no code implementations • 14 Nov 2023 • Vasilis Michalakopoulos, Sotiris Pelekis, Giorgos Kormpakis, Vagelis Karakolis, Spiros Mouzakitis, Dimitris Askounis
On top of this neural network, a function, based on physics equations, calculates the energy consumption of the building based on heat losses and enhances the loss function of the deep learning model.
no code implementations • 24 Oct 2023 • Alexandros-Menelaos Tzortzis, Sotiris Pelekis, Evangelos Spiliotis, Spiros Mouzakitis, John Psarras, Dimitris Askounis
Short-term load forecasting (STLF) is crucial for the daily operation of power grids.
no code implementations • 28 Aug 2023 • Loukas Ilias, Ioannis Michail Kazelidis, Dimitris Askounis
Next, we propose a multimodal approach, where we use TwHIN-BERT for getting the textual representation of the user description field and employ VGG16 for acquiring the visual representation for the image modality.
1 code implementation • 28 Jul 2023 • Sotiris Pelekis, Evangelos Karakolis, Theodosios Pountridis, George Kormpakis, George Lampropoulos, Spiros Mouzakitis, Dimitris Askounis
DeepTSF automates key aspects of the ML lifecycle, making it an ideal tool for data scientists and MLops engineers engaged in machine learning (ML) and deep learning (DL)-based forecasting.
no code implementations • 30 May 2023 • Loukas Ilias, Dimitris Askounis
People use social media to express their feelings.
no code implementations • 26 May 2023 • Loukas Ilias, Spiros Mouzakitis, Dimitris Askounis
To resolve the above issues, we present the first study in the task of depression and stress detection in social media, which injects extra linguistic information in transformer-based models, namely BERT and MentalBERT.
no code implementations • 25 May 2023 • Loukas Ilias, Dimitris Askounis
Alzheimer's disease (AD) constitutes a complex neurocognitive disease and is the main cause of dementia.
no code implementations • 1 Mar 2023 • Sotiris Pelekis, Angelos Pipergias, Evangelos Karakolis, Spiros Mouzakitis, Francesca Santori, Mohammad Ghoreishi, Dimitris Askounis
The k-means algorithm with dynamic time warping distance considering 14 clusters exhibits the highest performance with a PPS of 0. 689.
no code implementations • 23 Feb 2023 • Sotiris Pelekis, Ioannis-Konstantinos Seisopoulos, Evangelos Spiliotis, Theodosios Pountridis, Evangelos Karakolis, Spiros Mouzakitis, Dimitris Askounis
Short-term load forecasting (STLF) is vital for the effective and economic operation of power grids and energy markets.
no code implementations • 12 Feb 2023 • Michail Chatzianastasis, Loukas Ilias, Dimitris Askounis, Michalis Vazirgiannis
To the best of our knowledge, there is no prior work exploiting a NAS approach and these fusion methods in the task of dementia detection from spontaneous speech.
no code implementations • 8 Nov 2022 • Loukas Ilias, Dimitris Askounis, John Psarras
However, existing state-of-the-art works proposing multimodal approaches do not take into consideration the inter- and intra-modal interactions and propose early and late fusion approaches.
no code implementations • 6 Oct 2022 • Konstantinos Psychogyios, Loukas Ilias, Dimitris Askounis
Cardiovascular disease (CVD) is a class of diseases that involve the heart or blood vessels and according to World Health Organization is the leading cause of death worldwide.
no code implementations • 27 Oct 2021 • Loukas Ilias, Dimitris Askounis, John Psarras
Concurrently, little work has been done in terms of both the usage of transformer networks and the way the two modalities, i. e., speech and transcripts, are combined in a single neural network.
no code implementations • 14 Sep 2021 • Loukas Ilias, Dimitris Askounis
Alzheimer's disease (AD) is the main cause of dementia which is accompanied by loss of memory and may lead to severe consequences in peoples' everyday life if not diagnosed on time.