Nonstationary data stream classification with online active learning and siamese neural networks✩

K Malialis, CG Panayiotou, MM Polycarpou - Neurocomputing, 2022 - Elsevier
We have witnessed in recent years an ever-growing volume of information becoming
available in a streaming manner in various application areas. As a result, there is an …

Eye-lrcn: A long-term recurrent convolutional network for eye blink completeness detection

G de la Cruz, M Lira, O Luaces… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Computer vision syndrome causes vision problems and discomfort mainly due to dry eye.
Several studies show that dry eye in computer users is caused by a reduction in the blink …

Online learning with adaptive rebalancing in nonstationary environments

K Malialis, CG Panayiotou… - IEEE transactions on …, 2020 - ieeexplore.ieee.org
An enormous and ever-growing volume of data is nowadays becoming available in a
sequential fashion in various real-world applications. Learning in nonstationary …

Data augmentation on-the-fly and active learning in data stream classification

K Malialis, D Papatheodoulou… - 2022 IEEE …, 2022 - ieeexplore.ieee.org
There is an emerging need for predictive models to be trained on-the-fly, since in numerous
machine learning applications data are arriving in an online fashion. A critical challenge …

Autoencoder-based anomaly detection in streaming data with incremental learning and concept drift adaptation

J Li, K Malialis, MM Polycarpou - 2023 International Joint …, 2023 - ieeexplore.ieee.org
In our digital universe nowadays, enormous amount of data are produced in a streaming
manner in a variety of application areas. These data are often unlabelled. In this case …

Similarity learning based few shot learning for ECG time series classification

P Gupta, S Bhaskarpandit… - 2021 Digital Image …, 2021 - ieeexplore.ieee.org
Using deep learning models to classify time series data generated from the Internet of
Things (IoT) devices requires a large amount of labeled data. However, due to constrained …

Learning adaptive criteria weights for active semi-supervised learning

H Li, Y Wang, Y Li, G Xiao, P Hu, R Zhao, B Li - Information Sciences, 2021 - Elsevier
Batch mode active learning (BMAL) is devoted to training trustful learning models with
scarce labeled samples by efficiently asking the ground truth annotations of the most …

A hybrid active-passive approach to imbalanced nonstationary data stream classification

K Malialis, M Roveri, C Alippi… - 2022 IEEE …, 2022 - ieeexplore.ieee.org
In real-world applications, the process generating the data might suffer from nonstationary
effects (eg, due to seasonality, faults affecting sensors or actuators, and changes in the …

[HTML][HTML] Improving deep learning based bluespotted ribbontail ray (Taeniura Lymma) recognition

A Levy, A Barash, C Zaguri, A Hadad, P Polsky - Ecological Informatics, 2024 - Elsevier
This paper presents the novel task of bluespotted ribbontail (BR) ray (Taeniura lymma)
recognition using deep learning based computer vision methods to enable the identification …

[HTML][HTML] A Novel Implementation of Siamese Type Neural Networks in Predicting Rare Fluctuations in Financial Time Series

T Basu, O Menzer, J Ward, I SenGupta - Risks, 2022 - mdpi.com
Stock trading has tremendous importance not just as a profession but also as an income
source for individuals. Many investment account holders use the appreciation of their …