Reference no: EM133048377
Assessment Description
This assignment is a bit different. One of the key expectations from any published article is reproducibility of results, especially in data science. In the last assignment in this course, you are tasked with attempting to reproduce the study described in a peer-reviewed article, published by the National Institute of Health. This tasked is aimed at gradually building your capacity to tackle complex topics, familiarize yourself with academic discourse, and provide context and practice for the skills you will eventually need when working on your capstone thesis or project.
Ensemble-Based Classifier
Familiarize yourself with the ensemble package in Python and its use in a Jupyter notebook by utilizing the "Ensemble Methods for Classification of Physical Activities" to complete this assignment.
Note the additional digital resources in Supplemental Digital Content at the bottom of the article. Also, note that the dataset used in the article is available for download from the UCI repository and the direct link is included in the article in the Methods section, Data set 1.
Another useful resource is "A Comprehensive Guide to Ensemble Learning (with Python codes)."
Once you have reviewed the required resources, complete the following:
Follow the steps described in the article for acquiring the data and building a classifier (in Python) that implements an ensemble framework. It is expected that you will encounter obstacles along the way and not every step mentioned in the article will be straightforward to implement. Ideally, you will be able to reproduce the project in its entirety. Less than ideal, but still very useful, would be to attempt most steps, adapt some, maybe eliminate one or two classification methods from the ensemble, but still produce a working classifier. Given the breadth and depth of the projects you worked on in this course and given the detailed resources provided that cover both theory and implementation, you are expected to successfully complete this project.
In the event that you are able to fully implement the steps described in the article, it would make an excellent opportunity to write a paper informing the scientific community (and the authors) that you are corroborating the results. If you followed the steps to the letter, it would be even more interesting if you obtained a different result. In such case, the scientific community should hear from you.
Create a technical report (no need to rewrite the article), in which you document your work, all steps, including the code and its output. Compare the results to the ones in the article, even if your ensemble framework is not identical to the one described in the article.
APA style is expected, as well as formal and rigorous scientific writing, using appropriate mathematical notation and references.
Attachment:- Assignment Description.rar