Experimental study on ratio optimization and application of improved bonded dust suppressant based on wetting effect.

Traditional bonded dust suppressants have high viscosity, insufficient fluidity and poor permeability problems, which is adverse to the formation of a continuous and stable solidified layer of dust suppressant solution on the surface of a dust pile. Gemini surfactant has efficient wetting performance and environmental protection performance, it is introduced as a wetting component to improve the flow and penetration performance of bonded dust suppressant solution, polymer absorbent resin (SAP) and sodium carboxymethyl starch (CMS) were selected as the main components of dust suppressant. A proportioning optimization model was constructed based on response surface methodology (RSM), and the concentration of each dust suppression component was selected as the independent variable, water loss rate, moisture retention rate, wind erosion rate and solution viscosity were chosen as the dependent variables in this model.

Study on Multi-Factor Optimization and Application for Water Mist of a Wetting Dust Suppressant.

Aiming at the problem of low efficiency of capturing respirable and hydrophobic dust in water mist dust removal technology, a chemical dust suppression method is adopted. Based on the research idea of improving the wetting efficiency of water mist, prolonging the droplet retention time, and improving the contact opportunity with dust, the experiments of dust sedimentation time, solution spreading area, and water loss rate are selected to evaluate the wetting efficiency and anti-evaporation performance of dust suppression water mist. Considering the special double-chain structure of the Gemini surfactant and its high wettability, it is preferred as the main dust suppression component.

Informed Attentive Predictors: A Generalisable Architecture for Prior Knowledge-Based Assisted Diagnosis of Cancers.

Due to the high mortality of many cancers and their related diseases, the prediction and prognosis techniques of cancers are being extensively studied to assist doctors in making diagnoses. Many machine-learning-based cancer predictors have been put forward, but many of them have failed to become widely utilised due to some crucial problems. For example, most methods require too much training data, which is not always applicable to institutes, and the complicated genetic mutual effects of cancers are generally ignored in many proposed methods.

Gated Graph Attention Network for Cancer Prediction.

With its increasing incidence, cancer has become one of the main causes of worldwide mortality. In this work, we mainly propose a novel attention-based neural network model named Gated Graph ATtention network (GGAT) for cancer prediction, where a gating mechanism (GM) is introduced to work with the attention mechanism (AM), to break through the previous work's limitation of 1-hop neighbourhood reasoning. In this way, our GGAT is capable of fully mining the potential correlation between related samples, helping for improving the cancer prediction accuracy.