Machine learning algorithm selection for windage alteration fault diagnosis of mine ventilation system

Machine learning algorithms have been widely used in mine fault diagnosis. The correct selection of the suitable algorithms is the key factor that affects the fault diagnosis. However, the impact of machine learning algorithms on the prediction performance of mine fault diagnosis models has not been fully evaluated. In this study, the windage alteration faults (WAFs) diagnosis models, which are based on K-nearest neighbor algorithm (KNN), multi-layer perceptron (MLP), support vector machine (SVM), and decision tree (DT), are constructed. Furthermore, the applicability of these four algorithms in the WAFs diagnosis is explored by a T-type ventilation network simulation experiment and the field empirical application research of Jinchuan No. 2 mine. The accuracy of the fault location diagnosis for the four models in both networks was 100%. In the simulation experiment, the mean absolute percentage error (MAPE) between the predicted values and the real values of the fault volume of the four models was 0.59%, 97.26%, 123.61%, and 8.78%, respectively. The MAPE for the field empirical application was 3.94%, 52.40%, 25.25%, and 7.15%, respectively. The results of the comprehensive evaluation of the fault location and fault volume diagnosis tests showed that the KNN model is the most suitable algorithm for the WAFs diagnosis, whereas the prediction performance of the DT model was the second-best. This study realizes the intelligent diagnosis of WAFs, and provides technical support for the realization of intelligent ventilation.     

Ensemble relation network with multi-level measure

Fine-grained few-shot learning is a difficult task in image classification. The reason is that the discriminative features of fine-grained images are often located in local areas of the image, while most of the existing few-shotlearning image classification methods only use top-level features and adopt a single measure. In that way, the localfeatures of the sample cannot be learned well. In response to this problem, ensemble relation network with multi-level measure (ERN-MM) is proposed in this paper. It adds the relation modules in the shallow feature space tocompare the similarity between the samples in the local features, and finally integrates the similarity scores from thefeature spaces to assign the label of the query samples. So the proposed method ERN-MM can use local details andglobal information of different grains. Experimental results on different fine-grained datasets show that the proposedmethod achieves good classification performance and also proves its rationality.     

Opportunistic Routing Protocol Based EPO–BES in MANET for Optimal Path Selection

Wireless Personal Communications - Despite its various benefits, the Mobile Ad-hoc Network (MANET) has a number of obstacles due to its mobility, unstable topology, energy efficiency, and other...     

Effect of interface types on the heat-resistance of Cansas-II SiCf /SiC composites

The heat-resistance of the Cansas-II SiC/CVI-SiC mini-composites with a PyC and BN interface was studied in detail. The interfacial shear strength of the SiC/PyC/SiC mini-composites decreased from 15 MPa to 3 MPa after the heat treatment at 1500 °C for 50 h, while that of the SiC/BN/SiC mini-composites decreased from 248 MPa to 1 MPa, which could be mainly attributed to the improvement of the crystallization degree of the interface and the decomposition of the matrix. Aside from the above reasons, the larger declined fraction of the interfacial shear strength of the SiC/BN/SiC mini-composites might also be related to the gaps in the BN interface induced by the volatilization of B₂O₃·SiO₂ phase, leading to a significant larger declined fraction of the tensile strength of the SiC/BN/SiC mini-composites due to the obvious expansion of the critical flaws on the fiber surface. Therefore, compared with the CVI BN interface, the CVI PyC interface has better heat-resistance at high temperatures up to 1500 °C due to the fewer impurities in PyC.     

Fabrication of reduced Graphene Oxide supported Gd3+ doped V2O5 nanorod arrays for superior photocatalytic and antibacterial activities

In the current report, pure V₂O₅, a series of Gd doped V₂O₅ (1 wt%, 3 wt%, 5 wt% and 10 wt%) and graphene integrated Gd–V₂O₅ photocatalysts have been prepared using a facile wet chemical approach. The effect of Gd⁺³ ions substitution and RGO support on V₂O₅ was studied by the different analytical techniques. X-ray diffraction (XRD) results showed the orthorhombic crystal structure of synthesized samples with crystallize size in range of 22–35 nm. Morphological analysis showed nanorods and nanorod arrays like appearance of V₂O₅, Gd–V₂O₅ and GdV-₂O₅/RGO, respectively. Gd–V₂O₅ and Gd–V₂O₅/RGO exhibited enhanced optical response in the visible region along with decrease in the band gap values for Gd doped V₂O₅ samples. BET surface area of Gd–V₂O₅ and Gd- V₂O₅/RGO was calculated as 12.39 g/m² and 15.35 g/m² that was found to be higher than pristine V₂O₅. To study the photocatalytic activity of synthesized photocatalysts, methylene blue (MB) was chosen as model pollutant. Among the Gd doped V₂O₅ samples, highest photocatalytic activity (45.62%) was achieved by optimal concentration of 5 wt% Gd–V₂O₅ that is accredited to effective separation of electron-hole pairs. While Gd–V₂O₅/RGO showed 2.1 times higher dye removal (97.12%) than unsupported Gd–V₂O₅, under the visible light irradiation. The significantly high photocatalytic activity of Gd–V₂O₅/RGO is due to the synergistic effect aroused by combined action of Gd⁺³ ions doping and advantageous properties of highly conductive and large surfaced graphene. Recycling experiments for V₂O₅ derivatives showed good stability and recyclability of photocatalysts. Additionally, Gd–V₂O₅/RGO was found to be more potential anti-bacterial agent than V₂O₅ and Gd–V₂O₅.     

On the design of secure primitives for real world applications

This editorial paper provides an overview of new advances on hardware security challenges and promising solutions for real world applications. It first presents the increasing hardware vulnerabilities with the emergence of diverse computing platforms. Then, it details the technical challenges, research opportunities, and potential solutions to cyber-attacks on -physical- devices.     

Approximation Optimal Vibration Control with Applications to Jacket Offshore Platforms with Nonlinear Dynamic Characteristics

International Journal of Control, Automation and Systems - The vibration control problem of offshore jacket platforms is studied. The model of offshore platforms with nonlinear interactions of the...     

M2M energy saving strategy in 5G millimeter wave system

Telecommunication Systems - Machine to Machine technology has a broad application prospect in the 5G network, but there is a bottleneck in the energy consumption of intelligent devices powered by...     

Multiple clusterings of heterogeneous information networks

Machine Learning - Traditional clustering algorithms focus on a single clustering result; as such, they cannot explore potential diverse patterns of complex real world data. To deal with this...