Sensor Data Analytics and Machine Learning for Health Research: a review

Authors: Eun-Kyeong Kim*, University of Zurich
Topics: Spatial Analysis & Modeling, Medical and Health Geography, Behavioral Geography
Keywords: machine learning, sensor data analytics, health
Session Type: Paper
Day: 4/3/2019
Start / End Time: 9:55 AM / 11:35 AM
Room: Wilson A, Marriott, Mezzanine Level
Presentation File: No File Uploaded


Sensor Data Analytics is becoming pervasive in both our daily life and research thanks to advances in sensing technologies. Machine Learning (ML) is widely used since data is growing and more available than ever before; also data obtained from sensors is often analyzed with ML approaches. Computing power to train machines is also improving. ML is broadly applicable to a variety of problems but recently it has been actively applied to health domain. It is known that ML methods often outperform traditional statistical models in prediction, but there are important issues in applying ML techniques to health domain including the interpretability and generalization of models. In the talk, I will summarize the papers presented in this sessions as well as recent trends in health geography using ML and sensor data analytics, and then discuss about challenges and opportunities in adopting machine learning and sensor data analytics for health research in geography.

Abstract Information

This abstract is already part of a session. View the session here.

To access contact information login