聚类算法在高脂血症辨证分型研究中的应用

高脂血症的辨证分型标准化研究是中医基础研究的热点与难点,利用计算机挖掘技术中的聚类算法对高脂血症临床中医症状数据进行分析,得到具有统计学意义的分类结果,同时寻找其与中医证候相对应的关系具有重要研究价值.通过编写适用于中医证候分类的聚类算法并提供设置相似度阈值等交互界面,实现了大规模样本的自适应分类,从而使聚类结果更加科学客观.将得到的每个类别中所对应样本的病症特征与所属中医的证候类别联系起来,为辨证分型标准化奠定了基础.     

Building Sparse Multiple-Kernel SVM Classifiers

The support vector machines (SVMs) have been very successful in many machine learning problems. However, they can be slow during testing because of the possibly large number of support vectors obtained. Recently, Wu (2005) proposed a sparse formulation that restricts the SVM to use a small number of expansion vectors. In this paper, we further extend this idea by integrating with techniques from multiple-kernel learning (MKL). The kernel function in this sparse SVM formulation no longer needs to be fixed but can be automatically learned as a linear combination of kernels. Two formulations of such sparse multiple-kernel classifiers are proposed. The first one is based on a convex combination of the given base kernels, while the second one uses a convex combination of the so-called ldquoequivalentrdquo kernels. Empirically, the second formulation is particularly competitive. Experiments on a large number of toy and real-world data sets show that the resultant classifier is compact and accurate, and can also be easily trained by simply alternating linear program and standard SVM solver.     

Cell Development Enhanced Bionic Silk Hydrogel on Remodeling Immune Pathogenesis of Spinal Cord Injury via M2 Polarization of Microglial

Due to the complex spatial-temporal pathophysiology of spinal cord injury (SCI), effective modulation of SCI-specific inflammatory pathogenesis to achieve desirable therapeutic effects on functional recovery still remains challenging. Herein, cell-enhanced photocrosslinked silk fibroin hydrogels with extracellular matrix-mimicking cues of mechanical properties and RGD (Arg-Gly-Asp) signals are gelled in situ to fill the lesion site to modulate injury-induced neuroinflammation and promote neurite regrowth after SCI. The bionic hydrogel system provides biomimetic mechanical cues to promote neuronal differentiation of neural stem/progenitor cells (NPCs) and neurite growth by activating YAP nuclear expression. Importantly, favored by the strong capacity of silk fibroin hydrogels on macrophage/microglia recruitment, NPCs encapsulated hydrogel (NPCs@SFRGD0.1) effectively promotes recruited macrophages/microglia to M2 polarization in the lesion site by releasing S100A4 and thereby remodels the inflammatory microenvironment after SCI. Moreover, NPCs@SFRGD0.1 successfully reduces glial scar formation and accelerates corticospinal tract axon regrowth to improve locomotor recovery. Overall, this work contributes to illustrating the therapeutic mechanism of NPCs development based biomaterial therapies on modulating inflammatory microenvironment and this NPCs enhanced silk fibroin hydrogel provides a promising therapeutic strategy for SCI.     

GaP/GaNP Heterojunctions for Efficient Solar‐Driven Water Oxidation

The growth and characterization of an n‐GaP/i‐GaNP/p⁺‐GaP thin film heterojunction synthesized using a gas‐source molecular beam epitaxy (MBE) method, and its application for efficient solar‐driven water oxidation is reported. The TiO₂/Ni passivated n‐GaP/i‐GaNP/p⁺‐GaP thin film heterojunction provides much higher photoanodic performance in 1 m KOH solution than the TiO₂/Ni‐coated n‐GaP substrate, leading to much lower onset potential and much higher photocurrent. There is a significant photoanodic potential shift of 764 mV at a photocurrent of 0.34 mA cm^?2, leading to an onset potential of ≈0.4 V versus reversible hydrogen electrode (RHE) at 0.34 mA cm^?2 for the heterojunction. The photocurrent at the water oxidation potential (1.23 V vs RHE) is 1.46 and 7.26 mA cm^?2 for the coated n‐GaP and n‐GaP/i‐GaNP/p⁺‐GaP photoanodes, respectively. The passivated heterojunction offers a maximum applied bias photon‐to‐current efficiency (ABPE) of 1.9% while the ABPE of the coated n‐GaP sample is almost zero. Furthermore, the coated n‐GaP/i‐GaNP/p⁺‐GaP heterojunction photoanode provides a broad absorption spectrum up to ≈620 nm with incident photon‐to‐current efficiencies (IPCEs) of over 40% from ≈400 to ≈560 nm. The high low‐bias performance and broad absorption of the wide‐bandgap GaP/GaNP heterojunctions render them as a promising photoanode material for tandem photoelectrochemical (PEC) cells to carry out overall solar water splitting.     

偶联剂对玻璃纤维增强淀粉/聚乳酸复合材料性能的影响

分别以马来酸酐、KH550、KH560和KH570为偶联剂对玻璃纤维进行预处理,再与淀粉、聚乳酸(PLA)复合,通过熔融挤出法制备玻璃纤维增强淀粉/PLA复合材料。研究了偶联剂种类对玻璃纤维增强复合材料熔融指数、力学性能、热性能和熔融流变性能的影响。实验发现马来酸酐、KH550、KH570、KH560处理玻璃纤维增强淀粉/PLA复合材料的熔融指数和力学性能都依次增大,表明KH560处理玻璃纤维增强淀粉/PLA复合材料的界面黏结作用最强。对热性能进行表征发现,马来酸酐、KH550、KH570、KH560处理玻璃纤维增强淀粉/PLA复合材料玻璃化转变温度、重结晶温度、结晶度和热稳定性均依次提高。受玻璃纤维与淀粉/PLA基体界面黏结效果的影响,马来酸酐、KH550、KH570、KH560处理玻璃纤维增强淀粉/PLA体系的储能模量和复数黏度依次增大。     

Preliminary Study on Quantitative Research Methods of Discussion-based Teaching: CAD/CAM Course

Computer-aided design and manufacturing,or CAD/CAM,in a narrow sense,is the use of a computer for component design and machining. As a specialized course for students,CAD/CAM course is a required course for undergraduates majoring in mechanical engineering and related engineering majors and also the core technical skills to be mastered during the undergraduate study. Based on the teaching practices of CAD/CAM course,this paper tries to introduce the discussion-based method in curriculum design and the implementation of the course,and enhance the interaction between teachers and students through using new information interaction tools such as We Chat group and course homepage to stimulate students' interest,and also expand the learning space and time. Thus,the problems students have will be solved in real time. In this study,for the first time,the statistical methods are used to record detailed the speaking time,keywords and the frequency of teachers and students' interaction,and also carries out quantitative analysis in order to explore the interactive patterns between teacher and students in discussion-based teaching,so as to improve communication and learning efficiency between teacher and students. Meanwhile,this paper also discussed the advantages and the disadvantages of using discussion-based teaching in the hope that it can provide reference for the following discussion-based teaching of CAD/CAM course in mechanical or related engineering majors.     

Intrusion Detection Based on Bidirectional Long Short-Term Memory with Attention Mechanism

With the recent developments in the Internet of Things (IoT), the amount of data collected has expanded tremendously, resulting in a higher demand for data storage, computational capacity, and real-time processing capabilities. Cloud computing has traditionally played an important role in establishing IoT. However, fog computing has recently emerged as a new field complementing cloud computing due to its enhanced mobility, location awareness, heterogeneity, scalability, low latency, and geographic distribution. However, IoT networks are vulnerable to unwanted assaults because of their open and shared nature. As a result, various fog computing-based security models that protect IoT networks have been developed. A distributed architecture based on an intrusion detection system (IDS) ensures that a dynamic, scalable IoT environment with the ability to disperse centralized tasks to local fog nodes and which successfully detects advanced malicious threats is available. In this study, we examined the time-related aspects of network traffic data. We presented an intrusion detection model based on a two-layered bidirectional long short-term memory (Bi-LSTM) with an attention mechanism for traffic data classification verified on the UNSW-NB15 benchmark dataset. We showed that the suggested model outperformed numerous leading-edge Network IDS that used machine learning models in terms of accuracy, precision, recall and F1 score.