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.     

电信运营商云网规划数字化研究和实现

基于电信运营商数字化转型，系统性地提出了数据驱动的云网发展规划体系，以及六大关键数字化能力构建，设计和实现了一种云网规划数字化平台，该平台可用于实现目标网络精细规划、边缘计算精准预测等场景，并探讨了数字孪生在规划领域的应用前景，对运营商推进云网融合战略、推进高质量发展具有指导和参考意义。     

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.     

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.     

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。     

Freeze-drying and mechanical redispersion of aqueous PEDOT:PSS

Poly(3,4-ethylenedioxythiophene):poly(styrene sulfonate) (PEDOT:PSS) films are attracting famous applications in antistatic coating, energy storage and conversion, printed electronics, and biomedical fields due to their conductivity, optical transparency and flexibility. However, PEDOT:PSS has poor dispersion stability during long-term storage and transport. Moreover, the dried PEDOT:PSS films are insoluble in any solvent and cannot be redispersed again. In comparison to bake drying, here, a feasible strategy to achieve mechanically redispersed PEDOT:PSS with the help of freeze-drying process was reported. The redispersed PEDOT:PSS can recover not only the initial characters such as pH, chemical composition, viscosity, and particle size under similar solid contents, but also conductivity and surface morphology of treated films. In addition, the treated film exhibits self-healing properties similar to pristine film in terms of mechanical and electrical properties. This technology enables reuse and overcomes the technical problems of PEDOT:PSS dispersion, realizing real-time processing to meet variable applications.     

Nanolayer CrAlN/TiSiN coating designed for tribological applications

With the goal to produce a hard and tough coating intended for tribological applications, CrAlN/TiSiN nanolayer coating was prepared by alternative deposition of CrAlN and TiSiN layers. In the first part of the article, a detailed study of phase composition, microstructure, and layer structure of CrAlN/TiSiN coating is presented. In the second part, its mechanical properties, fracture and tribological behavior are compared to the nanocomposite TiSiN coating. An industrial magnetron sputtering unit was used for coating deposition. X-ray photoelectron spectroscopy, energy dispersive X-ray spectroscopy, X-ray diffraction, scanning electron microscopy, and transmission electron microscopy were used for compositional and microstructural analysis. Mechanical properties and fracture behavior were studied by instrumented indentation and focused ion beam techniques. Tribological properties were evaluated by ball-on-disk test in a linear reciprocal mode. A complex layer structure was found in the nanolayer coating. The TiSiN layers were epitaxially stabilized inside the coating which led to formation of dislocations at interfaces, to introduction of disturbances in the coating growth, and as a result, to development of fine-grained columnar microstructure. Indentation load required for the onset of fracture was twice lower for the nanolayer CrAlN/TiSiN, compared to the nanocomposite TiSiN coating. This agrees very well with their mechanical properties, with H³/E² being twice higher for the TiSiN coating. However, the nanolayer coating experienced less severe damage, which had a strong impact on tribological behavior. A magnitude of order lower wear rate and four times lower steady state friction coefficient were found for the nanolayer coating.     

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.