Personal tools

Edge Computing for Long-Term Wearable Biomedical Systems

From iis-projects

Revision as of 15:49, 22 June 2020 by Xiaywang (talk | contribs) (Status: Available)
Jump to: navigation, search
MindMaze.jpg

Short Description

Today sensors and wearable technologies are gaining popularity, with people increasingly surrounded by “smart” objects, from phones to clothing, from glasses to watches, from home automation to healthcare. Smart, connected products are made possible by vast improvements in processing power and device miniaturization and by the availability of ubiquitous wireless connectivity. The recent trend is towards billions of connected devices. This vision will create formidable research challenges and industrial opportunities. In particular, billions of sensor-rich connected devices are going to produce a mind-boggling quantity of data and potentially useful information. However, the data by themselves do not provide value unless we can turn them into actionable, contextualized information. Big data and data visualization techniques allow us to gain new insights by batch-processing and off-line analysis. Real-time sensor data analysis and decision-making are often done manually, but to make it scalable, it should preferably be automated.

This project aims to push beyond the current power walls for machine learning and signal to process and move toward milli-watt (or even micro-watt) continuously active, long-term wearable biomedical systems. This requires working on algorithms, architecture, circuits as well as designing methods for these new promising embedded and wearable devices with artificial intelligence capability under extreme constraints: tiny energy buffers (batteries), miniature energy harvesters providing tiny amounts of energy, low power sensors, and interfaces. Specifically, the project aims to study and develop the basis for a new generation of smart devices operating within a power envelope of a few mW. The objective of the project is to develop a prototype board with a patch form factor (4x4cm or smaller) which will integrate an existing PULP prototype chip (Mr. Wolf or GAP8), an analog frontend, an off-the-shelf low-power (BT5.0) transceiver, power supply and ultra-thin battery. The designed dveice will be initially targeting two application scenarios: behind-the-ear EEG and ECG wristband. The system will also be used to explore applications scenarios for augmenting current MindMaze product lines, such as MASK and GaitUp (Physiolog Platform). New sensors will also be explored (e.g. low power radar) to complement the information obtained by electro-physiology signals.


The project will be done in collaboration with the company Mindmaze (https://www.mindmaze.com/) based in Lausanne and Zurich.


Depending on the applicant's profile and project type, his tasks may involve some of the following:

  • lab. testing/characterization of sensors, radio, and embedded systems: verification of the prototype's characteristics w.r. design specification (simulations), measuring power-consumption, and assessing detection performance in lab. conditions
  • High-level software programming, signal processing, machine learning, wireless communication
  • programming the circuit for a specific application, field testing, data acquisition
  • Machine Learning for microcontrollers.
  • PCB design to build a working prototype which includes all the subsystems


Status: Available

  • Looking for Semester and Master Project Students
Supervisors: Michele Magno Xiaying Wang

Prerequisites

(not all need to be met by the single candidate)

  • Experience using the laboratory instrumentation - signal generators, oscilloscopes, DAQ cards, Matlab etc..
  • knowledge of microcontroller programming and PC programming (C/C++, preferably microcontroller with Bluetooth Low Energy but it is not mandatory)
  • basic knowledge or interests on signal processing, wireless communication for localization and machine learning is a plus
  • plus is also knowledge on printed circuit board (PCB) using Altium.


Character

35% Theory
45% Implementation
20% Testing

IIS Professor

Luca Benini

↑ top

Detailed Task Description

Goals

Practical Details

Results