Knowledge tracing(KT)is an important research problem in intelligent education,which predicts students'future answering behaviors by analyzing their historical interactions.Existing mainstream KT models only model students based on their knowledge mastery,neglecting the role of students'personal abilities in answering questions.Therefore,this paper proposes a deep knowledge tracing model(FKA-DKT)that integrates both knowledge and ability.First,we use the DKT model to construct a Knowledge-based Answer Prediction Network(KAPN),which predicts student answer correctness at the knowledge level.Then,we propose an Ability-based Answer Prediction Network(AAPN)to model students'abilities and predict answer correctness at the ability level.Finally,we linearly combine the predictions from KAPN and AAPN to integrate both knowledge and ability information for answer prediction.Experimental results on four publicly available datasets show that compared to existing mainstream methods,FKA-DKT achieves significant performance improvements in terms of the AUC metric.
Objective : To seek potential metastatic tumor markers in esophageal squamous cell carcinoma (ESCC) by bioinformatics. Methods : Four datasets (GSE70409, GSE26886, GSE161533, GSE17351) were downloaded from GEO database, and the differential expression of mRNA was screened by Limma software package. Gene ontology function and kyoto encyclopedia of genes and genomes pathway enrichment analysis were performed using the database for annotation; Protein–protein interaction network of these DEGs was constructed based on STRING database; then, the hub gene were identified by six algorithms of Cytoscape software. Using GEPIA2 database and OncoLnc database to analyze the survival of hub genes. Immune infiltration was analyzed by TIMER2 database and CIBERSORT deconvolution method. Results : A total of 244 differentially expressed genes(DEGs)were screened from 4 data sets of GEO database, including 164 up-regulated genes and 80 down-regulated genes, which were mainly enriched at extracellular region and extracellular space, and involved in biological processes such as cell adhesion and proteolysis related to tumor invasion and metastasis. KEGG results showed that DEGs were mainly enriched in PI3K-Akt signal pathway and extracellular matrix (ECM) receptor interaction signal pathway. Through the protein interaction analysis of DEGs, we found that three hub genes (CXCL8, MMP9 and MMP13) were highly expressed in ESCC. However, the GEPIA2 database shows that only CXCL8 is associated with the overall survival of ESCC patients. The results of immune infiltration showed that macrophages and resting dendritic cells increased significantly, while mast cells and monocytes decreased significantly. Conclusion : Three hub genes and immune infiltrating cells may play an important role in ESCC, and are expected to become potential tumor markers of ESCC and be used in the diagnosis and treatment of ESCC.
乡村旅游是乡村振兴的有效途径和重要举措,是农村地区发展转型的重要途径.但目前旅游流的研究鲜少涉及乡村旅游,为揭示乡村旅游的旅游流特征,以乡村旅游发展位居全国前列的浙江省为例,利用网络游记挖掘数据,综合应用时间分层法、社会网络分析等方法对旅游流时空特征进行分析,结果表明:(1)时间特征上,浙江省乡村旅游流年内总体上呈现"三峰"型分布特征,淡旺季明显,受游客来源、气候条件及闲暇时间影响显著.(2)目的地空间分布上,浙江省各市乡村旅游的游客接待数量基本与经济水平呈正相关;客源地分布上,浙江省乡村旅游流以省内游客为主体,周边省市为重要来源地.(3)浙江省乡村旅游流网络中,各城市扮演的角色存在较大差异,根据旅游流的中心度特征,浙江省地级市呈现出 4 级梯度.最后,总结出浙江省乡村旅游流的时空特征影响机制,并针对乡村旅游存在的问题提出管理建议.
红须腹菌(Rhizopogon rubescens(Tul.)Tul)是一类主要分布于中国云南省及福建省的根须腹菌属食用菌.本文以红须腹菌为原料提取红须腹菌多糖,再加以羧甲基化修饰,并通过体内动物实验对两种多糖的免疫活性进行比较研究.采用水提醇沉法提取红须腹菌多糖,并通过氢氧化钠-氯乙酸体系对多糖进行羧甲基化修饰.以小鼠血清细胞因子含量,血细胞数量,单核巨噬细胞吞噬能力及脏器组织形态作为指标评价两种多糖的免疫活性.研究结果表明,红须腹菌多糖总糖含量为 92.06%,羧甲基的取代度为 0.352.红须腹菌多糖及羧甲基多糖均对环磷酰胺造成的小鼠脏器指数下降,部分血清细胞因子含量减少,造血功能及巨噬细胞吞噬能力减弱,以及脾脏和胸腺的组织损伤有较为显著的缓解作用,其中以羧甲基多糖效果更佳.这表明红须腹菌多糖及羧甲基化多糖均具有一定的免疫调节功效,且羧甲基化多糖的体内免疫活性更为显著.
