Anomaly Detection Based on Data-Mining for Routing Attacks in Wireless Sensor Networks

With the increasing deployment of wireless sensordevices and networks,security becomes a criticalchallenge for sensor networks.In this paper,a schemeusing data mining is proposed for routing anomalydetection in wireless sensor networks.The schemeuses the Apriori algorithm to extract traffic patternsfrom both routing table and network traffic packetsand subsequently the K-means cluster algorithmadaptively generates a detection model.Through thecombination of these two algorithms,routing attackscan be detected effectively and automatically.Themain advantage of the proposed approach is that it isable to detect new attacks that have not previouslybeen seen.Moreover,the proposed detection schemeis based on no priori knowledge and then can beapplied to a wide range of different sensor networksfor a variety of routing attacks.

Genome-Wide Identification of Genes Responsive to ABA and Cold/Salt Stresses in Gossypium hirsutum by Data-Mining and Expression Pattern Analysis

For making better use of nucleic acid resources of Gossypium hirsutum, a data-mining method was used to identify putative genes responsive to various abiotic stresses in G. hirsutum. Based on the compiled database including genes involved in abiotic stress response in Arabidopsis thaliana and the comprehensive analysis tool of GENEVESTIGATOR v3, 826 genes up-regulated or down-regulated significantly in roots or leaves during salt or cold treatment in Arabidopsis were identified. As compared to these 826 Arabidopsis genes annotated, 38 homologous expressed sequence tags （ESTs） from G. hirsutum were selected randomly and their expression patterns were studied using a quantitative real-time reverse transcription-polymerase chain reaction method. Among these 38 ESTs, about 55% of the genes （21 of 38） were different in response to ABA between cotton and Arabidopsis, whereas 70% of genes had similar responses to cold and salt treatments, and some of them which had not been characterized in Arabidopsis are now being investigated in gene function studies. According to these results, this approach of analyzing ESTs appears effective in large-scale identification of cotton genes involved in abiotic stress and might be adopted to determine gene functions in various biologic processes in cotton.

Establishment of the Agricultural Knowledge Management System in the Knowledge-oriented Government

In order to optimizing the process of the government agricultural decision-making, based on the theories and technologies of the knowledge management, the meaning of the knowledge-based government is firstly analyzed. Combining with the detailed requirements of government for agricultural knowledge management, an agricultural knowledge management system including the agricultural knowledge sharing system, the agricultural Web data-mining system and the agricultural expert decision system is established in the paper.

Research of CBR, DM and smart algorithms based design methods for high-rise building structure form-selection

First, the high-rise building structure design process is divided into three relevant steps, that is, scheme generation and creation, performance evaluation, and scheme optimization. Then with the application of relational database, the case database of high-rise structures is constructed, the structure form-selection designing methods such as the smart algorithm based on CBR, DM, FINS, NN and GA is presented, and the original forms system of this method and its general structure are given. CBR and DM are used to generate scheme candidates; FINS and NN to evaluate and optimize the scheme performance; GA to create new structure forms. Finally, the application cases are presented, whose results fit in with the real project. It proves by combining and using the expert intelligence, algorithm intelligence and machine intelligence that this method makes good use of not only the engineering project knowledge and expertise but also much deeper knowledge contained in various engineering cases. In other words, it is because the form selection has a strong background support of vast real cases that its results prove more reliable and more acceptable. So the introduction of this method provides an effective approach to improving the quality, efficiency, automatic and smart level of high-rise structures form selection design.

Analysis of effect of external therapies of traditional Chinese medicine on eczema by data mining

Objective:To determine medication regularity external therapies of Traditional Chinese medicine of eczema by data mining.Methods:Papers were retrieved from databases Pubmed,CNKI,WF,VIP,CBM,Web of Science and Embase.From the establishment of the database to April 2020 were searched.The main points of Medication Regularity were established with Excel 2016 software;the characteristics and laws in external therapies of Traditional Chinese medicine Treatment of eczema were analyzed with the relevance rule and cluster analysis Methods in data mining technology.Results:The property and flavor of the herbs mainly used were cold,bitter,while the channel which are mostly involved included liver meridian,lung meridian and Bladder Meridian,The analysis of association rules showed that kushen and difuzi had the highest correlation.The clustering analysis figured out 7groups of the herbs.Conclusion:The study presents the common pair herbs in the treatment of external therapies of Traditional Chinese medicine of eczema,which provides the approach to syndrome differentiation and medication in clinical treatment of eczema.

Meta analysis and data mining of the method of yishenhuoxue in the treatment of nonproliferative diabetic retinopathy

Objective:To evaluate the efficacy and safety of the method of Yishen Huoxue in the intervention of nonproliferative diabetic retinopathy(NPDR)by Meta analysis and explore the medication regularity of Chinese Medicine(TCM)based on data mining.Methods:The related literature of TCM in the treatment of NPDR published in CNKI,VIP,WF,PubMed,the Cochrane Library,SinoMed,Embase were collected.The quality of the included literature was evaluated with reference to the Cochrane System Evaluators'Handbook,and statistical analysis was performed by applying Revman 5.4.1 software.After normalization of the Chinese medicine names,association rule analysis was performed by using SPSS Modeler 18,and then Cytoscape was used to produce complex network diagrams.Results:20 RCTs were included.Meta-analysis results showed that the method of Yishen Huoxue or Yishen Huoxue combined with western medicine were better than the control group in improving the total clinical efficiency[RR=1.21,95%CI(1.16,1.27),P<0.00001],TCM symptom efficacy[RR=1.28,95%CI(1.18,1.39),P<0.00001],and visual acuity[MD=0.11,95%CI(0.05,0.17),P=0.0001],HDL-C[MD=0.14,95%CI(0.03,0.25),P=0.02];reducing the number of fundus hemangiomas[MD=-3.51,95%CI(-5.73,-1.28),P=0.002],hemorrhagic spot area[MD=-0.70,95%CI(-0.95,-0.46),P<0.00001],CMT[MD=-35.31,95%CI(-55.47,-15.14),P=0.0006],FBG[MD=-0.39,95%CI(-0.72,-0.05),P=0.02],LDL-C[MD=-0.36,95%CI(-0.64,-0.08),P=0.01],whole high blood viscosity[MD=-0.43,95%CI(-0.75,-0.12),P=0.006],plasma viscosity[MD=-0.36,95%CI(-0.67,-0.06),P=0.02]and fibrinogen[MD=-0.50,95%CI(-0.81,-0.19),P=0.002].The differences were statistically significant.The 20 recipes entered involved a total of 70 herbal medicines.It is analyzed that the high-frequency drugs and the core drugsare gou qi,san qi,dan shen,haung qi,sheng di huang,et al.The association rule analysis summarizes the commonly used pairs including:sheng di huang-san qi,sheng di huang-gou qi,et al.Conclusions:Compared with western medicine treatment alone,the method of Yishen Huoxue or Yishen Huoxue combined with western medicine produce better effects,but it still needs to be verified by higher quality clinical studies.

基于数据挖掘和元模型的离心压缩机机匣多目标优化（英文）

Casing treatment(CT) has the potential to extend the stable operating range of a centrifugal compressor.A multi-objective optimization method is proposed to optimize the CT of centrifugal compressors. The method consists of Kriging metamodel, Genetic Algorithm(GA), data-mining techniques and CFD code. Firstly, data-mining techniques are used to analyze the initial design space. The correlations between design variables and objectives are extracted,resulting in a refined design space. Then, the global optimization of CT is conducted by GA based on data-mining results. After optimization, the performance of the centrifugal compressor shows a considerable improvement over the whole speed line. The isentropic efficiency increases by 2.05%, and the stall margin improves by 7.11%. Finally, the mechanism behind the performance improvement is further clarified by detailed flow analysis.

Acupoint selection rules for acupoint application in lung diseases in the post-epidemic era

Objective:To summarize the rules of acupoint selection of acupoint application to prevent and treat lung diseases under the background the post-epidemic era using data-mining technology.Method:The CNKI,Wanfang database,and VIP database were searched for clinical study articles on lung diseases treated by acupoint application published in the past 5 years.Data-eligible papers were extracted to establish a database of acupoint application for lung disease using Microsoft Excel 2019,with the goal of analyzing the frequency of acupoints,acupoint-meridian association,acupoint-location association,specific acupoint frequency,and cluster analysis.Association rules,consisting of acupoints with an application frequency of≥10,were devised by the Apriori algorithm to explore the correlation between acupoint groups and to analyze the rules of the compatibility of acupoint prescriptions.Results:A total of 229 eligible papers met our inclusion criteria.Forty-seven acupoints were applied,for a total frequency of acupoints of 1,035 times.Among these,acupoints for lung diseases were primarily distributed in the back-and-waist and chest-and-abdomen areas.From the analysis of the association rules,we obtained four groups of acupoint association rules based on acupoint clusters with a frequency≥10 and found that Feishu(BL 13),Tiantu(CV 22),Dazhui(GV 14),Dingchuan(EX-B1),and Danzhong(CV 17)constitute the core acupoints of prescriptions for clinical acupoint application to prevent and treat lung diseases.Conclusion:It is clearly shown that the core acupoints are relatively concentrated and that the selected acupoints were mainly locally selected,which could be a matching reference for the long-term prevention and treatment of lung diseases,including COVID-19.

Features of SAS Enterprise Guide for probabilistic Modeling System, Macroeconomic Analysis and Forecasting

This paper addresses to the problem of using SAS Enterprise Guide 6.1 as a means for building probabilistic models and as optimum method of modeling gross domestic product in terms of the economic crisis and social threats is proposed. Today in a complex socio-political and economic situation growing influence of external factors, presence of uncertainties and risks there exists a problem of anticipating potential threats in the humanitarian and social spheres and ways to overcome them aiming to provide food security and controllability of ecological situation. All these problems, as reported in the NATO program ＂Science for Peace and Security＂, are of high priority for the countries that need to take into account threats to security, including Ukraine. That is why in the framework of the project NUKR. SFPP G4877 ＂Modeling and Mitigation of Social Disasters Caused by Catastrophes and Terrorism＂ the problems of scientific prediction of national economy for the period to 2030 as one of the measures preventing growth of social tension in the country are disclosed.

Prediction of fracture initiation in cohesive soils based on data mining modelling and large-scale laboratory verification

Many empirical and analytical methods have been proposed to predict fracturing pressure in cohesive soils.Most of them take into account three to four specific influencing factors and rely on the assumption of a failure mode.In this study,a novel data-mining approach based on the XGBoost algorithm is investigated for predicting fracture initiation in cohesive soils.This has the advantage of handling multiple influencing factors simultaneously,without pre-determining a failure mode.A dataset of 416 samples consisting of 14 distinct features was herein collected from past studies,and used for developing a regressor and a classifier model for fracturing pressure prediction and failure mode classification respectively.The results show that the intrinsic characteristics of the soil govern the failure mode while the fracturing pressure is more sensitive to the stress state.The XGBoost-based model was also tested against conventional approaches,as well as a similar machine learning algorithm namely random forest model.Additionally,several large-scale triaxial fracturing tests and an in-situ case study were carried out to further verify the generalization ability and applicability of the proposed data mining approach,and the results indicate a superior performance of the XGBoost model.

An improved deep forest model for forecast the outdoor atmospheric corrosion rate of low-alloy steels

The paper proposes a new deep structure model,called Densely Connected Cascade Forest-Weighted K Nearest Neighbors(DCCF-WKNNs),to implement the corrosion data modelling and corrosion knowledgemining.Firstly,we collect 409 outdoor atmospheric corrosion samples of low-alloy steels as experiment datasets.Then,we give the proposed methods process,including random forests-K nearest neighbors(RF-WKNNs)and DCCF-WKNNs.Finally,we use the collected datasets to verify the performance of the proposed method.The results show that compared with commonly used and advanced machine-learning algorithms such as artificial neural network(ANN),support vector regression(SVR),random forests(RF),and cascade forests(cForest),the proposed method can obtain the best prediction results.In addition,the method can predict the corrosion rates with variations of any one single environmental variable,like pH,temperature,relative humidity,SO2,rainfall or Cl-.By this way,the threshold of each variable,upon which the corrosion rate may have a large change,can be further obtained.

Identification of charging behavior characteristic for large-scale heterogeneous electric vehicle fleet

This paper aims to accurately identify parameters of the natural charging behavior characteristic(NCBC)for plug-in electric vehicles(PEVs) without measuring any data regarding charging request information of PEVs. To this end, a data-mining method is first proposed to extract the data of natural aggregated charging load(ACL) from the big data of aggregated residential load. Then, a theoretical model of ACL is derived based on the linear convolution theory. The NCBC-parameters are identified by using the mined ACL data and theoretical ACL model via the derived identification model. The proposed methodology is cost-effective and will not expose the privacy of PEVs as it does not need to install sub-metering systems to gather charging request information of each PEV. It is promising in designing unidirectional smart charging schemes which are attractive to power utilities. Case studies verify the feasibility and effectiveness of the proposed methodology.

非线性光学数据库:理论预测助力材料的快速发现

现代激光技术迫切需要能够通过二次谐波产生相干光的非线性光学材料.然而,只有很少一部分非中心对称晶体材料的非线性光学性质被实验或者理论研究,针对高性能非线性光学晶体材料的探索仍非常有限.本工作建立了迄今为止最大的计算非线性光学晶体材料数据库,其中包含2354个非中心对称晶体结构,以及它们的倍频系数和带隙.本文提供了理论数据的计算细节和其与实验数据的对比验证,以及数据库的详细描述.该数据库的重要特点之一是它包含大量通过进化算法搜索发现的新的热力学稳定和亚稳定结构,这为寻找具有更好性能的新型非线性光学材料提供了可能性.

Multi-granularity decision rough set attribute reduction algorithm under quantum particle swarm optimization

The existing attribute reductions are carried out using equivalence relations under a complete information system,and there is less research on attribute reductions of incomplete information systems with new theoretical models such as multi-granularity decision rough sets.To address the above shortcomings,this paper first makes up a pessimistic-optimistic multi-granularity decision rough set model based on tolerance relations in incomplete information systems.The concepts of attribute importance and approximate distribution quality are introduced into the model to form an attribute reduction algorithm under incomplete information systems.Secondly,due to the NPhard problem of attribute reduction,in order to further ensure the accuracy of the reduction result,this paper proposes a pessimistic-optimistic multi-granularity reduction algorithm under quantum particle swarm optimization.Experimental results on multipleattribute data proved that the algorithm proposed in this paper can effectively attribute reduction in the decision table with missing data.At the same time,the algorithm of this paper has the role of iterative optimization search,ensuring the accuracy of the reduction results and increasing the applicability of multi-granularity decision rough sets.

Fitting logistic regression models to assess vitamin D deficiency with clinical parameters in chronic hepatitis B patients

Statistical models provide a quantitative structure with which clinicians can evaluate their hypotheses to explain patterns in observed data and generate forecasts.In contrast,vitamin D is an important immune modulator that plays an emerging role in liver diseases such as chronic hepatitis B(CHB).Therefore,we quantified 25(OH)D_(3) serum levels in 292 CHB patients tested for their association with clinical parameters.Of 292 patients,69(63%),95(47%),and 39(19%)had severe vitamin D deficiency(25(OH)D_(3)<10 ng/mL),vitamin D insufficiency(25(OH)D_(3)10 and<20 ng/mL),or adequate vitamin D serum levels(25(OH)D_(3)20 ng/mL),respectively.In both univariate and multivariate analyses,zinc serum level was a strong predictor of low 25(OH)D_(3) serum levels(P<0.001).Results of fitted models showed that lower vitamin D levels were significantly associated with:younger age,lower uric acid levels,HBeAg-positive status,lower calcium levels(p<0.05).Vitamin D deficiency(<20 ng/ml)or severe deficiency(<10 ng/ml)was observed more frequently among HBV patients(52%).Vitamin D deficiency was observed in most CHB patients.Generally,our results recommend that substitution of vitamin D can be a substitution method in the treatment of patients with HBV-associated disorders.

Web-Based Biomedical Literature Mining

With an upsurge in biomedical literature,using data-mining method to search new knowledge from literature has drawing more attention of scholars.In this study,taking the mining of non-coding gene literature from the network database of PubMed as an example,we first preprocessed the abstract data,next applied the term occurrence frequency(TF) and inverse document frequency(IDF)(TF-IDF) method to select features,and then established a biomedical literature data-mining model based on Bayesian algorithm.Finally,we assessed the model through area under the receiver operating characteristic curve(AUC),accuracy,specificity,sensitivity,precision rate and recall rate.When 1 000 features are selected,AUC,specificity,sensitivity,accuracy rate,precision rate and recall rate are 0.868 3,84.63%,89.02%,86.83%,89.02% and 98.14%,respectively.These results indicate that our method can identify the targeted literature related to a particular topic effectively.