Energy-Efficient Privacy-Preserving Time-Series Forecasting on User Health Data Streams

Arsalan, Muhammad (author): Tech Univ Carolo Wilhelmina Braunschweig, Braunschweig, Germany.

Imtiaz, Sana (author): KTH,Programvaruteknik och datorsystem, SCS,KRY Int AB, Stockholm, Sweden.

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.

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

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%.

By the author/editor: Arsalan, Muhamma ...; Di Matteo, David ...; Imtiaz, Sana; Abbas, Zainab; Vlassov, Vladimi ...; Issakov, Vadim

About the subject

ENGINEERING AND TECHNOLOGY: ENGINEERING AND ...; and Electrical Engin ...; and Computer Systems

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.