A model based LSTM and graph convolutional network for stock trend prediction.

Stock market is a complex system characterized by collective activity, where interdependencies between stocks have a significant influence on stock price trends. It is widely believed that modeling these dependencies can improve the accuracy of stock trend prediction and enable investors to earn more stable profits. However, these dependencies are not directly observable and need to be analyzed from stock data.

Electrochemical Performance of Deposited LiPON Film/Lithium Electrode in Lithium-Sulfur Batteries.

This paper presents a composed lithium phosphate (LiPON) solid electrolyte interface (SEI) film which was coated on a lithium electrode via an electrodeposit method in a lithium-sulfur battery, and the structure of the product was characterized through infrared spectrum (IR) analysis, X-ray photoelectron spectroscopy (XPS), X-ray diffraction (XRD), environment scanning electron microscope (ESEM), etc. Meanwhile, the electrochemical impedance spectrum and the interface stability of the lithium electrode with the LiPON film was analyzed, while the coulomb efficiency and the cycle life of the lithium electrode with the LiPON film in the lithium-sulfur battery were also studied. It was found that this kind of film can effectively inhibit the charge from transferring at the interface between the electrode and the solution, which can produce a more stable interface impedance on the electrode, thereby improving the interface contact with the electrolyte, and effectively improve the discharge performance, cycle life, and the coulomb efficiency of the lithium-sulfur battery.

Preparation and Characterization of Guaiacol-Furfuramine Benzoxazine and Its Modification of Bisphenol A-Aniline Oxazine Resin.

A new type of benzoxazine resin has been synthesized using a natural phenol source, guaiacol, and a biomass amines, furfuramine. The synthesis conditions were optimized; when the reaction molar ratio of guaiacol, furfuramine, and polyformaldehyde was 1:1:4, the highest synthetic yield was reached. The product was characterized via testing using transform infrared spectroscopy (FT-IR), gel permeation chromatography (GPC), mass spectrogram (MS), and nuclear magnetic resonance (H-NMR) to confirm its molecular structure.

Displacement identification of oil storage tank and calibration of tank capacity table model based on indicator function integral.

Based on the indicator function integral, this paper identifies the displacement of oil storage tank and calibrates the tank capacity table model. The displacement parameters of a cylinder oil tank with spherical caps at both ends are deduced by establishing an appropriate rectangular coordinate system while cross-section analysis, coordinate transformation, and the functional relationship between oil reserves and oil level height are used as well. Furthermore, the displacement parameters are determined by the least square method and alternating contraction search method to verify the data, which improves the accuracy of the calculation.

An Intelligent Channel Estimation Algorithm Based on Extended Model for 5G-V2X.

Car networking systems based on 5G-V2X (vehicle-to-everything) have high requirements for reliability and low-latency communication to further improve communication performance. In the V2X scenario, this article establishes an extended model (basic expansion model) suitable for high-speed mobile scenarios based on the sparsity of the channel impulse response. And propose a channel estimation algorithm based on deep learning, the method designed a multilayer convolutional neural network to complete frequency domain interpolation.

Intelligent Device for Harvesting the Vibration Energy of the Automobile Exhaust with a Piezoelectric Generator.

With increasing consumption of energy and increasing environmental pollution, research on capturing the vibration energy lost during transportation and vehicle driving is growing rapidly. There is a large amount of vibration energy in the automobile exhaust system that can be recycled. This paper proposes a self-powered intelligent device (SPID) using a piezoelectric energy generator.

Synthesis of a Novel Bifunctional Epoxy Double-Decker Silsesquioxane: Improvement of the Thermal Stability and Dielectric Properties of Polybenzoxazine.

In this study a new type of bifunctional epoxy compound (DDSQ-EP) based on double-decker silsesquioxane (DDSQ) was synthesized by process of alkaline hydrolysis condensation of phenyltrimethoxysilane and corner capping reaction with dichloromethylvinylsilane, followed by epoxidation reaction of vinyl groups. The resultant structures were confirmed using Fourier transform infrared spectrometry, nuclear magnetic resonance spectrometry and time-of-flight mass spectrometry, respectively. The DDSQ-EP was incorporated into polybenzoxazine to obtain the PBZ/DDSQ-EP nanocomposites.

Synthesis and Characterization of Benzoxazine Resin Based on Furfurylamine.

This paper presents an investigation of the modification of natural oxazines to traditional bisphenol A benzoxazines. Eugenol was reacted with furfurylamine to synthesize a new type of benzoxazine (eugenol-furfurylamine benzoxazine), with a yield of 77.65%; and another new type of benzoxazine (bisphenol A-furfurylamine benzoxazine) was generated from bisphenol A and furfurylamine, with the highest yield of 93.

Data-Driven and Machine-Learning Methods to Project Coronavirus Disease 2019 Pandemic Trend in Eastern Mediterranean.

The coronavirus disease 2019 (COVID-19) pandemic has become a major public health crisis worldwide, and the Eastern Mediterranean is one of the most affected areas. We use a data-driven approach to assess the characteristics, situation, prevalence, and current intervention actions of the COVID-19 pandemic. We establish a spatial model of the spread of the COVID-19 pandemic to project the trend and time distribution of the total confirmed cases and growth rate of daily confirmed cases based on the current intervention actions.