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

Data in varied nature and huge quantities are being generated every day. They range from tabulated, structured and semi-structured as well as numerical or categorical in terms of attributes. Data pre-processing presents data in a favourable format to apply analytics algorithm and derive knowledge therein. Data analytics has revolutionised millennial mankind unwinding the knowledge and patterns mined from data. Clustering is an unsupervised learning pattern which has popular algorithms based on distance, density, dimensions and other functions. These algorithms are operational on numerical attributes and special algorithms for data involving categorical features are also reported. In this paper we propose a straight forward way of clustering data involving both numerical and categorical features based on neighbourhood rough sets. It does not include calculation of any extra parameters like entropy, saliency, dependency or call for discretisation of data. Hence its complexity is lesser than algorithms proposed for categorical or mixed data and offers better efficiency.

Department of Software Systems

School of Computer Science and Engineering

Vellore Campus

Department of Analytics

International Journal of Advanced Intelligence Paradigms

Clustering mixed data using neighbourhood rough sets

Public healthcare plans are essential to regions present around the world and deriving optimal strategies to combat the negative effects is one of the tasks involved in the process. Measuring similarity between two regions based on a common attribute is a popular problem, and this paper aims to find a method for the same, the common attribute being a key statistic taken from public health surveillance records. The method uses the application of rough measurement concept to determine the similarity between different regions having disease-linked death rates, which in turn can effectively be used to derive contingency plans in the case of a relevant event or before the next one takes place. We also take advantage of GIS tools to help in the processing and visualization of spatial data, and this paper discusses the role of GIS in public health surveillance as well. © 2020, Springer Nature Singapore Pte Ltd.

VIT Unitversity

Advances in Intelligent Systems and Computing Soft Computing for Problem Solving

Enhancing Public Health Surveillance by Measurement of Similarity Using Rough Sets and GIS

There are many methods that can be used to compute the geographic similarity between regions represented through areas in a two dimensional space. However, it is the rough set based membership function that allows an estimate of the similarity between a subzone formed by the data. The major objective behind this paper is to measure the similarity of GIS subzones on a discrete dataset. This has a varied number of applications not only in GIS and epidemiology but also in clusters analysis and artificial intelligence. © 2019 IEEE.

2019 Second International Conference on Advanced Computational and Communication Paradigms (ICACCP)

Neighborhood Rough Set Based Similarity Measurement Ofsubzones Affected by West Nile Virus

Rough set theory partitions a universe using single-layered granulation. The equivalence classes induced by rough sets are based on discretized values. Considering the fact that the spatial data are continuous at large, discretizing them may cause loss of data. Neighborhood approximations can lead to closely related coverings using continuous values. Besides, the spatial attributes also need to be given due consideration and should be handled unlike non-spatial attributes in the process of dimensionality reduction. This chapter analyzes the use of neighborhood rough sets for continuous data and handling spatially correlated attributes using rough sets.

Advances in Computer and Electrical Engineering Advanced Methodologies and Technologies in Network Architecture, Mobile Computing, and Data Analytics

Neighborhood Rough-Sets-Based Spatial Data Analytics

With the growing amount of textual information in recent years, it has become quite challenging to keep up with content produced by humans. Many models have been proposed that can perform reading comprehension on a variety of texts; however, past models either excel at information retrieval on complex texts or inference on simple texts. In this paper, we propose a model called ALICE that can perform information retrieval as well as inference tasks on any text. It is scalable to any document size and can be used to aid professionals in quickly finding answers to their problems using natural language queries. We will explore how ALICE achieves this and test it on some common datasets. © 2018, Springer Nature Singapore Pte Ltd.

Soft Computing Systems Communications in Computer and Information Science

ALICE: A Natural Language Question Answering System Using Dynamic Attention and Memory

Artificial neural networks excel at doing specific tasks like image recognition, sequence learning, machine translation. But, the direction of research has moved towards the creation of more general purpose neural network architectures. Recently, DeepMind introduced Differentiable Neural Computer (DNC), with an external memory system that is capable of working on complex data structures. DNC can infer from graph problem, solve block puzzle using reinforcement learning and so on. DNC uses LSTM as controller network that manipulates the memory matrix. In this paper, we introduce a change to DNC architecture by replacing LSTM network with multiplicative LSTM and measure the performance of the improved model by training it on three different tasks; namely question answering task using bAbI dataset, character level modelling using harry potter text and planning search using air cargo problem. We compared the performance of the previous model to determine its behavior. © 2018, Springer Nature Singapore Pte Ltd.

An Improved Differential Neural Computer Model Using Multiplicative LSTM

Spatial data analysis is being used efficiently and the governments have realized that georeferenced data yields more insight with time and locations. Epidemiology is about the study of origin and distribution of diseases and dates back to the 1600s with the instance of cholera in London. Data Science has been evolving and when analyzed with Soft Computing techniques like Rough Set Theory (RST), Fuzzy Sets, Granulation Computing which encompasses the data in its original nature, results can be obtained with accrued accuracy. This survey paper highlights Spatial Data Mining methods used in the field of Epidemiology, identifies crucial challenges and discusses of the use of Soft Computing methods.

Jurnal Teknologi

DATA ANALYTICS IN SPATIAL EPIDEMIOLOGY: A SURVEY

Modern epidemiological studies involve understanding individual and social level inferences and their role in the transmission and distribution of disease instances. The geographic relevance in epidemiology has been analysed in concurrence with these inferences. The substantial amount of data involved in an epidemiological study is usually very large and intuitively involves missing values and uncertainty. Rough Set Theory (RST) has been used in medical informatics for ‘outcome prediction' and ‘feature selection'. It can be used to construct the decision system involving spatial, medical and demographic data effectively. This chapter proposes the use of rough sets in conjunction with parallel techniques like Fuzzy sets, Intuitionistic systems and Granular (Neighborhood Approximation) computing for the classic problem of data representation, dimensionality reduction, generation and harvest of minimal rules. RST handles missing values and uncertainty more specific to spatial and medical features of data.

Handbook of Research on Computational Intelligence Applications in Bioinformatics Advances in Bioinformatics and Biomedical Engineering

Rough Fuzzy Set Theory and Neighbourhood Approximation Based Modelling for Spatial Epidemiology

Epidemiological studies are carried out to understand the pattern and transmission of disease instances. Some prominent dimensions considered for analysis are cohort studies, ecological studies, transmission modeling and prediction. ‘Descriptive Epidemiology' is defined with respect to ‘people, time and place'. Place (geography) plays a key role in the pattern of disease outcomes in both epidemic outbreaks and chronic cases. A lot of research has documented the significance of spatial features in Epidemiology and have produced health/disease maps of a particular geography. This work proposes to identify similarity between regions in such maps using Rough set based measures. Thus spatial auto-correlation of disease instances in a geographic region can be analysed further to prepare mitigation strategies.