Machine learning in the medical area has become a very important requirement. The healthcare professional needs useful tools to diagnose medical illnesses. Classifiers are important to provide tools that can be useful to the health professional for this purpose. However, questions arise: which classifier to use? What metrics are appropriate to measure the performance of the classifier? How to determine a good distribution of the data so that the classifier does not bias the medical patterns to be classified in a particular class? Then most important question: does a classifier perform well for a particular disease? This paper will present some answers to the questions mentioned above, making use of classification algorithms widely used in machine learning research with datasets relating to medical illnesses under the supervised learning scheme. In addition to state-of-the-art algorithms in pattern classification, we introduce a novelty: the use of meta-learning to determine, a priori, which classifier would be the ideal for a specific dataset. The results obtained show numerically and statistically that there are reliable classifiers to suggest medical diagnoses. In addition, we provide some insights about the expected performance of classifiers for such a task.

Tinnitus is the perception of sound in the absence of any external acoustic stimulation. Transcranial direct current stimulation (tDCS) has shown promising though heterogeneous therapeutic outcomes for tinnitus. The present study aims to review the recent advances in applications of tDCS for tinnitus treatment. In addition, the clinical efficacy and main mechanisms of action of tDCS on suppressing tinnitus are discussed. The study was performed in accordance with the PRISMA guidelines. The databases of the PubMed (1980–2018), Embase (1980–2018), PsycINFO (1850–2018), CINAHL, Web of Science, BIOSIS Previews (1990–2018), Cambridge Scientific Abstracts (1990–2018), and google scholar (1980–2018) using the set search terms. The date of the most recent search was 20 May, 2018. The randomized controlled trials that have assessed at least one therapeutic outcome measured before and after tDCS intervention were included in the final analysis. Different tDCS protocols were used for tinnitus ranging single to repeated sessions (up to 10) consisting of daily single session of 15 to 20-min and current intensities ranging 1–2 mA. Dorsolateral prefrontal cortex (DLPFC) and auditory cortex are the main targets of stimulation. Both single and repeated sessions showed moderate to significant treatment effects on tinnitus symptoms. In addition to improvements in tinnitus symptoms, the tDCS interventions particularly bifrontal DLPFC showed beneficial outcomes on depression and anxiety comorbid with tinnitus. Heterogeneities in the type of tinnitus, tDCS devices, protocols, and site of stimulation made the systematic reviews of the literature difficult. However, the current evidence shows that tDCS can be developed as an adjunct or complementary treatment for intractable tinnitus. TDCS may be a safe and cost-effective treatment for tinnitus in the short-term application. The current literature shows moderate to significant therapeutic efficacy of tDCS on tinnitus symptoms. Further randomized placebo-controlled double-blind trials with large sample sizes are needed to reach a definitive conclusion on the efficacy of tDCS for tinnitus. Future studies should further focus on developing efficient disease- and patient-specific protocols.

People with severe disabilities require assistance to perform their routine activities; a Human–Machine Interface (HMI) will allow them to activate devices that respond according to their needs. In this work, an HMI based on electrooculography (EOG) is presented, the instrumentation is placed on portable glasses that have the task of acquiring both horizontal and vertical EOG signals. The registration of each eye movement is identified by a class and categorized using the one hot encoding technique to test precision and sensitivity of different machine learning classification algorithms capable of identifying new data from the eye registration; the algorithm allows to discriminate blinks in order not to disturb the acquisition of the eyeball position commands. The implementation of the classifier consists of the control of a three-wheeled omnidirectional robot to validate the response of the interface. This work proposes the classification of signals in real time and the customization of the interface, minimizing the user’s learning curve. Preliminary results showed that it is possible to generate trajectories to control an omnidirectional robot to implement in the future assistance system to control position through gaze orientation.

This paper introduces a new method of compressing digital images by using the Difference Transform applied in medical imaging. The Difference Transform algorithm performs the decorrelation process of image data, and in this way improves the encoding process, achieving a file with a smaller size than the original. The proposed method proves to be competitive and in many cases better than the standards used for medical images such as TIFF or PNG. In addition, the Difference Transform can replace other transforms like Cosine or Wavelet.

The scaling of Raceway bioreactors was studied by geometric and mechanical similarity, with an order of magnitude of 1:10. The hydrodynamic parameters involved (flow velocity, hydrodynamic stress or shear stress, dimensionless numbers of Re, Fr, and Euler Power) at different stirring speeds (30, 35, 40, and 45 rpm) were determined. The study, carried out using low-density particle imaging velocimetry (PIV), showed that the speed of the liquid medium remains above 30 cm/s from 30 rpm, which ensures turbulence in the system. The flow velocity suffers a decrease of approximately 18%, at different angular velocities, with similar biomass concentrations (3.24 × 10⁵–3.72 × 10⁵ cells/mL). This decrease in speed directly affects the values of all the parameters involved in the bioreactor. Furthermore, the measurement of hydrodynamic stress (τ) indicates that the microorganisms are exposed to a value of 0.299 Pa at 35 rpm and 0.370 Pa at 40 rpm. Due to mechanical agitation, hydrodynamic stress values in Raceway systems have not been previously reported. The studies were carried out in a 10 L Raceway bioreactor using a consortium of microalgae and cyanobacteria where Spirulina sp. and Pseudanabaena sp. predominate.

Associative memories in min and max algebra are of great interest for pattern recognition. One property of these is that they are one-shot, that is, in an attempt they converge to the solution without having to iterate. These memories have proven to be very efficient, but they manifest some weakness with mixed noise. If an appropriate kernel is not used, that is, a subset of the pattern to be recalled that is not affected by noise, memories fail noticeably. A possible problem for building kernels with sufficient conditions, using binary and gray-scale images, is not knowing how the noise is registered in these images. A solution to this problem is presented by analyzing the behavior of the acquisition noise. What is new about this analysis is that, noise can be mapped to a distance obtained by a distance transform. Furthermore, this analysis provides the basis for a new model of min heteroassociative memory that is robust to the acquisition/mixed noise. The proposed model is novel because min associative memories are typically inoperative to mixed noise. The new model of heteroassocitative memory obtains very interesting results with this type of noise.