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.     

Evolving an Accurate Decision Tree-Based Model for Predicting Carbon Dioxide Solubility in Polymers

Solubility is one of the most indispensable physicochemical properties determining the compatibility of components of a blending system. Research has been focused on the solubility of carbon dioxide in polymers as a significant application of green chemistry. To replace costly and time-consuming experiments, a novel solubility prediction model based on a decision tree, called the stochastic gradient boosting algorithm, was proposed to predict CO₂ solubility in 13 different polymers, based on 515 published experimental data lines. The results indicate that the proposed ensemble model is an effective method for predicting the CO₂ solubility in various polymers, with highly satisfactory performance and high efficiency. It produces more accurate outputs than other methods such as machine learning schemes and an equation of state approach.     

Lipase‐catalyzed synthesis of aliphatic poly(β‐thioether ester) with various methylene group contents: thermal properties,crystallization and degradation

A series of novel aliphatic poly(β‐thioether ester)s with various methylene group contents were prepared by direct lipase‐catalyzed polycondensation of the monomer with an acid‐labile β‐thiopropionate group. The polycondensation reaction using immobilized lipase B from Candida antarctica was carried out in diphenyl ether at 90 °C. Poly(β‐thioether ester)s with high molecular weights of 20 500–57 000 Da and narrow polydispersities in the range 1.40–1.48 were obtained. Thermogravimetric analysis, differential scanning calorimetry and wide‐angle X‐ray diffraction were used to investigate the thermal properties and crystal structures of these polyesters. All the poly(β‐thioether ester)s were semicrystalline polymers and thermally stable up to at least 200 °C. In vitro degradation studies showed that they can rapidly degrade under acidic conditions by the hydrolysis of the β‐thiopropionate groups, suggesting their potential as acid‐degradable polymeric materials. © 2019 Society of Chemical Industry     

A gradient boosting decision tree approach for insider trading identification: An empirical model evaluation of China stock market

Insider trading is a kind of criminal behavior in stock market by using nonpublic information. In recent years, it has become the major illegal activity in China’s stock market. In this study, a combination approach of GBDT (Gradient Boosting Decision Tree) and DE (Differential Evolution) is proposed to identify insider trading activities by using data of relevant indicators. First, insider trading samples occurred from year 2007 to 2017 and corresponding non-insider trading samples are collected. Next, the proposed method is trained by the GBDT, and initial parameters of the GBDT are optimized by the DE. Finally, out-of-samples are classified by the trained GBDT–DE model and its performances are evaluated. The experiment results show that our proposed method performed the best for insider trading identification under time window length of ninety days, indicating the relevant indicators under 90-days time window length are relatively more useful. Additionally, under all three time window lengths, relative importance result shows that several indicators are consistently crucial for insider trading identification. Furthermore, the proposed approach significantly outperforms other benchmark methods, demonstrating that it could be applied as an intelligent system to improve identification accuracy and efficiency for insider trading regulation in China stock market.     

Site-Specific PEGylation of Therapeutic Proteins

The use of proteins as therapeutics has a long history and is becoming ever more common in modern medicine. While the number of protein-based drugs is growing every year, significant problems still remain with their use. Among these problems are rapid degradation and excretion from patients, thus requiring frequent dosing, which in turn increases the chances for an immunological response as well as increasing the cost of therapy. One of the main strategies to alleviate these problems is to link a polyethylene glycol (PEG) group to the protein of interest. This process, called PEGylation, has grown dramatically in recent years resulting in several approved drugs. Installing a single PEG chain at a defined site in a protein is challenging. Recently, there is has been considerable research into various methods for the site-specific PEGylation of proteins. This review seeks to summarize that work and provide background and context for how site-specific PEGylation is performed. After introducing the topic of site-specific PEGylation, recent developments using chemical methods are described. That is followed by a more extensive discussion of bioorthogonal reactions and enzymatic labeling.     

Aqueous One-pot Synthesis of Glycopolymers by Glycosidase-catalyzed Glycomonomer Synthesis Using 4,6-Dimetoxy Triazinyl Glycoside Followed by Radical Polymerization

Glycopolymers have attracted increased attention as functional polymeric materials, and simple methods for synthesizing glycopolymers remain needed. This paper reports the aqueous one-pot and chemoenzymatic synthesis of four types of glycopolymers via two reactions: the β-galactosidase-catalyzed glycomonomer synthesis using 4,6-dimetoxy triazinyl β-D-galactopyranoside and hydroxy group-containing (meth)acrylamide and (meth)acrylate derivatives as the activated glycosyl donor substrate and as the glycomonomer precursors, respectively, followed by radical copolymerization of the resulting glycomonomer and excess glycomonomer precursor without isolating the glycomonomers. The resulting glycopolymers bearing galactose moieties exhibited specific and strong interactions with the lectin peanut agglutinin as glycoclusters.     

浅谈酶在非接触印刷废纸脱墨中的应用

简要地介绍了纤维素酶、半纤维素酶和淀粉酶在非接触印刷废纸脱墨中的研究及其应用