Vellore Institute of Technology (VIT) is a private university located in&nbsp;Tamil Nadu, India. Founded in 1984, as Vellore Engineering College, the institution offers 20 undergraduate, 34 postgraduate, four integrated and four research programs. It has campuses in Vellore, Amravati, Bhopal and Chennai.

VIT is one of the top ranked private universities in India according to NIRF, THE and QS Rankings.&nbsp;Govt. of India has recognized&nbsp;VIT, Vellore as an&nbsp;Institution of Eminence. This has allowed VIT to take independent quality initiatives and move up in world ranking.

&nbsp;

&nbsp;

VIT University

Terraform helps in building an Infrastructure for the Cloud Environment as a code. Management of the cloud infrastructure is an important and difficult task as the environment has a huge number of resources and maintaining, monitoring and cleansing of resources in each and every region will take up a lot of human effort and time. The work environment consists of number of instances and volumes made by many developers but it is necessary to keep a track on which user is making the Resources. This paper describes various automation methods, cloud tools and resources used to automate resource management and monitoring on cloud. The code has been developed on Amazon Web Services (AWS) Lambda for the serverless approach. The Lambda function gets triggered by various CloudWatch Events according to its Rule. The automation is to monitor the EC2 resources and provide Tag to know who has created the instance or EBS Volume and also to notify about the resources as well as deleting the resources. Jenkins is a software which supports continuous integration for faster delivery. The resource management on the Cloud platform is a difficult task. Hence, in the rapid growth on industries resulting in huge environment to be maintained, automated strategies are necessary for management of resources and will also help in Cost optimization of the Industry. © 2020, Springer Nature Singapore Pte Ltd.

Computer Science

School of Computer Science and Engineering

Chennai Campus

VIT Unitversity

Proceedings of 6th International Conference on Big Data and Cloud Computing Challenges Smart Innovation, Systems and Technologies

Automated Resource Management on AWS Cloud Platform

Gen Z-ers, being independent, self-confident and autonomous as their key characteristics are proven to be technologically more advanced than their previous generations. To reach the milestone of understanding and satisfying the Gen-Z community, and to make use of the digital adherence of this generation, a personalized recommender system using machine learning is designed that can recommend the areas which the students should strengthen themselves to lead and be distinct among their peers. The proposed work uses Support Vector Machine to predict the area of improvement which the student need to focus on. The proposed system will also recommend the list of online courses and materials that the users can make use of to strengthen themselves. The model is built using Python flask and Jupyter notebook and is tested using one public dataset and a private dataset. The results are convincing and accurate enough in identifying the proper areas that require improvement. © 2020 The Authors. Published by Elsevier B.V.

World University root node

Fulltext

Procedia Computer Science

Subjective areas of improvement: A personalized recommendation

Sorting is a basic data processing technique that is used in all day-day applications. To cope up with technological advancement and extensive increase in data acquisition and storage, Sorting requires improvement to minimize time taken for processing, response time and space required for processing. Various sorting techniques have been proposed by researchers but the applicability of those techniques for large volume of data is not assured. The main focus of this work is to propose a new sorting technique titled Neutral Sort, to reduce the time taken for sorting and decrease the response time for a large volume of data. Neutral Sort is designed as an enhancement to Merge Sort. The advantages and disadvantages of existing techniques in terms of their performance, efficiency and throughput are discussed and the comparative study shows that Neutral sort drastically reduces time taken for sorting and hence reduces the response time. © 2020 IJSTR.

International Journal of Scientific and Technology Research

An efficient methodology to sort large volume of data

In current world, craze for sports among the people is increasing exponentially. According to recent survey, FIFA world cup 2018 reached a total viewership of around 3.572 billion [1] that accounts to nearly half the world population. Forecasting of football match results is of extraordinary enthusiasm to fans and sports press particularly to cover audience. Over the most recent years, it has been the focal point of a few investigations. In this paper, an intelligent prediction methodology is proposed to anticipate the conclusive outcome of football matches using Multi-layer perceptron, Support vector machine and Adaboost algorithms. Past results, Home and Away team, Average Position, Odds of team winning, average quality of each side are used as major features for predicting the results. The procedure was validated using the results of 2018-2019 Ligue 1 matches and is lively tested for 2019-2020 Ligue 1 matches. The outcomes acquired utilizing this model had a genuinely decent precision. © 2020, Institute of Advanced Scientific Research, Inc. All rights reserved.

Journal of Advanced Research in Dynamical and Control Systems

Ligue – result prediction using machine learning

Chiller plants (CP) are accountable for regulating the comfort levels of most indoor environments. The CP uses water as the working medium and acts as a centralized cooling system for the controlled cooling of products, in the different production environments, machine tool industries, 3D printing, packaging, heat exchanging systems and to preserve agricultural produce, dairy products, and other edible items. The CP under study is used for providing cooling to sixteen storeyed hostel building at VIT Chennai. The refrigerant used in this system is Tetra fluoro ethane (R134a). The chilled water (ChW) from the evaporator is circulated to the rooms in the hostel through the secondary circuit and the air handling unit exchanges chillness from the chilled water and finally supplies to the hostel rooms. The chilled water from the hostel returns to the evaporator in a closed loop. The cooling water (CW) from the condenser of the refrigeration system rejects heat to the cooling tower (CT). Thus the performance of the CT is directly linked to the performance of the cooling provided to the hostel rooms. The objective of this research is to predict the temperature at the outlet of the CT integrated with the CP using machine learning algorithms. The predicted values are compared with the measured values and with the values calculated theoretically. The results are analyzed using the standard metrics and are observed to be appreciable. © Published under licence by IOP Publishing Ltd.

Mechanical

School of Mechanical Engineering

IOP Conference Series: Earth and Environmental Science

Prediction of Thermal Performance of Cooling Tower of a Chiller Plant Using Machine Learning

Prediction of patterns to prevent and control diseases is a challenging and a prominent requirement in medical domain. In this paper, we propose a machine learning framework to predict the possibility of having heart disease using various algorithms. The framework is executed using five algorithms Random Forest, Naïve Bayes, Support Vector Machine, Hoeffding Decision Tree, and Logistic Model Tree (LMT). Cleveland dataset is used for training and testing the model. The dataset is preprocessed followed by feature selection to select most prominent features. The resultant dataset is then used for training the framework. The results are combined and show that Random forest gives maximum accuracy. © 2020 IEEE.

International Conference on Emerging Trends in Information Technology and Engineering, ic-ETITE 2020

Cognitive Approach for Heart Disease Prediction using Machine Learning

With the ever growing population, increase in vehicle use, industrialization and urbanization, the level of pollution in the air has increased resulting in several harmful effects on the well-being of humans by directly affecting their health. This paper proposes a model based on IoT called the Air Sensing System which will help monitor the quality of air that we breathe over a cloud based platform and will trigger an alarm when the air quality dips below a certain level, which would basically suggest that there are significant number of pollutants present in the surrounding air like CO2, smoke, NO2, SO2, or LPG. The model will then display the air quality in PPM on the internet based platform making it extremely convenient to monitor. The proposed model uses MQ135 sensor which is the best choice for a pocket friendly device that can monitor air quality as it detects the most harmful gases and can measure their amount with precision and accuracy. The model offers ease of usage as the air quality can be monitored from anywhere using any computer or mobile. The model can act as a module for a air purifying system in the future where the model triggers some actuator like an Exhaust Fan or Air Conditioner when the pollution rises above a certain level or can be used to alert the owner through a message. With the ever growing pollution, such a low cost model is the need of the hour. © 2019 IEEE.

2019 3rd International Conference on Computing and Communications Technologies (ICCCT)

Low-Cost Air Sensing System

Online health communities generally provide a platform for patients and their families to learn about an illness, seek and suggest support, and connect with other peers in analogous situations. In this paper, an architecture and implementation of an automatic medicine dispenser is proposed to support and extend the online health communities. Through this solution, doctor in the online health community may suggest pills based on the health conditions of their patients as communicated by them through online platform. Each user is secured with a unique barcode while starting the communication between the doctor and the patient. The barcode may then be scanned in the nearby automatic pill dispenser that can dispatch the medicine. Cloud is used as a medium to support Storage as a Service. The proposed model eliminates the need to spend time to visit the doctor and the time to spend in pharmacy. Also, the patients are relieved from the errors that might be caused due to handwriting misinterpretation and change of medicine that exists in manual medicine dispensing system. © BEIESP.

International Journal of Recent Technology and Engineering

IOT based automated medicine dispenser for online health community using cloud

Data mining techniques are widely used for various educational researches. This article depicts the survey of various data mining techniques and tools which are used to guide students, course instructors, course developers, course administrators and organizations in respective fields based on future scope. This article also highlights how recommender systems rule the educational field though it's filtering mechanisms in recommending courses for students. It also illustrates future scope of data mining in educational needs.

International Journal of Web Portals

Educational Data Mining and Recommender Systems Survey

IoT (Internet of Things) is the network of physical devices which is embedded with the sensors to detect signals, software and actuators to take required action(s), electronics and network connectivity to collect and exchange data with other connected devices. These devices are also called smart devices. They are mostly connected remotely and can even send data to cloud. The concept of IoT can be implemented at homes, business, educational centers, medical fields and national security. This paper has implemented the concept of Internet of Things in schools or university classrooms where the attendance system is automated. With the help of a database, a student teacher interaction portal and physical devices, the paper aims to make an education institute smarter. In addition, our research also verifies the presence of a human being sitting on a chair using personal identification. The verification of the seat occupancy by a given individual can be confirmed from any part of the world at any given instance as the data is stored in cloud at all times. Sitting is the most prevalent conduct of human body in everyday life. People spend a lot of time sitting in a school chair, automobile seat or lounge chair in a day. It has been observed that as a result of some everyday activity or poor sitting postures can cause pains and other common complications for people like Endometriosis, Sacroiliac Joint Dysfunction, Degenerative Disc Disease and more. This paper aims to mitigate such issues, and in order to circumvent the adverse effects of improper sitting behavior. The smart chair will also try to promote a healthy lifestyle of the students by measuring the student sitting postures and suggesting to maintain a good healthy posture. The usability of the device can be improved by investing in powerful and more accurate sensors, smaller micro devices and better servers. Consequently, these improvements will help in reducing the overall size of the device; the device will be more robust and accurate with low failure rate and long term stability. © 2017 IEEE.

2017 International Conference on Inventive Computing and Informatics (ICICI)

Smart chair

This paper aims to reduce the time taken to search for data within a hash table by making use of a tree structure. The two most popular methods for collision avoidance within a hash table - Open Addressing and Separate Chaining each have their merits and demerits. Here we attempt to overcome the main demerits of each of these techniques which are - Filling up of the hash table in Open Addressing and Poor searching time in Separate Chaining. A different approach to the problem has been proposed here which prevents the filling up of the hash table by using a Binary Search Tree instead of a table to store the hash values and adds new nodes to this tree only when a new hash value is generated while entering data. Also, in place of using linked list to store the data within a hash bucket, we use another Binary Search Tree to reduce the search time within each hash bucket. Using this approach, we attempt to reduce both the amount of space and time that will be used as there would be no empty buckets for any hash values and we do not have to worry about filling up the hash table as we will be chaining the data under each bucket. We also try to take care of the main drawback of Separate Chaining i.e longer search time within a hash bucket, by using a Binary Search Tree instead of a linked list, thus reducing the worst case search time from O(n) to O(log n). © 2017 IEEE.

A tree based approach to improve traditional collision avoidance mechanisms of hashing

The aim of the paper is to design an economical system that monitors the drowsiness of the driver. The system will use a camera to monitor the driver’s eyes. To achieve this, the system will capture video from a day – night sensitive camera and use image processing algorithms running on a Raspberry Pi board to detect any drowsiness in eyes. This system focuses on development in the most economical way so that it can be implemented in comparatively lower end vehicles too which form the larger crown on roads and prevent loss of human life through accidents of such types. © IAEME Publication.

International Journal of Civil Engineering and Technology

A low cost design to detect drowsiness of driver

Proper subset selection for next release is one of the key factors responsible for the success of the software projects. Selecting a subset of requirements from a pool of requirements in a market driven product development is found to be challenging since it involves unknown customers who may be geographically distributed. The objective of this paper is to study the importance of requirements prioritization through a exploratory study of literature supported by a survey conducted with industry experts. We have also analyzed and identified the different stakeholders that are involved in the process. The use of social media for gathering information from unknown market and the reasons behind the negligence of prioritization in industries is also been discussed. © Springer International Publishing Switzerland 2016.

Proceedings of the 3rd International Symposium on Big Data and Cloud Computing Challenges (ISBCC – 16’) Smart Innovation, Systems and Technologies

Subset Selection in Market-Driven Product Development: An Empirical Study

Circuits and Systems

Multi-Criteria Decision Making Using ELECTRE

Requirements prioritization is a critical issue in the field of software engineering to identify a subset of requirements from a pool, by taking into account different classes of opinions. Identification of stakeholders and the mode of getting information from all stakeholders is still a challenging task. This activity becomes too difficult, if the stakeholders are geographically distributed which actually happens in practice. In this paper, we have discussed about the challenging task of identifying the stakeholders who have to be involved in prioritization. We have addressed the issues that happen to be the hindrance for the above said activity and have justified the need for automation for prioritization. © Research India Publications.

International Journal of Applied Engineering Research

Requirements prioritization – Stakeholder identification and participation

In software development, there are two broad schools of thought: the traditional sequential or the "Waterfall method" and the iterative or the "Agile method". This paper aims to discuss about the pitfalls of traditional methods in developing a product and the application of agile methods to improve the process. Agile aims to deliver a customer-driven product in time and budget. The paper is supported by the views of developers who had moved to agile from waterfall models.

2010 2nd International Conference on Computing, Communication and Networking Technologies, ICCCNT 2010

Progression towards agility: A comprehensive survey

Object-orientation has rapidly become accepted as the preferred paradigm for large-scale system design. The product created during Software Development effort has to be tested since bugs may get introduced during its development. This paper presents a comprehensive survey of the various software testing methodologies available to test object-oriented software. Software based on Object Oriented technology poses challenges to conventional testing techniques since it involves concepts like Inheritance, Polymorphism etc., It is very essential to monitor the behavior of every object during its lifetime by keeping track of where the object is defined and where such definition is referenced. In this paper we have discussed about how Unit testing, Integration Testing and System Testing are being carried out in the Object Oriented environment. To accommodate these strategies, several new techniques have been proposed like Fault-based Testing, Scenario-based Testing, Surface Structure testing and a brief discussion of these techniques has also been presented.