Data Mining and Knowledge Engineering

A. Nithya ¹, V. Sundaram ²

Affiliations
1 Nehru Arts and Science College, Coimbatore, Tamil Nadu, IN
2 MCA Department, Karpagam College of Engineering, Coimbatore, Tamil Nadu, IN

Abstract

Rice disease identification is one of the main issue of the country. The essence of the paper is identifying the rice disease in initial stage. This paper going to be create ready reckoned of the farmers. The main advantage of the paper is easily identifying the disease and gives the better solution for the farmers. It is the process which includes defining and redefining problems, formulating hypothesis, collecting, organizing and evaluating data; making deductions and reaching conclusions and at last presenting it in a detailed, accurate manner. This paper mainly focuses on concepts of data mining such as Classification, Decision Trees, and Neural Networks. A disease is an abnormal condition that injures the plant or causes it to function improperly. Diseases are readily recognized by their symptoms-associated visible changes in the plant. The organisms that cause diseases are known as pathogens. Many species of bacteria, fungus, nematode, virus and mycoplasma-like organisms cause diseases in rice. Disorders or abnormalities may also cause by abiotic factors such as low or high temperature beyond the limits for normal growth of rice, deficiency or excess of nutrients in the soil and water, pH and other soil conditions which affect the availability and uptake of nutrients, toxic substances such as H2S produced in soil, water stress and reduced light. However, here we will cover only the common diseases of rice those cause by pathogen.

Keywords

Decision Trees, Classification, Data Mining, Neural Network.

Full Text

     

G. Purusothaman ¹, A. Nithya ²

Affiliations
1 Rathnavel Subramaniam College of Arts and Science, Sulur, Coimbatore - 402, Tamil Nadu, IN
2 Department of CS, Rathnavel Subramaniam College of Arts and Science, Sulur, Coimbatore - 402, Tamil Nadu, IN

Abstract

Heart disease is the frequently found disease in various peoples which would cause more serious and dangerous effects. Various studies have been projected earlier whose major aim is to predict the heart disease more accurately. In our previous research method Fuzzy Rough Set Theory combined with Support Vector Machine (FRS - SVM) is introduced which can ensures the optimal prediction rate by selecting the risk factors accurately which can lead to improved accuracy rate. However FRS-SVM might lack in its performance in case of presence of more missing values in the database. This research method cannot support the large dimensional dataset which needs to be focused well enough for accurate prediction rate. This problem is resolved in this investigation by introducing the framework namely Heart disease prediction using Alpha Rough Set Theory combined with Fuzzy SVM (ARST-FSVM). In this research method, Modified K-Means clustering algorithm is utilized for preprocessing the input dataset which would avoid the noisy data present in the database. Then missing data value in the database is handled using normalization technique where NLLS imputation is applied. And then feature dimensionality reduction is done using Alpha rough set theory (α-RST) approach. From those reduced feature set, optimal feature selection in terms of relevancy is done using Hybrid Bee colony algorithm with Glowworm Swarm Optimization (HBC-GSO) approach. Finally heart disease prediction is done using classifier namely fuzzy based SVM. The overall research method ensures that the proposed research technique leads to ensure it can direct to most favorable and accurate heart disease diagnosis outcome.

Keywords

Large Data Set, Heart Disease Prediction, Missing Values, Accurate Observation, Feature Reduction.

Full Text