R&D projects and research

Most of our developments in the field of data analysis and machine learning are closely related to scientific activities carried out at the Faculty of Information Technologies and Programming of the St. Petersburg Research University of Information Technologies, Mechanics and Optics (ITMO). Our team members are young scientists, employees of scientific laboratories of the university and participants in research projects implemented in conjunction with leading Russian and international institutions. We are very proud that our technologies and products are developed at the intersection of mathematics, programming, big data visualization and find application in various areas of everyday human activity.

Основная тематика исследований связана с разработкой алгоритмов автоматического построения моделей машинного обучения. Наши исследования ведутся в таких областях, как:

  • Системы на базе компьютерного зрения
  • Генеративные нейронные сети
  • Автоматическое машинное обучение
  • Кластеризация данных
  • Выявление аномалий в данных
  • Обработка естественных языков
  • Сегментация данных
  • Поиск скрытых закономерностей в данных
  • Системы информационного поиска

Избранные публикации

Наши научные работы публикуются в рецензируемых журналах в России и за рубежом

  • Zabashta A., Smetannikov I., Filchenkov A. Rank aggregation algorithm selection meets feature selection [MLDM 2016]
  • Efimova V., Filchenkov A., Shalyto A. Reinforcement-based Simultaneous Algorithm and its Hyperparameters Selection [AWRL@ACML 2016]
  • A. Filchenkov, A. Pendryak Datasets Meta-Feature Description for Recommending Feature Selection Algorithm
  • Filchenkov A., Khanzhina N., Tsai A., Smetannikov I. Regularization of Autoencoders for Bank Client Profiling Based on Financial Transactions. Risks. 2021. Vol. 9. No. 3. pp. 54.
  • Filchenkov A., Krylov D.P., Khanzhina N., Zabashta A., Поляков С. Improving Multimodal Data Labeling with Deep Active Learning for Post Classi cation in Social Networks. ICMR. 2021. pp. 1-14.
  • Yang Q., Farseev A., Filchenkov A. Two-Faced Humans on Twitter and Facebook: Harvesting Social Multimedia for Human Personality Profiling. ICDAR '21: Proceedings of the 2021 on Intelligent Cross-Data Analysis and Retrieval Workshop. 2021. pp. 8.
  • Farseev A., Yang Q., Filchenkov A., Lepikhin K., Chu-Farseeva Y., Loo D. SoMin.ai: Personality-Driven Content Generation Platform. 14th ACM International Conference on Web Search and Data Mining, WSDM 2021. 2021. pp. 890-893.
  • Asadulaev A., Kuznetcov I.S., Stein G., Filchenkov A. Exploring and Exploiting Conditioning of Reinforcement Learning Agents. IEEE Access. 2020. Vol. 8. pp. 211951-211960.
  • Asadulaev A., Stein G., Filchenkov A. Transgenerators. ACM International Conference Proceeding Series. 2020. pp. 3446417.
  • Efimova V., Shalamov V., Filchenkov A. Synthetic Dataset Generation for Text Recognition with Generative Adversarial Networks. Proceedings of SPIE. 2020. Vol. 11433. pp. 1143315.
  • Muravyov S., Filchenkov A. A Cloud-based Network of 3D Objects for Robust Grasp Planning. ACM International Conference Proceeding Series. 2020. pp. 99-105.
  • Khanzhina N., Slepkova N.D., Filchenkov A. Synthetic images generation for text detection and recognition in the wild. Proceedings of SPIE. 2020. Vol. 11433. pp. 1143312.
  • Viuginov N., Grachev P., Filchenkov A. A Machine Learning Based Plagiarism Detection In Source Code. ACM International Conference Proceeding Series. 2020. pp. 3446420.
  • Kochetov K., Filchenkov A. Generative Adversarial Networks for Respiratory Sound Augmentation. ACM International Conference Proceeding Series. 2020. pp. 106-111.
  • Muravyov S., Antipov D., Buzdalova A., Filchenkov A. Efficient Computation Of Fitness Function For Evolutionary Clustering. Mendel. 2019. Vol. 25. No. 1. pp. 87-94.
  • Oreshin S., Filchenkov A., Petrusha P., Krasheninnikov E., Panfilov A., Glukhov I., Kaliberda Y., Masalskiy D., Serdyukov A., Kazakovtsev V.L., Khlopotov M., Podolenchuk T., Smetannikov I., Kozlova D. Implementing a Machine Learning Approach to Predicting Students' Academic Outcomes. ACM International Conference Proceeding Series. 2020. pp. 78-83.