Self-Aware Wearable Systems in Epileptic Seizure Detection

Forooghifar, Farnaz; Aminifar, Amir; Alonso, David Atienza

doi:10.1109/dsd.2018.00078

Cited by 24 publications

(13 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this article, we extend our previous work [36] and propose a novel wearable system by combining multi-parametric biosignal processing and machine learning with the selfawareness notion. Real-time monitoring and detection of epileptic seizures is done based on the time series extracted from the ECG signal.…”

Section: Introductionmentioning

confidence: 87%

“…This procedure is not restricted to the class of the random forest algorithm and can be applied considering any binary classification technique. The random forest is chosen as it achieves a higher quality with respect to the SVM classification used in [36]. The random forest method adopted in this work provides more robust results and avoids overfitting, due to bootstrap aggregating techniques.…”

Section: B Self-aware Energy Managementmentioning

confidence: 99%

See 1 more Smart Citation

A Self-Aware Epilepsy Monitoring System for Real-Time Epileptic Seizure Detection

Forooghifar

Aminifar

Cammoun³

et al. 2019

Mobile Netw Appl

Self Cite

View full text Add to dashboard Cite

Epilepsy is one of the most prevalent paroxystic neurological disorders that can dramatically degrade the quality of life and may even lead to death. Therefore, real-time epilepsy monitoring and seizure detection has become important over the past decades. In this context, wearable technologies offer a promising solution to pervasive epilepsy monitoring by removing the constraints with respect to time and location. In this paper, we propose a self-aware wearable system for real-time detection of epileptic seizures on a long-term basis. First, we propose a multi-parametric machine learning technique to detect seizures by analyzing both cardiac and respiratory responses to seizures, which are obtained using only the ECG signal. Second, in order to enable long-time epilepsy detection, we introduce the notion of self-awareness in our real-time wearable system. We evaluate the performance of our proposed solution based on an epilepsy database of more than 211 hours of recording, provided by the Lausanne University Hospital (CHUV), on the INYU wearable sensor. Our proposed system achieves a sensitivity of 88.66% and a specificity of 85.65% before applying self-awareness. Moreover, by controlling the energy-quality trade-offs using our self-aware energy-management technique, we can tune the battery lifetime of the wearable system to last between 67.55 and 136.91 days while, still outperforming the state-of-the-art techniques for wearable seizure detection, by achieving from 85.54% to 79.33% geometric mean of specificity and sensitivity.

show abstract

Section: Introductionmentioning

confidence: 87%

Section: B Self-aware Energy Managementmentioning

confidence: 99%

A Self-Aware Epilepsy Monitoring System for Real-Time Epileptic Seizure Detection

Forooghifar

Aminifar

Cammoun³

et al. 2019

Mobile Netw Appl

Self Cite

View full text Add to dashboard Cite

show abstract

“…Finally, there are works in the literature that present selfaware systems for personalized health care such as [23], [24]. Nevertheless, these systems tackle the problem of patient deterioration and not the specific problem of generating personalized training data.…”

Section: Related Workmentioning

confidence: 99%

A Self-Learning Methodology for Epileptic Seizure Detection with Minimally-Supervised Edge Labeling

Pascual

Aminifar

Atienza

2019

2019 Design, Automation &Amp; Test in Europe Conference &Amp; Exhibition (DATE)

Self Cite

View full text Add to dashboard Cite

Epilepsy is one of the most common neurological disorders and affects over 65 million people worldwide. Despite the continuing advances in anti-epileptic treatments, one third of the epilepsy patients live with drug resistant seizures. Besides, the mortality rate among epileptic patients is 2-3 times higher than in the matching group of the general population. Wearable devices offer a promising solution for the detection of seizures in real time so as to alert family and caregivers to provide immediate assistance to the patient. However, in order for the detection system to be reliable, a considerable amount of labeled data is needed to train it. Labeling epilepsy data is a costly and time-consuming process that requires manual inspection and annotation of electroencephalogram (EEG) recordings by medical experts. In this paper, we present a self-learning methodology for epileptic seizure detection without medical supervision. We propose a minimally-supervised algorithm for automatic labeling of seizures in order to generate personalized training data. We demonstrate that the median deviation of the labels from the ground truth is only 10.1 seconds or, equivalently, less than 1% of the signal length. Moreover, we show that training a real-time detection algorithm with data labeled by our algorithm produces a degradation of less than 2.5% in comparison to training it with data labeled by medical experts. We evaluated our methodology on a wearable platform and achieved a lifetime of 2.59 days on a single battery charge.

show abstract

“…The face of health-care systems across the globe is changing thanks to Wearable Health-care Systems (WHS) and Internet of Things (IoT), and their benefits such as cost effectiveness and the extended information they provide [1][2][3][4][5][6]. Their applications ranges from daily well-being purposes to emotion recognition [7,8], Early Warning Score (EWS) [4,9,10], and detection of epileptic seizures [11]. Moreover, typical medical devices in the health-care domain that are present in a hospital are expensive and need trained practitioners to operate them.…”

Section: Introductionmentioning

confidence: 99%

Detection and Removal of Motion Artifacts in PPG Signals

Pollreisz

TaheriNejad

2019

Mobile Netw Appl

View full text Add to dashboard Cite

With the rise of wearable devices, which integrate myriad of health-care and fitness procedures into daily life, a reliable method for measuring various bio-signals in a daily setup is more desired than ever. Many of these physiological parameters, such as Heart rate (HR) and Respiratory Rate (RR), are extracted indirectly and using other signals such as Photoplethysmograph (PPG). Part of the reason is that in some cases, such as RR measurements, the devices which directly measure them are cumbersome to wear and thus, rather impractical. On the other hand, signals, such as PPG from which the RR can be extracted, are not very clean. This poses a challenge on reliable extraction of these metrics. The most important problem is that they are corrupted by motion artifacts. In this paper, we review the state of the art algorithms which are used to detect and filter motion artifacts in PPG signals and compare them in terms of their performance. The insight provided by this paper can help the scientists and engineers to obtain a better understanding of the field and be able to use the most suitable technique for their work, or come up with innovative solutions based on existing ones.

show abstract

Self-Aware Wearable Systems in Epileptic Seizure Detection

Cited by 24 publications

References 26 publications

A Self-Aware Epilepsy Monitoring System for Real-Time Epileptic Seizure Detection

A Self-Aware Epilepsy Monitoring System for Real-Time Epileptic Seizure Detection

A Self-Learning Methodology for Epileptic Seizure Detection with Minimally-Supervised Edge Labeling

Detection and Removal of Motion Artifacts in PPG Signals

Contact Info

Product

Resources

About