5G核心网业务模型的智能化预测研究

摘 要：核心网业务模型的建立是5G网络容量规划和网络建设的基础，通过现有方法得到的理论业务模型是静态不可变的且与实际网络存在偏离。为了克服现有5G核心网业务模型与现网模型适配性较差以及规划设备无法满足用户实际业务需求的问题，提出了一种长短期记忆（long short-term memory，LSTM）网络与卷积LSTM （convolution LSTM，ConvLSTM）网络双通道融合的 5G 核心网业务模型预测方法。该方法基于人工智能（artificial intelligence，AI）技术以实现高质量的核心网业务模型的智能预测，形成数据反馈闭环，实现网络自优化调整，助力网络智能化建设。     

Simultaneous fractionation of multiple classes of polyphenols from honeybush tea using solid-phase extraction

The structural diversity of polyphenols and the inherent limitations of current extraction techniques pose a challenge to extract polyphenols using a simple and green method. Hence, in this study, a method was developed to simultaneously fractionate multiple classes of polyphenols by only varying ethanol-water solutions. Honeybush tea, which is rich in polyphenols, was selected as a model for this study. Solvent extraction followed by solid-phase extraction (SPE) was developed to obtain a polyphenol-rich fraction from six honeybush samples. Based on a gradient elution programme (10%, 30%, 50%, 70% and 90% (v/v) ethanol-water solution) of SPE, the Strata X cartridge showed a better recovery of most targeted polyphenols under 0.9 mL of the drying volume and 1 mL min⁻¹ of the dispensing speed. The elution programme for fractionating most polyphenols was as follows: single elution with 50% ethanol, followed by twice elution with 70% ethanol. The antioxidant capacity was used to analyse the differences among the polyphenol-rich fractions from six honeybush samples. Principal component analysis (PCA) revealed that unfermented C. genistoides (GG) has the greatest antioxidant capacity among the honeybush species studied. Additionally, mangiferin, isomangiferin and vicenin-2 were the main contributors to the antioxidant capacity in six honeybush fractions according to the correlation study.     

Authenticity green coffee bean species and geographical origin using near-infrared spectroscopy combined with chemometrics

To prevent the adulteration of agricultural resources and provide a solution to enhance the green coffee bean supply chain, authentication using the near-infrared spectroscopy (NIRS) technique was investigated. Partial least square with discrimination analysis (PLS-DA) models combined with various preprocessing methods were built from NIR spectra of 153 Vietnamese green coffee samples. The model combined with the standard normal variate and the first order of derivative yielded excellent performance in predicting coffee species with the error cross-validation of 0.0261. PLS-DA model of mean centre and first-order derivative spectra also yielded good performance in verifying geographical indication of green coffee with the error of 0.0656. By contrast, the predicting abilities of post-harvest methods were poor. The overall results showed a high potential of the NIRS in online authentication practices.     

Form selection of concomitant polymorphs: A case study informed by crystallization kinetics modeling

Molecular mechanisms and process kinetics of crystallizing concomitant polymorphs remain poorly understood. Solvent-mediated phase transformation and concomitant crystallization are difficult to be distinguished in practice, as multiple forms can be detected at the same time. Herein, we developed a population balance model to simulate a concomitant crystallization process of two polymorphs of tolfenamic acid. Our kinetic modeling aims to understand concomitant crystallization and help guide form selection of such a molecular system. Crystallization kinetics of ethanolic solutions were uncovered from induction time measurements, as well as seeded and unseeded crystallization experiments. Experimental and simulation results demonstrate that the stable form I crystallizes concomitantly with the metastable form II. The faster growing form II results in an intermediate decline in the composition of form I in crystallized samples, a characteristic feature of the concomitantly crystallized system. A four-quadrant scheme of attainable polymorph outcome was simulated under various crystallization conditions.     

High-Performance All-Solid-State Supercapacitor Electrode Materials Using Freestanding Electrospun Carbon Nanofiber Mats of Polyacrylonitrile and Novolac Blends

Herein, this paper reports a facile method to prepare electrospun carbon nanofiber mats (ECNFMs) with high specific surface area and interconnected structure using polyacrylonitrile (PAN) as a precursor and novolac resin (NOC) as a polymer sacrificial pore-making agent. Without additional treatment, the prepared ECNFMs have a highly porous structure because NOC decomposes in a wider temperature range than most polymer activators. The NOC content in the PAN nanofibers shows important effects on porosity. The BET specific surface area of ECNFMs reaches a maximum of 1468 m² g⁻¹ when the precursor nanofibers contained 30 wt% NOC (ECNFM-3) after carbonization at 1000 °C. The supercapacitor device from ECNFM-3 electrode and all-solid-state electrolyte shows excellent cycling durability and high specific capacitance: ≈99.72% capacitance retention after 10 000 charge/discharge cycles and ≈320 mF cm⁻² at 0.25 mA cm⁻². Furthermore, it shows a large energy density of ≈11.1 $\mu$Wh cm⁻² under the power density of 500 mW m⁻². Activation of carbon nanofibers simply by the addition of NOC into precursor nanofibers can offer a handy way to prepare ECNFMs for high-performance all-solid-state supercapacitors and other potential applications.     

Fabrication of bacterial cellulose with high efficient loading of Ag and TiO2 nanoparticles for removing organic dyes

As a new advanced oxidation technology, photocatalytic technology has broad application prospects in the field of wastewater treatment. However, in the actual use process, there will be difficulties in catalyst recovery and reuse. This article successfully prepared bacterial cellulose (BC) loaded silver and titanium dioxide nanoparticles (Ag-plated TiO₂/BC composite pellicle) by in situ embedding method. BC not only works as the carrier to load TiO₂ and Ag NPs but also adsorbs dyes to promote the reaction. As a reusable photocatalytic film, it is convenient to use and recycle in terms of testing and characterization compared with powders. The results show that Ag and TiO₂ nanoparticles were closely embedded in BC. We evaluated the photocatalytic degradation performance of the catalyst on methylene blue (MB), active red X-3B, and Rhodamine B. When the reaction time was 2 h, the dye removal rates were 71%, 68%, and 82.6%. At the same time, through the inhibition zone experiment, it was found that the material has a certain inhibitory effect on both Escherichia coli and Staphylococcus aureus. Therefore, the supported catalyst prepared by this method has the advantages of high catalytic activity, relatively stable property, easy recovery, and tailorability, making it potentially applicable in sewage post-treatment links.     

The Multifaceted Mas-Related G Protein-Coupled Receptor Member X2 in Allergic Diseases and Beyond

Recent research on mast cell biology has turned its focus on MRGPRX2, a new member of the Mas-related G protein-coupled subfamily of receptors (Mrgprs), originally described in nociceptive neurons of the dorsal root ganglia. MRGPRX2, a member of this group, is present not only in neurons but also in mast cells (MCs), specifically, and potentially in other cells of the immune system, such as basophils and eosinophils. As emerging new functions for this receptor are studied, a variety of both natural and pharmacologic ligands are being uncovered, linked to the ability to induce receptor-mediated MC activation and degranulation. The diversity of these ligands, characterized in their human, mice, or rat homologues, seems to match that of the receptor’s interactions. Natural ligands include host defense peptides, basic molecules, and key neuropeptides such as substance P and vasointestinal peptide (known for their role in the transmission of pain and itch) as well as eosinophil granule-derived proteins. Exogenous ligands include MC secretagogues such as compound 48/80 and mastoparan, a component of bee wasp venom, and several peptidergic drugs, among which are members of the quinolone family, neuromuscular blocking agents, morphine, and vancomycin. These discoveries shed light on its capacity as a multifaceted participant in naturally occurring responses within immunity and neural stimulus perception, as in responses at the center of immune pathology. In host defense, the mice Mrgprb2 has been proven to aid mast cells in the detection of peptidic molecules from bacteria and in the release of peptides with antimicrobial activities and other immune mediators. There are several potential actions described for it in tissue homeostasis and repair. In the realm of pathologic response, there is evidence to suggest that this receptor is also involved in chronic inflammation. Furthermore, MRGPRX2 has been linked to the pathophysiology of non-IgE-mediated immediate hypersensitivity drug reactions. Different studies have shown its possible role in other allergic diseases as well, such as asthma, atopic dermatitis, contact dermatitis, and chronic spontaneous urticaria. In this review, we sought to cover its function in physiologic processes and responses, as well as in allergic and nonallergic immune disease.     

First Principle and Experimental Study for Site Preferences of Formability Improved Alloying Elements in Mg Crystal

Some alloying elements (Al, Er, Gd, Li, Mn, Sn, Y, Zn) were proved recently by calculations or experiments to improve the formability of Mg alloys, but ignoring their site preference in Mg crystals during the calculated process. A crystallographic model was built via first principle calculations to predict the site preferences of these elements. Regularities between doping elements and site preferences were summarized. Meanwhile, in the basis of the crystallographic model, a series of formulas were deduced combining the diffraction law. It predicted that a crystal plane with abnormal XRD peak intensity of the Mg-based solid solutions, compared to that of the pure Mg, prefers to possess solute atoms. Thus, three single-phase solid solution alloys were then prepared through an original In-situ Solution Treatment, and their XRD patterns were compared. Finally, the experiment further described the site preferences of these solute atoms in Mg crystal, verifying the calculation results.     

基于知识图谱和协同过滤的电影推荐算法研究

针对协同过滤算法在推荐电影过程中只能考虑电影外部评论而不能考虑电影内部的相似度关系,提出构建知识图谱辅助计算电影内部相似度。已有的电影数据可能是不完整的,因此采用知识图谱推理补全缺失的电影知识。基于TransE模型的知识图谱无法有效描述电影间的片名、演员、导演等复杂的多关系。首先采用改进的TransHR模型表示出电影信息之间的多关系,提升关系表示的准确率;然后通过用户评分矩阵计算电影间相似度;最后将2种相似度融合并应用于矩阵分解的推荐技术中。对比实验结果表明,该算法在召回率、准确率、平均绝对误差MAE等指标上都有所提升。