Embedded AI research laboratory
TalTech priority area
Research classification (Frascati)
Head of the research group
Research group member
Doctoral students
Keyword
Overview
Sardtehisintellekti labor keskendub masinõppe lahenduste arendamisele sardsüsteemides. Labor teeb rahvusvaheliselt koostööd nii merenduse, meditsiini, targa linna, autonoomsete sõidukite ja tööstusautomaatika teadusgruppide ja ettevõtetega. Põhifookus on merenduse ja mobiilsusega seotud valdkonnad. Põhikompetentsid:• sardriistvara disain ja prototüüpimine,• masinõppemudelite optimeerimine sardriistvarale,• mobiilsete sensorite arvutustehnoloogiad,• pildi- ja videotöötlus sardriistvaral
The Embedded AI Research Lab focuses on developing and optimizing machine learning solutions in the embedded systems. The laboratorycollaborates internationally with research teamsand companies from the maritime, smart city,autonomous vehicles and industrial automationsectors. Main focus is on maritime and mobilitysolutions.Core competencies: Embedded hardware design and prototyping, Machine learning model optimization forembedded hardware, Hardware accelerators for edge computing, Image and video processing on edge devices.
Related projects
Period of activity of the research group
2023
2022
2021
2020
2019
Related department
Publications related to the research group
- Ademola, O. A., Leier, M., Petlenkov, E. Evaluation of deep neural network compression methods for edge devices using weighted score-based ranking scheme // Sensors (2021) vol. 21, 22, art. 7529.
https://doi.org/10.3390/s21227529 - Leier, M., Riid, A., Alumäe, T., Reinsalu, U., Pihlak, R., Udal, A., Heinsar, R., Vainküla, S. Smart elevator with unsupervised learning for visitor profiling and personalised destination prediction // 2021 IEEE International Conference on Cognitive and Computational Aspects of Situation Management (CogSIMA) : Virtual Conference, 14-22 May 2021 : proceedings. Danvers : IEEE, 2021. p. 9-16.
https://doi.org/10.1109/CogSIMA51574.2021.9475921 - Soom, J., Pattanaik, V., Leier, M., Tuhtan, J.A. Environmentally adaptive fish or no-fish classification for river video fish counters using high-performance desktop and embedded hardware // Ecological Informatics (2022) vol. 72, art. 101817, 14 p. : ill.
https://doi.org/10.1016/j.ecoinf.2022.101817 - Reinsalu U., Robal T., Leier M. Floor selection proposal for automated travel with smart elevator // Databases and Information Systems : 14th International Baltic Conference, DB&IS 2020, Tallinn, Estonia, June 16-19, 2020 : Proceedings. Cham : Springer, 2020. (Communications in computer and information science ; 1243).
https://doi.org/10.1007/978-3-030-57672-1_4 - Ruberg, P., Meinberg, E., Ellervee, P. Software parser and analyser for hardware performance estimations // 2022 International Conference on Electrical, Computer and Energy Technologies (ICECET), Prague, Czech Republic, 20-22 July 2022. : IEEE, 2022. p. 1-6.
https://doi.org/10.1109/ICECET55527.2022.9872951 - Robal, T., Reinsalu, U., Leier, M. Towards personalized elevator travel with smart elevator system // Baltic journal of modern computing (2020) vol. 8, 4, p. 675-697.
https://doi.org/10.22364/bjmc.2020.8.4.12 - Basov, K., Robal, T., Reinsalu, U., Leier, M. Elevator passenger in-cabin behaviour – a study on Smart-Elevator Platform // Digital Business and Intelligent Systems : 15th International Baltic Conference, Baltic DB&IS 2022, Riga, Latvia, July 4-6, 2022 : proceedings. Cham : Springer Nature, 2022. p. 3-18 : ill. (Communications in computer and information science ; 1598).
https://doi.org/10.1007/978-3-031-09850-5_1 - Robal, T., Basov, K., Reinsalu, U., Leier, M. A study into elevator passenger in-cabin behaviour on a smart-elevator platform // Baltic Journal of Modern Computing (2022) vol. 10, 4, p. 665-688 : ill.
https://doi.org/10.22364/bjmc.2022.10.4.05 - Grailoo, M., Leier, M., Pagliarini, S. Hardware Trojans for confidence reduction and misclassifications on neural networks // Proceedings Of The Twenty Third International Symposium On Quality Electronic Design (ISQED 2022). Danvers : IEEE, 2022. art. 180541, p. 230-235. (International Symposium on Quality Electronic Design).
https://doi.org/10.1109/ISQED54688.2022.9806246 - Ademola, O. A., Petlenkov, E., Leier, M. Ensemble of Tensor Train Decomposition and Quantization Methods for Deep Learning Model Compression // 2022 International Joint Conference on Neural Networks (IJCNN). : IEEE, 2022.
https://doi.org/10.1109/IJCNN55064.2022.9892626 - Ruberg, P., Ellervee, P., Tammemäe, K., Reinsalu, U., Rähni, A., Robal, T. Surviving the unforeseen - teaching IT and engineering students during COVID-19 outbreak // Proceedings - Frontiers in Education Conference, FIE. Piscataway, NJ : IEEE, 2022. Code 184790. (Volume 2022-October).
https://doi.org/10.1109/FIE56618.2022.9962383 - Janson, K., Pihlak, R., Azad, S.P., Niazmand, B., Jervan, G., Raik, J. Handling of SETs on NoC links by exploitation of inherent redundancy in circular input buffers [Online resource] // BEC 2018 : 2018 16th Biennial Baltic Electronics Conference (BEC) : proceedings of the 16th Biennial Baltic Electronics Conference, October 8-10, 2018. : IEEE, 2018. 4 p.: ill.
https://doi.org/10.1109/BEC.2018.8600989 - Malburg, J., Janson, K., Raik, J., Dannemann, F. Fault-aware performance assessment approach for embedded networks // 2019 22nd International Symposium on Design and Diagnostics of Electronic Circuits & Systems (DDECS), Cluj-Napoca, Romania : proceedings. Danvers : IEEE, 2019. 4 p. : ill.
https://doi.org/10.1109/DDECS.2019.8724670 - Allik, A., Mägi, S., Pilt, K., Karai, D., Fridolin I., Leier, M., Jervan, G. Comparison of predictive equations for basal metabolic rate // Wireless Mobile Communication and Healthcare : 7th International Conference, MobiHealth 2017, Vienna, Austria, November 14–15, 2017 : proceedings. Cham : Springer, 2018. p. 261-264 : ill. (Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering ; 247).
https://doi.org/10.1007/978-3-319-98551-0 - Allik, A., Pilt, K., Karai, D., Fridolin, I., Leier, M., Jervan, G. Classification algorithm improvement for physical activity recognition in maritime environments // World Congress on Medical Physics and Biomedical Engineering 2018 : June 3–8, 2018, Prague, Czech Republic (Vol. 3). Singapore : Springer Nature, 2019. p. 13-17. (IFMBE proceedings ; 68/3).
https://doi.org/10.1007/978-981-10-9023-3_3 - Janson, K., Pihlak, R., Azad, S.P., Niazmand, B., Jervan, G., Raik, J. AWAIT : an ultra-lightweight soft-error mitigation mechanism for network-on-chip links // 2018 13th International Symposium on Reconfigurable Communication-centric Systems-on-Chip (ReCoSoC), Lille, France, July 9th-11th, 2018. Piscataway : IEEE, 2018. p. 1-6 : ill.
https://doi.org/10.1109/ReCoSoC.2018.8449374 - Ruberg, P., Liiv, E., Lass, K., Ellervee, P. Data analysis for embedded software performance and energy consumption estimation // 2019 IEEE 2nd Ukraine Conference on Electrical and Computer Engineering : UKRCON-2019 : conference proceedings. Danvers : IEEE, 2019. p. 928-933 : ill.
https://doi.org/10.1109/UKRCON.2019.8879787 - Janson, K., Treudler, C.J., Hollstein, T., Raik, J., Jenihhin, M., Fey, G. Software-level TMR approach for on-board data processing in space applications // 21st IEEE International Symposium on Design and Diagnostics of Electronic Circuits and Systems : DDECS 2018 : Budapest, Hungary 25-27 April, 2018 : proceedings. Piscataway : IEEE, 2018. p. 147-152 : ill.
https://doi.org/10.1109/DDECS.2018.00033 - Leier, M., Jervan, G., Allik, A., Pilt, K., Karai, D., Fridolin, I. Fall detection and activity recognition system for usage in smart work-wear [Online resource] // BEC 2018 : 2018 16th Biennial Baltic Electronics Conference (BEC) : proceedings of the 16th Biennial Baltic Electronics Conference, October 8-10, 2018. : IEEE, 2018. 4 p.: ill.
https://doi.org/10.1109/BEC.2018.8600959 - Allik, A., Pilt, K., Karai, D., Fridolin, I., Leier, M., Jervan, G. Optimization of physical activity recognition for real-time wearable systems : effect of window length, sampling frequency and number of features // Applied sciences (2019) vol. 9, 22, art. 4833, 14 p. : ill.
https://doi.org/10.3390/app9224833 - Lebdeh, M. A., Reinsalu, U., Nguyen, H. A. D. et al. Memristive device based circuits for computation-in-memory architectures // 2019 IEEE International Symposium on Circuits and Systems (ISCAS) : proceedings. Piscataway : IEEE, 2019. 5 p. : ill.
https://doi.org/10.1109/ISCAS.2019.8702542 - Sell, R., Leier, M., Rassõlkin, A., Ernits, J.-P. Self-driving car ISEAUTO for research and education // Proceedings of the 2018 19th International Conference on Research and Education in Mechatronics : (REM 2018), Delft, The Netherlands, June 7-8, 2018. [S.l.] : IEEE, 2018. p. 111-116 : ill.
https://doi.org/10.1109/REM.2018.8421793 - Polukhin, A., Gordienko, Y., Leier, M., Jervan, G., Rokovyi, O., Alienin, O., Stirenko, S. Edge intelligence resource consumption by UAV-based IR object detection // UAVM '23 : proceedings of the 2023 Workshop on UAVs in multimedia : capturing the world from a new perspective. New York : ACM, 2023. p. 57-61.
https://doi.org/10.1145/3607834.3616566