Informatics Publishing Limited

I. Carol ¹, S. Britto Ramesh Kumar ¹

Affiliations
1 Department of Computer Science, St Joseph's College, Tiruchirappalli, IN

Abstract

Diabetes mellitus (DM) is a set of related diseases in which the body cannot regulate the amount of sugar in the blood sugar, either because the body does not produce enough insulin, or because the cells do not respond to the insulin that is produced. MSX is characterized by chronic hyperglycemia associated with disturbances of carbohydrate, fat, and protein metabolism due to absolute or relative deficiency in insulin secretion and/or action. It is also known as Metabolic Cum Vascular disorder. It causes long term damage, dysfunction and failure of various organs such as eyes, kidneys, nerves, heart and blood vessels. The Metabolic Syndrome x mainly affects the adult. A new methodology is used to find the stages of metabolic syndrome x using Multilayer perceptron (MLP) and EM Clustering. The symptoms and stages of Metabolic syndrome x are classified by using predictive modeling.In Multilayer perceptron technique, data objects are categorized based on the stages of metabolic syndrome x and find out their efficiency and accuracy.  It categorizes the data such as IDDM, NIDDM. It helps us to know the various stages of metabolic syndrome x and to predict the recommend preclusion to patients those who are affected by metabolic syndrome x and provide suggestions to that patient.

Keywords

Multilayer Perceptron (MLP), Metabolic Syndrome X (MSX)‚ Data Mining Techniques‚ Diabetes Mellitus (DM).

Full Text

     

I. Carol ¹, S. Britto Ramesh Kumar ¹

Affiliations
1 Department of Computer Science, St. Joseph’s College, Trichy - 620002, Tamil Nadu, IN

Abstract

Background/Objective: Creating queries for a single search term and identifying the viable solutions for the query are the two specific problems in retrieving the data. To resolve this issue, an effective information fusion technology should be provided to obtain effective results. This paper presents a method for resolving conflicts and eliminating duplicates with increased accuracy. Methods/Statistical Analysis: Universal wrappers are designed to retrieve the actual information from the heterogeneous data sources. The process of getting input itself is modified such that the retrieved results are relevant to the context. Ranking and duplicate eliminations are done accordingly to refine the obtained results to the user. Findings: Experimental results show that the improved accuracies of the data being fetched and with reduced conflicts and duplicates. This work uses major data sources from Google, New York Times and other offline data sources. By applying the proposed data retrieval techniques, the produced data is consistent by the help of wrappers. The proposed approach improves the data consistency which is relatively better than the existing technique. Finally, this proposed research work concludes that it is used to identify and resolve the conflict data and delivers the consistent data to the users in a ranked manner. Applications/Improvements: To create a unified repository which can be used for knowledge mining and warehouse based analysis of existing data and retrieve the result.

Keywords

Conflict Identification, Conflict Resolution, Data Retrieval, Ranking, Wrappers

Full Text