Search: id:"swepub:oai:lup.lub.lu.se:dfa00e67-b9b4-475c-b673-0f7467c02374" >
Decentralized Feder...
Decentralized Federated Learning for Epileptic Seizures Detection in Low-Power Wearable Systems
-
- Baghersalimi, Saleh (author)
- Swiss Federal Institute of Technology
-
- Teijeiro, Tomas (author)
- Basque Center of Applied Mathematics
-
- Aminifar, Amir (author)
- Lund University,Lunds universitet,Bredbandskommunikation,Forskargrupper vid Lunds universitet,LTH profilområde: AI och digitalisering,LTH profilområden,Lunds Tekniska Högskola,LTH profilområde: Teknik för hälsa,LU profilområde: Naturlig och artificiell kognition,Lunds universitets profilområden,LTH profilområde: Vatten,Broadband Communication,Lund University Research Groups,LTH Profile Area: AI and Digitalization,LTH Profile areas,Faculty of Engineering, LTH,LTH Profile Area: Engineering Health,Faculty of Engineering, LTH,LU Profile Area: Natural and Artificial Cognition,Lund University Profile areas,LTH Profile Area: Water,Faculty of Engineering, LTH
-
show more...
-
- Atienza, David (author)
- Swiss Federal Institute of Technology
-
show less...
-
(creator_code:org_t)
- 2024
- 2024
- English 16 s.
-
In: IEEE Transactions on Mobile Computing. - 1536-1233. ; 23:5, s. 6392-6407
- Related links:
-
http://dx.doi.org/10...
-
show more...
-
https://lup.lub.lu.s...
-
https://doi.org/10.1...
-
show less...
Abstract
Subject headings
Close
- In healthcare, data privacy of patients regulations prohibits data from being moved outside the hospital, preventing international medical datasets from being centralized for AI training. Federated learning (FL) is a data privacy-focused method that trains a global model by aggregating local models from hospitals. Existing FL techniques adopt a central server-based network topology, where the server assembles the local models trained in each hospital to create a global model. However, the server could be a point of failure, and models trained in FL usually have worse performance than those trained in the centralized learning manner when the patient's data are not independent and identically distributed (Non-IID) in the hospitals. This paper presents a decentralized FL framework, including training with adaptive ensemble learning and a deployment phase using knowledge distillation. The adaptive ensemble learning step in the training phase leads to the acquisition of a specific model for each hospital that is the optimal combination of local models and models from other available hospitals. This step solves the non-IID challenges in each hospital. The deployment phase adjusts the model's complexity to meet the resource constraints of wearable systems. We evaluated the performance of our approach on edge computing platforms using EPILEPSIAE and TUSZ databases, which are public epilepsy datasets.
Subject headings
- NATURVETENSKAP -- Data- och informationsvetenskap -- Annan data- och informationsvetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Other Computer and Information Science (hsv//eng)
Keyword
- Brain modeling
- Data models
- Deep learning
- Electrocardiogram
- Electrocardiography
- Electroencephalography
- Epilepsy
- Federated Learning
- Hospitals
- Knowledge distillation
- Multi-biosignal processing
- Seizure detection
- Servers
- Training
- Wearable systems
Publication and Content Type
- art (subject category)
- ref (subject category)
Find in a library
To the university's database