Personal tools

Difference between revisions of "SmartRing"

From iis-projects

Jump to: navigation, search
Line 7: Line 7:
 
* An accelerometer for motion tracking
 
* An accelerometer for motion tracking
 
Now we would like to upgrade the system by adding advanced machine learning capabilities for sensor fusion and replace the harvester with a more efficient chip.
 
Now we would like to upgrade the system by adding advanced machine learning capabilities for sensor fusion and replace the harvester with a more efficient chip.
Wearable devices, such as smartwatches and activity trackers, are strongly limited by the available energy in their batteries. Charging devices is cumbersome and can be avoided by adding energy-harvesting capabilities to autonomously supply the device with power. CSEM developed a state-of-the-art energy-harvesting chip that efficiently extracts power from the connected solar cells. This includes intelligent adaption to changing lighting conditions, variable light distributions over the set of cells and adaptive dynamic voltage and frequency scaling (ADVFS) within the chip.
+
 
 +
----
 +
We are searching for motivated students in any of the following domains:
 +
* '''Energy harvesting: Get an insight into state-of-the-art energy harvesting chips!'''
 +
Study the mechanisms of CSEM's state-of-the-art energy-harvesting chip (developed in-house) and develop an efficient control algorithm (running on the chip's controller) to extract as much power as possible from a set of attached solar cells. This includes intelligent adaption to changing lighting conditions, variable light distributions over the set of cells and adaptive dynamic voltage and frequency scaling (ADVFS) within the chip. In the end, upgrade the system with your energy harvesting solution. 
 +
* '''Machine learning: Make the device smarter by adding machine learning (ML) capabilities!'''
 +
Acquire data, learn from them and implement a system that is more robust and more intelligent. This can include taking motion-data from the accelerometer into account to compensate for motion-artefacts in the pulse monitoring, improve the algorithm by using ML systems (e.g. neural networks)
 +
 
 
{| style="text-align:left"
 
{| style="text-align:left"
 
|-
 
|-

Revision as of 11:40, 14 January 2019

Project Description

Build the next generation of wearbles during this project! In 2016 we built a self-powering ring oximeter that measures the heart rate and the oxygen saturation in the blood using a NIRS sensor, integrated in a wearable ring. It worked pretty well: detected holding the breath, output the current pulse rate and the oxygenation via Bluetooth onto an Android app and managed to recharge the battery. Basic features:

  • Bluetooth communications with a smartphone for data extraction
  • A solar panel connected to a COTS energy harvester chip to run the device without charging the battery
  • A low power microcontroller to compute the (pulse/oxygenation) algorithm on-board the device
  • An accelerometer for motion tracking

Now we would like to upgrade the system by adding advanced machine learning capabilities for sensor fusion and replace the harvester with a more efficient chip.


We are searching for motivated students in any of the following domains:

  • Energy harvesting: Get an insight into state-of-the-art energy harvesting chips!

Study the mechanisms of CSEM's state-of-the-art energy-harvesting chip (developed in-house) and develop an efficient control algorithm (running on the chip's controller) to extract as much power as possible from a set of attached solar cells. This includes intelligent adaption to changing lighting conditions, variable light distributions over the set of cells and adaptive dynamic voltage and frequency scaling (ADVFS) within the chip. In the end, upgrade the system with your energy harvesting solution.

  • Machine learning: Make the device smarter by adding machine learning (ML) capabilities!

Acquire data, learn from them and implement a system that is more robust and more intelligent. This can include taking motion-data from the accelerometer into account to compensate for motion-artefacts in the pulse monitoring, improve the algorithm by using ML systems (e.g. neural networks)

Ring components.png
Ring finger.png


Prerequisites

  • Some experience in programming microcontrollers and developing PCBs
  • Motivation to build a real systems

Detailed Description

TBD. A detailed task description will be worked out right before the project, taking the student's interests and capabilities into account.

Flyer

Status: Available

  • Looking for master/semester project students.

Organizational

↑ top