Search Results (1 - 3 of 3 Results)

Sort By  
Sort Dir
 
Results per page  

Zhu, DongqingTime-frequency and Hidden Markov Model Methods for Epileptic Seizure Detection
MS, University of Cincinnati, 2009, Engineering : Electrical Engineering
Epilepsy is a severe brain disease that affects more than 50 million individuals world-wide, which are about 1% of the world's population. A method capable of detecting seizures early enough to allow prompt medical treatment would greatly improve the life quality of patients with epilepsy. This thesis proposes two seizure detection methods based on Discrete Wavelet Transform (DWT) and Hidden Markov Model (HMM). 96.6% classification accuracy and good early seizure detection results (0.25 minute to 6 minutes before seizure onset) are achieved on two different data sets. Our methods are compared with two existing seizure detection algorithms and demonstrate great potentials for clinical applications in seizure detection and prediction.

Committee:

Howard Fan, PhD (Committee Chair); Carla Purdy, PhD (Committee Member); William Wee, PhD (Committee Member)

Subjects:

Biomedical Research; Electrical Engineering

Keywords:

human EEG; HMM; DWT; epilepsy; seizure detection; seizure prediction

Tang, YuangDetection and Suppression of Mesial Temporal Lobe Epilepsy
Doctor of Philosophy, Case Western Reserve University, 2012, Biomedical Engineering
Epilepsy is a complex neurological disease that affects more than 50 million people worldwide. Mesial temporal lobe epilepsy (MTLE) is the most common and refractory form of epilepsy. In this study, we present potential new therapies for the treatment of MTLE. First, we present a novel low frequency electrical stimulation paradigm, as a possible therapeutic treatment, for status epilepticus originating from the hippocampus as well as MTLE seizures. The paradigm utilizes the hippocampal commissure, as a unique stimulation target, to simultaneously influence large portions of the bilateral hippocampal network. In order to assess the efficacy of the proposed stimulation paradigm, an acute rat model of MTLE status epilepticus is developed, using bilateral micro-injections 4-Aminopyridine into the hippocampal structure. In animals that received stimulation, an 88% reduction in the powers of the bilateral epileptiform activity is achieved when compared to the control group. In addition, the stimulation paradigm is also shown to entrain the hippocampal network’s spontaneous epileptiform activity and disrupt the synchrony between the epileptiform activity within two sides of the hippocampi. Along with the low frequency stimulation paradigm, we also present a automated seizure detection algorithm. An effective automated seizure detector can reduce the significant human resources necessary for the care of patients suffering from epilepsy and offer improved solutions for closed-loop therapeutic devices such as implantable electrical stimulation systems. While numerous detection algorithms have been published, an effective detector in the clinical setting remains elusive. In this study, a novel detector is proposed based on a support vector machine assembly classifier (SVMA). Each member of the SVMA is trained with a different set of weights between the seizure and non-seizure data and the user can selectively control the output of the SVMA classifier. The algorithm can improve the detection performance compared to traditional methods by providing an effective tuning strategy for specific patients. The proposed algorithm also demonstrates a clear advantage over threshold tuning. When compared with the detection performances reported by other studies using the publicly available epilepsy dataset hosted by the University of BONN, the proposed SVMA detector achieved the best total accuracy of 98.72%.

Committee:

Dominique Durand, PhD (Advisor); Imad Najm, MD (Committee Member); Dawn Taylor, PhD (Committee Member); Diana Kunze, PhD (Committee Member); Melissa Knothe Tate, PhD (Committee Member); Dominique Durand, PhD (Committee Chair)

Subjects:

Biomedical Engineering

Keywords:

Epilepsy; seizure; detection; stimulation

Ghosh Dastidar, SamanwoyModels of EEG data mining and classification in temporal lobe epilepsy: wavelet-chaos-neural network methodology and spiking neural networks
Doctor of Philosophy, The Ohio State University, 2007, Biomedical Engineering
A multi-paradigm approach integrating three novel computational paradigms: wavelet transforms, chaos theory, and artificial neural networks is developed for EEG-based epilepsy diagnosis and seizure detection. This research challenges the assumption that the EEG represents the dynamics of the entire brain as a unified system. It is postulated that the sub-bands yield more accurate information about constituent neuronal activities underlying the EEG. Consequently, certain changes in EEGs not evident in the original full-spectrum EEG may be amplified when each sub-band is analyzed separately. A novel wavelet-chaos methodology is presented for analysis of EEGs and delta, theta, alpha, beta, and gamma sub-bands of EEGs for detection of seizure and epilepsy. The methodology is applied to three different groups of EEGs: healthy subjects, epileptic subjects during a seizure-free interval (interictal), and epileptic subjects during a seizure (ictal). Two potential markers of abnormality quantifying the non-linear chaotic EEG dynamics are discovered: the correlation dimension and largest Lyapunov exponent. A novel wavelet-chaos-neural network methodology is developed for EEG classification. Along with the aforementioned two parameters, the standard deviation (quantifying the signal variance) is employed for EEG representation. It was discovered that a particular mixed-band feature space consisting of nine parameters and LMBPNN result in the highest classification accuracy (96.7%). To increase the robustness of classification, a novel principal component analysis-enhanced cosine radial basis function neural network classifier is developed. The rearrangement of the input space along the principal components of the data improves the classification accuracy of the cosine radial basis function neural network employed in the second stage significantly. The new classifier is as accurate as LMBPNN and is twice as robust. Next, biologically realistic artificial neural networks are developed to reach the next milestone in artificial intelligence. First, an efficient spiking neural network (SNN) model is presented using three training algorithms: SpikeProp, QuickProp, and RProp. Three measures of performance are investigated: number of convergence epochs, computational efficiency, and classification accuracy. Next, a new Multi-Spiking Neural Network (MuSpiNN) and supervised learning algorithm (Multi-SpikeProp) are developed. Finally, the models are applied to the epilepsy and seizure detection problems to achieve high classification accuracies.

Committee:

Hojjat Adeli (Advisor)

Keywords:

Temporal Lobe Epilepsy; Electroencephalogram (EEG); EEG Classification; Epilepsy Diagnosis; Seizure Detection; Wavelet Transform; Chaos Theory; Artificial Neural Networks; Spiking Neural Networks; Principal Component Analysis; Cosine Radial Basis Function