This paper proposes a deep learning model based on an artificial neural network with a single hidden layer for predicting the diagnosis of multiple sclerosis. The hidden layer includes a regularization term that prevents overfitting and reduces the model complexity. The purposed learning model achieved higher prediction accuracy and lower loss than four conventional machine learning techniques. A dimensionality reduction method was used to select the most relevant features from 74 gene expression profiles for training the learning models. The analysis of variance test was performed to identify the statistical difference between the mean of the proposed model and the compared classifiers. The experimental results show the effectiveness of the proposed artificial neural network.

Breast cancer is one of the diseases of most profound concern, with the most prevalence worldwide, where early detections and diagnoses play the leading role against this disease achieved through imaging techniques such as mammography. Radiologists tend to have a high false positive rate for mammography diagnoses and an accuracy of around 82%. Currently, deep learning (DL) techniques have shown promising results in the early detection of breast cancer by generating computer-aided diagnosis (CAD) systems implementing convolutional neural networks (CNNs). This work focuses on applying, evaluating, and comparing the architectures: AlexNet, GoogLeNet, Resnet50, and Vgg19 to classify breast lesions after using transfer learning with fine-tuning and training the CNN with regions extracted from the MIAS and INbreast databases. We analyzed 14 classifiers, involving 4 classes as several researches have done it before, corresponding to benign and malignant microcalcifications and masses, and as our main contribution, we also added a 5th class for the normal tissue of the mammary parenchyma increasing the correct detection; in order to evaluate the architectures with a statistical analysis based on the received operational characteristics (ROC), the area under the curve (AUC), F1 Score, accuracy, precision, sensitivity, and specificity. We generate the best results with the CNN GoogLeNet trained with five classes on a balanced database with an AUC of 99.29%, F1 Score of 91.92%, the accuracy of 91.92%, precision of 92.15%, sensitivity of 91.70%, and specificity of 97.66%, concluding that GoogLeNet is optimal as a classifier in a CAD system to deal with breast cancer.

The objective of this work is to design and implement a scalable Field-Programmable Gate Array (FPGA)-based motion control system for DC servo motors using a parabolic velocity profile for industrial applications. The implementation in this device allows the obtaining of a fast, flexible and low-cost system. The system is divided into control, communication and closed-loop coupling. The work also addresses a comparative analysis of the most used profiles, the trapezoidal and parabolic. The comparison is made considering the energy consumption of both profiles. As a consequence of the comparison made, the velocity profile can be selected to reduce production costs by saving energy and reducing wear on machinery. The discrete models of the velocity profiles are obtained through numerical methods that permit the control blocks to be implemented in an FPGA. To reduce maintenance costs and energy consumption in servo mechanisms, the derivation of the acceleration or jerk of the motor is shown. A Graphic User Interface (GUI) is presented, which allows monitoring the position, velocity and angular acceleration of the motor shaft. In addition, the developed interface supports modification of parameters of the final position and maximum velocity in the motor. The delivered current is compared, evaluating its decrease using a parabolic velocity profile. Finally, the experimental results are illustrated.

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.

The direct integration of paper-based microfluidic fuel cells (μFC’s) toward creating autonomous lateral flow assays has attracted attention. Here, we show that an air-breathing paper-based μFC could be used as a power supply in pregnancy tests by oxidizing the human urine used for the diagnosis. We present an air-breathing paper-based μFC connected to a pregnancy test, and for the first time, as far as we know, it is powered by human urine without needing any external electrolyte. It uses TiO${}_2$-Ni as anode and Pt/C as cathode; the performance shows a maximum value of voltage and current and power densities of ∼0.96 V, 1.00 mA cm${}^{-2}$, and 0.23 mW cm${}^{-2}$, respectively. Furthermore, we present a simple design of a paper-based μFC’s stack powered with urine that shows a maximum voltage and maximum current and power densities of ∼1.89 V, 2.77 mA cm${}^{-2}$ and 1.38 mW cm${}^{-2}$, respectively, which powers the display of a pregnancy test allowing to see the analysis results.

In the last decade, there has been an increasing interest in the role of space in the learning process. However, there is limited research about how different Learning Spaces (LS) can lead to Sustainable Development (SD). Therefore, this paper presents a systematic literature review aimed to identify how physical, virtual, and hybrid LS have been designed and used to support SD. From an initial sample of 204 articles between 2009 and 2021 found in the Scopus database, 33 were included after inclusion criteria were applied. Findings show a wide variety of focus in the uses of LS (e.g., promote education quality, accessibility, or environmental sustainability). In general, the design process of LS implies a top-bottom approach, where students remain as passive actors. Nevertheless, it has been identified a growing interest in codesign processes that promote broader participation and bottom-top perspectives. This study contributes to orientate the understanding of the concept of LS, and looks towards inspiring new teaching and learning practices.