Published in AAAI-21 Workshop on Privacy-Preserving Artificial Intelligence, 2021
This paper explores accuracy and privacy bounds for the Data Collaboration method.
Recommended citation: Imakura, A., Bogdanova, A., Yamazoe, T., Omote, K., & Sakurai, T. (2021). Accuracy and privacy evaluations of collaborative data analysis. arXiv preprint arXiv:2101.11144.
Published in IJCAI 2020 International Workshop on Federated Learning for User Privacy and Data Confidentiality, 2020
This paper compares Federated Learning and Data Collaboration in a few-party distributed setting
Recommended citation: Bogdanova, A., Nakai, A., Okada, Y., Imakura, A., & Sakurai, T. (2020). Federated learning system without model sharing through integration of dimensional reduced data representations. arXiv preprint arXiv:2011.06803.
Published in ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part A: Civil Engineering. 6(3)., 2020
In this paper, we analyze the applicability of Federated Learning for health care applications in terms of scalability and the risks of membership inference attacks.
Recommended citation: Bogdanova, A., Attoh-Okine, N., & Sakurai, T. (2020). Risk and Advantages of Federated Learning for Health Care Data Collaboration. ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part A: Civil Engineering, 6(3), 04020031.
Published in Genetic and Evolutionary Computation Conference Companion (GECCO ’19 Companion), 2019
In this paper, we use grammatical evolution to automatically generate hybrids of known meta-heuristics from their building blocks.
Recommended citation: Bogdanova, A., Junior, J. P., & Aranha, C. (2019, July). Franken-swarm: grammatical evolution for the automatic generation of swarm-like meta-heuristics. In Proceedings of the Genetic and Evolutionary Computation Conference Companion (pp. 411-412).
Published in 2017 IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP), 2017
This paper proposes a novel method for gesture recognition based on Henkel subspace method, which achieves high discrimination of spatial and temporal information with low computational cost.
Recommended citation: Gatto, B. B., Bogdanova, A., Souza, L. S., & dos Santos, E. M. (2017, September). Hankel subspace method for efficient gesture representation. In 2017 IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP) (pp. 1-6). IEEE.