Salvato in:
Dettagli Bibliografici
Autori principali: Amirshahi, Alireza, Toosi, Maedeh H., Mohammadi, Siamak, Albini, Stefano, Schiavone, Pasquale Davide, Ansaloni, Giovanni, Aminifar, Amir, Atienza, David
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2408.01988
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913458291736576
author Amirshahi, Alireza
Toosi, Maedeh H.
Mohammadi, Siamak
Albini, Stefano
Schiavone, Pasquale Davide
Ansaloni, Giovanni
Aminifar, Amir
Atienza, David
author_facet Amirshahi, Alireza
Toosi, Maedeh H.
Mohammadi, Siamak
Albini, Stefano
Schiavone, Pasquale Davide
Ansaloni, Giovanni
Aminifar, Amir
Atienza, David
contents Wearable systems provide continuous health monitoring and can lead to early detection of potential health issues. However, the lifecycle of wearable systems faces several challenges. First, effective model training for new wearable devices requires substantial labeled data from various subjects collected directly by the wearable. Second, subsequent model updates require further extensive labeled data for retraining. Finally, frequent model updating on the wearable device can decrease the battery life in long-term data monitoring. Addressing these challenges, in this paper, we propose MetaWearS, a meta-learning method to reduce the amount of initial data collection required. Moreover, our approach incorporates a prototypical updating mechanism, simplifying the update process by modifying the class prototype rather than retraining the entire model. We explore the performance of MetaWearS in two case studies, namely, the detection of epileptic seizures and the detection of atrial fibrillation. We show that by fine-tuning with just a few samples, we achieve 70% and 82% AUC for the detection of epileptic seizures and the detection of atrial fibrillation, respectively. Compared to a conventional approach, our proposed method performs better with up to 45% AUC. Furthermore, updating the model with only 16 minutes of additional labeled data increases the AUC by up to 5.3%. Finally, MetaWearS reduces the energy consumption for model updates by 456x and 418x for epileptic seizure and AF detection, respectively.
format Preprint
id arxiv_https___arxiv_org_abs_2408_01988
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MetaWearS: A Shortcut in Wearable Systems Lifecycle with Only a Few Shots
Amirshahi, Alireza
Toosi, Maedeh H.
Mohammadi, Siamak
Albini, Stefano
Schiavone, Pasquale Davide
Ansaloni, Giovanni
Aminifar, Amir
Atienza, David
Machine Learning
Artificial Intelligence
Hardware Architecture
Wearable systems provide continuous health monitoring and can lead to early detection of potential health issues. However, the lifecycle of wearable systems faces several challenges. First, effective model training for new wearable devices requires substantial labeled data from various subjects collected directly by the wearable. Second, subsequent model updates require further extensive labeled data for retraining. Finally, frequent model updating on the wearable device can decrease the battery life in long-term data monitoring. Addressing these challenges, in this paper, we propose MetaWearS, a meta-learning method to reduce the amount of initial data collection required. Moreover, our approach incorporates a prototypical updating mechanism, simplifying the update process by modifying the class prototype rather than retraining the entire model. We explore the performance of MetaWearS in two case studies, namely, the detection of epileptic seizures and the detection of atrial fibrillation. We show that by fine-tuning with just a few samples, we achieve 70% and 82% AUC for the detection of epileptic seizures and the detection of atrial fibrillation, respectively. Compared to a conventional approach, our proposed method performs better with up to 45% AUC. Furthermore, updating the model with only 16 minutes of additional labeled data increases the AUC by up to 5.3%. Finally, MetaWearS reduces the energy consumption for model updates by 456x and 418x for epileptic seizure and AF detection, respectively.
title MetaWearS: A Shortcut in Wearable Systems Lifecycle with Only a Few Shots
topic Machine Learning
Artificial Intelligence
Hardware Architecture
url https://arxiv.org/abs/2408.01988