SINS - Sound INterfacing through the Swarm
From 01-10-2013 to 30-09-2017
Description
The SINS objectives can hence be clustered in performance, lifetime and showcase objectives:
1. Performance Objective: To increase the accuracy of sound source separation and sound localization (down to 0.25m) through collaborative, distributed measurements, exploiting the opportunities provided by the large number of microphones in the swarm.
2. Lifetime Objective: To increase lifetime of sound swarm sensors with a factor of 10, through the introduction of energy-proportionality at network level (consuming <1nJ/bit) and at node level(10μW average sensing power). Energy-proportional hardware and communication solutions allow to gracefully scale every component’s energy to the bare minimum required to deliver the instantaneous requested performance, and hence autonomically save energy when afore mentioned algorithmic (application) requirements drop below the node’s nominal performance.
3. Showcase Objective: To demonstrate increased accuracy and lifetime while acoustically monitoring cognitive decline through patient activity and patient mobility (>1 year on 1button cell battery). Demonstrate through a realistic showcase that it is possible to create novel swarm applications, to bring together the performance and lifetime objectives into a single sound swarm and build a framework for self-configuration for that novel application.
We will meet these objectives by combining expertise and scientific innovation in acoustic algorithms, wireless communication and sensing hardware towards a radically new swarm operating framework. Key in the SINS approach is the introduction of the novel concept of energy-proportionality, and this at and across all layers : The energy-consumption is continuously reduced to what is really needed by acertain application at a certain point in time.
To implement this, and achieve the performance-, lifetime- and showcase objectives, following research tasks will be carried out in the SINS project:
• The creation of a global system self-configuration framework to ensure a consistent configuration of the swarm for the target application. This should be portable across applications and is key in achieving the SINS multi-disciplinary approach and ensuring a coherent multi-layer swarm operation, self-configuring both at installation time, as well as at run-time.
• The creation of energy-proportional swarm components for communication, sensing and processing. This is key in achieving the lifetime-enhancement objectives of acoustic sensing networks through energy-proportional operation of run-time configurable nodes and network.
• The creation of performance-scalable swarm acoustic algorithms for sound source separation and sound localization, capable of leveraging the energy-proportionality of the swarm components and enhancing performance through distributed collaborative swarm-sensing.
• Application to a novel showcase concerning acoustic monitoring for ambient assisted living: Assessing mild cognitive decline through monitoring patient activity and patient mobility.
Team
- Greet Bilsen, Co-promoter (External)
- Sofie Pollin, Co-promoter (External)
- Werner Verhelst, Co-promoter (External)
- Karin Debruyn, Co-promoter (External)
- Lieven De Strycker, Co-promoter (External)
- Bart Vanrumste, Co-promoter
- Jean Pierre Goemaere, Co-promoter (External)
- Ben Geeraerts, Promoter (External)
- Marian Verhelst, Promoter (External)
Financing
Funding: IWT - Agentschap voor Innovatie door Wetenschap en Technologie
Program/Grant Type: IWT SBO - IWT Projects Strategic Basic Research
Events
2/09/2024:
PhD defense - Martijn Oldenhof
Machine Learning for Advanced Chemical Analysis and Structure Recognition in Drug Discovery
3/09/2024:
Meet the Jury Igor Tetko on Advanced Machine Learning in Drug Discovery
12/09/2024:
Multimodal analysis of cell-free DNA for sensitive cancer detection in low-coverage and low-sample settings
Seminar by Antoine Passemiers
News
STADIUS Alumni Herman Verrelst – new CEO of Biocartis
08 June 2017
Herman Verrelst, the founder of KU Leuven spin-off Cartagenia, who has been working in Silicon Valley, US for the last few years will be returning to Belgium to follow the steps of Rudi Pauwels as CEO of the Belgian diagnostic company, Biocartis.
Supporting healthcare policymaking via machine learning – batteries included!
29 May 2017
STADIUS takes the lead in the data analytics efforts in an ambitious European Project MIDAS.
Marc Claesen gives an interview about his PhD for the magazine of the Faculty of Engineering Sciences "Geniaal"
10 February 2017
Did you know that in Belgium approximately one third of type 2 diabetes patients are unaware of their condition?
Joos Vandewalle is nieuwe voorzitter KVAB
09 October 2016
Op 5 oktober 2016 heeft de Algemene Vergadering van de Academie KVAB Joos Vandewalle verkozen tot voorzitter van de KVAB.