Search: id:"swepub:oai:DiVA.org:kth-331213" >
Energy-Efficient Pr...
Energy-Efficient Privacy-Preserving Time-Series Forecasting on User Health Data Streams
-
- Arsalan, Muhammad (author)
- Tech Univ Carolo Wilhelmina Braunschweig, Braunschweig, Germany.
-
- Di Matteo, Davide (author)
- KTH
-
- Imtiaz, Sana (author)
- KTH,Programvaruteknik och datorsystem, SCS,KRY Int AB, Stockholm, Sweden.
-
show more...
-
- Abbas, Zainab (author)
- KTH,Programvaruteknik och datorsystem, SCS,KRY Int AB, Stockholm, Sweden.
-
- Vlassov, Vladimir, 1957- (author)
- KTH,Programvaruteknik och datorsystem, SCS
-
- Issakov, Vadim (author)
- Tech Univ Carolo Wilhelmina Braunschweig, Braunschweig, Germany.
-
show less...
-
KTH Tech Univ Carolo Wilhelmina Braunschweig, Braunschweig, Germany (creator_code:org_t)
- Institute of Electrical and Electronics Engineers (IEEE), 2022
- 2022
- English.
-
In: Proceedings - 2022 IEEE 21st International Conference on Trust, Security and Privacy in Computing and Communications, TrustCom 2022. - : Institute of Electrical and Electronics Engineers (IEEE). ; , s. 541-546
- Related links:
-
https://urn.kb.se/re...
-
show more...
-
https://doi.org/10.1...
-
show less...
Abstract
Subject headings
Close
- Health monitoring devices are gaining popularity both as wellness tools and as a source of information for healthcare decisions. In this work, we use Spiking Neural Networks (SNNs) for time-series forecasting due to their proven energy-saving capabilities. Thanks to their design that closely mimics the natural nervous system, SNNs are energy-efficient in contrast to classic Artificial Neural Networks (ANNs). We design and implement an energy-efficient privacy-preserving forecasting system on real-world health data streams using SNNs and compare it to a state-of-the-art system with Long short-term memory (LSTM) based prediction model. Our evaluation shows that SNNs tradeoff accuracy (2.2x greater error), to grant a smaller model (19% fewer parameters and 77% less memory consumption) and a 43% less training time. Our model is estimated to consume 3.36 mu J energy, which is significantly less than the traditional ANNs. Finally, we apply epsilon-differential privacy for enhanced privacy guarantees on our federated learning-based models. With differential privacy of epsilon = 0.1, our experiments report an increase in the measured average error (RMSE) of only 25%.
Subject headings
- TEKNIK OCH TEKNOLOGIER -- Elektroteknik och elektronik -- Datorsystem (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Electrical Engineering, Electronic Engineering, Information Engineering -- Computer Systems (hsv//eng)
Keyword
- Spiking neural networks
- differential privacy
- federated learning
- smart health care
- fitness trackers
Publication and Content Type
- ref (subject category)
- kon (subject category)
To the university's database