International Research Journal of Engineering and Technology (IRJET) Volume: 09 Issue: 07 | July 2022
www.irjet.net
e-ISSN: 2395-0056 p-ISSN: 2395-0072
Smart Health Guide App Alison Almeida1, Tanisha Sangodkar2, Sahil Naik3, Yash Sangodkar4, Shreedatta Sawant5, Diksha Prabhu Khorjuvenkar6 1,2,3,4Department
of Computer Engineering Agnel Institute of Technology and Design, Assagao, Goa, India Professor, Department of Computer Engineering Agnel Institute of Technology and Design, Assagao, Goa, India ---------------------------------------------------------------------***--------------------------------------------------------------------particular system. When information is handled within the Abstract - Health is a very important concern in today’s 5,6Assistant
system, each piece of information has a specific value and can be used to reach conclusions. Therefore, if it is easier to draw a valid conclusion from information, then the entropy will be lower in Machine Learning, or if the entropy is higher, then it will be hard to draw a conclusion from that information.
generation and the first step is following the right diet. Many people suffer from many diseases due to improper consumption of food. The root cause of this can be the lack of knowledge regarding the nutrients available in the food product. Some of the common diseases that the majority of the people suffer from are diabetes, cholesterol and jaundice. These diseases are caused when certain nutrients in a food product are consumed in excess. We have taken these three in consideration and created an application that will help the people to know the contents present in the food item and guide them if they should be consumed by them or not with respect to their health condition. An application that will allow the user to provide the disease he is suffering, allowing him to scan the food products barcode and guiding him if that food product is suitable for consumption according to his health condition.
2. LITERATURE SURVEY 2.1 Decision Tree Algorithms Process of extracting useful knowledge from a huge set of incomplete, noisy, fuzzy and random data is called data mining. Decision tree classification technique is one of the most popular data mining techniques. In decision tree divide and conquer technique is used as a basic learning strategy. A decision tree is a structure that includes a root node, branches, and leaf nodes. Each internal node denotes a test on an attribute, each branch denotes the outcome of a test, and each leaf node holds a class label. The topmost node in the tree is the root node. This paper focuses on the various algorithms of Decision trees (ID3, C4.5, CART), their characteristics, challenges, advantages and disadvantages.[1]
Key Words: Data Mining, Decision Tree, Entropy 1. INTRODUCTION The process of finding anomalies, trends and correlations in massive data sets using techniques of machine learning, statistics and database systems to anticipate outcomes is known as data mining.
2.2 Analysis of Decision Tree Algorithms
A root node, branches, and leaf nodes make up the structure of a decision tree. It is a supervised learning algorithm that can work on both discrete and continuous variables. It follows a top-down approach as the top region presents all the observations at a single place which splits into two or more branches that further split. A test on an attribute is shown by each internal node, the result of a test is indicated by each branch, and a class label is contained in each leaf node. The highest impure node within the tree is the root node. It splits the dataset into subsets on the basis of the most significant attribute in the dataset. How the decision tree identifies this attribute and how this splitting is done is decided by the algorithms.
In Data mining there are various techniques available to mine large amounts of data. The data mining techniques are Classification, Association rule mining, cluster analysis, outlier analysis. In this data mining techniques classification technique is the most powerful technique to classify our large amount of data. In this classification, the Decision trees are the most prominent classification technique in data mining. Decision tree induction is the learning of decision trees from class labeled training tuples. A decision tree is a flow chart like tree structure. Decision trees have been used to solve a wide variety of implications in the data mining process. This is used in statistics, machine learning. Data mining is also a predictive model. Decision trees are classified by using the two phases, first phase is tree building phase and the second phase is tree pruning phase. From this paper we
Entropy is defined as the randomness or measuring the disorder of the information being processed in Machine Learning. In other words, it measures the impurity in that
© 2022, IRJET
|
Impact Factor value: 7.529
|
ISO 9001:2008 Certified Journal
|
Page 2461