PyMedServer : a server framework for mobile data collection and machine learning
Author(s)
Mofor Nkaze, John.
Download1138946998-MIT.pdf (5.147Mb)
Alternative title
Server framework for mobile data collection and machine learning
Other Contributors
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.
Advisor
Richard R. Fletcher.
Terms of use
Metadata
Show full item recordAbstract
Over the past decade, the widespread adoption of smart phones has enabled their use as a primary data collection platform for a wide variety of research studies, including areas such as global health field research. In addition, smart phones also provide a portable means of collecting labelled data for use in Machine Learning and Artificial Intelligence. Despite these important global trends, existing scalable mobile data collection platforms are not available for use with machine learning data collection. In order to address this need, I have created PyMedServer, which is an easy-to-use server framework designed for large scale medical research spanning multiple distinct institutions. The framework provides built-in abstractions for clinicians, patients, medical measurements, clinician diagnoses, and machine learning analyses. To further facilitate adoption, PyMedServer provides client libraries for Android and Web. These libraries are compatible with any server built using the PyMedServer framework and provide features such as Local Storage, API integration, User Authentication and Authorization, Multi-Group Support and Measurement Labelling, to name a few. PyMedServer is written in Python and is designed to permit and facilitate the addition of plugins. Developers are granted access to labeled data and can contribute with Feature Extraction and Machine Learning plugins, while the framework takes care of concerns such as of Group Isolation, Security, Scalability, and Deployability.
Description
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2019 Cataloged from PDF version of thesis. Includes bibliographical references (pages 84-87).
Date issued
2019Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer SciencePublisher
Massachusetts Institute of Technology
Keywords
Electrical Engineering and Computer Science.