Register now After registration you will be able to apply for this opportunity online.
This opportunity is not published. No applications will be accepted.
Accelerometer Data Analysis for Health Monitoring
We aim to develop a machine learning model for accelerometer data collected from a user’s smartphone that can identify the user’s behavior and circadian rhythm.
Keywords: Time series analysis, biosignal analysis, data science, medical technologies, and digital health
The purpose of this study is to develop a machine learning algorithm or model that can use accelerometer data from a smartphone to predict and monitor a user’s circadian rhythm and basic activity (sleeping, being sedentary, walking, and driving). The accelerometer data shall be collected using an Android mobile application that is used for digital phenotyping. These algorithms could be of use for health clinical studies to help monitor a user’s behavior and circadian rhythm via a smartphone, without the need for additional wearable sensors.
The purpose of this study is to develop a machine learning algorithm or model that can use accelerometer data from a smartphone to predict and monitor a user’s circadian rhythm and basic activity (sleeping, being sedentary, walking, and driving). The accelerometer data shall be collected using an Android mobile application that is used for digital phenotyping. These algorithms could be of use for health clinical studies to help monitor a user’s behavior and circadian rhythm via a smartphone, without the need for additional wearable sensors.
- Literature review (10%)
- Collect behavioral data via smartphone app (10%)
- Design and implement an optimal filter for motion artifacts (30%)
- Design and implement a multiclass machine learning classifier (30%)
- Test, compare and evaluate results from different noise types (10%)
- Report and present results (10%)
**Your Profile**
- Background in Computer Science, Biostatistics, or related fields
- Prior experience with programming (Matlab or Python)
- Able to work independently, pay attention to detail, and deliver results remotely
- Can visualize data effectively using different charts such as boxplots and scatter plots
- Background in statistics, time series analysis, and machine learning is needed.
- Literature review (10%) - Collect behavioral data via smartphone app (10%) - Design and implement an optimal filter for motion artifacts (30%) - Design and implement a multiclass machine learning classifier (30%) - Test, compare and evaluate results from different noise types (10%) - Report and present results (10%)
**Your Profile**
- Background in Computer Science, Biostatistics, or related fields - Prior experience with programming (Matlab or Python) - Able to work independently, pay attention to detail, and deliver results remotely - Can visualize data effectively using different charts such as boxplots and scatter plots - Background in statistics, time series analysis, and machine learning is needed.
Dr. Moe Elgendi (moe.elgendi@hest.ethz.ch, Biomedical and Mobile Health Technology Research Group, ETH Zurich, http://bmht.hest.ethz.ch) will supervise the student during this project in collaboration with Dr. Rich Fletcher (fletcher@media.mit.edu, Mobile Technology Lab, MIT, http://www.mobiletechnologylab.org).
Dr. Moe Elgendi (moe.elgendi@hest.ethz.ch, Biomedical and Mobile Health Technology Research Group, ETH Zurich, http://bmht.hest.ethz.ch) will supervise the student during this project in collaboration with Dr. Rich Fletcher (fletcher@media.mit.edu, Mobile Technology Lab, MIT, http://www.mobiletechnologylab.org).