Search

A novel principal component analysis (PCA)-enhanced cosine radial basis function neural network classifier is presented. The two-stage classifier is integrated with the mixed-band wavelet-chaos methodology, developed earlier by the authors, for accurate and robust classification of electroencephalogram (EEGs) into healthy, ictal, and interictal EEGs. A nine-parameter mixed-band feature space discovered in previous research for effective EEG representation is used as input to the two-stage classifier. In the first stage, PCA is employed for feature enhancement. 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 (RBFNN) employed in the second stage significantly. The classification accuracy and robustness of the classifier are validated by extensive parametric and sensitivity analysis. The new wavelet-chaos-neural network methodology yields high EEG classification accuracy (96.6%) and is quite robust to changes in training data with a low standard deviation of 1.4%. For epilepsy diagnosis, when only normal and interictal EEGs are considered, the classification accuracy of the proposed model is 99.3%. This statistic is especially remarkable because even the most highly trained neurologists do not appear to be able to detect interictal EEGs more than 80% of the times. Index Terms--Chaos, classification, electroencephalogram (EEG) subbands, epilepsy, radial basis function neural network, principal component analysis, wavelet.

A novel wavelet-chaos-neural network methodology is presented for classification of electroencephalograms (EEGs) into healthy, ictal, and interictal EEGs. Wavelet analysis is used to decompose the EEG into delta, theta, alpha, beta, and gamma sub-bands. Three parameters are employed for EEG representation: standard deviation (quantifying the signal variance), correlation dimension, and largest Lyapunov exponent (quantifying the non-linear chaotic dynamics of the signal). The classification accuracies of the following techniques are compared: 1) unsupervised k-means clustering; 2) linear and quadratic discriminant analysis; 3) radial basis function neural network; 4) Levenberg-Marquardt backpropagation neural network (LMBPNN). To reduce the computing time and output analysis, the research was performed in two phases: band-specific analysis and mixed-band analysis. In phase two, over 500 different combinations of mixed-band feature spaces consisting of promising parameters from phase one of the research were investigated. It is concluded that all three key components of the wavelet-chaos-neural network methodology are important for improving the EEG classification accuracy. Judicious combinations of parameters and classifiers are needed to accurately discriminate between the three types of EEGs. It was discovered that a particular mixed-band feature space consisting of nine parameters and LMBPNN result in the highest classification accuracy, a high value of 96.7%. Index Terms--Chaos, EEG sub-bands, epilepsy, neural network classification, wavelet.

A wavelet-chaos methodology is presented for analysis of EEGs and delta, theta, alpha, beta, and gamma subbands of EEGs for detection of seizure and epilepsy. The nonlinear dynamics of the original EEGs are quantified in the form of the correlation dimension (CD, representing system complexity) and the largest Lyapunov exponent (LLE, representing system chaoticity). The new wavelet-based methodology isolates the changes in CD and LLE in specific subbands of the EEG. The methodology is applied to three different groups of EEG signals: 1) healthy subjects; 2) epileptic subjects during a seizure-free interval (interictal EEG); 3) epileptic subjects during a seizure (ictal EEG). The effectiveness of CD and LLE in differentiating between the three groups is investigated based on statistical significance of the differences. It is observed that while there may not be significant differences in the values of the parameters obtained from the original EEG, differences may be identified when the parameters are employed in conjunction with specific EEG subbands. Moreover, it is concluded that for the higher frequency beta and gamma subbands, the CD differentiates between the three groups, whereas for the lower frequency alpha subband, the LLE differentiates between the three groups. Index Terms--Chaos theory, EEG subbands, electroencephalogram (EEG), epilepsy, wavelet transform.

Recently, the writers developed a new mesoscopic-wavelet model for simulating freeway traffic flow patterns and extracting congestion characteristics. As an extension of that research, in this paper, a new neural network-wavelet microsimulation model is presented to track the travel time of each individual vehicle for traffic delay and queue length estimation at work zones. The model incorporates the dynamics of a single vehicle in changing traffic flow conditions. The extracted congestion characteristics obtained from the mesoscopic-wavelet model are used in a Levenberg-Marquardt backpropagation (BP) neural network for classifying the traffic flow as free flow, transitional flow, and congested flow with stationary queue. The neural network model is trained using simulated data and tested using both simulated and real data. The computational model presented is applied to five examples of freeways with two and three lanes and one lane closure with varying entry flow or demand patterns. The new microsimulation model is more accurate than macroscopic models and substantially more efficient than microscopic models. DOI: 10.1061/(ASCE)0733-947X(2006) 132:4(331) CE Database subject headings: Traffic flow; Traffic congestion; Traffic delay; Highway construction; Models; Neural networks; Simulation; Workspace.

A new mesoscopic-wavelet model is presented for simulating freeway traffic flow patterns and extracting congestion characteristics. A traffic speed-density relationship is introduced with a lane drop factor to take into account lane closures in freeway work zones. Patterns of multiple parameters are inputted to a congestion feature extraction algorithm. An approximate solution for this equation is found by space-time discretization. The high frequency fluctuations of the signal are not recognizable at normal resolutions. To overcome this problem, a multi-resolution wavelet filter is introduced in the proposed model to enhance traffic features and extract congestion characteristics from the traffic data. Fourth-order Coifman wavelets are used for filtering because of their good approximation for high-resolution scaling. CE Database subject headings: Workspace; Traffic flow; Highway construction; Models.

Objective: To evaluate the effectiveness of the electroencephalographic (EEG) Brain Function Index (BFI) for characterizing sports-related concussive injury and recovery. Participants: Three hundred fifty-four (354) male contact sport high school and college athletes were prospectively recruited from multiple locations over 6 academic years of play (244 control baseline athletes and 110 athletes with a concussion). Methods: Using 5 to 10 minutes of eyes closed resting EEG collected from frontal and frontotemporal regions, a BFI was computed for all subjects and sessions. Group comparisons were performed to test for the significance of the difference in the BFI score between the controls at baseline and athletes with a concussion at several time points. Results: There was no significant difference in BFI between athletes with a concussion at baseline (ie, prior to injury) and controls at baseline (P = .4634). Athletes with a concussion, tested within 72 hours of injury, exhibited significant differences in BFI compared with controls (P = .0036). The significant differences in BFI were no longer observed at 45 days following injury (P = .19). Conclusion: Controls and athletes with a concussion exhibited equivalent BFI scores at preseason baseline. The concussive injury (measured within 72 hours) significantly affected brain function reflected in the BFI in the athletes with a concussion. The BFI of the athletes with a concussion returned to levels seen in controls by day 45, suggesting recovery. The BFI may provide an important objective marker of concussive injury and recovery. [ABSTRACT FROM AUTHOR]

A novel wavelet-chaos-neural network methodology is presented for classification of electroencephalograms (EEGs) into healthy, ictal, and interictal EEGs. Wavelet analysis is used to decompose the EEG into delta, theta, alpha, beta, and gamma sub-bands. Three parameters are employed for EEG representation: standard deviation (quantifying the signal variance), correlation dimension, and largest Lyapunov exponent (quantifying the non-linear chaotic dynamics of the signal). The classification accuracies of the following techniques are compared: 1) unsupervised k-means clustering; 2) linear and quadratic discriminant analysis; 3) radial basis function neural network; 4) Levenberg–Marquardt backpropagation neural network (LMBPNN). To reduce the computing time and output analysis, the research was performed in two phases: band-specific analysis and mixed-band analysis. In phase two, over 500 different combinations of mixed-band feature spaces consisting of promising parameters from phase one of the research were investigated. It is concluded that all three key components of the wavelet-chaos-neural network methodology are important for improving the EEG classification accuracy. Judicious combinations of parameters and classifiers are needed to accurately discriminate between the three types of EEGs. It was discovered that a particular mixed-band feature space consisting of nine parameters and LMBPNN result in the highest classification accuracy, a high value of 96.7%. [ABSTRACT FROM AUTHOR]