This work proposes a metaheuristic-based approach to hyperparameter selection in a multilayer perceptron to classify EMG signals. The main goal of the study is to improve the performance of the model by optimizing four important hyperparameters: the number of neurons, the learning rate, the epochs, and the training batches. The approach proposed in this work shows that hyperparameter optimization using particle swarm optimization and the gray wolf optimizer significantly improves the performance of a multilayer perceptron in classifying EMG motion signals. The final model achieves an average classification rate of 93% for the validation phase. The results obtained are promising and suggest that the proposed approach may be helpful for the optimization of deep learning models in other signal processing applications.

To investigate the potential impact of strabismus and amblyopia on visual-perceptual skills (VPS) and visual-motor skills (VMS) of patients according to the type of strabismus, visual acuity (VA), state of binocularity, and sex. This observational, transverse, prospective study analyzed a sample of 146 children with strabismus (88 male and 58 female) aged 5-15 years from Querétaro, México. To determine the strabismus type, we considered the deviation direction, frequency, binocularity state, and associated and dissociated elements. VPS and VMS were evaluated using the Test of Visual-Perceptual Skills 3rd ed. (TVPS-3) and Visual-Motor Integration Test of Beery 6th ed. (VMI-6). Sex was the main variable associated with the performance of the analyzed patients on TVPS-3 and VMI-6 (p<0.05); boys obtained better scores than girls in all evaluated aspects. Stereopsis was not a determinant of the patients' performance level but was associated with the far and near angles of deviation in both types of strabismus, esotropia and exotropia. Amblyopia was associated with the spatial relationship (p=0.001) and visual closure abilities (p=0.044). Form constancy skill scores diminished in both types of strabismus (esotropia: p=0.011; exotropia: p=0.004), and VMS were the most affected in patients with strabismus. The performance of patients with strabismus with and without amblyopia on TVPS-3 and VMI-6 suggests that they adopt a mechanism to compensate for the impact of strabismus on their VPS and VMS.

This research measures and compares the cortical activity at baseline and during light stimulation (LS) in patients with strabismus and amblyopia (SA) and healthy controls (HCs), to understand the differences in its functionality and propose LS as a potential brain stimulator. This observational, longitudinal, prospective study enrolled 17 SA patients and 17 HCs from Querétaro, México. Electroencephalography (EEG) and digital brain mapping (DBM) were used to identify changes in frequency, voltage, and brain coherence. A total of 68 DBM was analyzed for this purpose. Our results indicate that at baseline, patients with strabismus and amblyopia present: i) lower frequency of alpha-wave activity ($p=0.029$ ) with an abnormal distribution within hemispheres, ii) theta-wave with a predominance in the frontal lobes, which relates these visual conditions to neurodevelopmental disorders, iii) higher values of low voltage ($p <; 0.001$ ) and lower values of and high voltage ($p=0.001$ ) iv) interhemispheric asynchronicity with a predominance in the left hemisphere. On the other hand, the administration of LS modulates the brain activity of SA patients by i) modifying high and low voltages ($p <; 0.001$ and 0.022 respectively), which define the anteroposterior gradient ii) eliminating theta-waves, iii) distributing alpha-wave activity towards the occipital lobes iv) bringing synchronicity between hemispheres. For the HC group, LS alters the distribution of alpha waves within hemispheres, and the state of interhemispheric synchronicity. There were no statistically significant changes in the frequency of the alpha-wave or the anteroposterior gradient. To summarize, LS provokes a state of malleability in the brain of SA patients, by increasing the cortical connectivity, enhancing neural activation and bringing to balance the interhemispheric communication, which converts it into a potential brain stimulator that should be considered as a complementary therapy in the treatment of these patients.

This work proposes a metaheuristic-based approach for hyperparameter selection in a multilayer perceptron to classify electromyographic signals. The main goal of the study is to improve the performance of the model by optimizing four important hyperparameters: the number of neurons, the learning rate, the epochs, and the training batches. The approach proposed in this work shows that hyperparameter optimization using particle swarm optimization and gray wolf optimizer significantly improves the performance of a multilayer perceptron for classifying EMG motion signals. The final model achieved an average classification rate of 93% for the validation phases. The results obtained are promising and suggest that the proposed approach may be helpful for the optimization of deep learning models in other signal processing applications.

Objectives: The main purpose of this work was to clinically assess the oculomotricity of one hundred Mexican children with poor reading skills but without any specific learning disorder. Methods: The D.E.M. psychometric test was used. Sex and age analyses of the ratio, type, horizontal and vertical performance, and errors were carried out. Results: Our data suggest that 84% of poor readers exhibit oculomotor difficulties. Sex did not significantly influence the results (p > 0.05), whereas age was associated with the horizontal (p = 0.04) and vertical (p = 0.29) performance, as well as the number of errors (p = 0.001). Omissions were the most prevalent error type. Conclusions: This research gives insights into the role of oculomotricity in children with poor reading skills. Our results suggest that oculomotor performance should be included in the evaluation protocol to assess poor readers to identify any influence of the visual system.

This article presents two procedures involving a maximal hyperconnected function and a hyperconnected lower leveling to segment the brain in a magnetic resonance imaging T1 weighted using new openings on a max-tree structure. The openings are hyperconnected and are viscous transformations. The first procedure considers finding the higher hyperconnected maximum by using an increasing criterion that plays a central role during segmentation. The second procedure utilizes hyperconnected lower leveling, which acts as a marker, controlling the reconstruction process into the mask. As a result, the proposal allows an efficient segmentation of the brain to be obtained. In total, 38 magnetic resonance T1-weighted images obtained from the Internet Brain Segmentation Repository are segmented. The Jaccard and Dice indices are computed, compared, and validated with the efficiency of the Brain Extraction Tool software and other algorithms provided in the literature.