EpilepsyNet: Interpretable Self-Supervised Seizure Detection for Low-Power Wearable Systems

Huang, Baichuan; Zanetti, Renato; Abtahi, Azra; Atienza, David; Aminifar, Amir

doi:10.1109/aicas57966.2023.10168560

Cited by 3 publications

(1 citation statement)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the advent of wearable devices and the integration of machine learning algorithms, the potential for real-time epilepsy seizure prediction has become increasingly tangible, revolutionizing the management of this neurological disorder. Noteworthy work in this direction includes EpilepsyNet, an interpretable self-supervised encoder-decoder model designed for wearable devices, proposed by Huang et al (2023).…”

Section: Related Workmentioning

confidence: 99%

EpilConNet: A Novel Multi-Class Epileptic Seizure Classification Model through Layer Concatenation

Ghosh¹,

Deepti

Gupta

2023

Preprint

View full text Add to dashboard Cite

Epilepsy is a neurological disorder characterized by recurrent seizures, which can affect individuals of all age groups, but infants and older individuals are particularly vulnerable. Sudden epileptic attacks can pose significant risks and be life-threatening, impacting the overall quality of life of affected individuals. With the progress made in medical science, Electroencephalography (EEG) has emerged as a valuable tool for diagnosing and predicting seizure occurrences. The availability of wearable EEG devices, including caps and helmets, has become increasingly prominent in the market. As a result, there has been a recent surge in the development of deep learning-based systems. These systems are helpful for diagnosis in hospital settings and for mobile applications that provide timely warnings and predictions regarding seizure onset. Most of the existing state-of-the-art (SOTA) approaches focus on distinguishing between healthy and epileptic patients. Some studies categorize individuals into three classes: healthy, experiencing the onset of a seizure, or currently having a seizure, specifically focusing on mobile applications. However, limited literature is available on the five-class problem, which is valuable for localization and diagnosis in hospitals and mobile applications. In this regard, we propose our novel model, named EpilConNet, and conduct extensive experiments on a real-world dataset to demonstrate its efficacy in all modes of classification.

show abstract

Section: Related Workmentioning

confidence: 99%

EpilConNet: A Novel Multi-Class Epileptic Seizure Classification Model through Layer Concatenation

Ghosh¹,

Deepti

Gupta

2023

Preprint

View full text Add to dashboard Cite

show abstract

Energy-Aware Integrated Neural Architecture Search and Partitioning for Distributed Internet of Things (IoT)

Huang,

Abtahi,

Aminifar

2024

IEEE Trans. Circuits Syst. Artif. Intel.

View full text Add to dashboard Cite

A Taxonomy of Low-Power Techniques in Wearable Medical Devices for Healthcare Applications

Tesema,

Jimma,

Khan

et al. 2024

Electronics

View full text Add to dashboard Cite

Chronic diseases are the most prevalent and non-communicable health crisis globally. Most chronic disease patients require continuous physiological monitoring, using wearable technology for timely treatment, precise illness detection, and preventive healthcare. Nonetheless, efficient power management is required for such resource-constrained wearable devices. This work aims to analyze low-power techniques (LPTs) in wearable medical devices using a data-driven approach and identify novel approaches promising higher power savings. Through an intensive literature analysis, we identify the most relevant LPTs for minimizing power consumption in wearable devices for physiological monitoring while recognizing the barriers to adopting these techniques. As a result, a novel taxonomy based on the common characteristics of the LPTs is proposed, along with strategies for the combination of LPTs. Through our analysis, we propose possible enhancements in using LPTs and suggest mechanisms for the medical device industry to facilitate their adoption. Overall, our proposed strategies guide the use of LPTs on wearable medical devices toward continuous physiological monitoring.

show abstract

EpilepsyNet: Interpretable Self-Supervised Seizure Detection for Low-Power Wearable Systems

Cited by 3 publications

References 26 publications

EpilConNet: A Novel Multi-Class Epileptic Seizure Classification Model through Layer Concatenation

EpilConNet: A Novel Multi-Class Epileptic Seizure Classification Model through Layer Concatenation

Energy-Aware Integrated Neural Architecture Search and Partitioning for Distributed Internet of Things (IoT)

A Taxonomy of Low-Power Techniques in Wearable Medical Devices for Healthcare Applications

Contact Info

Product

Resources

About