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.     

Cathode plasma electrolytic deposition of Al2O3 coatings doped with SiC particles

Semiconductor particles doped Al₂O₃ coatings were prepared by cathode plasma electrolytic deposition in Al(NO₃)₃ electrolyte dispersed with SiC micro- and nano-particles (average particle sizes of 0.5–1.7?µm and 40?nm respectively). The effects of the concentrations and particle sizes of the SiC on the microstructures and tribological performances of the composite coatings were studied. In comparison with the case of dispersing with SiC microparticles, the dispersion of SiC nanoparticles in the coatings was more uniform. When the concentration of SiC nanoparticles was 5?g/L, the surface roughness of the composite coating was reduced by 63%, compared with that of the unmodified coating. Friction results demonstrated that the addition of 5?g/L SiC nanoparticles reduced the friction coefficient from 0.60 to 0.38 and decreased the wear volume under dry friction. The current density and bath voltage were measured to analyze the effects of SiC particles on the deposition process. The results showed that the SiC particles could alter the electrical behavior of the coatings during the deposition process, weaken the bombardment of the plasma, and improve the structures of the coatings.     

Achieving Rich and Active Alkaline Hydrogen Evolution Heterostructures via Interface Engineering on 2D 1T‐MoS2 Quantum Sheets

Large‐scale production of hydrogen from water‐alkali electrolyzers is impeded by the sluggish kinetics of hydrogen evolution reaction (HER) electrocatalysts. The hybridization of an acid‐active HER catalyst with a cocatalyst at the nanoscale helps boost HER kinetics in alkaline media. Here, it is demonstrated that 1T–MoS₂ nanosheet edges (instead of basal planes) decorated by metal hydroxides form highly active ${\text{edge}}_{{\text{1T‐MoS}}_{\text{2}}}$/ ${\text{edge}}_{\text{Ni}{(\text{OH})}_{\text{2}}}$ heterostructures, which significantly enhance HER performance in alkaline media. Featured with rich ${\text{edge}}_{{\text{1T‐MoS}}_{\text{2}}}$/ ${\text{edge}}_{\text{Ni}{(\text{OH})}_{\text{2}}}$ sites, the fabricated 1T–MoS₂ QS/Ni(OH)₂ hybrid (quantum sized 1T–MoS₂ sheets decorated with Ni(OH)₂ via interface engineering) only requires overpotentials of 57 and 112 mV to drive HER current densities of 10 and 100 mA cm^?2, respectively, and has a low Tafel slope of 30 mV dec^?1 in 1 m KOH. So far, this is the best performance for MoS₂‐based electrocatalysts and the 1T–MoS₂ QS/Ni(OH)₂ hybrid is among the best‐performing non‐Pt alkaline HER electrocatalysts known. The HER process is durable for 100 h at current densities up to 500 mA cm^?2. This work not only provides an active, cost‐effective, and robust alkaline HER electrocatalyst, but also demonstrates a design strategy for preparing high‐performance catalysts based on edge‐rich 2D quantum sheets for other catalytic reactions.     

In Silico Analysis and Experimental Validation of Active Compounds from Cichorium intybus L. Ameliorating Liver Injury

This study aimed at investigating the possible mechanisms of hepatic protective activity of Cichorium intybus L. (chicory) in acute liver injury. Pathological observation, reactive oxygen species (ROS) detection and measurements of biochemical indexes on mouse models proved hepatic protective effect of Cichorium intybus L. Identification of active compounds in Cichorium intybus L. was executed through several methods including ultra performance liquid chromatography/time of flight mass spectrometry (UPLC-TOF-MS). Similarity ensemble approach (SEA) docking, molecular modeling, molecular docking, and molecular dynamics (MD) simulation were applied in this study to explore possible mechanisms of the hepato-protective potential of Cichorium intybus L. We then analyzed the chemical composition of Cichorium intybus L., and found their key targets. Furthermore, in vitro cytological examination and western blot were used for validating the efficacy of the selected compounds. In silico analysis and western blot together demonstrated that selected compound 10 in Cichorium intybus L. targeted Akt-1 in hepatocytes. Besides, compound 13 targeted both caspase-1 and Akt-1. These small compounds may ameliorate liver injury by acting on their targets, which are related to apoptosis or autophagy. The conclusions above may shed light on the complex molecular mechanisms of Cichorium intybus L. acting on hepatocytes and ameliorating liver injury.     

Combined effects of wheat gluten and carboxymethylcellulose on dough rheological behaviours and gluten network of potato–wheat flour-based bread

Incorporating high level of potato flour into wheat flour enhances nutritional values of bread but induces a series of problems that lead to the decline of the bread quality. To overcome the barrier, wheat gluten and carboxymethylcellulose (CMC) were added into potato–wheat composite flour to improve dough machinability and bread quality. The rheological properties, thermo-mechanical properties and microstructures of dough were investigated. The results showed that the interaction between gluten and CMC mitigated the discontinuity of gluten matrix and gluten protein aggregation caused by the addition of potato flour, which yielded a more branched and compact gluten network. The compact three-dimensional viscoelastic structure induced improvements of gas retention capacity and dough stability, making it mimic the machinability properties of wheat flour dough. Bread qualities were apparently improved with the combined use of 4% gluten and 6% CMC, of which specific volume increased by 42.86%, and simultaneously, hardness reduced by 75.93%.