Coronary Illness Prediction Using Machine Learning

dc.contributor.authorFairooz, Atia
dc.date.accessioned2021-04-22T04:47:45Z
dc.date.available2021-04-22T04:47:45Z
dc.date.issued2021-01-15
dc.description.abstractAfter the advancement of the automated structure, AI expects to be a basic part here. A machine exhibit just likes a person. The system responds subsequently subject to learning. Accurate learning gives the accurate result otherwise its produce mixed prediction. Thusly, this learning is most important part for automated system. AI is mainly prediction based. Machine can envision result without assistance from any other person depend upon the given dataset. To a great extent that foreseen result is more exact, occasionally not. The genuine conjecture is liable to learning precision. In this manner, AI is parceled into two systems dependent on learning, for instance, supervised learning and unsupervised learning. Guided strategies are dependent upon labeled data. Moreover, unstructured dataset is used in unsupervised learning, where model data is given at this point does not yield. In this work we tried to predict coronary diseases with supervised learning. For that we collected a dataset from web. A huge proportion of people kicks the pail purposes behind vascular infection at an early age. Early detection of this diseases may help the patient overcoming from the disease. This may be a way of preventing this disease. The AI technique is simply usable procedures thus.
dc.identifier.otherhttp://dspace.daffodilvarsity.edu.bd:8080/handle/123456789/5617
dc.identifier.urihttp://dspace.daffodilvarsity.edu.bd:8080/handle/123456789/5617
dc.language.isoen_US
dc.publisherDaffodil International University
dc.sourceDIU Institutional Repository
dc.subjectDisease Susceptibility
dc.subjectMachine Learning
dc.titleCoronary Illness Prediction Using Machine Learning
dc.typeOther

Files

Original bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
153-25-493 (16_).pdf.txt
Size:
75.9 KB
Format:
Adobe Portable Document Format

Collections