Resource-Aware Distributed Epilepsy Monitoring Using Self-Awareness From Edge to Cloud

Abstract

The integration of wearable devices in humans' daily lives has grown significantly in recent years and still continues to affect different aspects of high-quality life. Thus, ensuring the reliability of the decisions becomes essential in biomedical applications, while representing a major challenge considering batterypowered wearable technologies. Transferring the complex and energy-consuming computations to fogs or clouds can significantly reduce the energy consumption of wearable devices and result in a longer lifetime of these systems with a single battery charge. In this work, we aim to distribute the complex and energy-consuming machine-learning computations between the edge, fog, and cloud, based on the notion of self-awareness that takes into account the complexity and reliability of the algorithm. We also model and analyze the trade-offs in terms of energy consumption, latency, and performance of different Internet of Things (IoT) solutions. We consider the epileptic seizure detection problem as our realworld case study to demonstrate the importance of our proposed self-aware methodology.

Noninvasive detection of focal seizures in ambulatory patients

“…Such technology might improve >10× the system lifetime with respect to data transmitted to the central cloud medical system, and reduce the system latency by up to 60%. 65,66 Recent findings also demonstrate that multimodal wearables with multiparametric machine-learning techniques can detect seizures by selectively performing cross-modality analyses (ie, self-aware learning) with different types of algorithms according to the classification confidence and target system devices. 67 Cutting edge self-learning algorithms, such as generative adversarial networks, which proved highly effective for image processing, might also carry significant progress in FS detection and forecasting.…”

“…Alternatively, emerging technologies might distribute the complex and energy‐consuming machine‐learning computations among distributed levels of machine learning, combining both smart wearables or edge artificial intelligence and intermediate server levels at home (ie, fog computing). Such technology might improve >10× the system lifetime with respect to data transmitted to the central cloud medical system, and reduce the system latency by up to 60% 65,66 . Recent findings also demonstrate that multimodal wearables with multiparametric machine‐learning techniques can detect seizures by selectively performing cross‐modality analyses (ie, self‐aware learning) with different types of algorithms according to the classification confidence and target system devices 67 .…”

EpilepsyGAN: Synthetic Epileptic Brain Activities With Privacy Preservation

“…A promising solution to reduce mortality and to improve the living standard and independence of epilepsy patients is continuous real-time monitoring using wearable devices [5]- [10]. Wearable devices can continuously collect and process EEG signals from the patient in real time during extended periods of time in order to detect ictal periods.…”

Scalable Privacy-Preserving Distributed Extremely Randomized Trees for Structured Data With Multiple Colluding Parties

“…Existing literature on data mining over distributed platforms incorporate approaches based on cryptographic and secure multiparty computing techniques [16][17][18][19][20]. However, such methods significantly increase communication and computing overhead, making them inefficient and impractical for many real-world scenarios, where we have large-scale data or limited communication and computing features, e.g., in mobile phones or resource-limited wearable devices [21][22][23][24]. Several state-of-the-art solutions, such as [3,25,26], aim to address learning in distributed settings in terms of reducing communication and computational overheads.…”