RESUMO
Over time, a myriad of applications have been generated for pattern classification algorithms. Several case studies include parametric classifiers such as the Multi-Layer Perceptron (MLP) classifier, which is one of the most widely used today. Others use non-parametric classifiers, Support Vector Machine (SVM), K-Nearest Neighbors (K-NN), Naïve Bayes (NB), Adaboost, and Random Forest (RF). However, there is still little work directed toward a new trend in Artificial Intelligence (AI), which is known as eXplainable Artificial Intelligence (X-AI). This new trend seeks to make Machine Learning (ML) algorithms increasingly simple and easy to understand for users. Therefore, following this new wave of knowledge, in this work, the authors develop a new pattern classification methodology, based on the implementation of the novel Minimalist Machine Learning (MML) paradigm and a higher relevance attribute selection algorithm, which we call dMeans. We examine and compare the performance of this methodology with MLP, NB, KNN, SVM, Adaboost, and RF classifiers to perform the task of classification of Computed Tomography (CT) brain images. These grayscale images have an area of 128 × 128 pixels, and there are two classes available in the dataset: CT without Hemorrhage and CT with Intra-Ventricular Hemorrhage (IVH), which were classified using the Leave-One-Out Cross-Validation method. Most of the models tested by Leave-One-Out Cross-Validation performed between 50% and 75% accuracy, while sensitivity and sensitivity ranged between 58% and 86%. The experiments performed using our methodology matched the best classifier observed with 86.50% accuracy, and they outperformed all state-of-the-art algorithms in specificity with 91.60%. This performance is achieved hand in hand with simple and practical methods, which go hand in hand with this trend of generating easily explainable algorithms.
RESUMO
Two nonamidated host defense peptides named Pin2[G] and FA1 were evaluated against three types of pathogenic bacteria: two (Staphylococcus aureus UPD13 and Pseudomonas aeruginosa UPD3) isolated from diabetic foot ulcer patients, and another (Salmonella enterica serovar Typhimurium [ATCC 14028]) from a commercial collection. In vitro experiments showed that the antimicrobial performance of the synthetic peptides Pin2[G] and FA1 was modest, although FA1 was more effective than Pin2[G]. In contrast, Pin2[G] had superior in vivo anti-infective activity to FA1 in rabbit wound infections by the diabetic foot ulcer pathogens S. aureus UPD13 and P. aeruginosa UPD3. Indeed, Pin2[G] reduced bacterial colony counts of both S. aureus UPD13 and P. aeruginosa UPD3 by >100,000-fold after 48 to 72 h on skin wounds of infected rabbits, while in similar infected wounds, FA1 had no major effects at 72 to 96 h of treatment. Ceftriaxone was equally effective versus Pseudomonas but less effective versus S. aureus infections. Additionally, the two peptides were evaluated in mice against intragastrically inoculated S. enterica serovar Typhimurium (ATCC 14028). Only Pin2[G] at 0.56 mg/kg was effective in reducing systemic (liver) infection by >67-fold, equivalent to the effect of treatment with levofloxacin. Pin2[G] showed superior immunomodulatory activity in increasing chemokine production by a human bronchial cell line and suppressing polyinosinic-polycytidylic acid (poly[I:C])-induced proinflammatory IL-6 production. These data showed that the in vitro antimicrobial activity of these peptides was not correlated with their in vivo anti-infective activity and suggest that other factors such as immunomodulatory activity were more important.
Assuntos
Peptídeos Catiônicos Antimicrobianos , Infecções Estafilocócicas , Animais , Antibacterianos/farmacologia , Antibacterianos/uso terapêutico , Peptídeos Catiônicos Antimicrobianos/farmacologia , Humanos , Camundongos , Pseudomonas aeruginosa , Coelhos , Infecções Estafilocócicas/tratamento farmacológico , Staphylococcus aureusRESUMO
Habanero pepper production was assessed with drip irrigation and plastic mulch, based on two transplanting dates. The objectives of the study were: (i) to evaluate the effect of two transplanting dates and the use of plastic mulch on water productivity and habanero pepper fruit yield under drip irrigation conditions; and (ii) to determine the profitability and economic viability of the product in the regional market. The work was conducted in the municipality of Huimanguillo, state of Tabasco, Mexico, in loam soils classified as Eutric Fluvisol. The Jaguar variety of habanero pepper, developed by INIFAP and possessing better genetic and productive characteristics, was used. Two transplanting dates were studied, (i) 30 January 2013 and (ii) 15 February 2013, with and without plastic mulch. The conclusions were: (i) application of irrigation depths based on crop evapotranspiration (ETc) and plastic mulch transplanted on 30 January increased the fruit yield of the crop and improved the benefit-cost ratio of the production system; and (ii) water use efficiency based on the 30 January transplanting date was 8.68 kg m⻳ of water applied with plastic mulch, 6.51 kg m⻳ without plastic mulch, and 3.65 kg m⻳ for the 15 February transplanting date with plastic mulch.