Diverse Deep Matrix Factorization With Hypergraph Regularization for Multi-View Data Representation

Deep matrix factorization(DMF)has been demonstrated to be a powerful tool to take in the complex hierarchical information of multi-view data(MDR).However,existing multiview DMF methods mainly explore the consistency of multi-view data,while neglecting the diversity among different views as well as the high-order relationships of data,resulting in the loss of valuable complementary information.In this paper,we design a hypergraph regularized diverse deep matrix factorization(HDDMF)model for multi-view data representation,to jointly utilize multi-view diversity and a high-order manifold in a multilayer factorization framework.A novel diversity enhancement term is designed to exploit the structural complementarity between different views of data.Hypergraph regularization is utilized to preserve the high-order geometry structure of data in each view.An efficient iterative optimization algorithm is developed to solve the proposed model with theoretical convergence analysis.Experimental results on five real-world data sets demonstrate that the proposed method significantly outperforms stateof-the-art multi-view learning approaches.

An improved four-dimensional variation source term inversion model with observation error regularization

Aiming at the Four-Dimensional Variation source term inversion algorithm proposed earlier,the observation error regularization factor is introduced to improve the prediction accuracy of the diffusion model,and an improved Four-Dimensional Variation source term inversion algorithm with observation error regularization(OER-4DVAR STI model)is formed.Firstly,by constructing the inversion process and basic model of OER-4DVAR STI model,its basic principle and logical structure are studied.Secondly,the observation error regularization factor estimation method based on Bayesian optimization is proposed,and the error factor is separated and optimized by two parameters:error statistical time and deviation degree.Finally,the scientific,feasible and advanced nature of the OER-4DVAR STI model are verified by numerical simulation and tracer test data.The experimental results show that OER-4DVAR STI model can better reverse calculate the hazard source term information under the conditions of high atmospheric stability and flat underlying surface.Compared with the previous inversion algorithm,the source intensity estimation accuracy of OER-4DVAR STI model is improved by about 46.97%,and the source location estimation accuracy is improved by about 26.72%.

Identification of time-varying system and energy-based optimization of adaptive control in seismically excited structure

The combination of structural health monitoring and vibration control is of great importance to provide components of smart structures.While synthetic algorithms have been proposed,adaptive control that is compatible with changing conditions still needs to be used,and time-varying systems are required to be simultaneously estimated with the application of adaptive control.In this research,the identification of structural time-varying dynamic characteristics and optimized simple adaptive control are integrated.First,reduced variations of physical parameters are estimated online using the multiple forgetting factor recursive least squares(MFRLS)method.Then,the energy from the structural vibration is simultaneously specified to optimize the control force with the identified parameters to be operational.Optimization is also performed based on the probability density function of the energy under the seismic excitation at any time.Finally,the optimal control force is obtained by the simple adaptive control(SAC)algorithm and energy coefficient.A numerical example and benchmark structure are employed to investigate the efficiency of the proposed approach.The simulation results revealed the effectiveness of the integrated online identification and optimal adaptive control in systems.

Cold-Start Link Prediction via Weighted Symmetric Nonnegative Matrix Factorization with Graph Regularization

Link prediction has attracted wide attention among interdisciplinaryresearchers as an important issue in complex network. It aims to predict the missing links in current networks and new links that will appear in future networks.Despite the presence of missing links in the target network of link prediction studies, the network it processes remains macroscopically as a large connectedgraph. However, the complexity of the real world makes the complex networksabstracted from real systems often contain many isolated nodes. This phenomenon leads to existing link prediction methods not to efficiently implement the prediction of missing edges on isolated nodes. Therefore, the cold-start linkprediction is favored as one of the most valuable subproblems of traditional linkprediction. However, due to the loss of many links in the observation network, thetopological information available for completing the link prediction task is extremely scarce. This presents a severe challenge for the study of cold-start link prediction. Therefore, how to mine and fuse more available non-topologicalinformation from observed network becomes the key point to solve the problemof cold-start link prediction. In this paper, we propose a framework for solving thecold-start link prediction problem, a joint-weighted symmetric nonnegative matrixfactorization model fusing graph regularization information, based on low-rankapproximation algorithms in the field of machine learning. First, the nonlinear features in high-dimensional space of node attributes are captured by the designedgraph regularization term. Second, using a weighted matrix, we associate the attribute similarity and first order structure information of nodes and constrain eachother. Finally, a unified framework for implementing cold-start link prediction isconstructed by using a symmetric nonnegative matrix factorization model to integrate the multiple information extracted together. Extensive experimental validationon five real networks with attributes shows that the proposed model has very goodpredictive performance when predicting missing edges of isolated nodes.

Graph Regularized L_p Smooth Non-negative Matrix Factorization for Data Representation

This paper proposes a Graph regularized Lpsmooth non-negative matrix factorization(GSNMF) method by incorporating graph regularization and L_p smoothing constraint, which considers the intrinsic geometric information of a data set and produces smooth and stable solutions. The main contributions are as follows: first, graph regularization is added into NMF to discover the hidden semantics and simultaneously respect the intrinsic geometric structure information of a data set. Second,the Lpsmoothing constraint is incorporated into NMF to combine the merits of isotropic(L_2-norm) and anisotropic(L_1-norm)diffusion smoothing, and produces a smooth and more accurate solution to the optimization problem. Finally, the update rules and proof of convergence of GSNMF are given. Experiments on several data sets show that the proposed method outperforms related state-of-the-art methods.

Coalbed Methane Enrichment Regularity and Major Control Factors in the Xishanyao Formation in the Western Part of the Southern Junggar Basin

There are abundant coal and coalbed methane(CBM)resources in the Xishanyao Formation in the western region of the southern Junggar Basin,and the prospects for CBM exploration and development are promising.To promote the exploration and development of the CBM resources of the Xishanyao Formation in this area,we studied previous coalfield survey data and CBM geological exploration data.Then,we analyzed the relationships between the gas content and methane concentration vs.coal seam thickness,burial depth,coal reservoir physical characteristics,hydrogeological conditions,and roof and floor lithology.In addition,we briefly discuss the main factors influencing CBM accumulation.First,we found that the coal strata of the Xishanyao Formation in the study area are relatively simple in structure,and the coal seam has a large thickness and burial depth,as well as moderately good roof and floor conditions.The hydrogeological conditions and coal reservoir physical characteristics are also conducive to the enrichment and a high yield of CBM.We believe that the preservation of CBM resources in the study area is mainly controlled by the structure,burial depth,and hydrogeological conditions.Furthermore,on the basis of the above results,the coal seam of the Xishanyao Formation in the synclinal shaft and buried at depths of 700-1000 m should be the first considered for development.

Extracting Sub-Networks from Brain Functional Network Using Graph Regularized Nonnegative Matrix Factorization

Currently,functional connectomes constructed from neuroimaging data have emerged as a powerful tool in identifying brain disorders.If one brain disease just manifests as some cognitive dysfunction,it means that the disease may affect some local connectivity in the brain functional network.That is,there are functional abnormalities in the sub-network.Therefore,it is crucial to accurately identify them in pathological diagnosis.To solve these problems,we proposed a sub-network extraction method based on graph regularization nonnegative matrix factorization(GNMF).The dynamic functional networks of normal subjects and early mild cognitive impairment(eMCI)subjects were vectorized and the functional connection vectors(FCV)were assembled to aggregation matrices.Then GNMF was applied to factorize the aggregation matrix to get the base matrix,in which the column vectors were restored to a common sub-network and a distinctive sub-network,and visualization and statistical analysis were conducted on the two sub-networks,respectively.Experimental results demonstrated that,compared with other matrix factorization methods,the proposed method can more obviously reflect the similarity between the common subnetwork of eMCI subjects and normal subjects,as well as the difference between the distinctive sub-network of eMCI subjects and normal subjects,Therefore,the high-dimensional features in brain functional networks can be best represented locally in the lowdimensional space,which provides a new idea for studying brain functional connectomes.

Entropy Production in a Non-Isolated Thermodynamic System Taking into Account Regular Factors of Nonrandom Nature

The work illustrates the impossibility of decreasing entropy in a strictly random thermodynamic process in a non-isolated system using the example of heating a planet by solar radiation flux without and taking into account its rotation around its own axis. That is, the second law of thermodynamics formulated for isolated systems continues to govern such systems. We have shown that in order to achieve a stationary state at lower values of temperature and entropy far from thermodynamic equilibrium at a maximum of temperature and entropy, it is necessary to have regular factors of nonrandom nature, one of which in this example is the rotation of the planet around its own axis. This means that the reason for the appearance of ordered structured objects in non-isolated thermodynamic systems is not the random process itself, but the action of dynamic control mechanisms, such as periodic external influences, nonlinear elements with positive feedback, catalysts for chemical reactions, etc. We present the plots with dependences of temperature and entropy versus time in non-isolated systems with purely random processes and in the presence of a control factor of non-random nature-rotation.

Occurrence Factors and Efficient Green Prevention and Control Technology of Peanut Stem Rot Caused by Sclerotium rolfsii in Southern Mountainous Area of Shandong Province

Peanut stem rot caused by Sclerotium rolfsii is a soil-borne disease,and it has become the main disease of peanut in Yimeng mountainous area.S.rolfsii survives the winter as mycelia and sclerotia in soil and debris,becoming the primary source of infection in the following year.The disease resistance of peanut varieties,high temperature and humidity,and cultivation measures are the pathogenic factors affecting the occurrence of peanut stem rot.The disease can be effectively controlled by screening disease-resistant varieties and seed chemical treatment,improving soil by deep tillage and crop rotation,carrying out flowing water management of affected field,cutting off transmission routes,and strengthening seed dressing and triple spraying control.

基于真实世界的难治性高血压临床特征和中药治疗组方规律分析

目的:探讨难治性高血压区别于非难治性高血压的临床特征,挖掘难治性高血压的中药治疗组方规律,为其有效防治提供参考。方法:纳入2010年1月至2024年1月在山东中医药大学附属医院、济南市中医医院、济南市第五人民医院住院治疗的难治性高血压患者520例(难治性高血压组)和非难治性高血压患者550例(非难治性高血压组)。比较两组患者的一般资料、合并症、实验室指标等临床资料,研究难治性高血压和非难治性高血压在临床特征方面的差异,并利用Logistic回归分析探索难治性高血压的危险因素或保护因素。从医院电子医疗系统中收集难治性高血压组患者的中药处方,应用中医传承辅助系统分析处方中药物的使用频次、药性、归经及常用药物组合等规律。结果:与非难治性高血压组比较,难治性高血压组高血压病史更长(P<0.05),合并冠心病、脑梗死的患者占比更高(P<0.05),血钾水平更低(P<0.05),空腹血糖(FBG)、游离四碘甲腺原氨酸(FT4)水平更高(P<0.05)。FBG、FT4水平偏高为难治性高血压的危险因素,钾为难治性高血压的保护因素。中药组方分析显示,使用频次较高的中药包括川芎、天麻、白术、茯苓、钩藤等,中药“四气”中寒性频次最高、“五味”中甘味频次最高、归经中肝经频次最高,使用频次较高的药物组合包括川芎-天麻、钩藤-天麻、川芎-当归、川芎-茯苓、白术-茯苓等。结论:与治疗非难治性高血压相比,治疗难治性高血压更应注重患者血钾、FBG和FT4水平的变化,积极采取干预措施;目前中医治疗难治性高血压多采用活血化瘀、平肝息风、健脾利湿类中药。

尺度因子正则化BN算法

针对进一步提升深度神经网络训练的收敛速度问题,借鉴批规范化(Batch Normalization,BN)算法的特点,提出尺度因子正则化BN算法。通过对BN层中的可学习尺度因子γ施加L2正则化,使得γ得到衰减,进而参数的梯度上界降低,优化空间更加平滑。基于VGG16 Net与AlexNet,在cifar10、cifar100及裂缝图像数据集上进行该算法与BN算法的图像分类对比实验,结果表明该算法不仅提高了网络训练的收敛速度,而且在相同训练次数下提高了准确率。

基于MRSDAE-KPCA结合Bi-LST的滚动轴承剩余使用寿命预测

针对现有滚动轴承剩余使用寿命预测方法在提取数据特征时没有充分考虑数据的内部分布,且在构建健康因子时还需要专家经验进行人工提取等问题,提出一种基于流形正则化堆栈去噪自编码器、核主成分分析并结合双向长短时记忆网络的滚动轴承剩余使用寿命预测方法。首先采用无监督的堆栈去噪自编码器网络对原始振动数据进行深层特征提取,并使用核主成分分析法进一步降维,以提高健康因子的指标稳定性;然后在堆栈去噪自编码器中加入流形正则化,最大程度保留编码器隐藏层内部的数据分布结构,提高模型提取数据特征的有效性。最后使用双向长短时记忆网络预测轴承的剩余使用寿命,并采用AdaMax优化算法对网络模型的超参数进行自适应寻优。分析结果表明,提出的滚动轴承剩余使用寿命预测方法具有更高的精度。

龙陵县新寨-茅草园稀土矿特征及控矿条件浅析

龙陵新寨-茅草园地区花岗岩风化壳离子吸附型稀土矿床受内生地质和表生地质条件双重控制,主要赋存于白垩纪花岗岩体全风化层中下部及强风化层上部,V 1-1矿体分布面积38.59km 2,单工程控制矿体品位(SREO)0.035%~0.128%,平均0.047%;V 1-2矿体分布面积16.85 km 2,单工程控制矿体品位(SREO)0.035%~0.110%,平均0.048%,达大型远景规模,具有较好的勘查开发前景。

Non-uniform thermal behavior of single-layer spherical reticulated shell structures considering time-variant environmental factors: analysis and design

Contrary to conventional design methods that assume uniform and slow temperature changes tied to atmospheric conditions,single-layer spherical reticulated shells undergo significant non-uniform and time-variant temperature variations due to dynamic environmental coupling.These differences can affect structural performance and pose safety risks.Here,a systematic numerical method was developed and applied to simulate long-term temperature variations in such a structure under real environmental conditions,revealing its non-uniform distribution characteristics and time-variant regularity.A simplified design method for non-uniform thermal loads,accounting for time-variant environmental factors,was theoretically derived and validated through experiments and simulations.The maximum deviation and mean error rate between calculated and tested results were 6.1℃ and 3.7%,respectively.Calculated temperature fields aligned with simulated ones,with deviations under 6.0℃.Using the design method,non-uniform thermal effects of the structure are analyzed.Maximum member stress and nodal displacement under non-uniform thermal loads reached 119.3 MPa and 19.7 mm,representing increases of 167.5%and 169.9%,respectively,compared to uniform thermal loads.The impacts of healing construction time on non-uniform thermal effects were evaluated,resulting in construction recommendations.The methodologies and conclusions presented here can serve as valuable references for the thermal design,construction,and control of single-layer spherical reticulated shells or similar structures.

三维大地电磁测深阶段式自适应正则化反演

如何合理地确定正则化因子是地球物理正则化反演领域的研究热点。阶段式自适应算法可以充分发挥模型稳定器的作用,提高反演结果的稳定性,但是该算法仅在一维、二维大地电磁测深(Magnetotelluric,MT)反演中得以实现。目前,三维MT反演正在快速发展,基于此,本文将阶段式自适应正则化算法引入三维MT正则化反演,按照“阶段”而不是“迭代次数”自适应地调整正则化因子的取值,进而观察反演结果的变化。本文设计单块体和双块体模型试验,并特意设置了较大的迭代次数,进而观察反演结果随反演进程的变化情况。模型试验表明:阶段式自适应算法是适用于三维MT正则化反演的,该算法在反演的后期可以更好地保持解的稳定,故此,从解的稳定性这个角度去考量正则化因子的选择是一种值得探索的方向。

云南白牛厂银多金属矿床成矿元素组合与空间矿化规律研究

云南白牛厂银多金属矿床位于华夏地块、扬子地块和印支地块的结合处,受多期地质作用的影响,区域成矿地质条件优越。本文在建立探矿工程数据库和矿体模型的基础上,采用地球化学和统计学结合的方法,对主成矿元素数据进行深入挖掘。成矿元素三角图解结果显示,矿区Zn/Pb值集中分布在0.70~3.50之间,在该区间范围Ag、Sn和Cu元素品位也较高,Zn/Pb值对成矿流体示踪具有指示意义。主成分分析结果显示,P_(1)和P_(2)两个主成分能够解释原变量的大部分信息,其中P_(1)主成分元素组合为Ag-Pb-Zn,代表中温成矿元素组合;P_(2)主成分元素组合为Sn-Zn/Pb值,代表高温成矿元素组合。趋势面分析结果显示,P_(1)矿化强度南低北高,P_(2)矿化强度南高北低。因此,矿化热液的源头位于矿区南部,成矿流体由南向北运移并沉淀成矿。

两阶段非负矩阵分解算法及其在光谱解混中的应用

非负矩阵分解问题(nonnegative matrix factorization,NMF)模型已成功应用至高光谱遥感影像处理中的光谱解混工作,由于NMF优化模型具有多个局部极小点,使得分解结果不稳定。设计初始化方法或者选择带正则项的问题模型是提高分解精度的两种常用方法。本文提出了两阶段的NMF算法,实现了初始点选取和正则项设计的结合。第一阶段借助k-均值获得k个聚类中心,给出迭代的初始点;利用第一阶段的初始矩阵U^(0),定义了针对端元矩阵的正则项‖U-U^(0)‖_(F)^(2),第二阶段采用基于交替非负最小二乘框架的投影梯度算法,求解新的正则化NMF问题。正则项中的端元初始矩阵U^(0)除了采用k-均值获得k个聚类中心,也可采用真实地物光谱,它的引入提高了算法的灵活度。数值结果表明新算法更加稳定,且分解的精确性有效提高。

桥本甲状腺炎并发甲状腺毒症人群临床症状及证型分布规律研究

背景中国传统医学对桥本甲状腺炎并发甲状腺毒症的发生、发展和诊疗已经有了系统的认识,但是目前关于本病人群中医临床症状和证型分布情况研究甚少,国家行业标准中亦缺乏关于本病的证型分布及证候诊断标准的描述。目的运用因子分析联合聚类分析探讨桥本甲状腺炎并发甲状腺毒症人群临床症状及证型分布规律,为临床辨证提供依据,促进桥本甲状腺炎并发甲状腺毒症证候标准化研究。方法收集2020年12月—2021年12月就诊于北京中医药大学东直门医院东城院区、通州院区、北京中医药大学孙思邈医院甲状腺病科门诊符合诊断标准的171例桥本甲状腺炎并发甲状腺毒症患者,使用《桥本甲状腺炎并发甲状腺毒症中医四诊信息采集表》对症状/体征、舌、脉等四诊信息进行采集,基于因子分析和聚类分析研究桥本甲状腺炎并发甲状腺毒症的症状及证型分布规律。结果171例桥本甲状腺炎并发甲状腺毒症患者中男17例、女154例,平均年龄(39.98±13.30)岁,其中20~60岁患者占87.72%。症状分布方面出现频率较高的症状有神疲乏力、心慌心悸、烦躁或急躁易怒,体征有颈前肿大、手指震颤,频率较高的舌象有舌红、舌瘦薄和舌有齿痕,苔质为苔白和苔薄,脉象是脉弦、脉数。收集调查表的82个四诊条目因子分析,提取出25个公因子,累计方差贡献率为70.562%,筛选出具有意义的症状62项。利用因子分析得到的25个公因子结果作为变量对其进行R型系统聚类分析,共得到5类证候分型,分别是:肝郁痰凝证、阴虚火旺证、脾肾阳虚证、肝郁气滞证、气阴两虚证。结论桥本甲状腺炎并发甲状腺毒症的基本中医证候可分为肝郁痰凝证、阴虚火旺证、脾肾阳虚证、肝郁气滞证、气阴两虚证。

宁夏卫宁北山地区伴生钴矿床地质特征、控矿因素及找矿方向

卫宁北山地区位于北祁连造山带东段,是宁夏境内钴矿成矿条件最好的地区之一。为详细了解该地区钴矿形成条件及矿化规律,在详细野外调查基础上,综合前人勘查成果,对卫宁北山地区典型伴生钴矿床地质特征、控矿因素及时空分布规律进行了总结,提出了下一步找矿方向。研究表明:大铜沟铜钴矿、茶梁子铁钴矿和土窑铁钴矿是该地区目前已发现的3个代表性伴生钴矿床,其中大铜沟铜钴矿共发现铜钴矿体3个,Co品位最高达0.06%,含钴矿物主要为辉砷钴矿、含钴黄铁矿和含钴褐铁矿;茶梁子铁钴矿分布有4条矿带共8个铁钴矿体,Co品位最高达0.03%,含钴矿物主要为含钴褐铁矿;土窑铁钴矿只发现1条铁钴矿体,Co品位最高为0.20%,含钴矿物与茶梁子相似。钴矿受断裂构造控制明显,其中西部主要受EW向断裂及其与NE向断裂联合控制,东部主要受SN向断裂控制。钴矿主要赋存于上石炭统土坡组中,为主要矿源层;岩性控矿主要表现在“硅钙面”和能干性不同的岩性组合界面,控制了矿质沉淀。钴矿化形成时间主要为印支期,Co成矿主要与Cu、Au、Fe和Mn关系密切,且与Cu、Au有关的钴矿主要分布于西部,而与Fe、Mn有关的钴矿分布于东部。多期构造叠加及热液改造可能是造成该地区矿种多样的主要原因。卫宁北山西部EW向断裂及其与NE向断裂交汇部位、东部SN向石炭系和泥盆系界面断裂、土坡组内“硅钙面”和能干性不同的岩性组合界面是寻找钴矿最有利部位,孔雀石化、褐铁矿化等围岩蚀变是铜钴矿、铁钴矿最重要的找矿标志。

转录因子HNF1A、HNF4A和FOXA2调节肝细胞蛋白质N-糖基化

Hepatocyte nuclear factor 1 alpha(HNF1A),hepatocyte nuclear factor 4 alpha(HNF4A),and forkhead box protein A2(FOXA2)are key transcription factors that regulate a complex gene network in the liver,cre-ating a regulatory transcriptional loop.The Encode and ChIP-Atlas databases identify the recognition sites of these transcription factors in many glycosyltransferase genes.Our in silico analysis of HNF1A,HNF4A.and FOXA2 binding to the ten candidate glyco-genes studied in this work confirms a significant enrich-ment of these transcription factors specifically in the liver.Our previous studies identified HNF1A as a master regulator of fucosylation,glycan branching,and galactosylation of plasma glycoproteins.Here,we aimed to functionally validate the role of the three transcription factors on downstream glyco-gene transcriptional expression and the possible effect on glycan phenotype.We used the state-of-the-art clus-tered regularly interspaced short palindromic repeats/dead Cas9(CRISPR/dCas9)molecular tool for the downregulation of the HNF1A,HNF4A,and FOXA2 genes in HepG2 cells-a human liver cancer cell line.The results show that the downregulation of all three genes individually and in pairs affects the transcrip-tional activity of many glyco-genes,although downregulation of glyco-genes was not always followed by an unambiguous change in the corresponding glycan structures.The effect is better seen as an overall change in the total HepG2 N-glycome,primarily due to the extension of biantennary glycans.We propose an alternative way to evaluate the N-glycome composition via estimating the overall complexity of the glycome by quantifying the number of monomers in each glycan structure.We also propose a model showing feedback loops with the mutual activation of HNF1A-FOXA2 and HNF4A-FOXA2 affecting glyco-genes and protein glycosylation in HepG2 cells.