Abstract— health issues. But as almost everyone in recent

Abstract— There has been a tremendousgrowth in medical industry over theyears, due to the advancement in technology and an increase in health problemshave been observed.

Due to the hectic and busy schedules of people has led toincreased health issues. But as almost everyone in recent times carries theirsmartphones a healthcare android application can prove very beneficial. Theintention behind this project is to create an android application which can beused by people for managing their health.

Best services for writing your paper according to Trustpilot

Premium Partner
From $18.00 per page
4,8 / 5
4,80
Writers Experience
4,80
Delivery
4,90
Support
4,70
Price
Recommended Service
From $13.90 per page
4,6 / 5
4,70
Writers Experience
4,70
Delivery
4,60
Support
4,60
Price
From $20.00 per page
4,5 / 5
4,80
Writers Experience
4,50
Delivery
4,40
Support
4,10
Price
* All Partners were chosen among 50+ writing services by our Customer Satisfaction Team

This system will use decision treesalgorithm for prediction of diabetes. The user will have to answer aquestionnaire which will consist of various parameters regarding the user’shealth. This application will consist of features such as Order medicines, Bookdoctor’s appointment, medication and diet reminders. Decision trees uses treestructure to build the classification models.

It divides a dataset into smallersubsets. Leaf node represents a decision. Based on feature values of instances,the decision trees classify the instances. Each node represents a feature in aninstance in a decision tree which is to be classified, and each branchrepresents a value.

Classification of Instances starts from the root node andsorted based on their feature values. Categorical and numerical data can behandled by decision tress. Key word — data mining techniques, decision tree, C5 classifier, data sets I.INTRODUCTION Data mining is the method of examining huge pre-existingdatabases for generation of new information.

Diagnosing and Predicting anindividual’s health is an important goal of this project. It can be achieved byusing advanced machine learning algorithms of decision tree. An Androidapplication is one of the most easy method for a person for health managementdue to the increased use of smartphones. The application will consist of a setof questions which the user will have to answer. This will then use Decisiontrees which is a data mining algorithm. This will then immediately predict thepossibility if diabetes. Besides this the app will also consist of featureslike diet monitoring where a user can monitor his/her diet and the app willsend notifications or reminders about the same. Other features will be theprovision the book a doctor’s appointment.

The app will also allow the user theorder medicines. Different factors like gender, age, blood sugar level,cholesterol, hereditary disease and many other factors are taken into consideration in this proposed system.Thus to find out whether the user is prone to diabetes or not. The main objective is predict the occurance ofdiabetes and monitor an person’s health based on the answers provided by theuser of the questionnaire.

Other features also include diet monitoring, bookingdoctor’s appointment and ordering medicines. There are many predictionsalgorithms used but because of the parameter consideration or algorithminefficiency the accuracy is not so high. Hence, we are considering manyparameters and also using C5 Classifier algorithm which gives a high accuracy.

 The rest of the into 6 sections.In section 2 and 3, related work and proposed work is presented paper isstructured. In section 4, the proposed methodology is presented and detailsregarding the algorithm to be used is explained. In section 5, the conclusionand finally in section 6 future work has been included. II. RELATED WORK Health Monitoring Android Application and DiabetesPrediction using Data Mining Techniques 1, in this paper the authors haveproposed a project which seeks to apply information and to create an androidapplication which can be used by patients for management of their health careproblems and would thus enable them to have a good life. The applications also createsa system for predicting whether a person has a risk of developing the diseasediabetes in the next 10 to 15 years.

The system uses questionnaire method usingNaïve Bayes algorithm A Data Mining Approach for Prediction of Heart DiseaseUsing Neural Networks 2, the authors have proposed a Heart Disease Predictionsystem (HDPS) is developed using Neural network. The HDPS system predicts thelikelihood of patient getting a Heart disease. For prediction, the system usesblood pressure, gender, cholesterol like 14 medical parameters. Here two moreparameters are added i.e. smoking and obesity for higher accuracy. From theresults, it has been seen that neural network predicts heart disease withnearly 100% accuracy. Disease Predicting System Using Data Mining Techniques3 proposed a research paper which uses data mining for better diseaseprediction.

It uses Medical data mining techniques like classification,association rule mining, clustering is implemented to evaluate the differentkinds of heart related problems. Survey of Machine Learning Algorithms forDisease Diagnostic 4 provides us the comparative evaluation of differentmachine learning algorithms for diagnosis of different diseases such asdiabetes, heart disease, liver disease, dengue disease and hepatitis diseaseusing medical imaging. It brings attention towards the suite of machinelearning algorithms and tools that are used for the analysis of diseases anddecision-making process accordingly. C5.

0 Algorithm to Improved Decision TreewithFeature Selection and Reduced Error Pruning 5 compared ID3, C4.5 and C5.0with each other. Among all these classifiers C5.

0 gives more accurate andefficient result. This research paper used C5.0 as the base classifier soproposed system will classify the result set with high accuracy and low memoryusage.

Feature selection technique assumes that the data contains manyredundant features, so it removes those features which provides no usefulinformation in any context. This paper also uses Reduced Error PruningTechnique which is used to solve the over fitting problem of the decision tree.