Combining Artificial Immune System and Clustering Analysis: A Stock Market Anomaly Detection Model

Artificial intelligence research in the stock market sector has been heavily geared towards stock price prediction rather than stock price manipulation. As online trading systems have increased the amount of high volume and re-al-time data transactions, the stock market has increased vulnerability to at-tacks. This paper aims to detect these attacks based on normal trade behavior using an Artificial Immune System (AIS) approach combined with one of four clustering algorithms. The AIS approach is inspired by its proven ability to handle time-series data and its ability to detect abnormal behavior while only being trained on regular trade behavior. These two main points are essential as the models need to adapt over time to adjust to normal trade behavior as it evolves, and due to confidentiality and data restrictions, real-world manipula-tions are not available for training. This paper discovers a competitive alterna-tive to the leading approach and investigates the effects of combining AIS with clustering algorithms;Kernel Density Estimation, Self-Organized Maps, Densi-ty-Based Spatial Clustering of Applications with Noise and Spectral clustering. The best performing solution achieves leading performance using common clustering metrics, including Area Under the Curve, False Alarm Rate, False Negative Rate, and Computation Time.

Data Clustering Algorithm Based on Artificial Immune Network

For the problem that the termination condition of artificial immune network algorithm aiNet is difficult to determine, an intelligent artificial immune network algorithm S-aiNet is proposed. The S-aiNet determines whether the network is saturated by monitoring the change trend of new generation population in the iterative process according to the affinity of the new generation of network cells and existing cells. The algorithm improves the adaptability of aiNet and reduces the number of parameters. For the problem that the network of aiNet updates slowly, a regional search optimization algorithm AS-aiNet is proposed. The AS-aiNet equally divides the antibody space where the network cells and antigen located, and only searches the antibody cells located in the same region as antigens in the immune response. The AS-aiNet reduces the workload of search in the process of immune response and effectively enhances the time efficiency of algorithm operation. Adopting public data set, experiments show that the time efficiency of AS-aiNet is 10% better than that of aiNet.

Analysis on Characteristics of Typical Syndromes of Acquired Immune Deficiency Syndrome Based on the Feature Selection Method

Objective:To discover the population characteristics of the syndrome types of Acquired Immune Deficiency Syndrome.Methods:Data mining method for feature selection was used.Results:Main symptoms based on feature selection are as follows,deficiency of both qi and blood(pale complexion,fear of cold,easy to catch a cold,pale tongue,weak pulse);liver depression and qi stagnation with effulgent fire(anxiety,insomnia,chest and hypochondrium,irregular menstruation,thin and whitish coating on the tongue,stringy pulse);dual deficiency of qi and yin(low-grade fever and night sweating,yellow urine,pale complexion,dysphoria with feverish sensation in chest,dry cough with less phlegm,weakness,dizziness,dry and red tongue,little coating,thread and rapid pulse);deficiency of spleen and kidney,dampness pathogen blockage(diarrhea,loose stool,eat less and abdominal nausea,abdominal pain,sallow complexion,nausea,vomiting,loss of hair,deafness and tinnitus,pale tongue with whitish coating,deep and thready pulse,slippery and rapid pulse);qi deficiency with blood stasis(weakness,spontaneous sweating,dry mouth without desire to drink,easy to catch a cold,shortness of breath,sallow complexion,eat less and loose stools,dim tongue quality,hesitant pulse).Conclusion:Based on the feature selection method,we can find the main characteristics of Acquired Immune Deficiency Syndrome,and provide objective reference for clinical diagnosis and treatment.

Bioinformatics-based analysis of the relationship between core genes and immune infiltration and tumor metastasis in esophageal cancer

We analysed four gene microarray datasets by GEO2R and obtained differential genes expressed in oesophageal cancer.To further elaborate the functions of DGEs,this study performed gene ontology(GO)and Kyoto Encyclopedia of Genes and Genomes(KEGG)enrichment analysis of DEGs.We constructed protein interaction networks of DGEs through the String database and screened core genes.We used the GEPIA online database with the Kaplan-Meier plotter database to verify the expression of Hub genes in expressed normal versus tumour tissues and the effect of Hub genes on overall and disease-free survival in oesophageal cancer.To further understand the relationship between Hub gene and tumour metastasis,we analysed the difference in Hub gene expression in patients without metastatic oesophageal cancer versus those with metastatic oesophageal cancer with the help of the HCMDB database.The relationship between Hub genes and tumour immune infiltration was analysed by the TIMER database.We obtained a total of 149 DEGs,of which 49 were up-regulated genes and 100 were down-regulated genes.These DGEs were importantly enriched in IL-17 signalling pathway,ECM-receptor interactions,p53 signalling pathway,estrogen signalling pathway,complement and coagulation cascade response.We screened 10 Hub genes,MMP9,CXCL8,COL1A1,TIMP1,POSTN,MMP3,MMP1,COL3A1,SERPINE1,LUM,among 149 DGEs.hub genes were all up-regulated in expression in esophageal cancer tissues,in addition,MMP9,T1MP1,CXCL8,POSTN and The expression of COL3A1,LUM,MMP1,MMP3,MMP9,POSTN,SERPINE1 and TIMP1 was positively correlated with the infiltration of immune cells in the tumor microenvironment.In conclusion,our study identified 10 signature genes for oesophageal cancer.These genes are associated with the development,metastasis,prognosis and immune infiltration of oesophageal cancer and may be markers of development,metastasis and prognosis as well as targets for immunotherapy.

基于文献挖掘和网络药理学探析阴虚型免疫性血小板减少症用药规律与作用机制

目的利用数据挖掘技术及网络药理学探讨中药治疗阴虚型免疫性血小板减少症用药规律与潜在作用机制。方法运用中国知网、万方数据库检索中药治疗阴虚型免疫性血小板减少症相关文献,通过中医传承辅助平台V2.5软件分析组方规律,确定常用药对;运用中药系统药理学数据库与分析平台(TCMSP)、本草组鉴数据库、GeneCards数据库获取关键基因和主要靶点信息,利用STRING数据库构建交集靶点蛋白相互作用网络,采用Cytoscape 3.7.1软件中的CytoHubba和MCODE插件筛选出关键靶点信息,采用METASCAPE数据库基因本体(GO)功能富集分析和京都基因与基因组百科全书(KEGG)通路富集分析。结果共筛选得到129篇有效文献,共计130个中药处方,通过关联规则筛选出“生地黄—牡丹皮—旱莲草”为最佳中药复方,HSP90AA1、STAT3、VEGFA、MAPK3等为关键靶点,槲皮素、山柰酚、金合欢素与木犀草素等为主要有效成分,其主要作用机制可能是调控癌症通路、Th17细胞分化及核转录因子κB(NF-κB)信号通路等。结论治疗阴虚型免疫性血小板减少症应抓住止血、凉血、行血三要素,初步揭示常用复方“生地黄—牡丹皮—旱莲草”通过多成分—多靶点—多通路发挥治疗作用,为今后研究提供理论依据。

An artificial immune and incremental learning inspired novel framework for performance pattern identification of complex electromechanical systems

Performance pattern identification is the key basis for fault detection and condition prediction,which plays a major role in ensuring safety and reliability in complex electromechanical systems(CESs).However,there are a few problems related to the automatic and adaptive updating of an identification model.Aiming to solve the problem of identification model updating,a novel framework for performance pattern identification of the CESs based on the artificial immune systems and incremental learning is proposed in this paper to classify real-time monitoring data into different performance patterns.First,an unsupervised clustering technique is used to construct an initial identification model.Second,the artificial immune and outlier detection algorithms are applied to identify abnormal data and determine the type of immune response.Third,incremental learning is employed to trace the dynamic changes of patterns,and operations such as pattern insertion,pattern removal,and pattern revision are designed to realize automatic and adaptive updates of an identification model.The effectiveness of the proposed framework is demonstrated through experiments with the benchmark and actual pattern identification applications.As an unsupervised and self-adapting approach,the proposed framework inherits the preponderances of the conventional methods but overcomes some of their drawbacks because the retraining process is not required in perceiving the pattern changes.Therefore,this method can be flexibly and efficiently used for performance pattern identification of the CESs.Moreover,the proposed method provides a foundation for fault detection and condition prediction,and can be used in other engineering applications.

基于人工智能技术的轻量级网络入侵检测系统设计

以提升网络入侵检测技术水平为目的,设计基于人工智能技术的轻量级网络入侵检测系统。该系统数据采集层利用若干个用户探针连接IDS检测服务器后,使用网络数据包捕获模块捕获用户网络运行数据,再通过传输层内防火墙、核心交换机和MQTT/CoAP通信协议将用户网络运行数据发送到逻辑运算层内,该层利用数据预处理模块对用户网络运行数据进行去噪预处理后,将其输入到基于人工智能的网络入侵检测模块内,通过该模块输出轻量级网络入侵检测结果,然后将检测结果发送到展示层,通过入侵告警信息、数据可视化展示等模块实现人机交互。实验表明:该系统运行较为稳定,可有效检测不同类型网络入侵的同时,其检测及时性和入侵告警能力较好,应用效果良好。

基于数据挖掘和网络药理学研究中药免疫增强剂的作用机制及用药规律

目的采用数据挖掘的方法探究复方专利处方中用于增强免疫力的中药配伍规律,并运用网络药理学、分子对接技术分析其中核心药物的潜在作用机制。方法挖掘国家知识产权局中药增强免疫力的复方专利数据,进行中药频次、关联规则以及复杂网络分析,并筛选出核心药物。利用TCMSP平台筛选核心药物活性成分并进行靶点预测,于疾病数据库OMIM、DrugBank、GeneCards、Uniprot筛选免疫力相关靶点,获取核心中药与免疫力的交集靶点;对交集靶点进行蛋白互作(PPI)分析和基因本体(GO)功能及京都基因与基因组百科全书(KEGG)通路富集分析。使用分子对接技术对药物活性成分、关键靶点进行验证。结果分析中药复方专利得出5味核心药物:黄芪、人参、枸杞子、茯苓、当归,有效活性成分对应靶点214个,1784个免疫力相关靶点,交集靶点55个,关键作用靶点有RELA、TNF、TP53、IL-6。GO分析结果显示主要调控对细菌起源分子的反应、对脂多糖的反应、对生物刺激的反应等。KEGG通路160条,主要涉及脂质与动脉粥样硬化、南美洲锥虫病、TNF信号通路、癌症通路等多条信号通路。分子对接结果显示,槲皮素、山柰酚能较好地与RELA、TNF、TP53、IL-6进行结合。结论专利文献中增强免疫力的中药以补虚药为主,主要有效成分为槲皮素、山柰酚等化合物,以RELA、TNF、TP53、IL-6为关键靶点,通过脂质和动脉粥样硬化、南美洲锥虫病、TNF信号通路、癌症通路等多条通路发挥增强免疫力的作用。

数据挖掘在中医名家辨治血液病中的研究应用

血液病因其高危险性和低治愈率严重地威胁着患者的身心健康。中医治疗血液病有着明显的优势,名中医在辨治血液病方面具有丰富的经验,且临床疗效显著。但是由于中医的辨证依据大多是个人主观思考,无法广泛地指导临床,所以通过数据挖掘技术全面客观地总结临床医家的经验、辨证、方药,将更有利于挖掘出规范化的理法方药及应用规律,以科学、高效的方法实现中医药的继承和创新。

基于数据挖掘研究沈一平治疗免疫性血小板减少症用药规律

目的:基于数据挖掘技术研究沈一平教授运用中医药治疗免疫性血小板减少症(ITP)的用药规律。方法:选取2002年1月1日—2022年10月25日就诊于浙江省中医院血液内科沈一平教授门诊并符合纳入标准及排除标准的ITP患者,运用SPSS Modeler 18.0软件进行数据处理,进行药物频数分析、统计中西医疗效;采用SPSS Modeler 18.0中的Apriori算法进行药物关联规则分析;用SPSS statistics聚类算法对核心药物进行聚类分析。将分析结果请沈一平教授审阅并访谈。结果:共纳入处方2575首,药物频数分析结果示,居前10位中药分别为山药、太子参、无花果、薏苡仁、蒲公英、仙鹤草、防风、白术、黄芪、荆芥。药物归经频次从高到低依次为肝、脾、肺、胃、肾、心、胆、大肠、膀胱、小肠、三焦、心包。药物四气频次从高到低依次为寒、平、温、凉、热,其中,寒、平两种药物所占分别为34.48%、33.27%。药物五味频次以甘、苦、辛为主,酸、涩、淡、咸次之。高频药物关联规则分析结果获得:核心药物组合以止血、清热、疏风、益气、健脾治法为主。高频药物系统聚类分析,得到5个聚类结果:第1类为益气养阴止血药;第2类为清热疏风止血药;第3类为清热凉血药;第4类为补肾填精、温阳益气药;第5类为滋水涵木、酸收止血药。结合访谈发现,沈一平教授运用中医治疗ITP的思路随着时间而有改变,将其分为3个阶段进行观察,随着时间的变化:归肺经药物比例有一定的上升,而归肝经、肾经药物比例较前下降;辛味药比例稍有下降;逐渐增加疏风药、清热药的使用比例。结论:沈一平教授治疗ITP总体治则为健脾益气补肾。在此基础上,加强疏风固表,注意兼证,治病防变,辨病、辨证论治,融合四气五味之理。

基于改进人工免疫算法的天然气泄漏空间关联监测方法

为了实现对天然气泄漏的全面、快速检测,提出基于改进人工免疫算法的天然气泄漏空间关联监测方法。设计天然气泄漏空间关联监测网络,利用各传感器节点采集天然气管道上下游压力、流量、声波等数据。为不同位置传感网络节点分配不同强度等级,以高级网络节点为标准节点,结合各节点位置权值判定相邻节点。各相邻节点间,基于空间相关性,通过滑动窗口的相似度感知异常天然气数据,并通过改进人工免疫算法聚类分析天然气数据空间感知结果,实现天然气泄漏空间关联监测。实验结果说明,所提方法可以有效监测出天然气管道泄漏情况,并即刻断定泄漏地点,监测相对偏差平均值仅为0.12,应用所提方法可提升天然气管道的安全指数,降低管道被损毁程度。

基于数据挖掘分析中医药改善肿瘤患者免疫功能的用药规律

[目的]分析中医药改善肿瘤患者免疫功能的用药规律及组方特点。[方法]检索中国知识资源总库、万方数据知识服务平台、中文科技期刊数据库和中国生物医学文献数据库,筛选中医药改善肿瘤患者免疫功能的临床研究文献,纳入处方中药,建立数据库,对中药性味、归经、功效进行频次统计,对高频中药进行关联规则分析及聚类分析,并挖掘高频中药组合。[结果]共纳入186首处方,涉及中药256味,频次2250次。使用频次>20次的中药共24味,前3位为黄芪、茯苓、白术;中药药性主要为寒、温、平,药味主要为苦、甘、辛,归经主要为肝、肺、脾经,功效分类以补虚药、清热药为主。关联规则分析得到核心药对7个,核心药组43个;聚类分析得到5类处方。[结论]中医药改善肿瘤患者免疫功能以扶正祛邪为原则,扶正以益气为主,有气虚、气血、气阴的偏重;祛邪治标类中药则偏重于清热化痰、理气活血。

基于铁死亡相关长链非编码RNA对子宫内膜癌的预后分析

目的利用子宫内膜癌(EC)的铁死亡相关长链非编码RNA(lncRNA),构建疾病预后模型,为EC提供治疗靶点。方法TCGA中下载EC数据,FerrDb数据库下载铁死亡基因。通过R软件将疾病数据与铁死亡基因取交集得到差异表达基因(DEGs),并对DEGs进行GO和KEGG富集分析。根据Pearson相关分析,得到的lncRNA,通过Lasso-Cox构建模型,筛选用于构建模型的lncRNA,计算风险评分,以中位数区分高、低风险组。利用Kaplan-Meier生存曲线、受试者操作特征(ROC)、决策曲线分析法(DCA)曲线等评估模型的风险评分及临床特征,预测生存效果。应用TIMER、CIBERSORT等算法,对高、低风险组免疫细胞及功能进行分析。用R软件对两组lncRNA进行免疫细胞、功能、检查点及m6A的相关mRNA差异表达分析。结果248个铁死亡基因,与铁死亡相关lncRNA有1616个,80个DEGs。GO分析结果显示,DEGs主要参与氧化应激、调控基底质膜、有机阴离子跨膜转运蛋白活性等。KEEG结果显示,DEGs主要参与铁死亡、谷胱甘肽代谢通路等过程。单因素Cox回归分析初步筛选出45个与铁死亡相关的lncRNA,经Lasso-Cox优化,最终确定14个lncRNA用于构建预后模型。Kaplan-Meier生存曲线显示,低风险组生存状况优于高风险组(P<0.01)。ROC、DCA曲线显示:风险评分预测的生存效果优于传统临床特征;1、2、3年的AUC值分别为0.696、0.715、0.747。单因素、多因素Cox回归分析结果显示,模型风险评分是预测EC患者生存的独立影响因素[HR(95%CI)=1.105(1.081~1.129);HR(95%CI)=1.108(1.081~1.135),均P<0.01]。高、低风险组免疫细胞分布热图显示,两组免疫细胞水平比较,差异有统计学意义(P<0.05)。免疫功能结果显示,高、低风险组APC共同刺激、CCR等比较,差异有统计学意义(P<0.05);免疫检查点结果显示,高、低风险组PDCD-1、CTLA-4比较,差异有统计学意义(P<0.05);m6A甲基化结果显示,高、低风险组YTHDF1、FTO比较,差异有统计学意义(P<0.05)。结论14种铁死亡相关lncRNA可能在EC的肿瘤免疫中发挥重要作用,为治疗疾病提供潜在靶点。

基于国家专利数据库探讨中药复方治疗免疫性血小板减少症用药规律

目的基于国家专利数据库分析中药复方专利治疗免疫性血小板减少症(ITP)的用药及组方规律。方法检索国家专利数据库中建库至2022年5月1日公开治疗ITP的中药复方专利,采用中医传承辅助平台V2.5,利用频数分析、属性分析、关联规则、改进的互信息法及复杂系统熵聚类算法等分析四气五味、归经功效及组方用药规律并进行可视化处理。结果共纳入78首中药复方专利,涉及218味中药,高频药物居于前4位为黄芪、生地黄、牡丹皮、仙鹤草。四气以寒性为主,温、平为辅;五味以甘、苦味为主,其次为辛味;归经主要入肝、肾、脾经;核心组合12个,新处方6首。结论中药复方治疗ITP常用补气、健脾、益肾、填精、凉血、活血、止血之法,同时着眼于病机虚实及体质特点选用不同的核心药物组成,以提高临床疗效。

基于数据挖掘中药治疗免疫性不孕的用药规律

目的:基于数据挖掘技术探讨中药复方治疗免疫性不孕的用药特点及其规律。方法:通过计算机检索国家知识基础设施数据库(CNKI)、中文科技期刊数据库(CCD)、中国生物医学文献数据库(CBM)、中国学术期刊数据库(CSPD)、PubMed、Embase数据库和Cochrane图书馆中有关中医药治疗免疫性不孕疾病的文献,构建免疫性不孕的方药数据库,并运用Excel 2019、origin 21、IBM SPSS Statistics 25及IBM SPSS Modeler 14.1等软件进行频数统计、关联规则分析和系统聚类分析。结果:共纳入101首方药,共涉及1 350频次中药使用,药物118味,使用频率大于20次的药物有22味,依次为当归、菟丝子、甘草、丹参、黄芪、赤芍、枸杞子等,中药主要以补虚药、清热药、活血化瘀药为主,其中补虚药又以补肾药为主,药性以温为主,药味以甘为多,药物归经主要归肝、肾、脾经;关联规则分析得出58条核心关联,系统聚类分析得出药组4个。结论:临床上免疫性不孕的基本治疗大法为从肾论治,中药主要以补肾药为主,同时根据患者相关临床症状,随证配伍清热药、活血化瘀药、健脾益气药等药物进行治疗,往往取得不错的疗效。

基于数据挖掘探析中药促进HIV/AIDS患者免疫功能重建的用药规律

目的基于数据挖掘探析中药促进HIV感染者及AIDS患者(简称HIV/AIDS患者)免疫功能重建的用药规律。方法在中国知网数据库中检索关于口服中药促进HIV/AIDS患者免疫功能重建的文献,纳入相关中药处方并建立数据库。应用Microsoft Excel 2019软件进行分析获得高频中药(使用频次≥10次的中药),并对高频中药的药性、药味、归经、功效分布进行统计。应用TCM Miner关联规则挖掘功能进行高频中药关联规则分析以筛选核心药对。应用SPSS Modeler 14.1的网络模块对高频中药进行复杂网络分析以提取核心中药。应用SPSS 25.0的系统聚类模块对高频中药进行系统聚类分析。结果共获得151首中药处方,包含207味中药。其中高频中药40味,使用频率最高的前10味中药依次为甘草、黄芪、茯苓、白术、黄芩、当归、人参、党参、白芍、半夏;高频中药的药性以温性为主,药味以甘、苦、辛为主,中药归经以脾经、肺经为主,中药功效以补虚、清热为主。通过关联规则分析共得到8组核心药对;通过复杂网络分析提取得到以甘草为中心的29味核心中药,通过聚类分析将高频中药分为5类。结论重建HIV/AIDS患者免疫功能应以甘草、黄芪、白术、茯苓、当归等益气补血中药为主,还应重视应用黄芩、生地黄等中药以清热解毒。临床上可用四君子汤、八珍汤加减促进HIV/AIDS患者免疫功能重建,减少机会性感染的发生。

Screening responsive or resistant biomarkers of immune checkpoint inhibitors based on online databases

Immune checkpoint inhibitors are a promising strategy in the treatment of cancer, especially advanced types. However, not all patients are responsive to immune checkpoint inhibitors. The response rate depends on the immune microenvironment, tumor mutational burden (TMB), expression level of immune checkpoint proteins, and molecular subtypes of cancers. Along with the Cancer Genome Project, various open access databases, including The Cancer Genome Atlas and Gene Expression Omnibus, provide large volumes of data, which allow researchers to explore responsive or resistant biomarkers of immune checkpoint inhibitors? In this review, we introduced some methodologies on database selection, biomarker screening, current progress of immune checkpoint blockade in solid tumor treatment, possible mechanisms of drug resistance, strategies of overcoming resistance, and indications for immune checkpoint inhibitor therapy.

基于数据挖掘探讨含阿胶保健食品的组方规律及应用特点

基于数据挖掘探讨阿胶在保健食品中的应用及配伍规律,为其开发利用提供参考.利用Microsoft Office Excel 2017表统计分析阿胶保健食品的剂型、功效类别、原料使用频次等;借助VOSviewer1.6.5软件展示各原料的配伍关联及配伍密度.运用IBM SPSS Modeler 18.0挖掘原料间隐藏的配伍组合,使用Origin 21.0绘制关联组合气泡图.最终纳入阿胶保健食品232个,涉及原料167种,累计使用1471次.与阿胶配伍的中药多为补虚类、利水渗湿类、活血化瘀类.阿胶保健食品以口服液和胶囊为主,主要发挥增强免疫力、改善营养性贫血等保健功能.在增强免疫力方面,阿胶与党参、大枣、当归、熟地黄、茯苓、人参等密切配伍;而黄芪、党参、枸杞子、大枣、熟地黄、葡萄糖酸亚铁等,则是阿胶改善营养性贫血的关键配伍.

基于人工免疫系统的数据挖掘技术原理与应用

该文首先对人工免疫系统的发展历史和自然免疫系统机制进行简要介绍,之后重点对人工免疫系统在数据挖掘领域中的原理与应用研究进行详细分析综述。主要分两个部分,第一部分是从数据挖掘的主要任务——聚类和分类角度阐述人工免疫系统应用现状,第二部分主要从数据挖掘对象子领域——网络数据挖掘和文件挖掘角度分析人工免疫系统的应用,同时对有代表性的方法及其改进过程进行了详细介绍,指出人工免疫数据挖掘技术中的优点和缺点。最后提出新的研究方向。

免疫阴性选择分类器在信息恢复中的应用

文中的信息恢复系统是基于网络获取文本信息的系统,利用基于熵的信息抽取技术将获得的网络文本转换成特征向量文件.免疫阴性选择分类器是基于免疫系统T细胞选择原理设计检测器,利用协同进化算法进化检测器,进化得到的检测器对信息恢复系统中的文本特征向量进行分类.分类后得到的有用文件用于系统中的信息恢复.实验结果表明,与传统的朴素贝叶斯分类器比较,该方法具有更高的分类准确性,不仅验证了免疫阴性选择分类器的良好性能,同时也提高了信息恢复准确性.