1 code implementation • 22 Jul 2019 • Damian Pascual, Amir Aminifar, David Atienza, Philippe Ryvlin, Roger Wattenhofer
In this work, we generate synthetic seizure-like brain electrical activities, i. e., EEG signals, that can be used to train seizure detection algorithms, alleviating the need for recorded data.
no code implementations • 22 Dec 2020 • Valentin Gabeff, Tomas Teijeiro, Marina Zapater, Leila Cammoun, Sylvain Rheims, Philippe Ryvlin, David Atienza
Specifically, we focused the discussion on three main aspects: 1) how to aggregate the classification results on signal segments provided by the DL model into a larger time scale, at the seizure-level; 2) what are the relevant frequency patterns learned in the first convolutional layer of different models, and their relation with the delta, theta, alpha, beta and gamma frequency bands on which the visual interpretation of EEG is based; and 3) the identification of the signal waveforms with larger contribution towards the ictal class, according to the activation differences highlighted using the DeepLIFT method.
no code implementations • 4 Mar 2021 • Giovanni Agosta, William Fornaciari, David Atienza, Ramon Canal, Alessandro Cilardo, José Flich Cardo, Carles Hernandez Luz, Michal Kulczewski, Giuseppe Massari, Rafael Tornero Gavilá, Marina Zapater
RECIPE (REliable power and time-ConstraInts-aware Predictive management of heterogeneous Exascale systems) is a recently started project funded within the H2020 FETHPC programme, which is expressly targeted at exploring new High-Performance Computing (HPC) technologies.
Weather Forecasting Distributed, Parallel, and Cluster Computing
no code implementations • 29 Apr 2021 • Arman Iranfar, Adriana Arza, David Atienza
Continuous and multimodal stress detection has been performed recently through wearable devices and machine learning algorithms.
1 code implementation • 3 May 2021 • Una Pale, Tomas Teijeiro, David Atienza
Furthermore, we evaluate a post-processing strategy to adjust the predictions to the dynamics of epileptic seizures, showing that performance is significantly improved in all the approaches and also that after post-processing, differences in performance are much smaller between approaches.
no code implementations • 3 May 2021 • Lara Orlandic, Adriana Arza Valdes, David Atienza
Next, we classify each individual's POTP regardless of the task at hand, achieving an F-1 score of 77. 1% when distinguishing time passing faster rather than slower than usual.
no code implementations • 4 May 2021 • Una Pale, Nathan Müller, Adriana Arza, David Atienza
It achieves a detection Gmean accuracy of 94. 9%, 98. 6%, 90. 3%, and 84. 3% for the B, C, X, and O points, respectively.
no code implementations • 25 Jun 2021 • Silvio Zanoli, Flavio Ponzina, Tomás Teijeiro, Alexandre Levisse, David Atienza
At the same time, multi-channel signals (like the six-dimensional accelerometer signal) can still benefit from the designed circuit, achieving a reduction factor up to 80% with minor performance degradation.
2 code implementations • 7 Sep 2021 • David Atienza, Concha Bielza, Pedro Larrañaga
In addition, we present modifications of two well-known algorithms (greedy hill-climbing and PC) to learn the structure of a semiparametric Bayesian network from data.
1 code implementation • 16 Nov 2021 • Una Pale, Tomas Teijeiro, David Atienza
At the same time, the total number of sub-classes is not significantly increased compared to the balanced dataset.
1 code implementation • 8 Dec 2021 • Elisabetta De Giovanni, Tomas Teijeiro, Grégoire P. Millet, David Atienza
Additionally, the online adaptive process achieves an F1 score of 99% across five different exercise intensities, with a total energy consumption of 1. 55+-0. 54~mJ.
1 code implementation • 24 Jan 2022 • Una Pale, Tomas Teijeiro, David Atienza
Yet, most of them have not been tested on the challenging task of epileptic seizure detection, and it stays unclear whether they can increase the HD computing performance to the level of the current state-of-the-art algorithms, such as random forests.
no code implementations • 16 May 2022 • Una Pale, Tomas Teijeiro, David Atienza
As a result, we believe it can support the ML community to further foster the research in multiple directions related to feature and channel selection, as well as model interpretability.
no code implementations • 9 Jun 2022 • William Andrew Simon, Una Pale, Tomas Teijeiro, David Atienza
However, its accuracy is not yet on par with other Machine Learning (ML) approaches.
no code implementations • 5 Jul 2022 • Silvio Zanoli, Tomas Teijeiro, Giovanni Ansaloni, David Atienza
In this work, we leverage the self-similarity of the electrocardiogram (ECG) signal to recover missing features in event-based sampled ECG signals, dynamically selecting patient-representative templates together with a novel dynamic time warping algorithm to infer the morphology of event-based sampled heartbeats.
no code implementations • 20 Jul 2022 • Saleh Baghersalimi. Alireza Amirshahi, Farnaz Forooghifar, Tomas Teijeiro, Amir Aminifar, David Atienza
Integrating low-power wearable Internet of Things (IoT) systems into routine health monitoring is an ongoing challenge.
no code implementations • 9 Sep 2022 • Lara Orlandic, Tomas Teijeiro, David Atienza
In this work, we use a semi-supervised learning (SSL) approach to improve the labeling consistency of the COUGHVID dataset and the robustness of COVID-19 versus healthy cough sound classification.
no code implementations • 21 Feb 2023 • Una Pale, Tomas Teijeiro, David Atienza
Epilepsy is a chronic neurological disorder that affects a significant portion of the human population and imposes serious risks in the daily life of patients.
no code implementations • 26 Mar 2023 • Una Pale, Tomas Teijeiro, David Atienza
In this work, we demonstrate a few additional aspects in which HD computing, and the way its models are built and stored, can be used for further understanding, comparing, and creating more advanced machine learning models for epilepsy detection.
no code implementations • 28 Mar 2023 • Jingwei Sun, Zhixu Du, Anna Dai, Saleh Baghersalimi, Alireza Amirshahi, David Atienza, Yiran Chen
In this paper, we propose \textbf{Party-wise Dropout} to improve the VFL model's robustness against the unexpected exit of passive parties and a defense method called \textbf{DIMIP} to protect the active party's IP in the deployment phase.
1 code implementation • 20 Dec 2023 • Alireza Amirshahi, Giovanni Ansaloni, David Atienza
Additionally, we address the overhead of non-GEMM operations in transformer models within the scope of this memory data arrangement.
1 code implementation • 9 Feb 2024 • Hojjat Karami, David Atienza, Anisoara Ionescu
Furthermore, our results demonstrate that our approach can improve representation learning in EHRs and can be useful for clinical prediction tasks.
1 code implementation • 9 Feb 2024 • Hojjat Karami, Mary-Anne Hartley, David Atienza, Anisoara Ionescu
Time series in Electronic Health Records (EHRs) present unique challenges for generative models, such as irregular sampling, missing values, and high dimensionality.
3 code implementations • 20 Feb 2024 • Jonathan Dan, Una Pale, Alireza Amirshahi, William Cappelletti, Thorir Mar Ingolfsson, Xiaying Wang, Andrea Cossettini, Adriano Bernini, Luca Benini, Sándor Beniczky, David Atienza, Philippe Ryvlin
Based on existing guidelines and recommendations, the framework introduces a set of recommendations and standards related to datasets, file formats, EEG data input content, seizure annotation input and output, cross-validation strategies, and performance metrics.