Smart Wearable System For Vital Sign Monitoring Exploiting On Board and Cloud Machine Learning
Wearable technology is gaining popularity, with people wearing everything “smart” from clothing to glasses and watches. In this project, the students can deal with design, hardware and software implementation and in-field evaluation of a novel sensor-rich smart wearable device with wireless interface and eventually powered by energy harvesting. The specific goal of the device is to monitor the human body vital sign to achieve an intelligent system that process the data from one or more sensors to extract meanings from the raw data. The process of the data can be done at different levels (i.e. preliminary on the wearable device) or in an external mobile device(smartphone/PC) or in a remote host (Cloud). The first important target will be the collection of data from the wearable device and the the processing in a remote host, exploiting for example google Cloud or similar. On the wearable device side, both hardware and firmware will be designed with low power in mind and with the capability to be supplied for several days from a battery or even forever with energy harvesting (i.e solar panels or kinetic energy harvesting). There are many open project in this area in differ hardware and software, or combination of both domain. The final goal of the project is to design a new generation of wearable devices to using machine learning algorithms in an energy-efficient way exploiting the internet capabilities. The candidate will work with micro-controllers, sensors, wireless communication at firmware level as well as data analysis tools and training tools on the PC/cloud. The hardware and software load of the thesis will be balanced according with the skills and preferences of the candidate students when the details task description will be provided before the student project will start. In field, measurements of the system will be performed from the students as important activity in order to evaluate power consumption, reliability, functionality, classification accuracy and energy efficiency and to further optimize the system.
Depending on the applicant's profile and project type, his tasks may involve some of the following:
- lab. testing/characterization of the existing prototype: verification of the prototype's characteristics w.r. design specification (simulations), measuring power-consumption, and assessing detection performance in lab. Conditions
- Highlevel software programming, machine learning, wireless communication
- programming the circuit for specific application, field testing, data acquisition
- Looking for Semester and Master Project Students
- Supervisors: Michele Magno
(not all need to be met by the single candidate)
- experience using the laboratory instrumentation - signal generators, oscilloscopes, DAQ cards, Matlab etc.
- analog electronics and signal conditioning with operational amplifiers: amplifiers, filters, integrators etc.
- knowledge of microcontroller programming and PC programming (C/C++, preferably microcontroller with Bluetooth Low Energy but it is not mandatory)
- basic knowledge on signal processing is a plus.
- plus is knowledge on printed circuit board (PCB) using Altium.
- 30% Theory
- 50% Implementation
- 20% Testing