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.     

Data fusion and transfer learning empowered granular trust evaluation for Internet of Things

In the Internet of Things (IoT), a huge amount of valuable data is generated by various IoT applications. As the IoT technologies become more complex, the attack methods are more diversified and can cause serious damages. Thus, establishing a secure IoT network based on user trust evaluation to defend against security threats and ensure the reliability of data source of collected data have become urgent issues, in this paper, a Data Fusion and transfer learning empowered granular Trust Evaluation mechanism (DFTE) is proposed to address the above challenges. Specifically, to meet the granularity demands of trust evaluation, time–space empowered fine/coarse grained trust evaluation models are built utilizing deep transfer learning algorithms based on data fusion. Moreover, to prevent privacy leakage and task sabotage, a dynamic reward and punishment mechanism is developed to encourage honest users by dynamically adjusting the scale of reward or punishment and accurately evaluating users’ trusts. The extensive experiments show that: (i) the proposed DFTE achieves high accuracy of trust evaluation under different granular demands through efficient data fusion; (ii) DFTE performs excellently in participation rate and data reliability.     

Real-world single image super-resolution: A brief review

Single image super-resolution (SISR), which aims to reconstruct a high-resolution (HR) image from a low-resolution (LR) observation, has been an active research topic in the area of image processing in recent decades. Particularly, deep learning-based super-resolution (SR) approaches have drawn much attention and have greatly improved the reconstruction performance on synthetic data. However, recent studies show that simulation results on synthetic data usually overestimate the capacity to super-resolve real-world images. In this context, more and more researchers devote themselves to develop SR approaches for realistic images. This article aims to make a comprehensive review on real-world single image super-resolution (RSISR). More specifically, this review covers the critical publicly available datasets and assessment metrics for RSISR, and four major categories of RSISR methods, namely the degradation modeling-based RSISR, image pairs-based RSISR, domain translation-based RSISR, and self-learning-based RSISR. Comparisons are also made among representative RSISR methods on benchmark datasets, in terms of both reconstruction quality and computational efficiency. Besides, we discuss challenges and promising research topics on RSISR.     

A data-driven digital-twin prognostics method for proton exchange membrane fuel cell remaining useful life prediction

Prognostics and health management of proton exchange membrane fuel cell (PEMFC) systems have driven increasing research attention in recent years as the durability of PEMFC stack remains as a technical barrier for its large-scale commercialization. To monitor the health state during PEMFC operation, digital twin (DT), as a smart manufacturing technique, is applied in this paper to establish an ensemble remaining useful life prediction system. A data-driven DT is constructed to integrate the physical knowledge of the system and a deep transfer learning model based on stacked denoising autoencoder is used to update the DT with online measurement. A case study with experimental PEMFC degradation data is presented where the proposed data-driven DT prognostics method has applied and reached a high prediction accuracy. Furthermore, the predicted results are proved to be less affected even with limited measurement data.     

Nanogrooved carbon microtubes for wet three‐dimensional printing of conductive composite structures

Recent advances in three‐dimensional (3D) printing have enabled the fabrication of interesting structures which are not achievable using traditional fabrication approaches. The 3D printing of carbon microtube composite inks allows fabrication of conductive structures for practical applications in soft robotics and tissue engineering. However, it is challenging to achieve 3D printed structures from solution‐based composite inks, which requires an additional process to solidify the ink. Here, we introduce a wet 3D printing technique which uses a coagulation bath to fabricate carbon microtube composite structures. We show that through a facile nanogrooving approach which introduces cavitation and channels on carbon microtubes, enhanced interfacial interactions with a chitosan polymer matrix are achieved. Consequently, the mechanical properties of the 3D printed composites improve when nanogrooved carbon microtubes are used, compared to untreated microtubes. We show that by carefully controlling the coagulation bath, extrusion pressure, printing distance and printed line distance, we can 3D print composite lattices which are composed of well‐defined and separated printed lines. The conductive composite 3D structures with highly customised design presented in this work provide a suitable platform for applications ranging from soft robotics to smart tissue engineering scaffolds. © 2019 Society of Chemical Industry     

Deep eutectic solvent-based supramolecular gel polymer electrolytes for high-performance electrochemical double layer capacitors

Gel polymer electrolytes (GPEs) can avoid the electrolyte leakage risk of electrochemical double layer capacitors (EDLCs). But aqueous GPEs often suffer from narrow electrochemical windows. Herein, a series of deep eutectic solvent (DES)-based supramolecular GPEs are firstly developed for carbon-based EDLCs with wide voltage windows. The as-fabricated DES-based GPE shows an ionic conductivity of ~58 mS cm^?1, which makes the stable voltage window of a carbon-based EDLC reach 2.4 V. The carbon-based EDLC exhibits a specific capacitance of 32.1 F g^?1, an energy density of 24.6 Wh kg^?1 and a capacitance retention of ~90% after 15,000 charge-discharge cycles. Moreover, when quinhydrone is added into the DES-based GPE, the specific capacitance and energy density of the corresponding EDLC can be further expanded to 60 F g^?1 and 43.6 Wh kg^?1, respectively. Therefore, our work may present a universal strategy to prepare novel supramolecular GPEs for high-performance EDLCs with wide voltage windows.     

Competitive growth of Al2O3/YAG/ZrO2 eutectic ceramics during directional solidification: Effect of interfacial energy

The microstructure evolution and growth behavior of the Al₂O₃/Y₃Al₅O₁₂(YAG)/ZrO₂ ternary eutectic ceramics during directional solidification were well investigated. During directional solidification of the Al₂O₃/YAG/ZrO₂ ternary eutectic ceramics, {} Al₂O₃ paralleled with {001}ZrO₂ while they did not parallel with {001}YAG at the same time in the competitive growth stage. All of the interfaces parallel to each other finally. The area percentage of the Al₂O₃/ZrO₂ and YAG/ZrO₂ interfaces are 40.4 ± 0.2% and 30.8 ± 0.1%, respectively, higher than that of the Al₂O₃/YAG (28.8 ± 0.2%). The content of Al₂O₃ and YAG phases are 39.9% and 41.1%, respectively, almost double of that of ZrO₂. The interfaces of Al₂O₃/ZrO₂ and YAG/ZrO₂ are shorter and more dispersed than that of the Al₂O₃/YAG. It was found that the interfacial energy of Al₂O₃/ZrO₂ and YAG/ZrO₂ interfaces are lower than that of Al₂O₃/YAG. It can be concluded that interfacial energy plays a decisive role in affecting the crystallographic orientation and interfaces distribution in the Al₂O₃/YAG/ZrO₂ eutectic since the interfaces of Al₂O₃/ZrO₂ and YAG/ZrO₂ with lower interfacial energy can be formed more easily during directional solidification. Therefore, the contents of Al₂O₃/ZrO₂ and YAG/ZrO₂ interfaces are higher. This study can provide theoretical guidance for interface design of multi-phase materials.     

赤红球菌组氨酸激酶的融合表达和功能分析

对赤红球菌的组氨酸激酶基因进行密码子优化，将优化后的组氨酸激酶基因（rhks）构建重组表达质粒pGEX-4T-2-rhks。将此质粒导入到大肠杆菌BL21（DE3）中进行异源表达。在25 ℃和1 mmol/L异丙基-β-D-硫代吡喃半乳糖苷诱导条件下，组氨酸激酶融合蛋白（GST-RHK）获得成功表达，并具有催化活性。经谷胱甘肽琼脂糖亲和层析纯化，获得电泳纯的GST-RHK，其中纯化倍数为3.1，得率为19.5%。该蛋白大小约为72.75 kDa，Km、Vmax和Kcat值分别为20.92 μmol/L、0.17 μmol/（L·min）和1.4 min－1。野生型赤红球菌、组氨酸激酶基因增强株sdrhkE和组氨酸激酶基因敲减株sdrhkD在分别含有苯酚、甲苯、氯苯、异辛烷4 种有机溶剂的培养基中培养，菌株sdrhkD的生长情况都优于野生型赤红球菌，菌株sdrhkE的生长情况都低于野生型赤红球菌。本研究为进一步揭示赤红球菌SD3中组氨酸激酶涉及的信号转导途径与赤红球菌有机溶剂耐受性的关联机制提供一定参考依据。     

A Smart Deep Convolutional Neural Network for Real-Time Surface Inspection

A proper detection and classification of defects in steel sheets in real time have become a requirement for manufacturing these products, largely used in many industrial sectors. However, computers used in the production line of small to medium size companies, in general, lack performance to attend real-time inspection with high processing demands. In this paper, a smart deep convolutional neural network for using in real-time surface inspection of steel rolling sheets is proposed. The architecture is based on the state-of-the-art SqueezeNet approach, which was originally developed for usage with autonomous vehicles. The main features of the proposed model are: small size and low computational burden. The model is 10 to 20 times smaller when compared to other networks designed for the same task, and more than 700 times smaller than general networks. Also, the number of floating-point operations for a prediction is about 50 times lower than the ones used for similar tasks. Despite its small size, the proposed model achieved near-perfect accuracy on a public dataset of 1800 images of six types of steel rolling defects.