Aarhus University Seal / Aarhus Universitets segl

Projects by Signal Processing & Machine Learning

Are you looking for projects that the Section of Signal Processing & Machine Learning is currently working on? On this page you can find all projects by the Section of Signal Processing & Machine Learning - Department of Electrical and Computer Engineering, Aarhus University.

Below you can find a list of all current and previous projects of research, their status, mission, and funding:

Artificial Intelligence in Robotics

OpenDR: Open Deep Learning Toolkit for Robotics

01/01/2020 → 31/12/2022

PI in AU: Alexandros Iosifidis

coPI in AU: Erdal Kayacan

Programme: HORIZON 2020 - LEIT ICT WORK PROGRAMME 2018-2020

The core objective of OpenDR is to provide real-time (as defined by the specific use case requirements), light-weight (to be deployed in use-case specified embedded CPUs/GPUs like the NVIDIA TX1/2 and Xavier) and ultra light-weight (to be deployed in embedded architectures like Raspberry Pi, FPGAs, microcontrollers, etc.) deep learning architectures for performing inference and control in various robotics tasks.

AU Role: AU will lead a task on 2D/3D Object localization and tracking and will work on sensor information fusion, as well as contributing to object detection/recognition and semantic scene segmentation and understanding.  AU will also contribute on a work package by working on deep person/face/body part active detection/recognition and pose estimation, deep person/face/body part tracking, human activity recognition, social signal analysis and recognition and multi-modal human centric perception and cognition. AU will also work on another work package on deep planning, deep navigation and deep action and control.


Reliable AI for Marine Robotics (ReMaRo)

01/12/2020 → 1/12/2024

PI: Erdal Kayacan

Programme: HORIZON 2020 - H2020-MSCA-ITN-2020, European Union


Smart Parking System for Vessels and Ports

01/06/2020 → 01/04/2021

PI: Erdal Kayacan

Programme: European Regional Development Fund

The aim of this project, in a collaboration with a start up company in Denmark, is to measure the distance between the harbour and the vessel when parking in the harbour using aerial robots.


Vision-based inspection navigation algorithm for ship inspection

01/08/2020 → 01/08/2021

PI: Erdal Kayacan

Programme: European Regional Development Fund

The aim of this project, in a collaboration with a start up company in Denmark, is the autonomous inspection vessels using visual SLAM algorithms in the harbour using aerial robots.

Finished Projects

Visualization of Virtual Outcrops using Aerial Robots

01/03/2019 → 31/12/2019

Project Coordinator: Erdal Kayacan

In order to generate 3D virtual maps of outcrops in geoscience, a manual flight of aerial robots is often employed which is challenging due to various reasons: 1) piloted flight over curved/uneven surfaces requires auto-focusing, 2) wind disturbances make it difficult even for skilled pilots to precisely main- tain the desired overlap, and 3) hiring of a skilled pilot is expensive as the outcrop generation requires hours of visualization data. In this work, we propose to fully automate the visualization process using a learning-based control framework, i.e., position tracking nonlinear model predictive controller in conjunction with Gaussian process (GP)-based disturbance regression which facilitates a precise tracking of the generated path. Thanks to the long-short term memory feature of the designed GP model, the disturbance forces are accurately estimated even for increasing magnitude levels and time-periods. The simulation and real-world tests manifest that the proposed method could provide a time- and cost-saving yet reliable visualization framework.

Computer Vision and Biosystem Signal Processing

Name: FutureCropping

Duration: Mid-2015 - Mid-2020.

Granted by: The Innovation Fund and partners. 


Name: RoboWeedMaps

Duration: 2017 - 2020

Granted by: The Innovation Fund Denmark 


Name: Safer Autonomous Farming Equipment

Duration: Mid-2014 - 2017

Granted by: The Innovation Fund Denmark and partners.


Name: Automatic Scoring and Selection of Embryos for Improving Standard IVF Treatment

Duration: 2018 - 2021

Granted by: The Innovation Fund and partners. 


Name: CloverSense

Duration: Mid-2016 - 2019

Granted by: GUDP 


Name: Machine learning for optimisation of baggage handling and sorter systems for logistics

Duration: 2018 – 2021

Granted by: The Innovation Fund and partners.


Name: Visual Based Navigation for Autonomous Underwater Vehicle

Duration: 2018 – 2020

Granted by: The Innovation Fund and partners.


Name: Weather Forecasting using Deep Learning on Satellite Images

Duration: 2019 - 2021

Granted by: Private founding


Name: SmartGrass

Duration: 2017-2021

Granted by: The Innovation Fund and partners. 


Name: SqmFarm

Duration: 2018 - 2020

Granted by: GUDP

Digital Signal Processing

Geophysics, Instrumentation, and Signal Processing

Airtech4Water: The Airtech4Water was carried out in collaboration with SkyTEM and the Hydrogeophysics Group, Department of Geoscience, Aarhus University. We participated with research on new signal processing strategies for an all-digital TEM receiver system.

Duration: 2014-2018

Granted by: The Danish National Advanced Technology Foundation


Faster Surface NMR Groundwater Mapping with New Receiver Technology: In this project, we are developing a low noise surface NMR receiver system. Applicability in fieldwork is greatly enhanced by wireless communication between multiple receiver units.

Duration: 2016-2018

Granted by: The COWI Foundation


Abzu, game-changing surface NMR instrument for groundwater mapping: In the Abzu project, we are building a complete surface NMR system. A new transmitter, based on SkyTEM technology, has been constructed offering complete control over the NMR excitation pulses and pulse sequences.

Duration: 2016-2019

Granted by:  Aarhus University Research Foundation


MapField: In the MapField project, we are developing machine learning based tools for optimizing the signal to noise ratio of towed TEM and magnetometer data.

Duration: 2018-2021

Granted by: Innovation Fund Denmark


GIRem: In the GIRem project, we are developing machine learning based tools for optimizing the signal to noise ratio of cross-borehole direct current induced polarization data.

Duration: 2018-2022

Granted by: Innovation Fund Denmark


Flood and Drought: In this joint project with Department of Geoscience, we are researching new methodologies for surface NMR. The goals are vastly improved acquisition speed / signal-to-noise ratio and integration of surface NMR into hydrological models.

Duration: 2019-2023

Granted by: Independent Research Fund Denmark

Machine Learning and Computational Intelligence

Project name: Physics-informed Deep Learning for Wind Farm Flow Modeling (DeepWindFarm)

Duration: 5/2021 - 4/2024

Grated by: Independent Research Fund of Denmark

Role: co-Investigator

Amount: 2,878,821 DKK


Project name: Multimodal Extreme Scale Data Analytics for Smart Cities Environments (MARVEL)

Duration: 1/2021 – 12/2023

Granted by: H2020-ICT - RIA

Role: Principal Investigator (AU)

Amount: 334,610 € (total budget 5,998,086 €)


MADE FAST is the third major project coordinated by the MADE consortium in relation with manufacturing in Denmark. FAST is an acronym for Flexibility, Agility, Sustainability and Talent and the full budget is more than a quarter of a billion DKK, where 80MDKK comes from the Danish Innovation Foundation. It is a collaboration with more than 50 companies, 5 universities and 3 GTSs.

Part projects of MaLeCI and CPS groups at ENG-AU:

3.01: Digital twin with Co-simulation for Packing and Assembly Lines in Manufacturing

4.07: Improving Filter Insert Performance and Quality using Simulation and Data Analytics

4.08: Digital Twin of Movable Factory

4.09: Enabling Real-Time Release Testing using Digital Twin in Medical Device Assembly

4.10: Multimodal Digital Twins enhancing integration speed

4.18: Online process control and optimization using X-ray and AI  

Duration: 2020 - 2023

Granted by: MADE FAST (more information in https://digit.au.dk/research-projects/made-fast/)

Role: Principal Investigator (AU) or co-Principal Investigator (AU)

Amount: ~12,000,000 DKK­


Project title: Bayesian Neural Networks for Bridging the Gap Between Machine Learning and Econometrics (BBNmetrics)

Duration: 8/2020 - 7/2022

Granted by: H2020 MSC-IF

Role: Supervisor

Amount: 207,312 €­


Project title: Open Deep Learning platform for Robotics

Duration: 1/2020 – 12/2022

Granted by: H2020-ICT - RIA

Role: Principal Investigator (AU)

Amount: 897,500 € (total budget 6,661,685 €)


Project title: Data-driven Inter-stock Predictive Analytics - DISPA

Duration: 11/2019 – 10/2022

Granted by: Independent Research Fund Denmark

Role: Principal Investigator

Amount: 2,767,987 DKK


Project title: Agile Edge Intelligence for Delay Sensitive IoT

Duration: 4/2020 - 3/2023

Grated by: Independent Research Fund of Denmark

Role: Co-Investigator

Amount: 2,878,411 DKK 


Project title: Data-Driven Analytics for Unmanned Aerial Vehicles

Duration: 12/2019 – 10/2021

Granted by: AU-ST

Role: Principal Investigator

Amount: 2,400,000 DKK


Project title: Fast, effective and interpretable Deep Learning

Duration: 9/2018 – 8/2021 

Granted by: Centre for Digitalisation, Big Data and Data Analytics

Role: Co-Investigator

Amount: 1,500,000 DKK


Title: Weather Forecasting using Deep Learning and Satellite Images

Duration: 2/2019 – 2/2022

Granted by: Danske Commodities (Industrial PhD)

Role: Co-Principal Investigator 


Project title: Biotic interactions tracked by computer vision (BITCue)

Duration: 4/2019 –3/2022

Granted by: Independent Research Fund Denmark

Role: Co-Investigator

Amount: 2,587,991 DKK


Project title: Automatic Insect Detection (AID)

Duration: 2018 –2020

Granted by: Villum Fonden

Role: External Participant

Amount: 1,991,685 DKK


Project title: Promoting image-based data generation and extraction with machine learning

Duration: 8/2017 – 12/2018

Granted by: Aarhus University Interdisciplinary Network Grant

Role: Participant

Signal Processing and Distributed Computing

About

We have led and participated in numerous externally funded research projects and co-organised a number of conferences and workshops within our areas of expertise. We are grateful to the funding agencies that have supported and enabled our work. Grant sources include Independent Research Fund Denmark, Innovation Fund Denmark, EU Horizon 2020, The European Cooperation in Science and Technology (COST), The Otto Mønsted Foundation, and the Siemens Foundation. Through our activities, we have had the privilege of working in close collaboration with leading partners from industry, academia and the public sector.

2018-2019

  • Title: Machine Learning (ML) in Physiotherapy 1/2 (DK: Digitalt Understøttet Bedre Brug af Hjælpemidler)
  • Objective: ML to improve physiotherapy/rehabilitation plans for hospital dischargees
  • Funding: National Organization of Municipalities (DK: KL)
  • Partners: 5: AU/ENG, U. Coll. Nordjylland, Aalborg Municipality, DigiRehab, KL CfV
  • Read more about the project

2017-2020

  • Title: Early Diagnosis of Rheumatoid Arthritis (RA) Joint Destruction
  • Objective: Early RA diagnosis via CT image processing and disease modelling
  • Funding: Faculty of Health, AU
  • Partners: 2: AU/ENG, AUH/Rheumatology
  • Read more about the project

2017-2019

  • Title: Innovative Use of Big Data (DK: IBBD)
  • Objective: Sensor data processing/ decision support for energy usage min. in buildings
  • Funding: EU Regional Development Fund and the EU Social Fund
  • Partners: 5: AU/ENG, Alexandra Institute, Vitani, Develco, H.Karlsen
  • Read more about the project

2017-2017

  • Title: Workshop on sensor data processing for energy mgmt. in non-residential buildings
  • Objective: Two workshops for knowledge exchange and research funding preparation
  • Funding: AU Research Foundation
  • Partners: 1: AU/ENG and invited guests
  • Read more about the project

2015-2015

  • Title: Cluster computing equipment
  • Objective: To build Raspberry Pi compute clusters for teaching
  • Funding: Siemens Foundation Denmark
  • Partners: 1: AU/ENG
  • Read more about the project

2014-2018

  • Title: iV&L Net: Network on Integrating Vision and Language
  • Objective: Networking and knowledge exchange
  • Funding: ICT COST Action IC1307
  • Partners: 66: AU/ENG, University of Brighton, TU Wien, KU Leuven et al.
  • Read more about the project

2014-2016

  • Title: ValidAid
  • Objective: Early preeclampsia onset detection via smart sphygmomanometer
  • Funding:
  • Partners: 2: AU/ENG, Aarhus University Hospital
  • Read more about the project

2013-2017

  • Title: AAPELE: Algorithms, Architectures & Platforms for Enhanced Living Environments
  • Objective: Networking and knowledge exchange
  • Funding: ICT COST Action IC1303
  • Partners: 64: AU/ENG, University of Oxford, University of Oslo, Aalto University et al.
  • Read more about the project

2012-2014

  • Title: CareStore: Platform for Seamless Healthcare Device Marketing and Configuration
  • Objective: To develop a common driver/app-store for health care devices
  • Funding: EU FP7-SME-2012-315158
  • Partners: 6: AU/Dept. of Eng., U. of Minho, ESIGELEC, Romex, Sekoia and SSRG
  • Read more about the project

2011-2013

  • Title: Connect2Care / UNIK (DK: Ny og Innovativ Teknologi til Kroniske Patienter)
  • Objective: Open standards framework for assisted living for the chronically diseased
  • Funding: Danish Agency for Science, Technology and Innovation
  • Partners: 17: AU/ENG, U. of Copenhagen, Alexandra Institute, Intel, TDC et al.
  • Read more about the project