities are used .It involves multi environment for managing construction activities and time consuming too which in turn affect in clarifying the status of the project to the customer making it exceptionally tedious and troublesome. With this process the customer and store manager will not have the idea of the specialized terms used in the graphical representation and schedule .Thus the construction company necessitates an implement which can impact the 3 dimensional components and the schedule in particular individual environment from multi environment .Majority of commercial software’s used to generate a 4-Dimensional model but they don’t have the important functions like creation and modification of the created model in a single environment. Apart from using trivial methods of project schedule sheets and manual drawings , one can combine both in a single environment to generate the 4-Dimensional model in the GIS software. The objective of the current study was to create 4D model (3D geospatial model + time component) in a single platform using GIS for single storey residential building. The dynamic linkage between the drawings and respective scheduled activities in the GIS software helps in visualizing construction sequence and identifying logical errors that can occur in schedule. The proposed GIS based methodology can be used as replacement to many trivial manual techniques to take out the data from the accessible database and can easily maintain and modify majority of the information in the digital format.

Published by: Mohith J. Gowda, Dasari Sri Hari, Md Ashfaq Ahmed, Manoj R., Priya B. P.

Author: Mohith J. Gowda

Paper ID: V7I3-2044

Paper Status: published

Published: June 24, 2021

Full Details
Survey Report

A survey on docker container and its use cases

Docker is an open platform for rapidly building, delivering, and executing a variety of applications. It allows for faster software delivery by separating applications from infrastructure. Docker techniques encourage rapid shipping, testing, and deployment of code anywhere, reducing the time between code development and production deployment. It assists both developers and system administrators by letting developers write code without having to worry about the system on which it will eventually run. It also can minimize the number of systems and provide operations workers more flexibility. The principles of Docker containers are discussed in this paper and recent research on the subject. The document also contains significant use cases, as well as the pros and challenges of using it.

Published by: Abha Anand B., Darunya B. C., Anisha B. S., S. G. Raghavendra Prasad

Author: Abha Anand B.

Paper ID: V7I3-2052

Paper Status: published

Published: June 24, 2021

Full Details
Research Paper

Pollution monitoring and controlling using Internet of Things (IoT)

The level of pollution has increased with times by IoT of factors like the increase in population, increased vehicle use, industrialization and urbanization which results in harmful effects on human well-being by directly affecting health of population exposed to it. In order to monitor quality of air, water quality and sound level of the environment over IoT based new framework is proposed which is based on data acquisition, transmission and controlling.

Published by: M. Hariharan, C. Senthilkumar

Author: M. Hariharan

Paper ID: V7I3-1993

Paper Status: published

Published: June 24, 2021

Full Details