Constrained voting extreme learning machine and its application

Extreme learning machine(ELM)has been proved to be an effective pattern classification and regression learning mechanism by researchers.However,its good performance is based on a large number of hidden layer nodes.With the increase of the nodes in the hidden layers,the computation cost is greatly increased.In this paper,we propose a novel algorithm,named constrained voting extreme learning machine(CV-ELM).Compared with the traditional ELM,the CV-ELM determines the input weight and bias based on the differences of between-class samples.At the same time,to improve the accuracy of the proposed method,the voting selection is introduced.The proposed method is evaluated on public benchmark datasets.The experimental results show that the proposed algorithm is superior to the original ELM algorithm.Further,we apply the CV-ELM to the classification of superheat degree(SD)state in the aluminum electrolysis industry,and the recognition accuracy rate reaches87.4%,and the experimental results demonstrate that the proposed method is more robust than the existing state-of-the-art identification methods.     

A sparse algorithm for adaptive pruning least square support vector regression machine based on global representative point ranking

Least square support vector regression(LSSVR)is a method for function approximation,whose solutions are typically non-sparse,which limits its application especially in some occasions of fast prediction.In this paper,a sparse algorithm for adaptive pruning LSSVR algorithm based on global representative point ranking(GRPR-AP-LSSVR)is proposed.At first,the global representative point ranking(GRPR)algorithm is given,and relevant data analysis experiment is implemented which depicts the importance ranking of data points.Furthermore,the pruning strategy of removing two samples in the decremental learning procedure is designed to accelerate the training speed and ensure the sparsity.The removed data points are utilized to test the temporary learning model which ensures the regression accuracy.Finally,the proposed algorithm is verified on artificial datasets and UCI regression datasets,and experimental results indicate that,compared with several benchmark algorithms,the GRPR-AP-LSSVR algorithm has excellent sparsity and prediction speed without impairing the generalization performance.     

基于深度神经网络的高环境 适应性水声通信系统研究

深度神经网络中的自动编码器(Autoencoder,AE)通过收发端两个神经网络模块进行全局优化,利用端到端的训练方式以提高通信系统的可靠性.然而,现有对AE的研究未针对信道进行特殊设计,尤其对于时变的水声信道的多径效应,难以进行灵活调整,降低了该方法的实用性.本文提出一种提高水声通信系统信道环境适应性的Attention-Autoencoder网络模型,基于Attention网络可以高效地从大量信息中筛选出关键信息的特点,设计了一种针对水声信道的Attention机制,该机制能够增加网络提取水声信道特征的能力,使系统的适应性大大提高.仿真验证和湖试实验结果表明,基于Attention-Autoencoder网络模型的通信系统与基于文献中AE模型和没有引入神经网络的水声通信系统相比,具有更高的信道环境适应性.     

SAR image de-noising via grouping-based PCA and guided filter

A novel synthetic aperture radar(SAR)image de-noising method based on the local pixel grouping(LPG)principal component analysis(PCA)and guided filter is proposed.This method contains two steps.In the first step,we process the noisy image by coarse filters,which can suppress the speckle effectively.The original SAR image is transformed into the additive noise model by logarithmic transform with deviation correction.Then,we use the pixel and its nearest neighbors as a vector to select training samples from the local window by LPG based on the block similar matching.The LPG method ensures that only the similar sample patches are used in the local statistical calculation of PCA transform estimation,so that the local features of the image can be well preserved after coefficients shrinkage in the PCA domain.In the second step,we do the guided filtering which can effectively eliminate small artifacts left over from the coarse filtering.Experimental results of simulated and real SAR images show that the proposed method outstrips the state-of-the-art image de-noising methods in the peak signalto-noise ratio(PSNR),the structural similarity(SSIM)index and the equivalent number of looks(ENLs),and is of perceived image quality.     

Reactive scheduling of multiple EOSs under cloud uncertainties:model and algorithms

Most earth observation satellites(EOSs)are low-orbit satellites equipped with optical sensors that cannot see through clouds.Hence,cloud coverage,high dynamics,and cloud uncertainties are important issues in the scheduling of EOSs.The proactive-reactive scheduling framework has been proven to be effective and efficient for the uncertain scheduling problem and has been extensively employed.Numerous studies have been conducted on methods for the proactive scheduling of EOSs,including expectation,chance-constrained,and robust optimization models and the relevant solution algorithms.This study focuses on the reactive scheduling of EOSs under cloud uncertainties.First,using an example,we describe the reactive scheduling problem in detail,clarifying its significance and key issues.Considering the two key objectives of observation profits and scheduling stability,we construct a multi-objective optimization mathematical model.Then,we obtain the possible disruptions of EOS scheduling during execution under cloud uncertainties,adopting an event-driven policy for the reactive scheduling.For the different disruptions,different reactive scheduling algorithms are designed.Finally,numerous simulation experiments are conducted to verify the feasibility and effectiveness of the proposed reactive scheduling algorithms.The experimental results show that the reactive scheduling algorithms can both improve observation profits and reduce system perturbations.     

中国沉积岩容矿铅锌矿床中的关键金属

沉积岩容矿铅锌矿床主要包括碎屑岩赋矿(clastic-dominated, CD)矿床和密西西比河谷型(Mississippi-Valley type, MVT)矿床两种,它是世界上Cd、Ga、Ge等关键金属的重要来源,并具有In、Co、Tl的资源潜力.中国沉积岩容矿铅锌矿床主要分布在5个成矿区/带,提供了全国54%的铅锌用量,但其伴生关键金属的资源潜力和成矿机制尚不清楚.本文在综述沉积岩容矿铅锌矿床中伴生的主要关键金属和中国沉积岩容矿铅锌矿床的基础上,详细总结了中国沉积岩容矿铅锌矿床中关键金属的分布特征和富集机制.各类关键金属元素在中国沉积岩容矿铅锌矿床中分布不均,相对地壳丰度, Cd、Ge、In最为富集, Tl、Co有一定富集, Ga的富集程度较低;从矿床类型上来看, Cd、Ga、Ge、Tl在中国MVT矿床中相对富集, In、Co在CD矿床中相对富集;从区域分布上来看,不同元素的富集区带差异很大,除Cd在5个成矿区/带都有较好富集外,其他金属在三江带、扬子地台、厂坝成矿带出现不同程度富集.总结发现,沉积岩容矿铅锌矿床对所富集关键金属的种类具选择性,而关键金属在该类矿床中的富集程度也...     

联合卫星定位和测量机器人的超高层建造过程水平位移监测

在超高层建筑建造过程中,常用测量机器人监测中间楼层的监测点的变形。削弱建筑晃动影响对于监测结果的稳定性至关重要。为此,首先提出一种利用楼顶卫星接收机测量建筑晃动情况,通过内插得到中间楼层瞬时晃动影响的方法,并通过实验验证该方法的有效性。在此基础上,利用该方法对多期监测数据进行处理,结果表明该方法可获得更加稳定的监测结果。将处理结果与有限元分析的结果进行比较,结果表明使用该方法后监测结果与有限元分析的结果吻合度较高。     

改进模型估计与平差的多幅异源影像匹配方法

针对多幅异源影像匹配准确性不高的问题，提出了一种改进模型估计与平差的多幅异源影像匹配方法。首先利用基于快速自适应鲁棒性尺度不变的特征检测子与鲁棒性交叠的标准特征描述子，来增强特征匹配的鲁棒性；然后提出改进的随机抽样一致性算法，来提高模型估计的执行效率，同时保证鲁棒性；最后提出针对多幅异源影像匹配的平差方法，来优化异源匹配结果。实验结果表明，在异源影像存在较大差异的情况下，改进模型估计与平差的多幅异源影像匹配方法具有精度高的优势。      

基于MapReduce模型带准备时间的平行机调度优化

研究了一类基于MapReduce模型的平行机调度问题.每个工件包含Map和Reduce两道加工工序,Map工序可以分割为若干个子任务,并且在多台平行机上同时并行加工,Reduce工序只有在该工件的所有Map工序的子任务加工完成后才能进行,而且Reduce只能在一台机器上加工且不可中断.结合工件具有释放时间和加工准备时间等约束,以最小化最大完工时间为目标,构建了混合整数规划模型,并设计了采用差分变异策略和逐维Levy扰动机制的改进正弦余弦算法来求解该模型.最后,利用数值仿真实验与标准正弦余弦算法及遗传算法进行对比,实验结果表明,运用改进正弦余弦算法求解的结果与下界值的平均相对偏差GAP为3.02%,较标准正弦余弦算法以及遗传算法的效果提升显著,显示了该改进算法的有效性.