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.     

Learn decision trees with deep visual primitives

In this paper, we strive to propose a self-interpretable framework, termed PrimitiveTree, that incorporates deep visual primitives condensed from deep features with a conventional decision tree, bridging the gap between deep features extracted from deep neural networks (DNNs) and trees’ transparent decision-making processes. Specifically, we utilize a codebook, which embeds the continuous deep features into a finite discrete space (deep visual primitives) to distill the most common semantic information. The decision tree adopts the spatial location information and the mapped primitives to present the decision-making process of the deep features in a tree hierarchy. Moreover, the trained interpretable PrimitiveTree can inversely explain the constituents of the deep features, highlighting the most critical and semantic-rich image patches attributing to the final predictions of the given DNN. Extensive experiments and visualization results validate the effectiveness and interpretability of our method.     

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.     

高深溜井井筒堵塞的爆破处理实践

溜井是采用平硐-溜井方式开拓矿山的运输咽喉,溜井正常与否对矿山生产影响极大。本文通过黑沟铁矿高深溜井井筒堵塞处理实例,对其堵塞爆破处理方法及经验做了系统分析。重点介绍的爆破冲击波破拱疏通高深溜井井筒高位堵塞的爆破方法,富有新意,可供国内外同类型矿山参考借鉴。     

Metal chlorides-promoted ammonia absorption of deep eutectic solvent

Ammonia is considered as a promising hydrogen or energy carrier. Ammonia absorption or adsorption is an important aspect for both ammonia removal, storage and separation applications. To these ends, a wide range of solid and liquid sorbents have been investigated. Among these, the deep eutectic solvent (DES) is emerging as a promising class of ammonia absorbers. Herein, we report a novel type of DES, i.e., metal-containing DESs for ammonia absorption. Specifically, the NH₃ absorption capacity is enhanced by ca. 18.1–36.9% when a small amount of metal chlorides, such as MgCl₂, MnCl₂ etc., are added into a DES composed of resorcinol (Res) and ethylene glycol (EG). To our knowledge, the MgCl₂/Res/EG (0.1:1:2) DES outperforms most of the reported DESs. The excellent NH₃ absorption performances of metal–containing DESs have been attributed to the synergy of Lewis acid–base and hydrogen bonding interactions. Additionally, good reversibility and high NH₃/CO₂ selectivity are achieved over the MgCl₂/Res/EG (0.1:1:2) DES, which enables it to be a potential NH₃ absorber for further investigations.     

Passive micromixer with baffles distributed on both sides of microchannels based on the Koch fractal principle

Since the beginning of the 21st Century, the development of microfluidic chip technology has been very rapid and has attracted the attention of more and more scholars. As an important part of the microfluidic chip, the performance of the micromixer is critical. The fractal structure in the microchannels helps to improve the mixing performance of the micromixer and improve the mixing efficiency of the micromixer. The research results of other scholars are of great significance to the research of the present paper, which mainly studies the effect of changing the baffle state on the mixing efficiency of the micromixer based on the Koch fractal principle. Through simulation analysis, it was found that the mixing efficiency of the baffles distributed on both sides of the microchannel was higher than the mixing efficiency of the baffles distributed on the microchannel side. When the distance between adjacent baffles was divided into 0.15, 0.25 and 0.35 mm, simulated data suggested that the baffle distance of 0.15 mm was best. Increasing the number of baffles from six to eight groups increased the mixing path of the fluid in the microchannel and improved mixing efficiency. A comparison of mixing efficiencies of the 0°, 15° and 30° baffle angles revealed that very significant improvement in mixing efficiency was obtained at 30°. © 2019 Society of Chemical Industry     

Deep reinforcement learning-based cooperative interactions among heterogeneous vehicular networks

Most real-world vehicle nodes can be structured into an interconnected network of vehicles. Through structuring these services and vehicle device interactions into multiple types, such internet of vehicles becomes multidimensional heterogeneous overlay networks. The heterogeneousness of the overlays makes it difficult for the overlay networks to coordinate with each other to improve their performance. Therefore, it poses an interesting but critical challenge to the effective analysis of heterogeneous virtual vehicular networks. A variety of virtual vehicular networks can be easily deployed onto the native network by applying the concept of SDN (Software Defined Networking). These virtual networks reflect their heterogeneousness due to their different performance goals, and they compete for the same physical resources of the underlying network, so that a sub-optimal performance of the virtual networks may be achieved. Therefore, we propose a Deep Reinforcement Learning (DRL) approach to make the virtual networks cooperate with each other through the SDN controller. A cooperative solution based on the asymmetric Nash bargaining is proposed for co-existing virtual networks to improve their performance. Moreover, the Markov Chain model and DRL resolution are introduced to leverage the heterogeneous performance goals of virtual networks. The implementation of the approach is introduced, and simulation results confirm the performance improvement of the latency sensitive, loss-rate sensitive and throughput sensitive heterogeneous vehicular networks using our cooperative solution.     

Calorimetric study and thermodynamic description of Ga-Ge-Li liquid alloys

This publication contains the thermodynamic results received by the drop calorimetry method. The experiments were conducted for four different cross sections, at the temperature of 1080 K. The investigated alloys were as follows: (Ga_0.75Li_0.25)_1-xGe_x, (Ge_0.50Li_0.50)_1-xGa_x, (Ga_0.50Li_0.50)_1-xGe_x, (Ga_0.25Li_0.75)_1-xGe_x. The mixing enthalpy changes measured for all four cross sections of the Ga-Ge-Li system are characterized by negative deviations from the ideal solutions. The Muggianu model with the ternary interaction parameters was applied to elaborate the experimental data of the mixing enthalpy change with the use of the optimized thermodynamic parameters of the binary systems available in the literature.     

CFD Modeling of Active Volume Creation in a Non‐Newtonian Fluid Agitated by Submerged Recirculating Jets

Computational fluid dynamics (CFD) models were employed to investigate flow conditions inside a model reactor in which yield stress non‐Newtonian liquid is mobilized using submerged recirculating jets. The simulation results agree well with the experimental results of active volume in the reactor obtained using flow visualization by the authors in a previous study. The models developed are capable of predicting a critical jet velocity (v_c) that determines the extent of active volume obtained due to jet mixing. The v_c values are influenced both by the rheological properties of the liquid and the nozzle orientation. The liquid with higher effective viscosity leads to higher v_c for a downward facing injection nozzle. However, an upward facing injection nozzle along with a downward facing suction nozzle generates enhanced complementary flow fields which overcome the rheological constraints of the liquid and lead to lower v_c.