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.     

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。     

Superswelling Microneedle Arrays for Dermal Interstitial Fluid (Prote)Omics

The noninvasive sampling of dermal interstitial fluid (ISF) for the monitoring of clinical biomarkers is a greatly appealing area of research. The identification of molecular biomarkers in biological fluids has been accelerated with -omics analyses but remains limited in ISF because of its time-consuming and complex extraction process. Here, the generation of microneedle (MN) patches made of superabsorbent acrylate-based hydrogels for the rapid sampling of dermal ISF is described to explore its proteome. In depth, iterative optimization allows the identification of novel acrylate-based compositions with the required chemical, mechanical, and biocompatibility properties allowing proteomic analysis of the extracted ISF for the first time after sampling with swelling MNs. The generated MN arrays show no cytotoxic effect, successfully cross the stratum corneum, and can collect up to 6 µL of dermal ISF in 10 min in vivo. Proteomics lead to the detection of 176 clinically relevant biomarkers in the collected samples validating the use of ISF as a relevant bodily fluid for disease monitoring and diagnostic. Importantly, it is discovered that extraction fingerprint is strongly dependent on the MNs chemistry, and thus specific biomarkers could be selectively extracted by tuning the composition of the patch, making the system versatile and specific.     

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.     

基于面元素重排的三维网格模型数据隐藏算法

目的 为了解决目前三维数据隐藏算法不能兼顾无失真和盲提取的问题，提出一种新的完全无失真的三维网格模型数据隐藏盲算法。方法 首先使用混沌逻辑映射选择嵌入与提取模式，保证数据的安全性。然后利用面元素重排，完全不会造成三维模型失真的性质，通过不同嵌入模式规则对三角面元素进行重排，以嵌入秘密数据。接收端则可根据相应的提取模式规则提取秘密数据。结果 仿真结果与分析表明，该算法不会对三维模型造成任何失真，嵌入容量为每顶点2比特，且能抵抗仿射变换攻击、噪声攻击和平滑攻击等。结论 这种三维数据隐藏盲算法无失真，容量大、安全性高、鲁棒性强，适用于三维载体不容修改的情形，如军事、医学、秘密通信和版权保护等。     

Estimates of daily oxygen consumption,carbon dioxide and methane emissions,and heat production for beef and dairy cattle using spot gas sampling

A simulation study was conducted to examine accuracy of estimating daily O₂ consumption, CO₂ and CH₄ emissions, and heat production (HP) using a spot sampling technique and to determine optimal spot sampling frequency (FQ). Data were obtained from 3 experiments where daily O₂ consumption, emissions of CO₂ and CH₄, and HP were measured using indirect calorimetry (respiration chamber or headbox system). Experiment 1 used 8 beef heifers (ad libitum feeding; gaseous exchanges measured every 30 min over 3 d in respiration chambers); Experiment 2 used 56 lactating Holstein-Friesian cows (restricted feeding; gaseous exchanges measured every 12 min over 3 d in respiration chambers); Experiment 3 used 12 lactating Jersey cows (ad libitum feeding; gaseous exchanges measured every hour for 1 d using headbox style chambers). Within experiment, averages of all measurements (FQALL) and averages of measurements selected at time points with 12, 8, 6, or 4 spot sampling FQ (i.e., sampling every 2, 3, 4, and 6 h in a 24-h cycle, respectively; FQ12, FQ8, FQ6, and FQ4, respectively) were compared. Within study a mixed model was used to compare gaseous exchanges and HP among FQALL, FQ12, FQ8, FQ6, and FQ4, and an interaction of dietary treatment by FQ was examined. A regression model was used to evaluate accuracy of spot sampling within study [i.e., FQALL (observed) vs. FQ12, FQ8, FQ6, or FQ4 (estimated)]. No interaction of diet by FQ was observed for any variables except for CH₄ production in experiment 1. No FQ effect was observed for gaseous exchanges and HP except in experiment 2 where CO₂ production was less (5,411 vs. 5,563 L/d) for FQ4 compared with FQALL, FQ12, and FQ8. A regression analysis between FQALL and each FQ within study showed that slopes and intercepts became farther from 1 and 0, respectively, for almost all variables as FQ decreased. Most variables for FQ12 and FQ8 had root mean square prediction error (RMSPE) less than 10% of the mean and concordance correlation coefficient (CCC) greater than 0.80, and RMSPE increased and CCC decreased as FQ decreased. When a regression analysis was conducted with combined data from the 3 experiments (mixed model with study as a random effect), results agreed with those from the analysis for the individual studies. Prediction errors increased and CCC decreased as FQ decreased. Generally, all the estimates from FQ12, FQ8, FQ6, and FQ4 had RMSPE less than 10% of the means and CCC greater than 0.90 except for FQ6 and FQ4 for O₂ consumption and CH₄ production. In conclusion, the spot sampling simulation with 3 indirect calorimetry experiments indicated that FQ of at least 8 samples (every 3 h in a 24-h cycle) was required to estimate daily O₂ consumption, CO₂ and CH₄ production, and HP and to detect changes in those in response to dietary treatments. This sampling FQ may be considered when using techniques that measure spot gas exchanges such as the GreenFeed and face mask systems.     

Patterns in environmental priorities revealed through government open data portals

The ways in which environmental priorities are framed are varied and influenced by political forces. One technological advance--the proliferation of government open data portals (ODPs)--has the potential to improve governance through facilitating access to data. Yet it is also known that the data hosted on ODPs may simply reflect the goals and interests of multiple levels of political power. In this article, I use traditional statistical correlation and regression techniques along with newer natural language processing and machine learning algorithms to analyze the corpus of datasets hosted on government ODPs (total: 49,066) to extract patterns that relate scales of governance and political liberalism/conservatism to the priorities and meaning attached to environmental issues. I find that state-level and municipal-level ODPs host different categories of environmental datasets, with municipal-level ODPs generally hosting more datasets pertaining to services and amenities and state-level ODPs hosting more datasets pertaining to resource protection and extraction. Stronger trends were observed for the influences of political conservatism/liberalism among state-level ODPs than for municipal-level ODPs.