A self-adaptive synthetic over-sampling technique for imbalanced classification

Traditionally, in supervised machine learning, (a significant) part of the available data (usually 50%-80%) is used for training and the rest—for validation. In many problems, however, the data are highly imbalanced in regard to different classes or does not have good coverage of the feasible data space which, in turn, creates problems in validation and usage phase. In this paper, we propose a technique for synthesizing feasible and likely data to help balance the classes as well as to boost the performance in terms of confusion matrix as well as overall. The idea, in a nutshell, is to synthesize data samples in close vicinity to the actual data samples specifically for the less represented (minority) classes. This has also implications to the so-called fairness of machine learning. In this paper, we propose a specific method for synthesizing data in a way to balance the classes and boost the performance, especially of the minority classes. It is generic and can be applied to different base algorithms, for example, support vector machines, k-nearest neighbour classifiers deep neural, rule-based classifiers, decision trees, and so forth. The results demonstrated that (a) a significantly more balanced (and fair) classification results can be achieved and (b) that the overall performance as well as the performance per class measured by confusion matrix can be boosted. In addition, this approach can be very valuable for the cases when the number of actual available labelled data is small which itself is one of the problems of the contemporary machine learning.     

Crystallization of progesterone polymorphs using polymer-induced heteronucleation (PIHn) method

Progesterone is a natural hormone steroid used in humans for several treatments and in livestock for artificial insemination, which exhibits two polymorphic forms at ambient conditions: form 1 and form 2. Form 2 is metastable and more soluble than form 1; however, it is not suitable to use as powder raw material because it transforms into form 1 by the effects of grinding. A polymorphic screening of progesterone based on polymer-induced heteronucleation method was performed as an alternative to prepare the metastable form. Polyvinyl alcohol, hydroxypropyl methylcellulose (HPMC), dextran, gelatin, polyisoprene (PI) and acrylonitrile-butadiene (NBR) copolymer were used. Crystals were prepared from 0.5, 10 and 40?mg/mL solutions in acetone at room temperature by solvent evaporation. The samples were characterized by X-ray powder diffraction, differential scanning calorimetry (DSC), scanning electron microcopy and attenuated total reflectance infrared Fourier transform spectroscopy. Form 1 was nucleated from 40?mg/mL solutions on the six polymers and from 10?mg/mL solutions on PI and NBR. The mixture of form 1 and form 2 was obtained from 10?mg/mL solution on HPMC, dextran and gelatin and from 0.5?mg/mL solution crystallizations. Therefore, the polymeric devices, which crystallized the metastable and more soluble polymorph (2) of progesterone, would be a promissory alternative for the pharmaceutical applications.     

Effects of timing of formative feedback in computer-assisted learning environments

This study examines the effects of timing of corrective formative feedback on processing text information on question-answering. Undergraduate students read an expository text and answered questions in two attempts. Students were randomly assigned to a no feedback, immediate feedback and delayed feedback conditions. Students in the feedback conditions received feedback on the correctness of their answer after the first attempt and were informed about the right answer after the second attempt. Students were prompted to restudy the text after failing in their first attempt. However, students in the no feedback condition were just prompted to search the text. All students were tested on question-answering, corrective probability and a post-test cued-recall test. Results showed that: (a) feedback reduced the initial time reading the text; (b) feedback increased performance on question answering and cued-recall; (c) delayed feedback produced no advantages over immediate feedback. Theoretical and practical implications of these results are discussed.     

Capture of UAVs Through GPS Spoofing Using Low-Cost SDR Platforms

Wireless Personal Communications - The increased use of unmanned aerial vehicles (UAVs), better known as drones, by civilians has grown exponentially and their autonomous flight control systems...     

Double emulsions (W/O/W): physical characteristics and perceived intensity of salty taste

This study addressed the correlation between physical characteristics of double emulsions and sensory perception, as the microstructure of these systems may provide the mechanism to understanding the initial cause of the altered salty taste. Thus, double emulsions (W/O/W) were prepared using different volumes of the internal aqueous phase while maintaining the same fat and sodium contents in the evaluated systems. Polyglycerol polyricinoleate (PGPR) and tween 80 were used as hydrophobic and hydrophilic emulsifiers, respectively. After preparation, the samples were stored at 25 °C for 4 days and submitted to analysis of optical microscopy, distribution and polydispersity of the oil droplets size, electrical conductivity, rheological behaviour and sensorial analysis. It was found that the use of different emulsifier concentrations (PGPR) did not influence the physical characteristics of the emulsions with the same formulation, but emulsions with different internal aqueous phase concentrations presented different results. These distinct characteristics may have influenced sensorial perception, as the emulsion with higher internal phase concentration was considered saltier. Thus, it can be concluded that structural differences of the double emulsions can be used to decrease the sodium contents without perceivable changes in salty taste.     

Study of nanofiber scaffolds of PAA,PAA/CS,and PAA/ALG for its potential use in biotechnological applications

In recent times, electrospun nanofibers have been widely studied from several biotechnological approaches; in this work, poly(acrylic acid) (PAA) solutions mixed with chitosan and alginate were electrospun and characterized to determine the behavior of these fibers when used in combination with bacteria, different samples were incubated with the bacterial strains: Streptomyces spp., Micromonospora spp., and Escherichia coli and a OD600 test was performed. The formation of nanofibers via electrospinning and the physicochemical properties of the obtained fibers were evaluated. Results showed that the presence of chitosan enhanced the thermal stability of PAA, since PAA/alginate fibers lost 5% of their mass at 41°C, whereas PAA/chitosan lost this amount at around 125°C. The fibers demonstrated suitable characteristics to be used as a bacteria bioreactor.     

Antifungal and antimycotoxigenic effects of Zingiber officinale,Cinnamomum zeylanicum and Cymbopogon martinii essential oils against Fusarium verticillioides

ABSTRACT

There is an increasing demand for fungi control in grains, especially toxigenic. Also, there is growing concern on the use of synthetic fungicides; thus alternatives are needed. The aim of this study was to evaluate the antifungal and antimycotoxigenic action of essential oils (EOs) from Zingiber officinale, Cinnamomum zeylanicum and Cymbopogon martinii against Fusarium verticillioides, a spoilage and toxigenic fungus. Essential oils were first chemically characterised by gas chromatography coupled to mass spectrometry, and their antioxidant potential was measured by the DPPH, ABTS and FRAP methods. Minimum inhibitory concentration (MIC) and disc diffusion were used to assess antifungal activity. Scanning electron microscopy was used to evaluate morphological changes in the fungus. Antimycotoxigenic activity of the EOs against the production of fumonisin B₁ and B₂ by F. verticillioides was evaluated using ultra-high-performance liquid chromatography system. Z. officinale, C. zeylanicum and C. martinii EOs were predominantly composed by zingiberene and geranial; eugenol; and geraniol, respectively. All the EOs had high antioxidant power, especially that from C. zeylanicum. The MICs were 250, 500 and 2,000 µg mL^?1 for C. zeylanicum, C. martinii and Z. officinale EOs, respectively. Mycelial reduction of F. verticillioides was observed when EOs were used, and the lowest activity was detected in the Z. officinale EO. Overall, the tested EOs promoted structural damage to the fungal cell wall, decreased conidia size and mycelial reduction. Antimycotoxigenic evaluation of the EOs evidenced a significant reduction (p < .05) in the production of fumonisins B₁ and B₂ with all the EOs evaluated in the study. These results suggest that especially C. zeylanicum and C. martinii EOs are highly useful for controlling F. verticillioides and fumonisins production.