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:
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.
01/12/2020 → 1/12/2024
PI: Erdal Kayacan
Programme: HORIZON 2020 - H2020-MSCA-ITN-2020, European Union
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.
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.
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.
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
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
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
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.
