Publications

Journal

[J9] A. Pentari, G. Tzagkarakis, K. Marias, and P. Tsakalides, "Graph Denoising of Impulsive EEG Signals and the Effect of their Graph Representation," Elsevier Biomedical Signal Processing and Control, vol. 78, 2022, 103886, ISSN 1746-8094, DOI:10.1016/j.bspc.2022.103886.

[J8] K. Bountrogiannis, G. Tzagkarakis, and P. Tsakalides, "Distribution Agnostic Symbolic Representations for Time Series Dimensionality Reduction and Online Anomaly Detection," IEEE Transactions on Knowledge and Data Engineering, 2022, DOI:10.1109/TKDE.2022.3174630.

[J7] M. Giannopoulos, G. Tsagkatakis, and P. Tsakalides, "4D U-Nets for Multi-Temporal Remote Sensing Data Classification," MDPI Remote Sensing, Special Issue on Computer Vision and Pattern Recognition for the Analysis of 2D/3D Remote Sensing Data in Geoscience, vol. 14, no. 3, pp. 634, 2022, DOI:10.3390/rs14030634.

[J6] A. Pentari, G. Tzagkarakis, P. Tsakalides, P. Simos, G. Bertsias, E. Kavroulakis, K. Marias, N. J. Simos, and E. Papadaki, "Changes in Resting-State Functional Connectivity in Neuropsychiatric Lupus: A Dynamic Approach Based on Recurrence Quantification Analysis," Elsevier Biomedical Signal Processing and Control, vol. 72, part A, 2022, pages 103285, ISSN 1746-8094, DOI:10.1016/j.bspc.2021.103285.

[J5] E. Doutsi, L. Fillatre, M. Antonini, and P. Tsakalides, "Dynamic Image Quantization Using Leaky Integrate-and-Fire Neurons," IEEE Transactions on Image Processing, vol. 30, pp. 4305-4315, 2021, DOI:10.1109/TIP.2021.3070193.

[J4] A. Zervou, E. Doutsi, P. Pavlidis, and P. Tsakalides, "Structural Classification of Proteins Based on the Computationally Efficient Recurrence Quantification Analysis and Horizontal Visibility Graphs," Bioinformatics, 2021, btab407, DOI:10.1093/bioinformatics/btab407.

[J3] A. Aidini, G. Tsagkatakis, and P. Tsakalides, "Tensor Decomposition Learning for Compression of Multidimensional Signals," IEEE Journal of Selected Topics in Signal Processing, vol. 15, no. 3, pp. 476-490, April 2021, DOI:10.1109/JSTSP.2021.3054314.

[J2] G. Tzagkarakis, J. P. Nolan, and P. Tsakalides, "Robust Nonlinear Compressive Sampling Using Symmetric Alpha-Stable Distributions," Signal Processing, vol. 182, May 2021, DOI:10.1016/j.sigpro.2020.107944.

[J1] R. Stivaktakis, G. Tsagkatakis, and P. Tsakalides, "Semantic Predictive Coding with Arbitrated Generative Adversarial Networks," MDPI Machine Learning and Knowledge Extraction, 2020, 2, 307–326; DOI:10.3390/make2030017.

Conference

[C9] A. Zervou, E. Doutsi, and P. Tsakalides, "Secondary Structure Classification of Low-Homology Proteins with Graph Neural Networks," in Proc. 30th European Signal Processing Conference (EUSIPCO ‘22), Belgrade, Serbia, August 29-September 2, 2022.

[C8] M. Giannopoulos, G. Tsagkatakis, and P. Tsakalides, "4D Convolutional Neural Networks For Multi-Spectral and Multi-Temporal Remote Sensing Data Classification," in Proc. 2022 International Conference on Acoustics, Speech, and Signal Processing (ICASSP ‘22), Singapore, May 22-27, 2022.

[C7] A. Zervou, E. Doutsi, and P. Tsakalides, "Visibility Graph Network of Multidimensional Time Series Data for Protein Structure Classification," in Proc. 29th European Signal Processing Conference (EUSIPCO ‘21), Dublin, Ireland, August 23-27, 2021.

[C6] A. Zervou, E. Doutsi, P. Pavlidis, and P. Tsakalides, "Efficient Dynamical Analysis of Low-Similarity Protein Sequences for Structural Class Prediction," in Proc. 28th European Signal Processing Conference (EUSIPCO ‘20), Amsterdam, The Netherlands, January 18-22, 2021.

[C5] A. Pentari, G. Tzagkarakis, K. Marias, and P. Tsakalides, "Graph-Based Denoising of EEG Signals in Impulsive Environments," in Proc. 28th European Signal Processing Conference (EUSIPCO ‘20), Amsterdam, The Netherlands, January 18-22, 2021.

[C4] E. Doutsi, M. Antonini, and P. Tsakalides, "An End-to-End Spike-based Image Compression Architecture," in Proc. 54th Annual Asilomar Conference on Signals, Systems and Computers, Pacific Grove, CA, Nov. 1-5, 2020.

[C3] A. Pentari, G. Tzagkarakis, K. Marias, and P. Tsakalides, "A Study on the Effect of Distinct Adjacency Matrices for Graph Signal Denoising," in Proc. 20th IEEE International Conference on BioInformatics and BioEngineering (BIBE ‘20), virtual conference, October 26-28, 2020.

[C2] A. Aidini, G. Tsagkatakis, and P. Tsakalides, "Quantized Tensor Robust Principal Component Analysis," in Proc. 45th International Conference on Acoustics, Speech, and Signal Processing (ICASSP ‘20), Barcelona, May 4-8, 2020.

[C1] A. Aidini, G. Tsagkatakis, and P. Tsakalides, "Tensor Dictionary Learning with Representation Quantization for Remote Sensing Observation Compression," in Proc. Data Compression Conference (DCC ‘20), Cliff Lodge, Snowbird, UT, March 24-27, 2020.

Software

Uncertainty-Aware Deep Neural Networks

This code is used for generating training/validation data and executing training/inference based on a novel deep neural network architecture that can handle arbitrary uncertainty intervals associated with the training data set labels as input, provides probability distributions as output, and adopts a composite loss function.

GitHub repository: https://github.com/gtsagkatakis/Residual-Models-with-DNNs

Data

OMBRIA dataset

This is a Sentinel-1 and Sentinel-2 imagery dataset constructed for benchmarking the OmbriaNet deep learning CNN architecture. OmbriaNet was designed for addressing the flood mapping problem. Each satellite module contains three folders:

1. The folder named BEFORE contains images of a region taken before a selected flood event.

2. The folder named AFTER contains images of the same region taken after the flood event.

3. The folder named MASK contains binary ground truth images of the region as produced by the EMS Rapid mapping. 

GitHub repository: https://github.com/gtsagkatakis/OMBRIA