Supervised local and non-local structure preserving projections with application to just-in-time learning for adaptive soft sensor

In soft sensor field, just-in-time learning(JITL) is an effective approach to model nonlinear and time varying processes. However, most similarity criterions in JITL are computed in the input space only while ignoring important output information, which may lead to inaccurate construction of relevant sample set. To solve this problem, we propose a novel supervised feature extraction method suitable for the regression problem called supervised local and non-local structure preserving projections(SLNSPP), in which both input and output information can be easily and effectively incorporated through a newly defined similarity index. The SLNSPP can not only retain the virtue of locality preserving projections but also prevent faraway points from nearing after projection,which endues SLNSPP with powerful discriminating ability. Such two good properties of SLNSPP are desirable for JITL as they are expected to enhance the accuracy of similar sample selection. Consequently, we present a SLNSPP-JITL framework for developing adaptive soft sensor, including a sparse learning strategy to limit the scale and update the frequency of database. Finally, two case studies are conducted with benchmark datasets to evaluate the performance of the proposed schemes. The results demonstrate the effectiveness of LNSPP and SLNSPP.

New supervised learning classifiers for structural damage diagnosis using time series features from a new feature extraction technique

The motivation for this article is to propose new damage classifiers based on a supervised learning problem for locating and quantifying damage.A new feature extraction approach using time series analysis is introduced to extract damage-sensitive features from auto-regressive models.This approach sets out to improve current feature extraction techniques in the context of time series modeling.The coefficients and residuals of the AR model obtained from the proposed approach are selected as the main features and are applied to the proposed supervised learning classifiers that are categorized as coefficient-based and residual-based classifiers.These classifiers compute the relative errors in the extracted features between the undamaged and damaged states.Eventually,the abilities of the proposed methods to localize and quantify single and multiple damage scenarios are verified by applying experimental data for a laboratory frame and a four-story steel structure.Comparative analyses are performed to validate the superiority of the proposed methods over some existing techniques.Results show that the proposed classifiers,with the aid of extracted features from the proposed feature extraction approach,are able to locate and quantify damage;however,the residual-based classifiers yield better results than the coefficient-based classifiers.Moreover,these methods are superior to some classical techniques.

Global Inference Preserving Projection for Semi-supervised Discriminant Analysis

Semi-supervised dimensionality reduction is an important research area for data classification. A new linear dimensionality reduction approach, global inference preserving projection （GIPP）, was proposed to perform classification task in semi-supervised case. GIPP provided a global structure that utilized the underlying discriminative knowledge of unlabeled samples. It used path-based dissimilarity measurement to infer the class label information for unlabeled samples and transformd the diseriminant algorithm into a generalized eigenequation problem. Experimental results demonstrate the effectiveness of the proposed approach.

Semi-Supervised Dimensionality Reduction of Hyperspectral Image Based on Sparse Multi-Manifold Learning

In this paper, we proposed a new semi-supervised multi-manifold learning method, called semi- supervised sparse multi-manifold embedding (S3MME), for dimensionality reduction of hyperspectral image data. S3MME exploits both the labeled and unlabeled data to adaptively find neighbors of each sample from the same manifold by using an optimization program based on sparse representation, and naturally gives relative importance to the labeled ones through a graph-based methodology. Then it tries to extract discriminative features on each manifold such that the data points in the same manifold become closer. The effectiveness of the proposed multi-manifold learning algorithm is demonstrated and compared through experiments on a real hyperspectral images.

SpectraTr:A novel deep learning model for qualitative analysis of drug spectroscopy based on transformer structure

The drug supervision methods based on near-infrared spectroscopy analysis are heavily dependent on the chemometrics model which characterizes the relationship between spectral data and drug categories.The preliminary application of convolution neural network in spectral analysis demonstrates excellent end-to-end prediction ability,but it is sensitive to the hyper-parameters of the network.The transformer is a deep-learning model based on self-attention mechanism that compares convolutional neural networks(CNNs)in predictive performance and has an easy-todesign model structure.Hence,a novel calibration model named SpectraTr,based on the transformer structure,is proposed and used for the qualitative analysis of drug spectrum.The experimental results of seven classes of drug and 18 classes of drug show that the proposed SpectraTr model can automatically extract features from a huge number of spectra,is not dependent on pre-processing algorithms,and is insensitive to model hyperparameters.When the ratio of the training set to test set is 8:2,the prediction accuracy of the SpectraTr model reaches 100%and 99.52%,respectively,which outperforms PLS DA,SVM,SAE,and CNN.The model is also tested on a public drug data set,and achieved classification accuracy of 96.97%without preprocessing algorithm,which is 34.85%,28.28%,5.05%,and 2.73%higher than PLS DA,SVM,SAE,and CNN,respectively.The research shows that the SpectraTr model performs exceptionally well in spectral analysis and is expected to be a novel deep calibration model after Autoencoder networks(AEs)and CNN.

Thread Structure Prediction for MOOC Discussion Forum

Discussion forums are an indispensable interactive component for Massive Open Online Courses(MOOC).However,the organization of current discussion forums is not well-designed.Trouble-shooting threads are valuable for both learners and instructors,but they are drowned out in the forums with huge amounts of threads.This work first built a labeled data set for trouble-shooting thread structure prediction by crowdsourcing and then proposed methods for trouble-shooting thread detection and thread structure prediction on the data set.The output of this work can be used to spot trouble-shooting threads and show them along with structure tags in MOOC discussion forums.

Model-constrained and data-driven double-supervision acoustic impedance inversion

Seismic impedance inversion is an important technique for structure identification and reservoir prediction.Model-based and data-driven impedance inversion are the commonly used inversion methods.In practice,the geophysical inversion problem is essentially an ill-posedness problem,which means that there are many solutions corresponding to the same seismic data.Therefore,regularization schemes,which can provide stable and unique inversion results to some extent,have been introduced into the objective function as constrain terms.Among them,given a low-frequency initial impedance model is the most commonly used regularization method,which can provide a smooth and stable solution.However,this model-based inversion method relies heavily on the initial model and the inversion result is band limited to the effective frequency bandwidth of seismic data,which cannot effectively improve the seismic vertical resolution and is difficult to be applied to complex structural regions.Therefore,we propose a data-driven approach for high-resolution impedance inversion based on the bidirectional long short-term memory recurrent neural network,which regards seismic data as time-series rather than image-like patches.Compared with the model-based inversion method,the data-driven approach provides higher resolution inversion results,which demonstrates the effectiveness of the data-driven method for recovering the high-frequency components.However,judging from the inversion results for characterization the spatial distribution of thin-layer sands,the accuracy of high-frequency components is difficult to guarantee.Therefore,we add the model constraint to the objective function to overcome the shortages of relying only on the data-driven schemes.First,constructing the supervisor1 based on the bidirectional long short-term memory recurrent neural network,which provides the predicted impedance with higher resolution.Then,convolution constraint as supervisor2 is introduced into the objective function to guarantee the reliability and accuracy of the inversion results,which makes the synthetic seismic data obtained from the inversion result consistent with the input data.Finally,we test the proposed scheme based on the synthetic and field seismic data.Compared to model-based and purely data-driven impedance inversion methods,the proposed approach provides more accurate and reliable inversion results while with higher vertical resolution and better spatial continuity.The inversion results accurately characterize the spatial distribution relationship of thin sands.The model tests demonstrate that the model-constrained and data-driven impedance inversion scheme can effectively improve the thin-layer structure characterization based on the seismic data.Moreover,tests on the oil field data indicate the practicality and adaptability of the proposed method.

经济状态演变与银行业系统性风险监管

经济状态演变是引致银行业系统性风险的重要因素。本文使用引入时变转移概率的马尔科夫区制转移模型,将经济状态未来信息纳入系统性风险度量,探究经济状态的结构性转变和持续对银行业系统性风险的影响,并分析了不同类型银行受经济状态演变影响的差异。研究发现,经济状态演变通过利率和资产市值渠道对系统性风险产生影响,由扩张向收缩的经济状态结构性转变以及扩张期的持续,会提升系统性风险;而由收缩向扩张的经济状态结构性转变则有助于稳定系统性风险。研究还发现,银行业系统性风险受经济状态影响的主要来源是中小型银行。基于以上研究成果,本文建议监管部门应关注银行业系统性风险的顺周期特征,并结合受经济状态演变的影响程度,对不同类型银行制定差异化的监管措施。

NHCL:一种基于原生结构增强的超图对比学习

基于自监督学习的超图对比学习已被广泛研究,然而,当前超图对比学习大多采用传统图表示学习中的数据增强方法,较少考虑超图的原生结构,并没有充分利用超图中的高阶关系。为了解决这一局限性,提出了一系列基于超图原生结构的数据增强操作,即针对超图中的超边和节点进行扰动。通过对超边之间的包含、组合及相交等关系和节点之间交互关系的研究,提出了一系列面向超边和节点的基本扰动操作,并在此基础上对面向超边和节点之间的基本操作进行了组合,帮助模型进行学习。通过使用基本数据增强操作及其组合,生成用于超图对比学习模型进行学习的正负样本对,使用超图神经网络学习其表征信息并进行编码,通过损失函数指导模型训练,从而帮助模型学习到超图中的高阶关系。为了验证该方法的有效性,对Cora-CA、PubMed和ModelNet40等12个常用的超图基准数据集进行了节点分类实验。实验结果表明,相比于现有两个超图自监督方法Self和Con、超图对比学习方法HyperGCL和TriCL,该方法在节点分类准确率上提升了2%~7%。

部门协作何以突破本位主义的困境?——基于C市“审管分离”改革的实证分析

中国国家治理场域内,本位主义困境始终是制约高质量政府部门协作的关键因素之一。对此,现有研究并未将重心放置于改变部门原有的科层化组织结构。C市“审管分离”改革的案例研究表明,通过结构性改革改变部门原有的科层化组织结构,为推进政府部门协作突破本位主义的困境提供了一个创新视角和有效方案。依托结构性改革打造能够代表整体协作利益的职能部门、削弱部门过度维护自身利益的资源基础、拓展弱连带关系以强化部门间的信任水平,有助于提升职能部门协作质量与公共行政整体绩效。为此,应当尽快将实践层面的探索创新转化为法理层面的制度规范,为顺利推进改革提供法治保障,为合理示范推广夯实可行性基础。

基于自训练半监督神经网络的结构损伤识别

为解决结构损伤识别中标签样本不足的问题,提出一种基于自训练半监督神经网络(self-training semi-supervised neural networks,SSNN)的结构损伤识别框架,该框架利用自训练半监督方法对多层感知机(multilayer perceptron,MLP)神经网络进行训练,从无标签样本中挑选置信度高的样本标注伪标签,扩大样本训练集,并采用归一化频率变化率和损伤特征指数作为输入特征,用于识别结构损伤。首先,介绍自训练半监督学习的基本理论和方法;其次,从神经网络构建、损伤特征提取、分类器评估等方面,给出结构损伤识别流程;最后,通过空间桁架的数值案例及3层框架的试验数据,验证所提出的损伤识别方法。结果表明:自训练半监督学习能够从无标签样本中选取置信度较高的样本,为损伤识别提供更充足的有标签样本;在标记样本不足的条件下,SSNN比MLP神经网络的损伤识别效果更好;相较于MLP神经网络,SSNN在单一位置损伤工况下,识别准确率提升约4%,2个位置损伤识别准确率提升约9%。

权力监督何以有效——传统中国权力监督的分工式结构及运作困境的现代审思

有效性是权力监督的重要价值和目标。传统中国自上而下的集权分工式官僚结构是皇权专制政治的产物。随着古代监察制度的不断充实、发展与完善,监督的途径和方式趋于多样化,多种监督手段得到综合运用,形成一套完备的分工式权力监督体系。秦汉以来“设官分职”分工式分权模式,在维护传统中国权力监督的有效性、保证传统官僚体制正常运转的同时,存在着集权专制、人治传统以及程序缺失等诸多制度性缺陷,导致权力监督趋于低效空转乃至最终失效,对王朝政治产生严重的负面影响。有效的监督制约是通过科学的权力系统和结构设计,明确权力界限和职责、疏通权力通道、防止并纠正权力倾斜,使权力在既定的空间范围内畅通无阻地发挥作用,让权力监督达到最佳境界,在防范权力越轨的同时,最大程度地实现行政效能的传统中国权力监督思想与实践,为当前我国监察制度改革和权力监督有效性的建构提供了宝贵的历史资源。

推进监察执法与刑事司法有机衔接

监察执法与刑事司法有机衔接,作为党的二十届三中全会提出的部署要求,具有确保反腐败格局中职能责任的依法履行、确保反腐败法网密织及流程贯通、确保反腐败执法司法公平公正的时代价值。推进监察执法与刑事司法有机衔接,亟需从理论上回应“结构平衡说”“监察中心主义说”等学术争议。其一,构建以监察执法为主导的监察执法与刑事司法衔接结构形式。应当从反腐败格局中的职责定位来深刻把握腐败治理与社会治理在刑事诉讼领域的差异,深刻把握党的自我革命引领社会革命的政治逻辑。其二,明确监察执法与刑事司法衔接的主体责任。该主体责任是建立在监察机关履行反腐败法定职能基础之上的监察机关与审判、检察、公安及相关执法特定机构和人员所承担的法法衔接职责和义务。其三,完善监察执法与刑事司法衔接机制,主要包括监察机关在查办职务犯罪案件中与审判机关的协调配合机制,如证据审查认定、审判信息通报配合等,以及与检察机关的衔接机制,如重大疑难案件提前介入、案件移送等,其要旨是通过监察执法与刑事司法的配合制约,确保反腐败执法司法在法治轨道上运行。

论《监察法学》的框架结构与编撰要点

《监察法学》被列入中国法学类马工程重点教材申报范围,标志着监察法学教材建设进入新阶段。监察法学既是纪检监察学科的重要组成部分,又是法学学科的重要分支。《监察法学》应以坚持和完善党的自我革命规范体系、国家反腐败法治体系为逻辑起点,以监察法律法规为研究主干,以监察法治实践及其规律性研究为范畴,以政治学、宪法学、法理学、诉讼法学等社会科学理论为学理支撑,按照基本原理、组织制度、程序制度、履职规范、实施保障的立法逻辑进行架构设计和各板块、各章节内容编撰,从监察法理、监察源流、监察制度、监察实践四个维度构建中国监察法学自主知识体系。

基于高职院校现代化治理的内部控制体系优化研究

以G高校为例,对高校内部控制体系建设和运行存在的内部控制意识不强、内部治理结构僵化、内部治理风险评估机制落后、内控体系信息化建设薄弱、内部控制体系建设专业人才缺乏等问题进行分析。从优化内部治理结构、加强风险管理、推进内部控制信息化建设、健全内部控制监督机制等方面提出基于现代化治理的高校内部控制体系优化路径,以期有助于提升高校治理现代化水平。

基于深度学习的图像分割综述

图像分割是计算机视觉中的一项基本任务,其主要目的是从图像输入中提取有意义和连贯的区域。多年来,图像分割领域已经开发出了各种各样的技术,包括基于传统方法,以及利用卷积神经网络的最新图像分割技术。随着深度学习的发展,更多的深度学习算法也被应用到图像分割任务中。特别地,近两年学者对深度学习的兴趣高涨,涌现了许多应用于图像分割任务的深度学习算法。然而大部分新的算法还没有被归纳分析,这将不利于后续研究的进行。文中对近两年发表的基于深度学习的图像分割研究进行了全面回顾。首先对图像分割的常用数据集进行简要介绍,然后阐明了基于深度学习的图像分割的新分类,最后讨论了现有的挑战并对今后的研究方向进行了展望。

数字金融对绿色技术创新的影响及机制研究

基于2011—2021年各地区数字普惠金融指数和绿色技术创新水平,从产业结构升级视角检验了数字金融助推我国绿色技术创新的影响机制。结果显示:首先,数字金融能够有效促进绿色技术创新,并且这一结果在数字金融滞后一期、替换解释变量等内生性分析与稳健性检验后依然成立。其次,推动产业结构升级是数字金融影响绿色技术创新的重要机制。最后,异质性结果显示,与东部地区相比,中西部地区的绿色技术创新所受的促进作用更为明显;数字金融在金融监管程度高的地区对绿色技术创新的促进作用更大。据此,提出要加快数字金融发展水平,充分发挥数字金融在推动产业结构升级方面的积极作用,持续提高我国绿色技术创新水平。

融合片内语义和片间结构特征的自监督CT图像分类方法

针对CT(Computed Tomography)图像分析存在人工标签稀缺、分类性能不佳等问题,文中提出一种融合片内语义和片间结构特征的自监督CT图像分类方法。该方法利用CT图像的层次结构特性和局部组成要素的语义特点,通过混淆切片生成算法对无标签的病灶部位图像进行处理,生成空间指数和混淆切片作为监督信息。在自监督辅助任务中利用ResNet50网络从混淆切片中同时提取与病灶部位相关的CT片内语义和片间结构特征,将学习到的特征迁移到后续医学分类任务中,使得最终模型从无标签数据中获得增益。实验结果表明,当被使用的有标签数据有限时,相比其他针对CT图像的二维模型和三维模型,所提方法的分类性能和标签利用效率更优。

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。

基于密度峰值聚类的Tri-training算法

Tri-training利用无标签数据进行分类可有效提高分类器的泛化能力,但其易将无标签数据误标,从而形成训练噪声。提出一种基于密度峰值聚类的Tri-training(Tri-training with density peaks clustering,DPC-TT)算法。密度峰值聚类通过类簇中心和局部密度可选出数据空间结构表现较好的样本。DPC-TT算法采用密度峰值聚类算法获取训练数据的类簇中心和样本的局部密度,对类簇中心的截断距离范围内的样本认定为空间结构表现较好,标记为核心数据,使用核心数据更新分类器,可降低迭代过程中的训练噪声,进而提高分类器的性能。实验结果表明:相比于标准Tritraining算法及其改进算法,DPC-TT算法具有更好的分类性能。