Abstract
We used genetic algorithms to detect active voxels in the human brain imaged using functional magnetic resonance images. The method that we called EVOX deploys multivoxel pattern analysis to find the fitness of most active voxels. The fitness function is a classifier that works in a leave-one-run-out cross-validation. In each generation, the fitness value is calculated as the average performance over all cross-validation folds. Experimental results using functional magnetic resonance images collected while humans (subjects) were responding to attention visual stimuli showed certain situations that EVOX has could be useful compared to univariate ANOVA (analysis of variance) and searchlight methods. EVOX is an effective multivoxel evolutionary tool that can be used to tell where in the brain patterns responding to stimuli are.

Abstract
Permutation tests have extensively been used to estimate the significance of classification. Permutation tests usually use the test error as a dataset statistic to measure the difference between two or more populations. Then, to estimate the p-value(s), the test error is compared to a set of permuted test-error(s), which is usually obtained after permuting the labels of the populations. In this study, we investigate how several dataset factors, e.g., the number of samples, the number of classes, and the dimensionality size, may affect the p-value obtained via permutation tests. We performed the analysis using the standard permutation test procedure that uses the overall all test error dataset statistic and compared it to the permutation test procedure that uses per-class test error as a dataset statistic that we recently have proposed (doi:10.1016/j.neucom.2011.11.007). We found that permutation tests that use a per-class test error as a dataset statistic are not only more reliable in addressing the null hypothesis but also are highly sensitive to changes in the dataset factors that we investigated in this work. An important finding of this study is that when the dimensionality is low and the number of classes is up to several, say ten, highly above chance accuracy would be required to state the significance. For the same low dimensionality, however, slightly above chance accuracy would be adequate to state significance in a two-class problem.

Abstract
There has been increasing interest in pattern classification methods and neuroimaging studies using permutation tests to estimate the statistical significance of a classifier (p-value). Permutation tests usually use the test error as a dataset statistic to estimate the p-value(s) by measuring the dissimilarity between two or more populations. Using the test error as a dataset statistic; however, may camouflage the lowest recognizable classes, and the resulting p-value will be biased toward better values (usually lower values) because of the highly recognizable classes; thus, lower p-values could sometimes be the result of undercoverage. In this study, we investigate this problem and propose the implementation of permutation tests based on a per-class test error as a dataset statistic. We also propose a model that is based on partially scrambling the testing samples (in this model, the training samples are not scrambled) when computing the non-permuted statistic in order to judge the p-value's tolerance and to draw conclusions regarding, which permutation test procedures are more reliable. For the same purpose, we propose another model that is based on chance-level shifting of the permuted statistic. We tested these two proposed models on functional magnetic resonance imaging data that were collected while human subjects responded to visual stimulation paradigms, and our results showed that these models can aid in determining, which permutation test procedure is superior. We also found that permutation tests that use a per-class test error as a dataset statistic are more reliable in addressing the null hypothesis that all classes in the problem domain are drawn from the same distribution.

Abstract
The analysis of epileptic seizures is typically performed by visual inspection, limited by interrater variation. Our aim was to differentiate seizures characterized by automatisms with an objective, quantitative movement analysis. In part 1 of this study we found parameters (extent and speed of movement of the wrist and trunk) separating seizures with predominant proximal (hyperkinetic, n=10) and distal (automotor, n=10) limb automatisms (P<0.002). For each movement parameter we used the lowest value recorded for a hyperkinetic seizure in part 1 as the cutoff parameter in part 2 on a consecutive sample of 100 motor seizures. As in part 1, the difference between hyperkinetic and non-hyperkinetic seizures was highly significant (<0.001). When all movement parameters were above the threshold, a hyperkinetic seizure was identified with a probability of 80.8%, but the probability for a non-hyperkinetic seizure to have all parameters above the threshold was only 0.02%.

Abstract
Purpose: To quantitatively evaluate the difference of ictal head turning movements between patients with temporal lobe epilepsy (TLE) and frontal lobe epilepsy (FLE). Methods: We investigated 38 seizures of 31 patients with unilateral TLE and 22 seizures of 14 patients with unilateral FLE where head turning occurred in the seizure evolution. The head movements were defined as ipsilateral or contralateral in reference to the lateralization of the patient's focal epilepsy syndrome. Head movements were quantified by either referencing the head position with manually placed markers or by automatic detection of infrared marked reference points. The time of onset, duration, and angular speed of the head movements were computed, and interindividual and intraindividual analyses were performed. Key Findings: All of the TLE seizures had both contralateral and ipsilateral head turning, whereas all FLE had contralateral head turning; only 6 of 22 seizures were associated with ipsilateral head turning. Ipsilateral head turning always preceded contralateral head turning in both TLE and FLE. The head turning occurred significantly sooner after clinical seizure onset in FLE than in TLE patients (ipsilateral 0.5 vs. 16.0 s, contralateral: 4.5 vs. 21.3 s; p < 0.001). Furthermore, the duration of head turning was shorter in FLE for contralateral head turning (4.1 s) than in TLE (contralateral 6.0 s, p < 0.01); the ipsilateral head turning in the two groups did not differ (3.0 vs. 2.9 s) in duration. The angular speed of head turning did not differ for ipsilateral and for contralateral head turning in FLE and TLE. Significance: Quantitative analysis of head turning demonstrates significant differences between patients with FLE and TLE. These differences likely represent differences in spread of epileptic activity. This information may be useful in the seizure evaluation of patients considered for resective epilepsy surgery.

Abstract
Purpose: To quantitatively evaluate the lateralizing significance of ictal head movements of patients with temporal lobe epilepsy (TLE). Methods: We investigated EEG-video recorded seizures of patients with TLE, in which the camera position was perpendicular to the head facing the camera in an upright position and bilateral head movement was recorded. Thirty-eight seizures (31 patients) with head movement in both directions were investigated. Ipsilateral and contralateral head movements were defined according to ictal EEG. Head movements were quantified by selecting the movement of the nose in relation to a defined point on the thorax (25/s) in a defined plane facing the camera. The duration of the head version was determined independently of the camera angle. The angle, duration, and angular speed of the head movements were computed and inter and intrasubject analyses were performed (Wilcoxon rank sum). Results: Ipsilateral movement always preceded contralateral movement. The positive predictive value was 100% for movement in both directions. The duration of contralateral head version was significantly longer than ipsilateral head movement (6.4 +/- 4.1 s vs. 3.9 +/- 3.1 s, p < 0.001). The angular speed of both movements was similar (15.5 +/- 12.1 deg/s vs. 17.3 +/- 13.0 deg/s). Conclusion: The quantitative analysis shows the importance of sequence in the seizure's evolution and duration, but not angular speed for correct lateralization of versive head movement. This quantitative method shows the high lateralizing value of ictal lateral head movements in TLE.