TalTech Data Repository
Not a member yet
221 research outputs found
Sort by
annotation_tool_models
No full text<p>models for https://github.com/alexandrakolosova/AnnotationTool</p>
Personal Healthcare. Building healthcare systems for the future
No full text<p>This white paper provides a practical roadmap for healthcare systems to rapidly embrace digitally enabled personalized healthcare and address both urgent challenges and future demands.</p><p>This paper argues that digital transformation can only bring about the long heard promises when it is designed and delivered in a systematic and comprehensive, ecosystem supporting way. While cultural models like 4P or 6P6, data value enhancing approaches and standards like openEHR or FHIR7 or overall domain-driven design practices support the effort in an ideological way, there is still a need for practical approach that systematizes the digitalization journey while providing actionable recommendations that would support the transition.</p><p>The structure of this paper guides healthcare systems through this transformation:</p><p>Desired outcomes:</p><p>Showcasing how the digital transformation will help to achieve the three most important objectives for healthcare systems across the world: to expand access to care, enhance the quality of healthcare services and achieve all that in a sustainable way.</p><p>Key policies and recommendations:</p><p>Examining the foundational policies necessary for this transformation, including fostering a whole-of-society approach, ensuring trust and transparency through ethical data use, and empowering strategic investment in person-centred healthcare solutions.</p><p>Implementation approach:</p><p>A step-by-step guide to layered systematization of digital transformation that organically supports a well-functioning health system, progressing from basic data exchange to intelligent systems that personalize care and boost efficiency.</p><p>Personal healthcare in practice:</p><p>Real-world examples demonstrating how intelligent systems can deliver smarter, more sustainable healthcare, improving both patient outcomes and operational efficiency.</p>
PV Generation and Consumption Dataset of an Estonian Residential Dwelling
No full text<p>This is a Residential PV generation and consumption data set from an Estonian house. At the time of submission, one year (2023) of data was available. The data was logged at a 10-second resolution. The untouched dataset can be found in the raw data folder, which is separated month-wise. A few missing points in the dataset were filled with a simple KNN algorithm. However, improved data imputation methods based on machine learning are also possible. To carry out the imputing, run the scripts in the script folder one by one in the numerical serial order (SC1..py, SC2..py, etc.).</p>
<p>Data Descriptor (Scientific Data): <a title="Solar PV Generation and Consumption Dataset of an Estonian Residential Dwelling" href="https://doi.org/10.1038/s41597-025-04747-w">https://doi.org/10.1038/s41597-025-04747-w</a></p>
<p><strong>General Information:</strong></p>
<p><strong>Duration:</strong> January 2023 – December 2023</p>
<p><strong>Resolution:</strong> 10 seconds</p>
<p><strong>Dataset Type:</strong> Aggregated consumption and PV generation data</p>
<p><strong>Logging Device:</strong> Camile Bauer PQ1000 (×2)</p>
<p><strong>Load/Appliance Information:</strong></p>
<ul>
<li>5 kW Rooftop PV array connected to AC Bus via 4.2kW 3-ϕ Inverter</li>
<li>Air conditioner: 0.44 kW (Cooling), 0.62 kW (Heating)</li>
<li>Air to Water (ATW) Heat Pump: 2.5kW (Cooling), 2.6 kW (Heating)</li>
<li>ATW Cylinder unit: 0.21 kW (Controller), 9 kW (Booster Heater)</li>
<li>Microwave oven: 0.9 kW</li>
<li>Coffee Maker: 1 kW</li>
<li>Cooktop Hot Plate: 4.6 kW</li>
<li>TV: 0.103 kW</li>
<li>Vacuum Cleaner: 1.5 kW</li>
<li>Ventilation: 0.1 kW</li>
<li>Washing Machine: 2.2 kW</li>
<li>Electric Sauna: 10 kW</li>
<li>Lighting: 0.25 kW</li>
<li>EV charger: 2.4 kW 1-ϕ</li>
</ul>
<p><strong>Measurement Points:</strong></p>
<ol>
<li>PV converter-side current transformer, potential transformer (Measurement of PV generation).</li>
<li>Utility meter-side current transformer, potential transformer (Measurement of power exchange with the grid).</li>
</ol>
<p><strong>Measured Parameters:</strong></p>
<ul>
<li>Per-phase mean power recorded within the sampling period</li>
<li>Per-phase Minimum power recorded within the sampling period</li>
<li>Per-phase maximum power recorded within the sampling period</li>
<li>Quadrant-wise mean power recorded within the sampling period (1st + 3rd), (2nd + 4th)</li>
<li>Quadrant-wise minimum power recorded within the sampling period (1st + 3rd), (2nd + 4th)</li>
<li>Quadrant-wise maximum power recorded within the sampling period (1st + 3rd), (2nd + 4th)</li>
<li>mean power Factor recorded within the sampling period</li>
<li>Minimum power Factor recorded within the sampling period</li>
<li>Maximum power Factor recorded within the sampling period</li>
<li>System Voltage</li>
<li>Minimum system Voltage</li>
<li>Maximum system Voltage</li>
<li>Mean Voltage between phase and neutral</li>
<li>Minimum voltage between phase and neutral</li>
<li>Maximum voltage between phase and neutral</li>
<li>Zero displacement voltage 4-wire systems (mean, min, max)</li>
</ul>
<p><strong>Script Description:</strong></p>
<p><strong>SC1_PV_auto_sort.py</strong> : This fixes timestamp continuity by resampling at the original sampling rate for PV generation data.</p>
<p><strong>SC2_L2_auto_sort.py</strong> : This fixes timestamp continuity by resampling at the original sampling rate for meter-side measurement data.</p>
<p><strong>SC3_PV_KNN_impute.py</strong> : Filling missing data points by simple KNN for PV generation data.</p>
<p><strong>SC4_L2_KNN_impute.py</strong> : Filling missing data points by simple KNN for meter-side measurement data.</p>
<p><strong>SC5_Final_data_gen.py</strong> : Merge PV and meter-side measurement data, and calculate load consumption.</p>
<p>The dataset provides all the outcomes (CSV files) from the scripts. All processed variables (PV generation, load, power import, and export) are expressed in kW units.</p>
<p>Update: 'SC1_PV_auto_sort.py' & 'SC2_L2_auto_sort.py' are adequate for cleaning up data and making the missing point visible. 'SC3_PV_KNN_impute.py' & 'SC4_L2_KNN_impute.py' work fine for short-range missing data points; however, these two scripts won't help much for missing data points for a longer period. They are provided as examples of one method of processing data. Future updates will include proper ML-based forecasting to predict missing data points. </p>
<p><br><strong>Funding Agency and Grant Number:</strong></p>
<ol>
<li>European Union's Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement no. 955614.</li>
<li>Estonian Research Council under Grant PRG1086.</li>
<li>Estonian Centre of Excellence in Energy Efficiency, ENER, funded by the Estonian Ministry of Education and Research under Grant TK230.</li>
</ol>
annotation_tool_models
No full text<p>models for https://github.com/alexandrakolosova/AnnotationTool</p>
Radio Access Network Subslicing in Closed Control Loop for Improved Slice Performance Management
No full text<p>Presentation of a PhD thesis</p>
preannotation_standalone_models
No full text<p>models for https://github.com/alexandrakolosova/Preannotation_standalone/tree/main</p>
Synthetic dataset for warehouse equipment and pallet recognition (Camera 2)
No full text<p>This dataset provides a collection of synthetic images simulating various warehouse scenarios, specifically designed for training and evaluating computer vision models for equipment and pallet recognition tasks. The images feature a diverse range of warehouse environments, including different lighting conditions, object arrangements, and occlusions.</p><p>This dataset was created as part of a project funded by <a href="https://www.etis.ee/Portal/Projects/Display/196065ff-51bc-48c8-9790-62115a68dec3"><strong>AI & ROBOTICS ESTONIA (EDIH)</strong></a></p><p>Due to upload size limits the dataset was split into 4 pieces.</p><ul><li><a href="/records/nmw7y-41a87"><strong>Camera 1</strong></a></li><li><strong>Camera 2</strong></li><li><a href="/records/c6182-bgd05"><strong>Models</strong></a></li><li><a href="/records/e9wxe-qpv69"><strong>Videos</strong></a></li></ul><p>For an in depth explaination about the dataset creation and model training process see the thesis in <i>Related works</i>.</p><p><strong>Format:</strong> <a href="https://cocodataset.org/#format-data">COCO</a></p><p><strong>Dataset description:</strong><br>Both camera 1 and 2 contain images from the same virtual warehouse.<br>The difference between the two sets in how much the camera position is randomized between frames.<br>Camera 1 has a wide movement and rotation range to capture objects of interest from as many different angles as possible.<br>Camera 2 mimics a security camera - staying high up and looking down. Its position and orientation is randomized somewhat but it is much more constrained.</p><p><strong>Split:</strong></p><ul><li>Train - 2208 (65%)</li><li>Test - 679 (20%)</li><li>Val - 509 (15%)<br> </li></ul><p><strong>Total:</strong> 3396</p><p><strong>Classes:</strong></p><ol><li>person</li><li>pallet_jack_empty</li><li>mover_pallet</li><li>forklift</li><li>forklift_full</li><li>pallet_jack</li><li>pallet_jack_full</li><li>stacker</li><li>stacker_full</li><li>forklift_empty</li><li>stacker_empty</li></ol>
Ice extent analysis of coastal areas of Estonia
Full text link<p>Average ice days per year for coastal areas of Estonia and mean & std time series of ice extent of Gulf of Riga and Gulf of Finland.</p>
The impact of the intensity ratio between vowels and voiceless plosives on the intelligibility of sung text
No full text<p>Poster from 20th International Congress of the Phonetic Sciences; Prague, Czech Republic, August 7-11, 2023.</p><p>In classical singing the intelligibility of the sung text is often less clear than in speaking. In singing, it is the vowels that mainly determine the general sonority of the voice, while to secure text intelligibility a much greater functional load is on consonants. Some voice teachers claim that consonants in singing should be pronounced with exaggerated power, while others have stated that singers, on the contrary, should avoid this.</p>
Using seawater thermal energy for district heating: an oceanographic point of view
No full text<p>Abstract:<br>Replacing the usage of fossil fuels by renewable energy sources is an emerging task of EU climate and energy policies, including the Green Deal. Although deep seawater has in the Baltic Sea low temperature, it is relatively stable throughout the year, and it is still warm enough that heat can be extracted from the water before cooling to the freezing temperature. However, extracting the heat in large quantities (tens of MW) needed for town district scale, requires the pumped seawater volume to be rather large, comparable to the flow rates of rivers. Therefore, with long pipelines, energy loss for pumping may become considerable. Another option, pumping the seawater through short tubes from a coastal location, is limited in time for three late autumn months, because of the seasonal cycle of sea surface temperature. Based on the Copernicus Marine Service reanalysis data 1993-2021, southern coast of the Gulf of Finland has one of the most favorable locations for seawater heat extraction in the Baltic Sea, because of the short distance to the unfreezing sub-halocline layers.</p><p>More detailed oceanographic, environmental, and engineering aspects of using seawater thermal energy are analyzed in the Tallinn Bay area with the data from different sources, including Estonian marine forecast system with a 1-km resolution, remote sensing, and dedicated observations and very-high-resolution modelling.</p>