Tabular data: Deep learning is not all you need

A key element in solving real-life data science problems is selecting the types of models to use. Tree ensemble models (such as XGBoost) are usually recommended for classification and regression problems with tabular data. However, several deep learning models for tabular data have recently been proposed, claiming to outperform XGBoost for some use cases. This paper explores whether these deep models should be a recommended option for tabular data by rigorously comparing the new deep models to XGBoost on various datasets. In addition to systematically comparing their performance, we consider the tuning and computation they require. Our study shows that XGBoost outperforms these deep models across the datasets, including the datasets used in the papers that proposed the deep models. We also demonstrate that XGBoost requires much less tuning. On the positive side, we show that an ensemble of deep models and XGBoost performs better on these datasets than XGBoost alone.     

Nanoraspberry-like palladium/spongy nickel oxide for electrooxidation of five light fuels

The spongy nickel oxide (SNO) was synthesized the solution combustion method. The SNO was selected as a promoter to boost the catalytic activity of nanoraspberry-like palladium (NRPd) toward electrooxidation of five light fuels (LFs): methanol, ethanol, formaldehyde, formic acid, and ethylene glycol. The X-ray powder diffraction, Fourier-transform infrared spectroscopy (FT-IR), scanning electron microscopy, and field emission scanning electron microscope techniques were used for the materials characterization. In comparison with nonpromoted Pd, the NRPd-SNO electrocatalyst shown an excellent efficiency in parameters like the electrochemical active surface area and anti-CO poisoning behavior. The turnover data and the parameters, including reaction order, activation energy, and the coefficients of electron transfer and diffusion, were evaluated for the each process of LFs electrooxidation. The outcome for NRPd-SNO activity toward LFs electrooxidation was compared to some reported electrodes. The SNO increases the removal of intermediates created in the oxidation of LFs that can poison the surface of palladium catalyst. This is due to the presence of the lattice oxygens in SNO structure and Ni switching between its high and low valances. The compatibility of the adsorption process of LFs on the surface of the NRPd-SNO catalyst with different isotherms was determined by studying the Tafel polarization and calculating the surface coverage.     

Nano fibrillated cellulose-based foam by Pickering emulsion: Preparation,characterizations, and application as dye adsorbent

An ecofriendly and biodegradable porous structure was prepared from drying aqueous foams based on nano fibrillated cellulose (NFC), extracted from softwood pulp by subcritical water/CO₂ treatment (SC-NFC). The primary aim of this work was to use the modified SC-NFC as stabilizer for a water-based Pickering emulsion which upon drying, yielded porous cellulosic materials, a good dye adsorbent. In order to exploit the carboxymethylated SC-NFC (CMSC-NFC, with a degree of substitution of 0.35 and a charge density of 649 μeqv/g) as a stabilizer for water-based Pickering emulsion in subsequent step, an optimized quantity of octyl amine (30 mg/g of SC-NFC) was added to make them partially hydrophobic. A series of dry foam structures were prepared by varying the concentrations of treated CMSC-NFCs and 4 wt% was found to be the optimum concentration to yield foam with high porosity (99%) and low density (0.038 g/cc) along with high compression strength (0.24 MPa), superior to the conventionally extracted NFC. The foams were applied to capture as high as 98% of methylene blue dyes, making them a potential green candidate for treating industrial effluent. In addition, the dye adsorption kinetics and isotherms were found to be well suited with second order kinetics and Langmuir isotherm models.     

Synthesis of thermoresponsive copolymer/silica-coated magnetite nanoparticle composite and its application for heavy metal ion recovery

To enhance chemical stability and suppress of aggregation of magnetite nanoparticles (MNPs), which are used as a support for thermoresponsive copolymer immobilization, silica coating of the MNPs is applied via the electrooxidation method. Although the resulting silica coated-MNPs also formed aggregates, the size distribution of the aggregate shifted to smaller size range. Because of that, the surface area available for copolymer immobilization increased approximately 6.7 times at maximum as compared with that of the uncoated MNPs. It contributed to the increase of the amount of the immobilized copolymer on the silica-coated MNPs, which is approximately four times larger than that on the uncoated MNPs. Fe₃O₄ dissolution test confirmed enhancement of chemical stability of MNPs. The thermoresponsive copolymer immobilized on the silica-coated MNPs shows the ability to recycle Cu(II) ion from Cu(II) containing solution by changing temperature with significantly shorter time than those in other thermoresponsive adsorbents in gel form.     

Marine Phospholipids from Fishery By-Products Attenuate Atherosclerosis

In this study, the anti-atherosclerotic properties of three marine phospholipids (MPLs) extracts from fishery by-products including codfish roe, squid gonad, and shrimp head are verified. Their effects on key factors involved in atherosclerosis are examined and compared to explore whether the differences in their constitutions lead to the differences in the function. All three MPLs dampen oxidation of low- density lipoproteins (LDL) in vitro. Treating RAW264.7 macrophages and HUVECs endothelial cells with each MPLs ranging 10–100 µg mL⁻¹ does not decrease cell viability, yet ox-LDL caused cytotoxicity of both cells are alleviated by 50 or 100 µg mL⁻¹ MPLs treatment. In addition, the three MPLs reduce ox-LDL induced macrophage foam-like transition, mainly through inhibition of lipid uptake. Of the three MPLs, the one from squid gonad exhibits the best effect. On the other hand, all three MPLs modulate inflammatory responses, equally, by inhibiting the adhesion of monocytes to endothelial cells, and decreasing secretion of pro-inflammatory cytokines IL-6 and MCP-1. Using a high-cholesterol diet induced zebrafish model, it is found that all three MPLs, especially the one from squid gonad, alleviates cholesterol accumulation in early plaques, and decreases total cholesterol as well as lipid peroxide in vivo. Practical Applications: As a way of making the best of the increasingly scarce marine resources, valuable lipid components can be recovered from by-products and wastes from the fishery industry. Here, we tested the anti-atherosclerotic effects and the mechanisms of three MPLs extracted from codfish roe, squid gonad, and shrimp head. Our study provides further evidence that marine phospholipids extracted from fishery by-products could protect against atherosclerosis, and helps to elucidate the structure-function relationship of MPLs.     

Development of silica based organic slurries for stereolithographic printing process

In this study, silica based slurries for stereolithographic printing of glass structures are developed and characterized. Stereolithography has the potential to print complex structures with high resolution. Therefore, acrylate based photocurable slurries have been developed and their viscosities are examined as a function of the solid loading. A critical shear rate can be derived, which must not be exceeded during the printing process. Therefore, rheological characterizations provide important insights into the printing process and the ability to produce samples with precise structures. Other properties such as polymerization time and curability kinetic were investigated with time dependent attenuated total reflection infrared spectroscopy (ATR-IR). Afterwards, the slurries were printed on a commercial printer operating with visible light. For debinding the printed green bodies, the decomposition temperatures were derived from thermogravimetric analysis in order to obtain stable and transparent samples.     

Soft sensor for real-time cement fineness estimation

This paper describes the design and implementation of soft sensors to estimate cement fineness. Soft sensors are mathematical models that use available data to provide real-time information on process variables when the information, for whatever reason, is not available by direct measurement. In this application, soft sensors are used to provide information on process variable normally provided by off-line laboratory tests performed at large time intervals. Cement fineness is one of the crucial parameters that define the quality of produced cement. Providing real-time information on cement fineness using soft sensors can overcome limitations and problems that originate from a lack of information between two laboratory tests. The model inputs were selected from candidate process variables using an information theoretic approach. Models based on multi-layer perceptrons were developed, and their ability to estimate cement fineness of laboratory samples was analyzed. Models that had the best performance, and capacity to adopt changes in the cement grinding circuit were selected to implement soft sensors. Soft sensors were tested using data from a continuous cement production to demonstrate their use in real-time fineness estimation. Their performance was highly satisfactory, and the sensors proved to be capable of providing valuable information on cement grinding circuit performance. After successful off-line tests, soft sensors were implemented and installed in the control room of a cement factory. Results on the site confirm results obtained by tests conducted during soft sensor development.     

Questioning numerical integration methods for microsphere (and microplane) constitutive equations

In the last few years, more and more complex microsphere models have been proposed to predict the mechanical response of various polymers. Similarly than for microplane models, they consist in deriving a one-dimensional force vs. stretch equation and to integrate it over the unit sphere to obtain a three-dimensional constitutive equation. In this context, the focus of authors is laid on the physics of the one-dimensional relationship, but in most of the case the influence of the integration method on the prediction is not investigated.Here we compare three numerical integration schemes: a classical Gaussian scheme, a method based on a regular geometric meshing of the sphere, and an approach based on spherical harmonics. Depending on the method, the number of integration points may vary from 4 to 983,040! Considering simple quantities, i.e. principal (large) strain invariants, it is shown that the integration method must be carefully chosen. Depending on the quantities retained to described the one-dimensional equation and the required error, the performances of the three methods are discussed. Consequences on stress–strain prediction are illustrated with a directional version of the classical Mooney–Rivlin hyperelastic model. Finally, the paper closes with some advices for the development of new microsphere constitutive equations.