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

Department of Software Systems

Smart Hydroponics System using the IoT techniques (Arduino) has achieved great excellence with the accessibility of different kinds of soil and different regions of temperatures available to train on, many resources are now accessible which can be used to train the sensors to transfer learning and developing a new model . By installing a pH sensor, water sensor, and temperature sensor, it is an essential technique of condition monitoring of soil and farming. Manual examination methods and other traditional techniques are available for agriculture and are complicated with more risk, and also the time taken for governing is high. Old conventional methods should be stopped for the inspection, so the uncertainties become less. To overcome all these problems, a Smart hydroponics System (SHS) can be used to reduce the risk and to maintain the proper nutrition in soil using different sensors. Throughout the project, the main concern was to train the model to achieve good accuracy with a different set of parameters varied to come up with the best SHS model. Also, at last, a proof of concept attempt is made to deploy the model for measuring different soil nutrients into many different classes, such that the model can be used anywhere when required. © 2020, Institute of Advanced Scientific Research, Inc. All rights reserved.

World University root node

School of Computer Science and Engineering

Vellore Campus

Journal of Advanced Research in Dynamical and Control Systems

A novel approach to smart hydroponics system using IoT

The field of Bug Reporting and Triaging has of late been a hot area of study among researchers trying to improve system management techniques. There is an increasing importance for developers to consider and address the various issues faced by users in order to not only ensure the delivery of quality service but also to understand the performance of the system under real-life scenarios. Hence, in this project, there is an attempt to develop a system that can improve the process of handling bug reports submitted by users of a software. This will be done through Bug Severity Prediction using the eXtreme Gradient Boosting (XGBoost) algorithm and the inclusion of a class balancing function to offset the bias due to the presence of majority and minority classes. The project would also include a study on the work that has already been done along with a proposal of the system architecture, methodologies used and the various hardware and software requirements. The main aim of the project is to shed light on the advantages of developing a Bug Severity Prediction system that can help reduce the dependence on users for providing accurate information. With the help of models built based on the history of bug reports received till date, the system should be able to take up some of the responsibilities of the user reporting the bug. © 2020 IEEE.

Proceedings of the 2020 IEEE International Conference on Machine Learning and Applied Network Technologies, ICMLANT 2020

Bug Severity Prediction System Using XGBoost Framework

In the earlier days when natural disasters are occurred that information is communicated through phone calls, telegram, direct observations or personal interview due to which relief operations used to get late; thus human lives and animal mortality will get increases and sufferings eventually increased. The internet technologies developed are used now days to some extent to control the rate of the sufferings. Tweets are the fast and real-time sources for information. We perform various approaches to identify which process can work faster compare to others. First we collect data from social media which is considered as fastest medium to reach vast number of people. Then we classify according to our needs and make clusters using algorithm. For better understanding, we use various tools to visualize and to identify the specified region to provide necessities like food, shelter and medicines in an earliest possible time. © 2020, Springer Nature Singapore Pte Ltd.

Lecture Notes in Electrical Engineering

Identification of Disaster Prone Areas-A Machine Learning Approach

This is a comparative study of clustering techniques, but focused in the area of market segmentation. By understanding the potential benefits of clustering large amounts of data, the work is to relate clustering into the field of competitive marketing. This is achieved by gathering data from the Twitter using necessary tools and then cautiously applying various clustering algorithms. From these algorithms, we are able to build graphs based on the output, and from these graphs, useful information can be advantages from a strategic marketing point of view. From the clustering of Twitter data, it is easy to identify potential social media influencers. For future implementation, one method is that the companies that are struggling to grow in terms of online marketing can benefit from this study, allowing them to identify their own social media influencers, identify social media trends and determine the online social media market segmentation. All of which will provide them an advantage in further promoting their company more effectively and efficiently. © 2020, Springer Nature Singapore Pte Ltd.

Department of Computer Applications

School of Information Technology and Engineering

Lecture Notes in Networks and Systems

Comparative Study of Clustering Techniques in Market Segmentation

The need and significance for extracting information from the web is rising up with an increasing trend. Almost every day, we end up in a circumstance, where we need to extract information from the web. This is not always about finding new courses, but we also have to prone for reviews and data for providing a brief about them. Mostly, the issue is how we scrap the data and store it, but not on the strategy we use to perform it. The project done here is a proof of concept for how we could integrate it with php to make the updating by running python on the server. Here, we are going to use the python script to extract the info from a website and parse it to get the required information regarding our needs. Then, the data is send to the webserver hosted on the internet, the php running on the server will get the data from the python script. The data is been store on the mysql server using the php script and every time, we run the python, the data in the website changes. © Springer Nature Singapore Pte Ltd. 2020.

Advances in Intelligent Systems and Computing

Web Scraping for Unstructured Data Over Web

Movie reviews help users decide if the movie is worth their time. A summary of all reviews for a movie can help users make this decision by not wasting their time reading all reviews. Movie-rating websites are often used by critics to post comments and rate movies which help viewers decide if the movie is worth watching. Sentiment analysis can determine the attitude of critics depending on their reviews. Sentiment analysis of a movie review can rate how positive or negative a movie review is and hence the overall rating for a movie. Therefore, the process of understanding if a review is positive or negative can be automated as the machine learns through training and testing the data. This project aims to rate reviews using two classifiers and compare which gives better and more accurate results. Classification is a data mining methodology that assigns classes to a collection of data in order to help in more accurate predictions and analysis. Naïve Bayes and decision tree classifications will be used and the results of sentiment analysis compared. © Springer Nature Singapore Pte Ltd 2020.

Sentiment analysis on movie reviews

A user-based Course Recommendation System is developed in this paper. The recommender system is constructed as an online website/application which is capable of producing a personalized list of courses which a user can take. Modern versions of traditional recommender system, such as collaborative filtering are considered to be efficient in this domain of user-based recommendation. On the basis of collaborative filtering principle, the recommendation process is divided into three steps, representation of student data, generation of neighbor user (student) and the generation of course recommendations. In order to compute the likenesses amid each user, the Cosine method is adopted during the process of the generation of neighbors. Then the course recommendations are generated according to the ratings of the other students and his personal ratings. © Springer Nature Singapore Pte Ltd. 2020.

Critical Review on Course Recommendation System with Various Similarities

Group activity detection is a crucial task for an automated analysis of human actions in many environments, such as surveillance or sport footage. Group activity recognition focuses on identifying the activities of one or more individuals through a sequence of observations on the conduct of the individuals. Numerous approaches have been proposed for the same using deep learning neural networks. In this paper, we focus on graphical convolutional neural network (GCN) which uses graphs as inputs, aggregate the vectors using aggregation functions and attempt to create models which can provide ample knowledge innate in human mobility. The paper aims to build a GCN method by adding the application of Polynomial Aggregation Function (PAF) to ensure the precision in investigating the activities is improved and further increases the accuracy of identification of human actions. The experiment is carried out using VGG16, GCN and GCN embedded with PAF on the Collective dataset. The experimental results obtained show that the whole group's actions as an entity is recognized and the proposed method provide better accuracy. © 2020 IEEE.

4th IEEE Conference on Information and Communication Technology, CICT 2020

GCN embedded with polynomial aggregation function for group activity recognition

In recent years, Heterogeneous Wireless Sensor Networks are widely used to perform a variety of real-time applications. Since sensor nodes are battery powered, developing an energy efficient algorithm to increase the network life time is challenging. This paper proposes a cluster based mechanism, namely, Augmented EDEEC, to improve the network life time. This algorithm is obtained by modifying the distance metric and level of heterogeneity in the existing Protocol. This new protocol exhibits 1.25 times more network lifetime than the existing Distributed Energy Efficient Clustering algorithms. The results are benchmarked with the energy efficient clustering protocols like DEEC, DDEEC and EDEEC. © 2020, Springer Nature Switzerland AG.

Department of Analytics

Advances in Intelligent Systems and Computing Intelligent Systems Design and Applications

An Augmented Algorithm for Energy Efficient Clustering

Brain tumors are major causes of death in today’s world and methods of detecting them prematurely require vast improvement. The objective of this project is to detect the tumors early from MR image scans by utilizing deep convolutional networks to locate the tumor.The tumor is divided at first in the main stage and the generated bounding box is utilized for the center of the tumor in second step. This is trailed by division based on the bounding box of the tumor center division result. Examinations are performed with the BraTS 2017 validation set. This is a numerous division issue. © 2020, World Informations Syndicate. All rights reserved.