Patient-Optimized Temporally-Adaptive Neurostimulation for Epilepsy Using Deep-EDMD Koopman MPC

Simple item page
dc.contributor.advisorKassiri, Hossein
dc.contributor.authorSalahi, Rojin
dc.date.accessioned2024-11-07T11:20:21Z
dc.date.available2024-11-07T11:20:21Z
dc.date.copyright2024-09-27
dc.date.issued2024-11-07
dc.date.updated2024-11-07T11:20:20Z
dc.degree.disciplineElectrical and Computer Engineering
dc.degree.levelMaster's
dc.degree.nameMASc - Master of Applied Science
dc.description.abstractThis thesis presents the design and implementation of a closed-loop neurostimulator controller for delivering patient-optimized, temporally-adaptive stimulation pulses to control epileptic seizures. The method employs a predictive model and a Model Predictive Controller (MPC) to optimize stimulation. The predictive model, based on a deep learning extended dynamic mode decomposition algorithm, approximates the Koopman operator, capturing a patient's brain dynamics and forecasting stimulation efficacy. The MPC uses these predictions to converge rapidly to an optimal set of stimulation parameters. The system is capable of adapting to changes in brain dynamics over time, ensuring continuous optimization. Both the predictive model and MPC are implemented in software and on hardware (FPGA and ASIC synthesis), achieving a power consumption of 97.09 μW. Additionally, we present a framework incorporating a neural mass model (NMM) fine-tuned to patient pre-recorded data. The NMM generates synthetic intracranial electroencephalography (iEEG) highly correlated with real iEEG during normal and seizure periods. This framework is used to test and validate other patient-optimized, temporally-adaptive stimulation approaches. Our temporally-adaptive stimulation optimization for seizure control was validated using this framework.
dc.identifier.urihttps://hdl.handle.net/10315/42521
dc.languageen
dc.rightsAuthor owns copyright, except where explicitly noted. Please contact the author directly with licensing requests.
dc.subject.keywordsEpilepsy
dc.subject.keywordsSeizure treatments
dc.subject.keywordsNeuromodulation
dc.subject.keywordsNeurostimulation
dc.subject.keywordsDBS
dc.subject.keywordsVNS
dc.subject.keywordsClosed-loop stimulation
dc.subject.keywordsAdaptive closed-loop stimulation
dc.subject.keywordsNeural mass model
dc.subject.keywordsPatient-specific NMM
dc.subject.keywordsWilson-Cowan model
dc.subject.keywordsiEEG signal processing
dc.subject.keywordsReal-time optimization
dc.subject.keywordsKoopman operator
dc.subject.keywordsSeizure control
dc.subject.keywordsModel predictive control
dc.subject.keywordsFPGA implementation
dc.subject.keywordsSpectral correlation
dc.subject.keywordsSeizure detection
dc.subject.keywordsStimulation optimization
dc.subject.keywordsDynamic mode decomposition
dc.subject.keywordsKoopman
dc.subject.keywordsDeep EDMD
dc.subject.keywordsKoopman deep EDMD
dc.subject.keywordsModel predictive controller
dc.subject.keywordsFIR filters
dc.subject.keywordsASIC synthesis
dc.titlePatient-Optimized Temporally-Adaptive Neurostimulation for Epilepsy Using Deep-EDMD Koopman MPC
dc.typeElectronic Thesis or Dissertation

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Salahi_Rojin_2024_Masters.pdf
Size:
11.39 MB
Format:
Adobe Portable Document Format
Download

Collections

Electrical and Computer Engineering

All items in the YorkSpace institutional repository are protected by copyright, with all rights reserved except where explicitly noted.