Projects

The proposed experimental research is part of the EU project Co-Udlabs, one of whose partners is the field laboratory of Aalborg University in Frejlev. The air and water stratified-flow pipe at the Frejlev research station will be reconstructed in order to examine the ventilation conditions of the water collection system.

The existing solid face fermentation systems do not ensure the optimal oxygen supply, nor temperature, high microbial contamination risk is also common for those systems. The aim of current project is to develop a simple and cheap system for cultivation of fungi or mycelium equipped with oxygen and temperature control. That improves the growth rate and yield of fungal biomass. System is universal, in addition to cultivation of fungi it enables to carry out high temperature composting. We use 20 - 200 L polypropylene bags as cultivation vessels, that are equipped with process control head. This cultivation vessel enables sterilization, aseptic inoculation, aeration and cooling of growth substrate. Cultivation vessel is connected to control system for oxygen and temperature monitoring and process control at least in 4 individual cultivation vessels.

"Pitt-Hopkins syndrome is a cognitive functional disorder, caused by a de novo genetic mutation of one allele of the transcription factor 4 (TCF4) gene. It has been reported that postnatal restoration of TCF functions in Pitt-Hopkins syndrome animal model (partially) rescues the phenotype, indicating that therapeutic approaches increasing TCF4 levels or activity might also help patients. It has also been reported that inhibiting histone deacetylase activity increases TCF4 transcriptional activity and rescues memory deficiencies associated with TCF4 haploinsufficiency in a mouse model. These effects are likely conveyed by some TCF4 co-repressor, such as ETO/RUNX1T1 recruiting HDACs. However, HDAC inhibitors have a very broad effect on the cellular transcription and can cause various side-effects. Here, we hypothesize that by modulating the activity of specific TCF4 co-activators or co-repressors or their interaction with TCF4 could increase TCF4-dependent transcription, thus alleviating the symptoms of Pitt-Hopkins syndrome and have less side effects for the patients. To this end, we pursue to thoroughly identify the co-regulators participating in TCF4-dependent transcription, and to find means to modulate their activity. The specific aims are as follows: (1) Identify the co-regulatory proteins of different TCF4 protein isoforms. (2) Determine the mechanism of action and the interacting regions between TCF4 and co-regulatory proteins. (3) Develop means to modulate the transcriptional activity or binding of the TCF4 co-regulatory proteins."

Copper-related compounds were identified in human serum albumin samples with the aim of improving the quality of these products.

The aim of the study is to determine the chemical composition of 30 propolis samples collected from different counties of Estonia and to study their antioxidant and antibacterial effects.

Monitoring, recording and analysis of the correct parameters of production equipment at the prototype level using AI.

New methods for producing mat type material from wood springs will be developed based on current equipment and by complementing this with collaborative robot. Possibilities to form the wood spring mat with suitable gripping method will be researched to find an optimal solution to produce this type of packaging material. The found trajectories and kinematics by using the collaborative robot (Omron) will be later used as input for developing next generation of production machine. The generated trajectories and kinematics information from robot programs can be also optimized by using AI tools (Machine Learning) to find more optimized solutions (for trajectory and weaving) considering production speed, travelled trajectories, movement dynamics, created mat density etc. as an input parameters.

The aim of the project is to update the existing subject "Production Digitalization" (6 ECTS), modernize the content of the subject according to the latest rapid developments in the field. New development tools based on virtual (VR) and augmented (AR) reality are introduced on a significant scale, and applications based on them in the areas of processing and production.

A reconfigurable robot system is being developed to check the quality and correct function of machine vision IoT modules. Variations of IoT modules and different are different visual quality control reliability is 80-87%. To make and fix the products, we have designed and manufactured a multi-position special jig, which is controlled by a robot. In order to identify products, a database of IoT modules was created, with the help of which algorithms identify and select the product. Also, quality assessment works based on the same logic. Checked products are divided into two: OK and defective. Defective products are separated and determined to be the actual defect.

The objective of the EEV5040 Industrial Automation and Drives activity is to introduce students to the importance of industrial automation and electric drives and the latest trends in these fields (including IoT). As a result of the development activities, students will acquire in-depth knowledge of electric drive management, model-based design methodology and IoT applications in industrial automation in the future. They are able to create, adapt and analyse electric motor control systems and solve real problems in this field. These results influence the quality of industry-specific ICT teaching, providing students with the practical skills and knowledge essential to today's industrial automation. Within the framework of the development project, the subject EEM0040 Machine vision is also amended, where the traditional machine vision curriculum is added to it by adding the hyperspectral technology component. The aim of the development activity is to combine concepts of machine vision with hyperspectral data processing. Within the subject, students will develop practical skills in the use of hyperspectral cameras, from camera setup to processing of various hyperspectral images. They acquire knowledge of the specifics of hyperspectral data, such as the wavelength spectrum and its relationship to the properties of materials. In addition, they learn the methods of machine vision, which allow to identify different objects and characteristics from hyperspectral images.

The objective of this collaborative project is to enable trustworthy AI hardware by explainable and efficient Deep Neural Networks. As the main contribution to achieving this objective, the project will establish an EnTrustED Framework for DNN hardware design analysis that will follow the novel design flow. First, at the design-time phase, a combination of DNN-tailored AxC techniques will be provided to enhance the compute-efficiency of the DNN inference hardware. The Framework will enable a simulation-based analysis for identifying the neurons that are not practical for the optimisation and must keep their initial Exact Computing (ExC) implementation or the approximation should be reduced. It aims to equip the AI hardware with self-test mechanisms to detect hardware errors and fault-tolerance mechanisms for recovering from an error that has occurred and, thereby, continue the AI algorithm uninterruptedly. As one of the novelties, this project views eXplainable AI (XAI) from a hardware perspective. We intend to consider the AxC during the explainability and thus ensure a correct explanation of the decision taken by the DNN. Once we guarantee the correct behaviour of the hardware, and we have properly considered AxC, we can safely run explainability approaches to profile the DNN implantation still at the design-time for identification of DNN input specific significant neurons. The experimental nature of the project and the high interdependency of the contributions by EC-Lyon and TalTech make the envisioned face-to-face visits essential to achieving the goals of the collaboration.

With a current market value of 150 billion EUR/year, fish are among the most economically valuable species on the planet. The implementation of the European Water Framework and Habitats Directives ensure that long-term environmental monitoring is in demand across the EU. Economically valuable fish species include Salmon and critically endangered European Eel (native in Estonia). They must migrate from the sea into rivers as part of their lifecycle. Existing solutions for fish monitoring are expensive, requiring manual processing of 1000s of hours of video for each location. The "ExoFish" project will provide a highly needed and valuable commercial system capable of automatically detecting and counting wild fish with significantly better performance at 50% of the cost of existing technologies, by utilizing custom hardware and underwater artificial intelligence methods developed at TalTech in collaboration with the Estonian Environmental Agency and international commercial partners.

Field study of risk of fish injury and mortality at two large hydropower plants in Norway and two in Sweden.

The WaveTwin project aims to further develop a digital twin for estimating the wave state in the Baltic Sea from Synthetic Aperture Radar (SAR) data. Previous methods for SAR data are not successful enough for enclosed water bodies where steep wind waves are dominating. It is apparent that the Baltic Sea also cannot be covered fully with wave buoys to measure the energy spectrum, i.e. the distribution of wave energy by frequency. The use of SAR data allows us to effectively evaluate the wave spectrum over the entire Baltic Sea, skipping the high costs of installing and operating wave buoys. To achieve this goal, the team will use their expertise in the application of deep learning techniques to estimate wave spectra based on SAR images. Environmental protection and navigation at sea (e.g. for the construction and maintenance of wind farms) are two of the most important application areas. A growing interest in such problems is also evident in the field of situational awareness systems.