Sökning: onr:"swepub:oai:DiVA.org:kth-195466" >
Parallel real time ...
Parallel real time seizure detection in large EEG data
-
- Ahmed, Laeeq (författare)
- KTH,Beräkningsvetenskap och beräkningsteknik (CST)
-
- Edlund, Åke (författare)
- KTH,Beräkningsvetenskap och beräkningsteknik (CST)
-
- Laure, Erwin (författare)
- KTH,Beräkningsvetenskap och beräkningsteknik (CST)
-
visa fler...
-
Whitmarsh, S. (författare)
-
visa färre...
-
(creator_code:org_t)
- SciTePress, 2016
- 2016
- Engelska.
-
Ingår i: IoTBD 2016 - Proceedings of the International Conference on Internet of Things and Big Data. - : SciTePress. - 9789897581830 ; , s. 214-222
- Relaterad länk:
-
https://urn.kb.se/re...
-
visa fler...
-
https://doi.org/10.5...
-
visa färre...
Abstract
Ämnesord
Stäng
- Electroencephalography (EEG) is one of the main techniques for detecting and diagnosing epileptic seizures. Due to the large size of EEG data in long term clinical monitoring and the complex nature of epileptic seizures, seizure detection is both data-intensive and compute-intensive. Analysing EEG data for detecting seizures in real time has many applications, e.g., in automatic seizure detection or in allowing a timely alarm signal to be presented to the patient. In real time seizure detection, seizures have to be detected with negligible delay, thus requiring lightweight algorithms. MapReduce and its variations have been effectively used for data analysis in large dataset problems on general-purpose machines. In this study, we propose a parallel lightweight algorithm for epileptic seizure detection using Spark Streaming. Our algorithm not only classifies seizures in real time, it also learns an epileptic threshold in real time. We furthermore present "top-k amplitude measure" as a feature for classifying seizures in the EEG, that additionally assists in reducing data size. In a benchmark experiment we show that our algorithm can detect seizures in real time with low latency, while maintaining a good seizure detection rate. In short, our algorithm provides new possibilities in using private cloud infrastructures for real time epileptic seizure detection in EEG data.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences (hsv//eng)
- MEDICIN OCH HÄLSOVETENSKAP -- Medicinska och farmaceutiska grundvetenskaper -- Neurovetenskaper (hsv//swe)
- MEDICAL AND HEALTH SCIENCES -- Basic Medicine -- Neurosciences (hsv//eng)
Nyckelord
- BigData
- Epilepsy
- MapReduce
- Real Time
- Seizure Detection
- Spark
- Algorithms
- Electric sparks
- Electroencephalography
- Electrophysiology
- Internet
- Internet of things
- Neurodegenerative diseases
- Neurophysiology
- Automatic seizure detections
- Benchmark experiments
- Clinical monitoring
- Epileptic seizure detection
- Map-reduce
- Big data
Publikations- och innehållstyp
- ref (ämneskategori)
- kon (ämneskategori)
Hitta via bibliotek
Till lärosätets databas