CS229 Project: A Machine Learning Approach to Stroke Risk Prediction
نویسندگان
چکیده
In this paper, we consider the prediction of stroke using the Cardiovascular Health Study (CHS) dataset. Missing data imputation, feature selection and feature aggregation were conducted before training and making prediction with the dataset. Then we used a mixture of support vector machine (SVM) and stratified Cox proportional hazards model to predict the occurrence of stroke. Different methods and variations of models were evaluated and compared to find the best algorithm.
منابع مشابه
Cs229 Project: Tls, Using Learning to Speculate
We apply machine learning to thread level speculation, a future hardware framework for parallelizing sequential programs. By using machine learning to determine the parallel regions, the overall performance is nearly as good as the best heuristics for each application.
متن کاملUnstructured Document Recognition on Business Invoice CS229: Machine Learning
This project describes a bag-of-words approach for business invoice recognition. Bags of potential features are generated to capture layout and textual properties for each field of interest, and weighted to reveal key factors that identify a field. Feature selection, threshold tuning, and model comparison are evaluated. Overall, we achieved 8.81% for training error and 13.99% for testing error.
متن کاملCS229: Grant Prediction with Network Features
This project investigates supervised learning to predict grant proposal approval or rejection, using the Mimir project’s data on external grants applied for by Stanford faculty. Baseline features relating to the grant itself and faculty features are used, in particular the novel use of a faculty member’s network to extract features is investigated and its effects on grant prediction.
متن کاملTransparent Machine Learning Algorithm Offers Useful Prediction Method for Natural Gas Density
Machine-learning algorithms aid predictions for complex systems with multiple influencing variables. However, many neural-network related algorithms behave as black boxes in terms of revealing how the prediction of each data record is performed. This drawback limits their ability to provide detailed insights concerning the workings of the underlying system, or to relate predictions to specific ...
متن کاملStock Price Prediction using Machine Learning and Swarm Intelligence
Background and Objectives: Stock price prediction has become one of the interesting and also challenging topics for researchers in the past few years. Due to the non-linear nature of the time-series data of the stock prices, mathematical modeling approaches usually fail to yield acceptable results. Therefore, machine learning methods can be a promising solution to this problem. Methods: In this...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2009