Lukáš Povoda

  • Senior Developer / Artificial Intelligence Researcher
  • Brno, Czech Republic
  • povoda.eu
  • Contact me

Short Biography

Lukas Povoda was born in 1990. He received his Ph.D. from the Faculty of Electrical Engineering and Communication, Brno University of Technology, Czech Republic in 2018. His research interests include data-mining (especially text-mining), machine learning and optimization techniques in this field. His primary objective is to determine the meaning of texts with deep learning methods and deep text understanding methods. Currently, he is working as a Fullstack Senior Developer on multiple web applications. He is also interested in latest technologies in web development, high availability backends and DevOps.

Work Experiences

  • Senior Developer, SnugDesign s.r.o.

    2020 - now

    Analytical work for further development of growing projects, implementation and automation of development processes, collaboration on development of financial platform eDO finance.

  • Artificial Intelligence Researcher, MLJ solutions a.s

    2020 - 2022

    External consulting of data mining projects, designing of Artificial Intelligence solutions and discussing achieved results. Cooperation on development of recommendation systems and operation management systems.

  • Senior Developer, a-netgroup, a.s.

    2013 - 2019

    Development of e-commerce platform “a-net guru” in PHP language, includes system architecture design, DevOps. Collaboration on the project EximTOURS.cz (and other language versions) includes analytical activities, implementation of the interlayer in Spring Framework (Java language). Code review and leadership of junior programmers.

  • Junior Researcher, Brno University of Technology

    2014 - 2020

    Co-researcher on scientific projects. Latest year as an consultant in the fiels of web development and artificial intelligence based text analysis.

  • Java Developer, Brno University of Technology

    2013 - 2013

    Participation on the project optimization processes. The output of this project is a system capable of scheduling the work of employees and make decisions better than human.

  • Junior PHP Developer, WDT, s.r.o.

    2013 - 2013

    Programming in vanilla PHP and JavaScript (mostly jQuery). Work in a team, developing of CMS magnetpro, custommer support.

Research Experiences

  • MPO reg. no. FV20044, with 3S, s.r.o.

    2017 - 2020

    Expert system for automatic analysis and management of large data repositories of manufacturing companies. Keywords: artificial intelligence; big data; data warehouses; predictive analytics.

  • MVČR reg. no. VI2VS/554, with GiTy, a.s.

    2017 - 2019

    Hardware-accelerated identification of people using videos using deep machine learning. Keywords: convolutional neural network; data mining; image similarity; noise training.

  • MVČR reg. no. VI2VS/554, with Honeywell International Inc.

    2016 - 2016

    Connected homes - thermostat datamining (economic treaty), reference person Ondřej Lipták - Leader of electronic design group at Honeywell, Brno Hardware Center of Excellence.

  • IGA reg. no. FEKT/FSI-J-16-3564, with Institute of Physical Engineering

    2016 - 2016

    Classification of metallurgical materials by laser-induced plasma spectrometry using deep neural networks.

  • TAČR reg. no. TH01010503, with Honeywell Czech, spol. s r.o.

    2015 - 2016

    Advanced meteorological information for aviation. Aim to provide flight crew with actual and precise weather information in a way which brings high added value without significant investments into the avionics equipment or ground infrastructure.

  • MPO reg. no. FR-TI4/151, with Webnode CZ, s.r.o.

    2014 - 2015

    Research and development of emotion detection technology in unstructured data. The software prototype implementation can help the manufacturing companies to evaluate emotions in text. Keywords: data mining; emotion recognition; genetic algorithms; text processing.

Education

  • Ph.D., on Brno University of Technology

    2018

    Department of Telecommunications, Faculty of Electrical Engineering and communication.

    Doctoral Thesis: Text Mining Based on Artificial Intelligence Methods.

  • Ing. / MSc., on Brno University of Technology

    2014

    Communications and Informatics on Faculty of Electrical Engineering and communication.

    Master's Thesis: Job Scheduling in Logistic Warehouses.

  • Bc., on Brno University of Technology

    2012

    Teleinformatics on Faculty of Electrical Engineering and communication.

    Bachelor's Thesis: Electronic Booking System for Laboratories and Laboratory Equipment.

Skills

Artificial IntelligenceEnglish B2/C1Keras / TensorflowJavaPHPGoOOPReactive XGitLabGit FlowDocker / SwarmCI / CDNette frameworkNextras ORMSpring BootSpring Cloud
AndroidCakePHPDoctrine ORMElasticSearchHTML5IPMA Level DMySQLNodeJSPythonRedisCSS / Sass / LessSentry

Publications

  • Povoda, L., Burget, R., Brezany, P. Text sentiment analysis for operational management, WILLEY, book chapter (2019)
  • Povoda, L., Burget, R., Masek, J., Uher, V., & Dutta, M. K. (2016). Optimization Methods in Emotion Recognition System. Radioengineering, 25(3), 565-572.
  • Masek, J., Burget, R., Povoda, L., & Dutta, M. K. (2016). Multi–GPU Implementation of Machine Learning Algorithm using CUDA and OpenCL. International Journal of Advances in Telecommunications, Electrotechnics, Signals and Systems, 5(2), 101-107.
  • Kolařík, M., Burget, R., Uher, V., Povoda, L. Superresolution of MRI brain images using unbalanced 3D Dense-U-Net network. In 2019 42nd International Conference on Telecommunications and Signal Processing (TSP). (pp. 643-646). ISBN: 978-1-7281-1864-2.
  • Myška, V., Burget, R., Povoda, L., Dutta, M. Linguistically independent sentiment analysis using convolutional-recurrent neural networks model. In 2019 42nd International Conference on Telecommunications and Signal Processing (TSP). (pp. 212-215). ISBN: 978-1-7281-1864-2.
  • Rajnoha, M., Burget, R., Povoda, L. Image Background Noise Impact on Convolutional Neural Network Training. In 2018 10th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT). (pp. 168-171). ISBN: 978-1-5386-9361-2.
  • Rajnoha, M., Povoda, L., Masek, J., Burget, R., & Dutta, M. K. (2018, February). Pedestrian Detection from Low Resolution Public Cameras in the Wild. In 2018 5th International Conference on Signal Processing and Integrated Networks (SPIN) (pp. 291-295). ISBN: 978-1-5386-3045-7.
  • Povoda, L., Burget, R., Dutta, M. K., & Sengar, N. (2017, February). Genetic optimization of big data sentiment analysis. In 2017 4th International Conference on Signal Processing and Integrated Networks (SPIN) (pp. 141-144). IEEE.
  • Mehta, G., Dutta, M. K., Burget, R., & Povoda, L. (2016, June). Biometric data security using Fractional Fourier Transform and chaotic theory. In 2016 39th International Conference on Telecommunications and Signal Processing (TSP) (pp. 533-537). IEEE.
  • Povoda, L., Burget, R., & Dutta, M. K. (2016, June). Sentiment analysis based on Support Vector Machine and Big Data. In 2016 39th International Conference on Telecommunications and Signal Processing (TSP) (pp. 543-545). IEEE.
  • Masek, J., Burget, R., Povoda, L., & Harvanek, M. Image Search Using Similarity Measures Based on Circular Sectors. In Computer Science & Information Technology (CS & IT).
  • Povoda, L., Arora, A., Singh, S., Burget, R., & Dutta, M. K. (2015, October). Emotion recognition from helpdesk messages. In 2015 7th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT) (pp. 310-313). IEEE.
  • Sengar, N., Dutta, M. K., Burget, R., & Povoda, L. (2015, July). Detection of diabetic macular edema in retinal images using a region based method. In 2015 38th International Conference on Telecommunications and Signal Processing (TSP) (pp. 412-415). IEEE.
  • Povoda, L., Burget, R., Masek, J., & Dutta, M. K. (2015, February). Job shop scheduling problem with heuristic genetic programming operators. In 2015 2nd International Conference on Signal Processing and Integrated Networks (SPIN) (pp. 702-707). IEEE.
  • Karasek, J., Burget, R., Povoda, L., Dutta, M. K., & Singh, A. (2014, November). Genetic programming operators for work-flow optimization in logistic distribution centers. In 2014 International Conference on Medical Imaging, m-Health and Emerging Communication Systems (MedCom) (pp. 105-109). IEEE.
  • Karasek, J., Burget, R., & Povoda, L. (2014). Logistic warehouse process optimization through genetic programming algorithm. In Modern Trends and Techniques in Computer Science (pp. 29-40). Springer, Cham.