Research on Data Fusion of Adaptive Weighted Multi-Source Sensor

Data fusion can effectively process multi-sensor information to obtain more accurate and reliable results than a single sensor.The data of water quality in the environment comes from different sensors,thus the data must be fused.In our research,self-adaptive weighted data fusion method is used to respectively integrate the data from the PH value,temperature,oxygen dissolved and NH3 concentration of water quality environment.Based on the fusion,the Grubbs method is used to detect the abnormal data so as to provide data support for estimation,prediction and early warning of the water quality.

The characterization of weighted local hardy spaces on domains and its application

In this paper, we give the four equivalent characterizations for the weighted local hardy spaces on Lipschitz domains. Also, we give their application for the harmonic function defined in bounded Lipschitz domains.

Weighted Composition Operators from the Bloch Space to Weighted Banach Spaces on Bounded Homogeneous Domains

We study the bounded and the compact weighted composition operators from the Bloch space into the weighted Banach spaces of holomorphic functions on bounded homogeneous domains, with particular attention to the unit polydisk. For bounded homogeneous domains, we characterize the bounded weighted composition operators and determine the operator norm. In addition, we provide sufficient conditions for compactness. For the unit polydisk, we completely characterize the compact weighted composition operators, as well as provide ＂computable＂ estimates on the operator norm.

Weighted Bergman Spaces on Bounded Symmetric Domains

On bounded symmetric domain Ω of C^n, we investigate the properties of functions in weighted Bergman spaces A^P（Ω,dvs） for 0 〈 p ≤ ＋∞ and -1 〈 s 〈 4-∞. Based on the estimate of Bergman kernel, we obtain some characterizations of functions in A^P（Ω, dvs） in terms of a class of linear operators D^αB. Making use of these characterizations, we extend A^P（Ω,dvs） to the weighted Bergman spaces Aα^p,B（Ω,dvs） in a very natural way for 1 〈 p 〈 4-∞ and any real number s, that is, -∞ 〈 s 〈 ＋∞. This unified treatment covers some classical Bergman spaces, Besov spaces and Bloch spaces. Meanwhile, the boundedness of Bergman projection operators on Aα^P,β（Ω, dvs） and the dual of Aα^P,B（Ω, dvs） are given.

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.

A Precise Asymptotic Behaviour of the Large Deviation Probabilities for Weighted Sums

Let {Xn, n ≥ 1} be a sequence of independent and identically distributed positive valued random variables with a common distribution function F. When F belongs to the domain of partial attraction of a semi stable law with index α, 0 < α < 1, an asymptotic behavior of the large deviation probabilities with respect to properly normalized weighted sums have been studied and in support of this we obtained Chover’s form of law of iterated logarithm.

IMPROVED REGULARITY OF HARMONIC DIFFEOMORPHIC EXTENSIONS ON QUASIHYPERBOLIC DOMAINS

Let X be a Jordan domain satisfying certain hyperbolic growth conditions.Assume that φ is a homeomorphism from the boundary ?X of X onto the unit circle.Denote by h the harmonic diffeomorphic extension of φ from X onto the unit disk.We establish the optimal Orlicz-Sobolev regularity and weighted Sobolev estimate of h.These generalize the Sobolev regularity of h in [A.Koski,J.Onninen,Sobolev homeomorphic extensions,J.Eur.Math.Soc.23(2021) 4065-4089,Theorem 3.1].

融合多特征信息与GWO-SVM的机械关键设备故障诊断

为了提高机械关键设备故障诊断的精度,建立机械关键设备故障诊断模型。文章提出一种融合机械关键设备故障信号多特征信息与灰狼优化算法(Grey Wolf Optimization Algorithm,GWO)改进支持向量机(Support Vector Machine,SVM)(GWO-SVM)的机械关键设备故障诊断模型。首先,提取机械关键设备故障信号的时域特征、频域特征和多尺度加权排列熵特征,分别对比不同特征的机械关键设备故障诊断结果。其次,为提高SVM模型性能,运用GWO算法对SVM模型的惩罚参数P和核函数参数g进行优化选择,提出一种融合多特征信息与GWO-SVM的机械设备故障诊断模型。与GA-SVM、PSO-SVM和SVM相比,基于GWO-SVM的机械设备故障诊断模型的诊断精度最高。这里算法可以有效提高机械关键设备故障诊断正确率,为机械关键设备故障诊断提供了新的方法。

自适应调零天线动态性能影响因素研究

本文针对卫星导航接收机的功率倒置(PI)算法在动态环境下受到最优权值处理速度的制约,导致动态抗干扰性能下降这一个问题,通过建立动态仿真环境,以七阵元均匀圆阵作为天线布阵的仿真模型,研究了不同权值更新速率对动态抗干扰性能的影响,证明了权值更新速率的提升对动态抗干扰性能也有相应的提高。并且分析了在不同快拍数以及不同时域抽头数对动态抗干扰性能的影响,证明了可以通过适当选择快拍数和时域抽头数来提高权值更新速率。本研究为建立更加完善的工程实现方案提供了理论依据,对存在类似需求的空时自适应调零天线抗干扰系统具有一定的参考价值。

关于连续Domain权的进一步结果

在连续格理论的基础上继续探讨连续 Domain的权与相应 Scott拓扑空间的权之间的关系 ,并进一步讨论其与相应的 Lawson拓扑空间的权之间的关系 ,最后给出在连续 Domain中 W(P) =W(ΣP)=W(Λ P)的结论。

拟连续Domain的拟基及其权

在定向完备偏序集(即dcpo)上引入了拟基的概念,给出了拟基的若干刻画并在此基础上定义了拟连续Domain的权。探讨了拟连续Domain的权与该拟连续Domain上赋予内蕴拓扑时的拓扑空间的权之间的关系。

基于特征融合与域自适应的刀具磨损在线监测

机床状态监测对于机床健康管理以及保证工件加工质量具有重要意义。针对现有刀具磨损预测模型存在训练时间长、收敛速度慢以及泛化能力弱等问题,提出了一种分布式一维卷积神经网络对刀具磨损进行预测。采用残差连接与通道注意力模块顺序堆叠的方式作为特征提取模块,并通过交叉验证以选择合适的网络层数。由于不同传感器所提取到的特征信息可能存在冗余,使用权重差异策略以提高特征提取的有效性以及全面性。此外,考虑到训练集与测试集分布可能存在差异从而影响模型的泛化性能,引入了域自适应方法提高模型在未知数据集中的表现。为验证模型效果,使用PHM 2010铣刀磨损数据集进行实验。实验结果表明,该模型在C1、C4、C6三把刀具上的平均RMSE和平均MAE分别为6.97和6.29,与TCN、TDConvLSTM等模型相比有12%以上的提升。

加权多源域对抗迁移学习运动想象脑电识别

运动想象脑电信号个体差异大且数据采集成本高,构建小样本、跨被试的运动想象脑电识别模型是脑机接口中需要解决的关键问题。针对小样本跨领域学习,提出一种基于预对齐策略和对抗迁移学习的加权多源域自适应方法,把迁移学习和对抗训练相结合,将域对抗神经网络扩展到多源域,对各源域进行皮尔逊相关系数加权,实现多个源域和目标域在特征上的加权对齐,并采用预对齐策略提高域间数据分布的一致性。在BCI Competition运动想象数据集上,跨被试的运动想象任务识别正确率达到84.43%,与不迁移方法相比提高了9.17%,相较于域对抗神经网络提高了5.0%。实验结果表明,所提方法能够有效减小不同被试间脑电数据分布以及特征分布差异,实现数据和特征双重对齐,从而提升跨被试运动想象脑电分类性能。

局部判别损失无监督域适应方法

在无监督域适应任务中,源域和目标域的分布不同,源域数据标签已知,但是目标域的数据标签未知。最大平均差异MMD是一种具有代表性的分布度量方法,广泛应用于源域与目标域之间的分布差异度量。然而,MMD度量及其变种方法通常忽略了样本的类内紧凑性和类间可分离性,降低了特征表达的可判别性。因此,提出局部判别损失无监督域适应方法,从2个方面提升域适应方法的判别能力:(1)重新设计MMD度量方法的权重,解决类别不均衡问题,使难对齐类别在域间分布上保持一致;(2)探索局部对比损失,平衡正样本对和负样本对之间的关系,从而学习到更好的判别性特征。结合域间损失和类间损失,可使同一类样本靠近,不同类样本之间远离。该方法简单有效,即插即用,可扩展至注意力机制的网络结构上。在多个域适应数据集上,该方法的有效性均得到了验证。

基于自适应权重的多源部分域适应

作为机器学习的一个新兴领域,多源部分域适应(MSPDA)问题由于其源域自身的复杂性、领域之间的差异性以及目标域自身的无监督性,给相关研究带来了挑战,以致目前鲜有相关工作被提出.在该场景下,多个源域中的无关类样本在域适应过程中会造成较大的累积误差和负迁移.此外,现有多源域适应方法大多未考虑不同源域对目标域任务的贡献度不同.因此,提出基于自适应权重的多源部分域适应方法(AW-MSPDA).首先,构建了多样性特征提取器以有效利用源域的先验知识;同时,设计了多层次分布对齐策略从不同层面消除了分布差异,促进了正迁移;此外,为量化不同源域贡献度以及过滤源域无关类样本,利用相似性度量以及伪标签加权方式构建自适应权重;最后,通过大量实验验证了所提出AW-MSPDA算法的泛化性以及优越性.

Domain-specific feature elimination:multi-source domain adaptation for image classification

Multi-source domain adaptation utilizes multiple source domains to learn the knowledge and transfers it to an unlabeled target domain.To address the problem,most of the existing methods aim to minimize the domain shift by auxiliary distribution alignment objectives,which reduces the effect of domain-specific features.However,without explicitly modeling the domain-specific features,it is not easy to guarantee that the domain-invariant representation extracted from input domains contains domain-specific information as few as possible.In this work,we present a different perspective on MSDA,which employs the idea of feature elimination to reduce the influence of domain-specific features.We design two different ways to extract domain-specific features and total features and construct the domain-invariant representations by eliminating the domain-specific features from total features.The experimental results on different domain adaptation datasets demonstrate the effectiveness of our method and the generalization ability of our model.

第二类广义华罗庚域上从α-Bloch空间到Bers型空间的加权复合算子的有界性和紧性

本文在第二类广义华罗庚域上定义了加权Bloch空间和Bers型空间,并讨论了从α-Bloch空间到Bers型空间之间的加权复合算子的有界性和紧性,得到了该加权复合算子是有界算子或紧算子的充分条件和必要条件.

FLUS模型和PLUS模型在年楚河流域土地利用模拟中的应用与对比

为准确进行西藏年楚河流域未来土地利用模拟,对比分析了FLUS模型(Future Land Use Simulation Model)和PLUS模型(Patch-generating Land Use Simulation Model)在该流域LUCC(土地利用(Land use)/土地覆盖变化(Land cover change))模拟的结果,并在此基础上开展了研究区2030年的土地利用模拟应用。结果表明:(1)采用本地化参数的FLUS模型获得的模拟结果与真实数据的Kappa系数(0.6350)、FOM系数(0.0800)以及模拟图像的总体精度(0.8240)均优于PLUS模型模拟的结果,表明FLUS模型在研究区具有更好的适用性;(2)依据过去的土地利用变化数据对模型的领域权重和转移矩阵参数进行本地化处理,可提高模拟结果与真实数据的Kappa系数,有助于增强模型在区域的适用性;(3)基于FLUS模型的2030年年楚河流域土地利用模拟结果显示,该区域草地、湿地与水体面积将继续减少,耕地、城市、未利用土地、积雪与冰川将增加,林地变化不大,其中,最主要的土地利用变化由草地变为未利用土地。

一种改进的连续域蚁群算法

针对连续域蚁群算法(ACOR)陷入局部最优、收敛精度较差等缺陷,提出了一种改进连续域蚁群算法.首先,通过改进ACOR算法选择指导解的方式增强种群多样性;其次,利用惯性权重对均值更新公式进行了改进,并对ACOR算法中ζ参数进行线性递减处理;最后,为了帮助算法在陷入停滞时尽快跳出局部最优,用差分变异策略对算法的搜索进行监控,搜索陷入停滞时产生新解,并通过筛选出更好的解跳出局部最优.设计了两种维度环境的实验,其中包括16个可变维度函数和4个固定维度函数,并展示了改进算法与其他几种算法的寻优结果.结果表明,所提出的改进算法在搜索的过程中有效地缓解了上述缺陷.

改进电机全速域无位置传感器转速控制系统研究

针对宽速电机的全速域应用场景,提出改进传统加权平均法,并利用改进后的中高速域滑模观测器法和低速域脉振高频注入法进行复合,实现精确的全速域无位置传感器控制。首先,针对滑模观测器法中符号函数导致的系统抖振,提出指数型复合函数用来替代原观测器中的符号函数;其次,针对脉振高频注入法中高频电流分量与注入信号的相位延迟,提出使用另一轴系高频电流替代注入信号;再次,针对加权平均法在过渡区域的权重分配不合理,提出新型指数型加权系数,同时为平稳过渡提出滞留缓冲带;最后,在MATLAB/Simulink仿真平台搭建基于滞留缓冲加权法的全速域转速控制系统,进行仿真验证。通过仿真结果,表明了改进后的全速域转速控制系统对转速误差和平稳过渡的优化效果。