Showing posts with label data analytics. Show all posts
Showing posts with label data analytics. Show all posts

Predictive Analytics using Machine Learning Algorithm

Predictive Analytics using Machine Learning Algorithm


Use case - Stroke Prediction


Problem:-

  • Stroke a major cause of death and serious long-term disability. A stroke can affect a person at any age, and it usually occurs suddenly. But, strokes can be prevented through therapeutic manipulation, and the modifiable risk factors are crucial. Today there is much collected data regarding cases of various diseases in medical science and it can be utilized to predict chances of stroke in a patient early.


Benefits:- 

  • The insurance company and Hospital get major benefit of ML based stroke prediction.
  • The ML based stroke prediction could help  hospital/health care system to predict strokes with high accuracy. For example, the development of simulated blood vessels provides us a different way of thinking about the causes of diseases. That is, the predicted result can help doctors to objectively diagnose, and doctors can provide a personalized warning and a lifestyle correction message
  • Doctors can provide the appropriate treatment to patients early



Sample Dataset  - Metadata:-


iris dataset, dataset, madical dataset
sample data



ML –Stroke Prediction -Process:-


stroke prediction

Cloud Deployment:-

aws, cloud deployment, model deployment, ml model deployment

Result Verification – Original Stroke vs Predicted Stroke:-

predicted result, ml result, ml prediction


Key Learnings:-  

After doing above we will learn following:-
  1. Python - Basics(syntax and usage)
  2. Python –Libraries(Pandas, Numpy, Matplotlib, Bokeh)
  3. Machine Learning – Understanding of supervised and unsupervised learning , different types of algorithms available.
  4. Logistic Regression Algorithm application.
  5. Random Forest Algorithm application.
  6. GIT.
  7. Hosting Python application on Amazon cloud (EC2).
Read More

Predictive Analytics using machine learning

Predictive Analytics using Machine Learning Algorithm


Use case - Hard Drive Failure Prediction


Problem:-

  • A hard drive failure occurs when a hard disk drive malfunctions and the stored information cannot be accessed with a properly configured computer.
  • A hard disk failure may occur in the course of normal operation, or due to an external factor such as exposure to fire or water or high magnetic fields, or suffering a sharp impact or environmental contamination, which can lead to a head crash.
  • Today there is much collected data regarding cases of various reason for hard drive failure and it can be utilized to predict chances of hard drive failure early.


Benefits:- 

  • The hard drive manufacturing company and user get major benefit of ML based hard drive failure prediction.
  • The ML based hard drive failure prediction could help  manufacturing company  to predict failure with high accuracy That is, the predicted result can help manufacturing company to objectively diagnose, and company can provide a personalized warning and a lifestyle correction message.
  • Hard drive manufacturing company  can provide the appropriate treatment to hard drive early.


S.M.A.R.T:-


   Predicting hard drive failure based on S.M.A.R.T. statistics reported by each drive. S.M.A.R.T. (Self-Monitoring, Analysis and Reporting Technology; 

      often written as SMART) is a monitoring system included in hard disk drives (HDDs), solid-state drives (SSDs),[1] and eMMC drives.

      Its primary function is to detect and report various indicators of drive reliability with the intent of anticipating imminent hardware failures.


Sample Dataset  - Metadata:-


ml dataset

ML –Hard Drive Failure Prediction -Process:-

predictive analytics example

Cloud Deployment:-

code management deployment

Result Verification – Original HDD Failure vs Predicted HDD Failure:-

prediction example

Read More

Visitor