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

Training a Machine Learning (ML) model on bigger datasets is a difficult task to accomplish, especially when a high-end configuration is not accessible. A relatively good configuration may also not always produce quick outcomes and depending on the dataset size, the time taken would be anything between seconds to several hours. More often, the tasks we are interested in involve big datasets and complex models. The purpose of our work was to see how effective Hadoop can be in terms of increasing the efficiency of working with Machine Learning for a given problem. Out of many models to choose from, Logistic Regression was chosen, which is relatively simpler to implement. Three Logistic Regression models were implemented and trained on MNIST Handwritten Digits dataset. First one was implemented in Python using NumPy without any ML libraries. The second implementation used LogisticRegression class that comes with the Scikit-learn Python package, and the third implementation was done using PySpark MLlib. Towards the end of the paper, we present the observations and results obtained from the execution of each. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2021.

World University root node

Department of Information Technology

School of Information Technology and Engineering

Vellore Campus

Advances in Intelligent Systems and Computing

Logistic regression on hadoop using pyspark

From past decade, the advancement in the field of RDF data management poses many challenges to researchers. Processing large volumes of RDF data is very difficult task in the cloud. The RDF data actually contains complex graphs along with large number of schemas. Distributing the RDF data with traditional approaches or partitioning them with conventional mechanism leads to faulty distribution as well as generated large number of join operations. To address the above issues, this paper developed architecture for distributed query processing using the adaptive hash partitioning approach along with hash join operation. This paper also developed an algorithm for executing the query by minimizing the joins. This paper presented an evaluation of the proposed model with other standard model. The experimental results proved that the proposed method had faster response time compared to the other standard models. © 2019, Springer-Verlag GmbH Germany, part of Springer Nature.

Department of Analytics

School of Computer Science and Engineering

Evolutionary Intelligence

Architecture for distributed query processing using the RDF data in cloud environment

Storage and processing of intensively growing data has become easier with the invent of cloud computing. Computing paradigms have evolved from the era of centralized to distributed, distributed to grid and grid to cloud. Parallel programming models to process large data and with utilization of more cpus have got a new color with the introduction of mapreduce programming model. Hadoop, a framework for handling millions of data in clusters of computer uses MapReduce programming model. Users prefer java for their MapReduce jobs as Hadoop is written in Java. Here, we discuss the MapReduce programming approach and other approaches/languages that can be used to write MapReduce jobs. © Medwell Journals, 2016.

Asian Journal of Information Technology

A Study on Non Java Options for Mapreduce Programming with Hadoop

Analytical and computational requirements are increasing in data warehousing systems. So it is very crucial to identify semantically equivalent data, linking them and discovering structural dependencies. This can be performed using dashboards. Dynamic dashboard will perform the customization of information for specific need of user. And we are using an improved method for dashboard development using hyper graph approach and ontology exploration. Existing dashboard design satisfies given user query and provides flexibility in changing user interactions. In this paper a quick specification of dashboard interfaces is obtained for detailed DB (data base) query language where semantics of user interaction is in a declarative manner.

International Journal of Engineering and Technology

Ontology and hyper graph based dashboards in data warehousing systems

Encryption is most effective way to achieve data security. This is done by converting the data into cipher text. The existing way of doing this was using Armstrong number. Since there are few Armstrong numbers therefore a crypt-analyst can easily find the key. In this paper, we are proposing a new algorithm for encryption technique, UPMM algorithm, which is applied on ASCII value of data. ASCII values are encrypted using a key involving Palindrome numbers and unique alphanumeric id, which is also converted into ASCII value to provide authentication over the network. This paper gives a technique to send data over the network in set of three keys. Normally a crypt-analyst can easily find out the key however in this approach a mixture of palindrome number and matrix multiplication is used for encrypting the data. In the same way decryption will also be done at receiver's side by using inverse of encoding matrix. © 2014 IEEE.

Department of Software and Systems Engineering

The 2014 International Symposium on Networks, Computers and Communications

ASCIi based cryptography using unique id, matrix multiplication and palindrome number

International Journal of Applied Engineering Research

Retriving top result cells from a text cube

Department of English

School of Social Sciences & Languages

VIT Unitversity

Advances in Computing and Information Technology Advances in Intelligent Systems and Computing

Processing RDF Using Hadoop

The system is intended to provide an ease in purchasing accessories for face from an online shopping website. The system creates a virtual store environment where the individual could trial accessories upon their interests. The application can help in analyzing if the accessory/s fits an individual's personality. This study is intended to processes the image using image preprocessing techniques, detects the face from the processed image using face detection techniques and identifies the unique facial features using feature extraction techniques. When the accessory for trial is set, then the product is displayed at the respective feature of an individual's. Using image fusion, the feature with the accessory is fused with the original image. © Medwell Journals, 2014.