Personal tools

Difference between revisions of "Autonomous Smart Watches: Toward an ultra low power microphone detector with events classification"

From iis-projects

Jump to: navigation, search
 
(5 intermediate revisions by 2 users not shown)
Line 1: Line 1:
 
[[File:Smartwatch.jpg|400px|right|thumb]]
 
[[File:Smartwatch.jpg|400px|right|thumb]]
 
==Short Description==
 
==Short Description==
Wearable sensors are most commonly used for monitoring, and detection of events related to the wearer (e.g. abnormalities in physiological functions, detection of seizures and symptoms, patterns of movement, behavior etc.) and/or his surroundings (e.g. determining the context of his actions, location...).
+
Today sensors and wearable technologies are gaining popularity, with people increasingly surrounded by “smart” objects. Machine learning is used with great success in wearable devices and sensors in several real-world applications. In this project we address the challenges of context recognition on low energy and self-sustainable wearable devices.
  
Event sensing implemented by digital signal processing traditionally implies continuous (non-interrupted), periodic signal sampling, storing and processing, at some rate (e.g. sampling frequency) sufficient for the particular application, in order not to miss the event. However,  the rate of occurrence of the event of interest is usually very low (rare). Thus, even by employing aggressive power management strategies, such as cycling to lowest-power modes between successive samples, or shortening processing time by optimizing executed algorithms, much energy is wasted. Energy inefficiency of the approach may compromise wearable sensor's battery autonomy, or the rate at which device is able to harvest the energy from the environment.
+
You will investigate the possibility to implement neural network in a ultra low power energy efficient micro-controller (Ambiq Apollo). The mail goal of the project will be implement and evaluate a complete neural network using already available framework to achieve context recognition. The idea behind this project would be to build a working prototype of a wearable multi-sensor devices which is able to collect and process data directly on board matching the requirements of long life time when supplied by a battery.
 
 
 
 
 
In order to mitigate the problem of the total power spent for event detection, we propose an alternative, two-stage system architecture consisting of: 1. "wake-up sensing" (WUS) circuit, and 2. main microprocessor (MCU or DSP). WUS is an ultra-low power, but always-on circuitry, continuously monitoring the sensor signal. Circuit usually operates in the analog or mixed signal domain, and provides a coarse recognition of some pattern related to occurrence of the monitored event. Upon recognition, it outputs a digital single-bit wake-up signal engaging the second stage implementing the classical signal sampling and digital signal processing for a more thorough detection. This enables for energy-hungry main microprocessor to be completely turned-off until reception of the wake-up signal.
 
 
 
 
 
 
In the course of our previous research, a laboratory-prototype of a WUS circuit was designed, aimed at the detection of audio events in urban environments (e.g. human voice, cry, train horns, police sirens, tram bells, engine noise etc.) MEMS microphone is used as an signal input. Prototype implements analog-domain spectral decomposition using multiple band-pass filtering banks. Frequency, and pass-band width of each bank (channel) are programmable. Output of each channel is fed to the detector integrating the signal energy contained in the particular spectral band over a preprogrammed time-window. Circuit elements are constructed using discrete electronic components (operational amplifiers, comparators, passives etc.). Wake-up signal is generated by  comparing the temporal sequence of outputs of each channel to some pre-set classification template. Sequential template matching state-machine logics is implemented on a low-power MCU.
 
 
 
 
 
 
The idea behind this project would be bringing the laboratory prototype of a WUS circuitry one step closer to the implementation suitable for integration into the existing wearable smart-watch device.
 
 
 
 
  
 
Depending on the applicant's profile and project type, his tasks may involve some of the following:
 
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
+
* Developing the context recognition algorithm with neural network and implement them on the Ambiq Apollo
 
+
* Design and develop a new version of the wearable device which include sensors and the new micrcoprocessor (Ambiq Apollo)
- implementing the template-matching wake-up logics on the low-power microcontroller
+
* 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
 
+
* programming the circuit for specific application, field testing
- implementing and testing of advanced functionality: in-operation tuning of circuit's parameters by digital potentiometers
+
* printed circuit-board design to make it suitable for long term monitoring.  
 
 
- redesign of the signal energy detector subsystem
 
 
 
- programming the circuit for specific application, field testing
 
 
 
- revision of printed circuit-board design to make it suitable for integration in smart watch
 
 
 
- design of template-matching wake-up logics using integrated programmable logics (e.g. PAL, CPLD)
 
 
 
 
 
 
 
 
  
 
===Status: Available ===
 
===Status: Available ===
* Looking for Semester Project Students
+
* Looking for Semester and Master Project Students
 
: Supervisors: [[:User:magnom|Michele Magno]]
 
: Supervisors: [[:User:magnom|Michele Magno]]
 +
: Supervisors: [[:User:Lukasc|Lukas Cavigelli]]
  
 
===Prerequisites===
 
===Prerequisites===
 
+
(''not all need to be met'' by the single candidate)
(not all need to be met by the single candidate)
+
* analog electronics and signal conditioning with operational amplifiers: amplifiers, filters, integrators etc.
: experience using the laboratory instrumentation - signal generators, oscilloscopes, DAQ cards, Matlab etc.
+
* knowledge of micro-controller programming (C)
 
+
* basic knowledge on signal processing is a plus.
: analog electronics and signal conditioning with operational amplifiers: amplifiers, filters, integrators etc.
+
* plus is knowledge on printed circuit board (PCB) using Altium.
 
 
: knowledge of microcontroller programming (C, preferably Texas Instruments MSP430)
 
 
 
: basic knowledge on audio signal processing is a plus.
 
 
 
: basic understanding of fundamental pattern recognition concepts is favorable.
 
 
 
: plus is knowledge on digital systems design with programmable logics (PAL, CPLD, FPGA)
 
  
 
===Character===
 
===Character===
Line 87: Line 54:
  
 
[[Category:Digital]]
 
[[Category:Digital]]
 +
[[Category:Available]]
 +
[[Category:Semester Thesis]]
 
[[Category:Master Thesis]]
 
[[Category:Master Thesis]]
 +
[[Category:System Design]]
 +
 +
<!--
 +
 +
COPY PASTE FROM THE LIST BELOW TO ADD TO CATEGORIES
 +
 +
GROUP
 +
[[Category:Digital]]
 +
[[Category:Analog]]
 +
[[Category:Nano-TCAD]]
 +
[[Category:Nano Electronics]]
 +
 +
STATUS
 +
[[Category:Available]]
 +
[[Category:In progress]]
 +
[[Category:Completed]]
 
[[Category:Hot]]
 
[[Category:Hot]]
[[Category:Available]]
+
 
 +
TYPE OF WORK
 +
[[Category:Semester Thesis]]
 +
[[Category:Master Thesis]]
 +
[[Category:PhD Thesis]]
 +
[[Category:Research]]
 +
 
 +
NAMES OF EU/CTI/NT PROJECTS
 +
[[Category:UltrasoundToGo]]
 +
[[Category:IcySoC]]
 +
[[Category:PSocrates]]
 +
[[Category:UlpSoC]]
 +
[[Category:Qcrypt]]
 +
 
 +
YEAR (IF FINISHED)
 +
[[Category:2010]]
 +
[[Category:2011]]
 +
[[Category:2012]]
 +
[[Category:2013]]
 +
[[Category:2014]]
 +
 
 +
--->

Latest revision as of 11:11, 16 February 2016

Smartwatch.jpg

Short Description

Today sensors and wearable technologies are gaining popularity, with people increasingly surrounded by “smart” objects. Machine learning is used with great success in wearable devices and sensors in several real-world applications. In this project we address the challenges of context recognition on low energy and self-sustainable wearable devices.

You will investigate the possibility to implement neural network in a ultra low power energy efficient micro-controller (Ambiq Apollo). The mail goal of the project will be implement and evaluate a complete neural network using already available framework to achieve context recognition. The idea behind this project would be to build a working prototype of a wearable multi-sensor devices which is able to collect and process data directly on board matching the requirements of long life time when supplied by a battery.

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

  • Developing the context recognition algorithm with neural network and implement them on the Ambiq Apollo
  • Design and develop a new version of the wearable device which include sensors and the new micrcoprocessor (Ambiq Apollo)
  • 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
  • programming the circuit for specific application, field testing
  • printed circuit-board design to make it suitable for long term monitoring.

Status: Available

  • Looking for Semester and Master Project Students
Supervisors: Michele Magno
Supervisors: Lukas Cavigelli

Prerequisites

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

  • analog electronics and signal conditioning with operational amplifiers: amplifiers, filters, integrators etc.
  • knowledge of micro-controller programming (C)
  • basic knowledge on signal processing is a plus.
  • plus is knowledge on printed circuit board (PCB) using Altium.

Character

30% Theory
50% Implementation
20% Testing

Professor

Luca Benini

↑ top

Detailed Task Description

Goals

Practical Details

Results