Projects

How to feed the world in the future in a sustainable way is the largest challenge for mankind. Understanding plant response mechanisms to stresses at the molecular level is essential for developing crops with better performance. Plants perceive pathogens and induce signaling events to activate immunity. However, the associated signaling pathways are still incomplete. I have recently identified SHEER (Stress induced Heme Receptor) in Arabidopsis as the first heme receptor in plant immune signaling. In humans, heme is a well-established signaling molecule to induce immunity. However, in plants so far there is no evidence of the function of free heme in immune signaling. My aim is to address the molecular regulation of SHEER, a completely new player in plant immunity. Furthermore, obtained knowledge will be transferred to economically important barley by CRISPR technology. We expect to provide potential molecular genetic targets for engineering crops with enhanced fitness in the future.

The project aims at validating the contemplated objectives and operation model of the Copyright Infrastructure Task Force (CITF) at hand of components of the AI and Copyright Use Case, and paving the way for the CITF to potentially become a Use Case Group of the Europeum EDIC, focusing on the interoperability and trustworthiness of rights data exchanged between rightsholders and rights users as well as among rightsholders.

One of the challenges that this demonstration project sought to solve was the robotic production of acoustic panels to reduce the time needed to manufacture these. The demonstration project tested the robotic screwing process for acoustic panels of different configurations, taking into account the different dimensions of the panels, the number of screws to be installed and their installation. This demonstration project linked robotics (UR10 collaborative robot), automation (screw feeder, automatic screwdriver, intelligent jig), AI tools (digital twin workstation, machine vision tools, simulation of robot work trajectory). The solution took into account the company's specific production processes and the requirements for acoustic panel parameters, as well as the possibilities for implementing fully automated production in the company or for deployment in other companies in the sector. Results of the demonstration project: realization of the product assembly operation, development of the assembly cell concept, selection of a suitable robot for the assembly operation, selection of the tools, simulation and testing, data collection, analysis and verification of the results.

The novelty of the demo project is the joint handling of non-form-retaining textile materials and solid frame materials by intelligent and flexible robot/assembly robot stations. The active control method detects the performance of the robot’s working organs and checks the quality assurance data with the real ones. Through the analysis and pattern recognition of the collected data, artificial intelligence must be able to make changes to the drafting process. During testing, data will be collected and algorithms created for artificial intelligence to make decisions.

The project aims to explore the adoption of open-source platforms for monitoring production lines and to develop a solution for monitoring Balsnack waffle production line. The objective is to extend the solution to other production lines after successful validation. The project created an integrated production monitoring solution that combines machine vision-based quality control with inputs from sensors. Machine vision facilitates visual quality control and product identification. Product identification will automatically provide the system with preset values that will be compared with inputs from sensors.

The project "Testing of the Applicability of an AI-based Optimization Model for Production Processes using a Digital Twin of the Factory" focuses on creating digital models of the factory and using AI to identify and mitigate bottlenecks in production processes. By using Siemens Plant Simualtion software, the project simulates the factory's actual process times to create a digital twin, enabling production optimization without disrupting real manufacturing. The project utilizes an AI optimization model based on machine learning and data analysis to improve production throughput and resource efficiency.

The Demonstration Project is designed to test the various configurations of advanced AI and Robotics technologies in 5.0 ROBOTICS’ manufacturing processes. This project focuses on evaluating various platforms for AI-driven anomaly detection, real-time parallel simulations, depth-sensing cameras, and AR visualization solutions. These technologies aim to enhance human-robot cooperation, minimize human errors, and optimize production processes. The insights gained will inform our decisions for future large-scale investments.

Project objective: Develop a solution for automatic processing of medical texts, identification and structuring of clinical terms using SNOMED CT codes and FHIR standard. Work plan: 1. Clinical term identification - Preprocessing of Estonian medical texts - Application of machine learning/language models for term identification from text - Structuring of identified terms for further processing 2. Standardization and coding - Linking identified terms with SNOMED CT codes - Semantic matching of data with standardized ontologies - Converting results to FHIR format Demo solution and expected outputs: - Practical demonstration solution for complete workflow - Working system for automatic identification of clinical terms from Estonian texts - Structured output of terms linked with SNOMED CT codes - Standard data presentation in FHIR format for further use Keywords: medical texts, SNOMED CT, FHIR, language processing, clinical terms, automatic annotation, structured data

The ENACT (https://enact-eu.net/) strengthens crime prevention and counter-terrorism efforts by supporting cutting-edge technologies like the Drug Hunter Analyzer. Developed by TalTech and the Estonian Police and Border Guard Board, Drug Hunter enables fast and reliable on-site drug detection in oral fluid within minutes. ENACT funding aims to enhance the visibility of Drug Hunter by supporting pilot studies, validation, and dissemination efforts, ensuring its successful adoption in law enforcement and forensic applications.

This research aims to determine the properties of different DCA mixtures produced from oil shale, determining which DCA mixtures are most efficient as plasticizers, determine the usable temperature range for DCA ester plasticizers and demonstrate the availability of energetic plasticizers that are free from non-NATO imports.

Experimental research for the development of asphalt mixtures with optimum lignin content.

The project aim is to build competencies in digital transformation for higher education institutions in Southeast Asia by developing digital strategic plan, improve the quality of learning and teaching methodologies and pedagogical approaches for digital learning.