Information and technology revolution has brought a radical change in the way data are collected. The data collected is of no use unless some useful information is derived from it. Therefore, it is essential to think of some predictive analysis for analyzing data and to get meaningful information. Much research has been carried out in the direction of predictive data analysis starting from statistical techniques to intelligent computing techniques and further to hybridize computing techniques. The prime objective of this paper is to make a comparative analysis between statistical, rough computing, and hybridized techniques. The comparative analysis is carried out over financial bankruptcy data set of Greek industrial bank ETEVA. It is concluded that rough computing techniques provide better accuracy 88.2% as compared to statistical techniques whereas hybridized computing techniques provides still better accuracy 94.1% as compared to rough computing techniques.

Debi Prasanna Acharjya

Department of Computational Intelligence

School of Computer Science and Engineering

Vellore Campus

Anitha A

Department of Software and Systems Engineering

School of Information Technology and Engineering

Fulltext

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

International Journal of Ambient Computing and Intelligence

Image segmentation is one of the major research domains in several applications including retinal blood vessel segmentation, which is an active research area. Vasculature structure analysis is an interesting and effective method for disease detection and analysis. In this work, a gradient-based blood vessel segmentation technique is proposed to assist retinal image analysis and to extract the retinal vessels. Edge detection is considered one of the major steps in the present work to characterize the boundaries. Itis used to reduce the unusual information and to preserve the necessary structural information. Various filters are constructed to gradient computation and edge detection. In the current work, a new method along with a new filter (kernel) has been proposed to detect edges efficiently. The results are compared with some well-known kernels. The proposed approach achieved Pratt Score 99.1536 value, which outperformed the corresponding values obtained by the other standard edge detectors, namely Sobel, Prewitt, Canny, and Robert's. © 2017 IEEE.

2017 4th IEEE Uttar Pradesh Section International Conference on Electrical, Computer and Electronics, UPCON 2017

Gradient approximation in retinal blood vessel segmentation

Water is one of the most important necessities for human survival. In municipal corporation areas, water quality affects a large part of the population. Good quality water supply is an imperative parameter that influences individuals' health. Automated accurate water quality determination becomes an urgent necessity. Detecting the drinking water quality can prevent such scenarios prior to the critical stage. Recent research works have achieved reasonable success in predicting the water quality by deploying several machine learning-based techniques and utilising different aspects to analyse water quality. The accuracy levels of already proposed models are to be improved, keeping in mind the sensitivity of the problem domain. In the current work, Non-dominated Sorting Genetic Algorithm-II (NN-NSGA-II) was employed to train the artificial neural network (ANN) to improve its performance over its traditional counterparts. The proposed model gradually minimises two different objective functions, namely the root mean square error (RMSE) and Maximum Error (ME) in order to find the optimal weight vector for the ANN. The proposed model was compared with another two well-established models namely ANN trained with Genetic Algorithm (NN-GA) and ANN trained with Particle Swarm Optimisation (NN-PSO) in terms of accuracy, precision, recall, F-Measure, Matthews correlation coefficient (MCC) and Fowlkes-Mallows (FM) index. Furthermore, a data perturbation-based stability analysis is proposed to test the stability of the proposed method. The simulation results established superior accuracy of NN-NSGA-II over the other models. © 2018 World Scientific Publishing Co.

Journal of Information and Knowledge Management

Non-dominated sorting genetic algorithm-II-induced neural-supported prediction of water quality with stability analysis

In Indian economy, agriculture is the prime vocation that avails in the overall development of the country. Tamil Nadu occupies approximately 7% of the nation's population, with 3% of water resources and 4% of land resources at the country level. The crop suitability prediction is of prime importance to enhance the nutritional security to the developing country. Based on several crops grown in a particular place, and the availability of natural resources, one can identify the suitability of crops that can be grown in a particular place. To this end, many mathematical tools were developed, but they failed to include processing of uncertainties present in the accumulated data. Therefore, in this paper an effort has been made to process the uncertainties by hybridizing rough set on fuzzy approximation space and neural network. The rough set on fuzzy approximation space identifies the almost indiscernibility among the natural resources and helps in minimizing the computational procedure on employing data reduction techniques, whereas neural network helps in prediction process. The proposed model is analysed on agriculture data of Vellore District of Tamil Nadu, India, and achieved 93% of classification accuracy in validation. The model is compared with an earlier model and achieved 8% more accuracy while predicting unseen associations. © 2017, The Natural Computing Applications Forum.

Neural Computing and Applications

Crop suitability prediction in Vellore District using rough set on fuzzy approximation space and neural network

The amount of data collected across various sources in real life situations is never in its complete form. That is, it is never precise or it never gives definite knowledge. It always contains uncertainty and vagueness. Therefore, most of our traditional tools for formal modelling, reasoning and computing can not handle efficiently. Therefore, it is very challenging to organize this data in formal system which provides information in more relevant, useful, and structured manner. There are many techniques available for knowledge extraction form this high dimensional data. This chapter discusses various rough computing based knowledge extraction techniques to obtain meaningful knowledge from large amount of data. A real life example is provided to show the viability of the proposed research.

Improving Knowledge Discovery through the Integration of Data Mining Techniques Advances in Data Mining and Database Management

Knowledge Extraction from Information System Using Rough Computing

Currently, internet is the best tool for distributed computing, which involves spreading of data geographically. But, retrieving information from huge data is critical and has no relevance unless it provides certain information. Prediction of missing associations can be viewed as fundamental problems in machine learning where the main objective is to determine decisions for the missing associations. Mathematical models such as naive Bayes structure, human composed network structure, Bayesian network modelling, etc., were developed to this end. But, it has certain limitations and failed to include uncertainties. Therefore, effort has been made to process inconsistencies in the data with the introduction of rough set theory. This paper uses two processes, pre-process and post-process, to predict the decisions for the missing associations in the attribute values. In preprocess, rough set is used to reduce the dimensionality, whereas neural network is used in postprocess to explore the decision for the missing associations. A real-life example is provided to show the viability of the proposed research. © 2015 Inderscience Enterprises Ltd.

Journal	International Journal of Ambient Computing and Intelligence
Publisher	IGI Global
ISSN	1941-6237
Open Access	Yes