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.     

LinkingPark: An automatic semantic table interpretation system

In this paper, we present LinkingPark, an automatic semantic annotation system for tabular data to knowledge graph matching. LinkingPark is designed as a modular framework which can handle Cell-Entity Annotation (CEA), Column-Type Annotation (CTA), and Columns-Property Annotation (CPA) altogether. It is built upon our previous SemTab 2020 system, which won the 2nd prize among 28 different teams after four rounds of evaluations. Moreover, the system is unsupervised, stand-alone, and flexible for multilingual support. Its backend offers an efficient RESTful API for programmatic access, as well as an Excel Add-in for ease of use. Users can interact with LinkingPark in near real-time, further demonstrating its efficiency.     

Evolution of the structure and mechanical performance of Cansas-II SiC fibres after thermal treatment

Herein, an in-depth analysis of the effect of heat treatment at temperatures between 900 and 1500 °C under an Ar atmosphere on the structure as well as strength of Cansas-II SiC fibres was presented. The untreated fibres are composed of β-SiC grains, free carbon layers, as well as a small amount of an amorphous SiC_xO_y phase. As the heat-treatment temperature was increased to 1400 °C, a significant growth of the β-SiC grains and free carbon layers occurred along with the decomposition of the SiC_xO_y phase. Moreover, owing to the decomposition of the SiC_xO_y phase, some nanopores formed on the fibre surface upon heating at 1500 °C. The mean strength of the Cansas-II fibres decreased progressively from 2.78 to 1.20 GPa with an increase in the heat-treatment temperature. The degradation of the fibre strength can be attributed to the growth of critical defects, β-SiC grains, as well as the residual tensile stress.     

An infinite chain, {[Ni(tn)2]3[Fe(CN)4(μ-CN)2]2}n,a new catalyst for electrochemical-driven water splitting and photochemical-driven hydrogen evolution from water under blue light

A new catalyst for both water reduction and oxidation, based on an infinite chain, {[Ni(tn)₂]₃ [Fe(CN)₄ (μ-CN)₂]₂}_n, is formed by the reaction of NiCl₂, 1,3-propanediamine (tn) and K₃ [Fe(CN)₆]. {[Ni(tn)₂]₃ [Fe(CN)₄ (μ-CN)₂]₂}_n can electro-catalyze hydrogen evolution from a neutral aqueous buffer (pH 7.0) with a turnover frequency (TOF) of 1561 mol of hydrogen per mole of catalyst per hour (H₂/mol catalyst/h) at an overpotential (OP) of 837 mV {[Ni(tn)₂]₃ [Fe(CN)₄ (μ-CN)₂]₂}_n also can electro-catalyze O₂ production from water with a TOF of ～45 mol O₂ (mol cat)^?1s^?1 at an OP of 591 mV. Under blue light (λ = 469 nm), together with CdS nanorods (CdS NRs) as a photosensitizer, and ascorbic acid (H₂A) as a sacrificial electron donor, {[Ni(tn)₂]₃ [Fe(CN)₄ (μ-CN)₂]₂}_n can photo-catalyze hydrogen generation from an aqueous buffer (pH 4.0) with a turnover number (TON) of 11,450 mol H₂ per mole of catalyst (mol of H₂ (mol of cat)^?1) during 10 h irradiation. The average of apparent quantum yield (AQY) is as high as 40.96% during 10 h irradiation. Studies indicate that {[Ni(tn)₂]₃ [Fe(CN)₄ (μ-CN)₂]₂}_n exists in two forms: a cyano-bridged chain ({[Ni(tn)₂]₃ [Fe(CN)₄ (μ-CN)₂]₂}_n) in solid, and a salt ([Ni(tn)₂]₃ [Fe(CN)₆]₂) in aqueous media; Catalytic reaction occurs on the nickel center of [Ni(tn)₂]²⁺, and the introduction of [Fe(CN)₆]^3- can improve the catalytic efficiency of [Ni(tn)₂]²⁺ for H₂ or O₂ generation. We hope these findings can afford a new method for the design of catalysts for both water reduction and oxidation.     

Benchmark experiment of large-angle scattering reaction cross section of iron at 14 MeV using two shadow bars – Comparison of experimental results with ENDF/B-VIII –

ABSTRACT

It is important to perform neutron transport simulations with accurate nuclear data in the neutronics design of a fusion reactor. However, absolute values of large-angle scattering cross sections vary among nuclear data libraries even for well-examined nuclide of iron. Benchmark experiments focusing on large-angle scattering cross sections were thus performed to confirm the correctness of nuclear data libraries. The series benchmark experiments were performed at a DT neutron source facility, OKTAVIAN of Osaka University, Japan, by the unique experimental system established by the authors’ group, which can extract only the contribution of large-angle scattering reactions. This system consists of two shadow bars, target plate (iron), and neutron detector (niobium). Two types of shadow bars were used and four irradiations were conducted for one experiment, so that contribution of room-return neutrons was effectively removed and only large-angle scattering neutrons were extracted from the measured four Nb reaction rates. The obtained experimental results were compared with calculations for five nuclear data libraries including JENDL-4.0, JEFF.-3.3, FENDL-3.1, ENDF/B- VII, and recently released ENDF/B-VIII. It was found from the comparison that ENDF/B-VIII showed the best result, though ENDF/B-VII showed overestimation and others are in large underestimation at 14 MeV.     

Modeling unaccounted-for gas among residential natural gas consumers using a comprehensive fuzzy cognitive map

Residential natural gas consumption depends on several factors. Available tools and methods to identify, categorize, and validate effective factors have some limitations, making consumption modeling more complex. Once a comprehensive model of effective consumption factors is developed for residential gas consumers, it can predict consumption. In addition, such a model could be used to verify the accuracy of measuring devices in order to reduce unaccounted for gas (UFG). The key factors affecting residential gas consumption were identified based on previous studies and their mutual effects were analyzed using a fuzzy cognitive mapping (FCM) method. The most significant factors and their effects on natural gas consumption in the residential sector were determined. In this study, for the first time, the expected consumption for each consumer was estimated using a consumption index. Generally, if the estimated consumption is significantly different from the amount recorded by the meter, it could suggest a potential source of UFG. The proposed method was applied to the data collected from the residential gas consumers of a small region in Iran (Dasht-e Arjan region, Fars province), and the results demonstrate the effectiveness of the proposed method.     

基于K-means和SOM的水下传感器数据采集方法

随着海洋资源勘探和海洋污染物监控工作的开展，水文数据的监测和采集等已经成为重要的研究方向。其中，水下无线传感器网络在水文数据采集过程中起着举足轻重的作用。本文研究的是水下无线传感器二维监测网络模型中，传感器节点数据采集的问题，其设计方法是通过自组织映射（Self-organizing mapping，SOM）对传感器节点进行路径最优化处理，结合优化的路径图形和K-means算法找到路径内部聚合点，利用聚合点和传感器的节点得到传感器通信半径内的数据采集点，最后通过SOM得到水下机器人（Autonomous underwater vehicle，AUV）到各个数据采集点采集数据的最优路径。经过实验验证，在水下1 200 m×1 750 m范围内布置52个传感器节点的情景下，数据采集点相比于传感器节点路径规划采用相同的采集顺序得到的路径优化了6.7%；对数据采集点重新进行自组织路径规划得到的路径比传感器结点路径的最优解提高了12.2%。增加传感器节点的数量，其结果也大致相同，因此采用该方法可以提高水下机器人采集数据的效率。     

新型地锚张弦梁式泥石流格栅坝构件受力的简化计算方法

针对常见泥石流防治结构被冲击破坏的问题，基于“柔性消能”理念，结合张弦梁结构和竖向预应力锚杆技术，提出一种既能改善结构受力性能、增加结构整体抗冲击能力、保证结构安全可靠，又能减小结构构件截面尺寸、节约成本、便于现场施工组装和后期运营维护的新型地锚张弦梁式泥石流格栅坝，并阐述其技术原理。根据泥石流荷载分布和新型地锚张弦梁式泥石流格栅坝的受力特征，给出其简化的内力计算方法；并利用SAP2000建立新结构有限元模型，分析了结构的整体受力，验证了构件简化计算方法的合理性；结合Python语言和Qt De? signer软件开发了相应的设计计算软件，对新型地锚张弦梁式泥石流格栅坝的内力进行求解。结果表明：提出的新结构抗冲击性能好，构件受力均匀；以后设计中应关注竖杆的剪切脆性破坏和立柱偏心受力情况，保证结构安全；变形协调仅使底层张弦梁与竖杆内力偏大，实际工程应用时，应着重验算底层构件，防止其破坏；文中提出的简化计算方法能较准确的反映结构的受力特性，具有一定的合理性，研究可为新型地锚张弦梁式泥石流格栅坝的设计计算和推广应用提供理论依据和技术支持。     

A new signal processing-based islanding detection method using pyramidal algorithm with undecimated wavelet transform for distributed generators of hydrogen energy

Machine learning-based fault detection methods are frequently combined with wavelet transform (WT) to detect an unintentional islanding condition. In contrast to this condition, these methods have long detection and computation time. Thus, selecting a useful signal processing-based approach is required for reliable islanding detection, especially in real-time applications. This paper presents a new modified signal processing-based islanding detection method (IDM) for real-time applications of hydrogen energy-based distributed generators. In the study, a new IDM using a modified pyramidal algorithm approach with an undecimated wavelet transform (UWT) is presented. The proposed method is performed with different grid conditions with the presence of electric noise in real-time. Experimental results show that oscillations in the acquired signal can be reduced by the UWT, and noise sensitivity is lower than other WT-based methods. The non-detection zone is zero and the maximum detection and computational time is also 75 ms at a close power match.