Diabetes Prediction Using Data Mining

 

Objective

To predict diabetes in healthcare industry using data mining.

Project Overview

Diabetes is one of the major international health problems. World Health Organization reports says that around 422 million people have diabetes worldwide. Data mining plays a huge role in predicting diabetes in the healthcare industry. There are many algorithms developed for prediction of diabetes. But most of the algorithms failed in case of the accuracy estimation. Also, there is a need to automate the overall process of diabetes prediction. This automation of diabetic database helps in identification of impact of diabetes on various human organs.More the accuracy of prediction, more the chances of accurate severity estimation. Therefore this project concentrated on providing different prediction methods of diabetes.

Proposed System

Dataset

Here PIMA Indian diabetes data set is considered. The data set is taken from UCI machine learning repository. The data set consists of 9 attributes: number of times pregnant, plasma glucose concentration, diastolic blood pressure, triceps skin folds thickness, serum insulin, body mass index, pedigree type, age,and class. Here, the class label is binary classification. It has two values

• Tested positive (1) which means diabetic
• Tested negative (0) which saysnondiabetic

Diabetes Prediction Using Data Mining Methodology

Data pre processing and data mining algorithms are used for the further process in the project. Data pre processing technique data transformation is applied to the data set before applying data mining algorithms. The decision tree and regression models are built. Decision trees and Regression models are used to predict the final binary target variable. After running different types of models, model comparison needed to select the best algorithm. The best algorithm and best model is selected based on the high accuracy rate.

Performance Metrics

The following performance metrics are used to evaluate the performance of various algorithms.

• True positive (TP) – people have the disease,and the prediction also has a positive
• True negative (TN) – people not having the disease and the prediction also has a negative
• False positive (FP) – people not having the disease but the prediction has a positive
• False negative (FN) – people having the disease and the prediction also has a positive
• TP and TN can be used to calculate accuracy rate and the error rates can be computed using FP and FN values.
• True positive rate can be calculated as TP by a total number of people having the disease in reality.
• False positive rate can be calculated as FP by a total number of people not having the disease in reality.
• Precision is the TP/ total number of people having prediction result as yes.
• Accuracy is the total number of correctly classified records.

Diabetes Prediction Using Data Mining Results

Finally,decision tree is built using c4.5 decision tree algorithm. All the results are displayed to the end user using weka data visualization. Regression provides the predicted outcome to end user.

Software Requirements

• Windows OS
• Weka

Hardware Requirements

• Hard Disk – 1 TB or Above
• RAM required – 8 GB or Above
• Processor – Core i3 or Above

Technology Used

• Data Mining
• Data Visualization

 

Abstract Download

An Efficient Hotel Recommendation System

Objective

The objective of this project is to recommend the traveler’s the name of the best hotels based on their preferences, by analyzing the other traveler’s reviews together with the rating value to improve the prediction accuracy.

Project Overview

Nowadays, as the e-commerce industry is growing and becoming complex, everyone uses online websites for getting reviews and giving the reviews on the site in the form of review comments.Comment type varies from best level worst level.So to classify these comments or to predict the best outcome among the posted comments recommendation is needed. Recommend er System considers person’s opinion to identify their content more appropriately and selectively. This system applied to the various domain, but studies say that service-based recommendation system plays a significant role. In this decade, the growth rate of online hotel searching has been increased much faster and makes this online hotel searching a tough task due to the rich amount of online information.Reviews and comments written by the travelers replace the manual work but then to searching becomes the time-consuming task based on user preference.

People come to conclusions every day for some every question. “Which hotel should I see?” “Which item should I eat?”. People have many picks and but little time to explore there requirements. The technology advancement gives the different solutions to this type of problems. Although the availability of massive amount of data can be helpful, it can also make the managerial process more difficult. Users and customers have a lot of options to choose best possible and the most suitable item. It is essential to filter the information and personalize it for the use of each specific user. Recommend er systems used for making personalized suggestions of things to the users based on their requirements and preferences.

Proposed System

The proposed system introduces new hybrid recommendation approach by analyzing the user’s behavior using both textual content and rating data of user’s reviews. Mainly project focuses on building a Recommendation System based on hotel industry domain where traveler reviews will be mined to determine the sentiments of a traveler towards the hotel features which will help to analyze the user’s preference. Increasing the performance of recommendation is essential. So both rating of a hotel characteristics, as well as its sentiment orientation, considered. Also by collecting demographic information of the new user, the context-based hybrid recommendation will help to solve the issue of cold start problem. Rapid Miner is used to implement this recommendation system.

Features

The following list of features considered for recommending hotels to the customers.

• Food and drink
  • Coffee shop, tea, breakfast, lunch, dinner, fruit,varieties, bread.
• Location
  • Location, area, city, street, station, train, distance, bus, airport.
• Service and Infrastructure
  • Reception, Laundry, Dry cleaning,Cash withdrawal, Smoking area,service, front desk,luggage lobby.

 Software Requirements

• Windows OS
• RapidMiner

 Hardware Requirements

• Hard Disk – 1 TB or Above
• RAM required – 8 GB or Above
• Processor – Core i3 or Above

Technology Used

• Recommender System
• Data Mining
• Data Visualization