Research on the Information Fusion Method of Oil Diagnosis and Vibration Diagnosis Based on the Rough Sets Theory

The improved method has been presented for knowledge reduction in rough sets （R-S） theory, when R-S is used to model the information expression of oil and vibration diagnosis. Therefore, the typical fault simulation tests of rolling bearings have been made, and the application method of R-S has been also analysed in this paper. The diagnosis model of holding rack fault in rolling bearing was presented based on the improved reduction method. It is suited to information fusion to combine information when oil analysis and vibration analysis are combined for fault diagnosis.

The feelings and thoughts of mental health nurses concerning the management of distressed and disturbed in-patients: A comparative qualitative European study

High levels of distress and disturbance amongst those experiencing acute mental illness can be a major problem for mental health nurses. The feelings experienced by these nurses when caring for and supporting disturbed and/or distressed patients along with their concurrent thoughts are not well described in the literature. To date, this complex issue has not been explored within a comparative European context. The objective of this qualitative study was to explore the feelings and thoughts of mental health nurses when supporting and caring for distressed and/or disturbed patients in 6 European countries. Methods: Focus groups were used to collect data from 130 mental health nurses working in acute inpatient psychiatric settings. Results: Data were analysed using content analysis. Findings highlighted 6 broad themes: 1) Mixed emotions: expressive and responsive, 2) Procedure for caring for and supporting disturbed and/or distressed patients, 3) Use of guidelines for caring and supporting disturbed and/or distressed patients, 4) Team and organisational support, 5) Ethical concerns: Cognitive dissonance and 6) Education and training. Commonalities and differences were?found across all themes. Approaches to care, nurses’ role and education, clinical guidelines and/or standards vary from country to country, therefore the care, treatment and management of distressed and/or disturbed patients are various. As a result, mental health nurses have different experiences, various emotional quandaries concurrent with cognitive dissonance and different coping strategies when caring for and supporting distressed and disturbed patients. Conclusions: More emphasis needs to be given to the emotional quandaries and concurrent cognitive dissonance experienced by mental health nurses caring for distressed and/or disturbed inpatients in acute psychiatric settings. Increased access to education and training with particular attention to interpersonal communication and relationship building within clinical teams needs to be a priority given the experiences described by mental health nurses.

Fusion of Infrared and Visible Images Using Fuzzy Based Siamese Convolutional Network

Traditional techniques based on image fusion are arduous in integrating complementary or heterogeneous infrared(IR)/visible(VS)images.Dissimilarities in various kind of features in these images are vital to preserve in the single fused image.Hence,simultaneous preservation of both the aspects at the same time is a challenging task.However,most of the existing methods utilize the manual extraction of features;and manual complicated designing of fusion rules resulted in a blurry artifact in the fused image.Therefore,this study has proposed a hybrid algorithm for the integration of multi-features among two heterogeneous images.Firstly,fuzzification of two IR/VS images has been done by feeding it to the fuzzy sets to remove the uncertainty present in the background and object of interest of the image.Secondly,images have been learned by two parallel branches of the siamese convolutional neural network(CNN)to extract prominent features from the images as well as high-frequency information to produce focus maps containing source image information.Finally,the obtained focused maps which contained the detailed integrated information are directly mapped with the source image via pixelwise strategy to result in fused image.Different parameters have been used to evaluate the performance of the proposed image fusion by achieving 1.008 for mutual information(MI),0.841 for entropy(EG),0.655 for edge information(EI),0.652 for human perception(HP),and 0.980 for image structural similarity(ISS).Experimental results have shown that the proposed technique has attained the best qualitative and quantitative results using 78 publically available images in comparison to the existing discrete cosine transform(DCT),anisotropic diffusion&karhunen-loeve(ADKL),guided filter(GF),random walk(RW),principal component analysis(PCA),and convolutional neural network(CNN)methods.

Knowledge discovery method for feature-decision level fusion of multiple classifiers

To improve the performance of the multiple classifier system, a new method of feature-decision level fusion is proposed based on knowledge discovery. In the new method, the base classifiers operate on different feature spaces and their types depend on different measures of between-class separability. The uncertainty measures corresponding to each output of each base classifier are induced from the established decision tables （DTs） in the form of mass function in the Dempster-Shafer theory （DST）. Furthermore, an effective fusion framework is built at the feature-decision level on the basis of a generalized rough set model and the DST. The experiment for the classification of hyperspectral remote sensing images shows that the performance of the classification can be improved by the proposed method compared with that of plurality voting （PV）.

RANDOM SETS: A UNIFIED FRAMEWORK FOR MULTISOURCE INFORMATION FUSION

The more diverse the ways and means of information acquisition are,the more complex and various the types of information are. The qualities of available information are usually uncertain,vague,imprecise,incomplete,and so on. However,the information is modeled and fused traditionally in particular,name some of the known theories: evidential,fuzzy sets,possibilistic,rough sets or conditional events,etc. For several years,researchers have explored the unification of theories enabling the fusion of multisource information and have finally considered random set theory as a powerful mathematical tool. This paper attempts to overall review the close relationships between random set theory and other theories,and introduce recent research results which present how different types of information can be dealt with in this unified framework. Finally,some possible future directions are discussed.

Multi-Source Adaptive Selection and Fusion for Pedestrian Dead Reckoning

Accurate multi-source fusion is based on the reliability, quantity, and fusion mode of the sources. The problem of selecting the optimal set for participating in the fusion process is nondeterministic-polynomial-time-hard and is neither sub-modular nor super-modular. Furthermore, in the case of the Kalman filter(KF) fusion algorithm, accurate statistical characteristics of noise are difficult to obtain, and this leads to an unsatisfactory fusion result. To settle the referred cases, a distributed and adaptive weighted fusion algorithm based on KF has been proposed in this paper. In this method, on the basis of the pseudo prior probability of the estimated state of each source, the reliability of the sources is evaluated and the optimal set is selected on a certain threshold. Experiments were performed on multi-source pedestrian dead reckoning for verifying the proposed algorithm. The results obtained from these experiments indicate that the optimal set can be selected accurately with minimal computation, and the fusion error is reduced by 16.6% as compared to the corresponding value resulting from the algorithm without improvements.The proposed adaptive source reliability and fusion weight evaluation is effective against the varied-noise multi-source fusion system, and the fusion error caused by inaccurate statistical characteristics of the noise is reduced by the adaptive weight evaluation.The proposed algorithm exhibits good robustness, adaptability,and value on applications.

An Exact Mathematical Picture of Quantum Spacetime

Using von Neumann’s continuous geometry in conjunction with A. Connes’ noncommutative geometry an exact mathematical-topological picture of quantum spacetime is developed ab initio. The final result coincides with the general conclusion of E-infinity theory and previous results obtained in the realm of high energy physics. In particular it is concluded that the quantum particle and the quantum wave spans quantum spacetime and conversely quantum particles and waves mutates from quantum spacetime.

天空地一体化多目标跟踪算法研究综述

为实现全时全域“泛在连接”,构建天空地一体化网络已成为国家重大需求,而基于天空地一体化网络下跨域协同系统进行多目标跟踪是其中一个重要的发展方向,其在军民用领域都极具应用价值。本文详细阐述了天空地一体化网络背景下多目标跟踪方法研究进展。首先,介绍了天空地一体化跨域协同多目标跟踪的研究背景与意义。其次,从基于视觉的多目标跟踪、基于模型的多目标跟踪和基于多模态融合的多目标跟踪三个方面概述了当前的代表性研究方法:在基于视觉的多目标跟踪算法方面,介绍了单摄像头和多摄像头融合的多目标跟踪方法;对于基于模型的多目标跟踪,先介绍了单传感器多目标跟踪方法,以及在多种复杂场景下的改进,然后介绍了多传感器融合方法;在基于多模态信息融合的目标跟踪方面,在对多传感器时空配准方法和有代表性的多模态信息融合方法介绍的基础上,概括了基于多模态融合的多目标跟踪算法。最后探讨了当前存在的问题和未来发展方向:无论基于视觉的还是基于模型的多目标跟踪方法都有不少问题有待解决,特别是两种方法的结合值得深入研究;在面临复杂干扰时,基于多传感器信息融合的多目标跟踪由于能实现信息的互补,成为未来的主流发展方向;此外,跨域协同系统,由于能利用更多的资源和信息,其多目标跟踪问题研究极具价值,不过其中通信安全问题和多目标跟踪模型轻量化问题值得探讨。本文对从事目标跟踪及空天地一体化协同控制相关理论与技术研究的科研工作者具有重要参考价值。

突发灾难事件中舆情发酵机理与内在逻辑研究——基于融知发酵模型

[研究目的]突发灾难事件网络舆情发酵为社会治理带来很大的压力,剖析突发灾难事件中舆情发酵机理,是提高突发灾难网络舆情事件治理精度和效率的实践理据。[研究方法]基于融知发酵模型,采用NCA与fsQCA相融合的方法,选取2018-2022年期间的133个突发灾难舆情事件,以发酵底物、发酵菌株、媒体酶、公众酶、发酵场域、发酵周期为条件变量,以发酵产物为结果变量,探究突发灾难事件舆情的发酵机理和理论模式。[研究结论]研究表明:单个变量对发酵产物的影响是有限的,各变量均不构成发酵产物产生的必要条件;突发灾难事件舆情发酵机理的组态包括10条路径;归纳了交融碰撞型、演化推进型和衍生变异型3种驱动突发灾难事件舆情发酵的理论模式。

一种基于人体轮廓形变场的双流网络步态识别方法

步态识别易受相机视角、服装和携带物等外界因素影响而性能下降。为此,该文将非刚性点集配准引入步态识别,利用相邻步态帧之间的形变场表征行走过程中人体轮廓发生的位移量,从而提升对人体形态变化的动态感知能力。在此基础上,该文提出一种基于人体轮廓形变场的双流卷积神经网络GaitDef,该网络模型由形变场和步态剪影两路特征提取分支构成。针对形变场数据的稀疏性设计多尺度特征提取模块,以获取形变场的多层次空间结构信息。针对步态剪影提出动态差异捕捉模块和上下文信息增强模块,以捕捉动态区域的变化特性和利用上下文信息增强步态表征能力。双分支网络的输出特征经过特征融合得到最终的步态表示。大量实验结果表明了该文方法的有效性,在CASIA-B和CCPG数据集上,该文方法的平均Rank-1准确率分别能达到93.5%和68.3%。

基于随机有限集的多目标跟踪技术综述

随机有限集理论为多目标跟踪、多传感器融合和态势评估等问题提供了完整、统一的理论框架和解决方案。基于随机有限集的跟踪算法将多目标状态和量测建模为随机有限集,自然地引入航迹起始、终结机制,可实现目标数量和状态的同时估计。通过对随机有限集框架下的概率假设密度、带势概率假设密度、多目标多伯努利滤波器、扩展标签随机集滤波器和泊松多伯努利混合滤波器的研究进展进行详细梳理和综合对比,对基于随机有限集的多目标跟踪领域未来发展方向进行了分析和展望。

基于多模态融合的开放域三维模型检索算法

为了满足开放域下海量新增模型数据的管理和检索需求,提出开放域三维模型检索算法,可以有效地利用多模态信息的语义一致性.借助无监督算法探寻未知样本间的类别信息,利用该类别信息实现网络模型的参数优化,使得网络模型在开放域条件下具有更好的模型表征性能及检索结果.提出基于Transformer结构的层级化多模态信息融合模型,有效地剔除了多模态间的冗余信息,得到鲁棒性更强的模型表征向量.在数据集ModelNet40上进行实验,通过与其他典型算法的对比实验可知,所提方法在mAP指标上优于所有的对比方法,验证了该方法在检索性能提升上的有效性.

柔性传感器智能脉诊系统信号采集处理技术

脉搏诊断仪器的研发和使用为传统中医的智能诊断提供了客观基础,但现有的脉搏诊断设备没有考虑采集部位(寸、关、尺)与压力(浮、中、沉)共同作用时对诊断结果的影响,诊断精度仍有提升空间。为了更加准确地识别脉象,本文提出了一种基于柔性传感器的智能脉诊系统和相应的脉搏信号处理方法。在寸、关、尺采集部位安装3个阵列柔性传感器,通过设置浮、中、沉不同压力阈值,获取多组脉象信号,接着提取信号特征,并基于多重集典型相关分析(Multi-set canonical correlations analysis,MCCA)方法对多通道特征进行融合,以获得更多脉搏信息。实验结果表明,本文所提方法在4种典型脉象分类中,脉象分类准确度得到进一步提升。本文设计的采集部位、压力相结合的脉象感应方法可以模拟还原中医诊断过程,有助于提取真实的脉搏信号,为后续基于柔性传感器的智能脉搏诊断设备的研发提供了理论基础和参考价值。

基于Android系统的机顶盒及其摇控器的设计与实现

基于Android系统的机顶盒及其遥控器是以Android系统为平台开发一款硬件与软件相结合的产品,在传统机顶盒的基础上实现对电视和电脑屏幕的无线控制,最终实现三屏融合。不但能够利用当前Android移动终端自身强大的计算处理能力、丰富的网络交互功能和各种硬件资源,提供给用户智能人性化的应用,还能相应地降低开发和生产的成本,便于将产品在市场中推广。

模糊集合下多传感器信息融合算法仿真

多传感器数据融合通常涉及大量数据,受到噪声、不完整性、不准确性等因素的影响,导致融合结果的不确定性增加。为此,提出一种基于模糊集合的多传感器信息融合算法。利用局部保持投影(Locality Preserving Projection, LPP)处理多传感器信息,采用主成分分析(Principal Component Analysis, PCA)分离特征值较大的反射信号,删除特征值较小的随机噪声。利用隶属函数得到不同传感器提供的可信度,将支持度以及可信度转换为基本概率分配函数,引入证据理论(Dempster-Shafer, D-S),实现多传感器信息融合优化。仿真分析表明,所提方法可以得到高精度和高效率的多传感器信息融合结果,峰值信噪比达60dB以上,信噪比一直处于12dB以上,融合最长耗时仅为2.01ms,使其融合性能得到有效优化。

论胡祗遹题画诗的隐逸情怀

题画诗在元代逐渐成熟,在元初题画及隐逸之风盛行的情形下,以胡祗遹为代表的元初北方文人以画境寄托归隐心境,其山水类题画及题陶画诗托画寄意、诗画相融,以题画诗作为超脱现实的心灵寄托,表达超脱世俗的隐逸情怀。通过梳理这些诗歌,可以感悟元初题画诗托画寄意、诗画相资的艺术风貌,体会元初文人的慕陶情结,窥探胡祗遹务实济世思想之外的林泉之趣、隐逸之思及其题画诗重要的思想价值。

基于CNN算法及多特征融合的老人摔倒预测系统构建

随着中国老龄化社会的到来,应对老年人口安全问题,特别是摔倒问题,变得越来越重要。提出了一种基于卷积神经网络(CNN)和多特征融合的预测系统。该系统整合了图像和生理信号等多种类型的特征信息,以提高摔倒预测的准确性。实验验证了基于CNN的多模型结构在老人摔倒预测中的优越性,以及多特征融合策略对模型性能的提升作用。与其他方法相比,所提出的方法在准确率、召回率、精确率和F1分数方面表现出优越性,准确率可达到95.93%。此研究为预测和预防老年人摔倒提供了一种高效且可靠的方法。

基于信息融合的电力系统继电保护整定计算方法

为保证电力系统的正常运行,研究一种基于信息融合的电力系统继电保护整定计算方法。建立信息融合适应度函数,分析电力数据间逻辑关系及故障元件特性条件,建立期望函数,对继电保护中元件故障编码位置识别,通过多源信息的输入,分析电力系统拓扑结构和参数信息,构建识别框架,利用信息核心理论建立继电保护整定规则,明确整定计算思路,完成对应计算。实验结果证明,所提方法效率高,最低仅为2 s,且故障识别率高,保护整定效果好,能减少电力系统越区跳闸的可能性,令继电保护装置之间协调配合,维持电网稳定。

基于随机历史集的有反馈MSIF目标识别方法

为提高复杂战场环境下的目标识别准确度,提出了一种分布式MSIF模型,并通过加入反馈信息流,对时域内的序贯信息进行处理。以经典D-S证据理论为基础,针对其不能处理高冲突证据的弊端,采用费雪耶兹洗牌方法,置乱泛传感器矩阵中的信息排序,生成随机历史集,并随着运算次数增加,算法反复迭代。通过改进算法,修正了由于高冲突证据过早出现所带来的识别结果偏差。数值算例表明,该方法既能提高信息利用率,同时可克服信息先入性陷阱的影响,准确度较高,且计算量较小,能有效减轻系统负担,适合MSIF目标识别中的大数据量处理。

基于多流融合的柔性互联配电网数据驱动鲁棒供电恢复方法

传统配电网通过柔性互联实现了“业务流-能量流-信息流-控制流”多流融合,随之而来的是如何更好地解决分布式光伏出力不确定性对供电恢复业务流的影响,为此,提出了基于多流融合的柔性互联配电网数据驱动鲁棒供电恢复方法。首先,在柔性互联配电网多流融合框架下建立多时段供电恢复模型,主要包括供电恢复业务流目标和能量流-信息流-控制流融合约束条件;然后,针对描述分布式光伏出力不确定性的凸包多面体集合存在放缩过程中保守性大的问题,建立了数据驱动的超平面多面体集合模型;进一步,将所建立的不确定集合应用到供电恢复模型中,构建了柔性互联配电网鲁棒供电恢复模型,并采用列与约束生成算法对鲁棒供电恢复模型进行求解。最后,通过改进IEEE 33节点系统和实际示范工程系统进行仿真验证,结果表明基于多流融合的柔性互联配电网数据驱动鲁棒供电恢复方法可以降低保守性,提高供电恢复结果的鲁棒性。