Multi-Step Model Predictive Control Based on Online Support Vector Regression Optimized by Multi-Agent Particle Swarm Optimization Algorithm

As optimization of parameters affects prediction accuracy and generalization ability of support vector regression (SVR) greatly and the predictive model often mismatches nonlinear system model predictive control, a multi-step model predictive control based on online SVR (OSVR) optimized by multi-agent particle swarm optimization algorithm (MAPSO) is put forward. By integrating the online learning ability of OSVR, the predictive model can self-correct and adapt to the dynamic changes in nonlinear process well.     

基于CNN-SVR混合深度学习模型的短时交通流预测

精准且快速的短时交通流预测是智能交通发展的重要组成部分.本文针对当前交通流预测模型不能充分提取交通流数据的时空特征、预测性能容易受到外界干扰因素影响的问题,提出一种基于深度学习的短时交通流预测模型,该模型结合卷积神经网络(Convolutional Neural Network,CNN)与支持向量回归分类器(Support Vector Regression,SVR)的特点:在网络底层应用CNN进行交通流特征提取,并将提取结果输入到SVR回归模型中进行流量预测.为验证模型的有效性,取G103国道的实际交通流量数据进行试验.结果表明,提出的预测模型与传统的预测模型相比具有更高的预测精度,预测性能提高了11%,是一种有效的交通流预测模型.     

Support vector regression based color image restoration in YUV color space

A support vector regression(SVR) based color image restoration algorithm is proposed.The test color images are firstly mapped into the YUV color space,and then SVR is applied to build up a theoretical model between the degraded images and the original one.Performance comparisons of the proposed algorithm versus traditional filtering algorithms are given.Experimental results show that the proposed algorithm has better performance than traditional filtering algorithms and has less computation time than iterat...     

基于票务数据的团体旅客出行目的推断

为推进城际交通大数据的应用，需要补全出行目的信息，将团体旅客出行目的决策与文本主题生成类比，开发基于无监督学习框架的出行目的推断方法.提出嵌入出发时间生成模块的主题模型，以及团体旅客重建和语义化特征设计方法，并通过吉布斯采样估计参数. 基于调查数据的模型对比研究发现，模型对一般私务辨识性能提升7.7%；基于票务数据的案例研究发现，模型对出发时间预测精度达到90.9%，间接验证了模型的可靠性.主题标注表明，模型不仅推断出4种与典型模式相符的出行目的，还辨识出既有认识外的非常规模式.对道路客运分析表明，出行目的构成呈现地区差异，高铁开通对不同出行目的出行量的负向影响程度不一.     

基于票务数据的团体旅客出行目的推断

为推进城际交通大数据的应用，需要补全出行目的信息，将团体旅客出行目的决策与文本主题生成类比，开发基于无监督学习框架的出行目的推断方法.提出嵌入出发时间生成模块的主题模型，以及团体旅客重建和语义化特征设计方法，并通过吉布斯采样估计参数. 基于调查数据的模型对比研究发现，模型对一般私务辨识性能提升7.7%；基于票务数据的案例研究发现，模型对出发时间预测精度达到90.9%，间接验证了模型的可靠性.主题标注表明，模型不仅推断出4种与典型模式相符的出行目的，还辨识出既有认识外的非常规模式.对道路客运分析表明，出行目的构成呈现地区差异，高铁开通对不同出行目的出行量的负向影响程度不一.     

Inverse Learning Control of Nonlinear Systems Using Support Vector Machines

An inverse learning control scheme using the support vector machine (SVM) for regression was proposed. The inverse learning approach is originally researched in the neural networks. Compared with neural networks, SVMs overcome the problems of local minimum and curse of dimensionality. Additionally, the good generalization performance of SVMs increases the robustness of control system. The method of designing SVM inverse learning controller was presented. The proposed method is demonstrated on tracking problems and the performance is satisfactory.     

Single Image Super-Resolution Method via Refined Local Learning

In this paper,we propose a refined local learning scheme to reconstruct a high resolution(HR)face image from a low resolution(LR)observation.The contribution of this work is twofold.Firstly,multi-direction gradient features are extracted to search the nearest neighbors for each image patch,then the non-negative matrix factorization(NMF)is used to reduce the complexity in weight calculation,and the initial HR embedding is estimated from the training pairs by preserving local geometry.Secondly,a global reconstruction constraint and post-processing by non-local filtering is incorporated into super-resolution(SR)reconstruction process to reduce the image artifacts and further improve the image visual quality.Experimental results show that the proposed algorithm improves the SR performance both in subjective and objective assessments compared with several existing methods.     

改进SVR及其在铁路客运量预测中的应用

为了提高铁路客运量现有预测方法的预测能力,用训练样本与测试样本间的马氏距离对惩罚因子进行加权,对传统的支持向量回归机(SVR)进行了改进,在此基础上提出了基于改进SVR的铁路客运量时间序列预测方法.以1980~1998年铁路客运量预测为例,对SVR方法和BP人工神经网络(BPANN)方法进行了比较,结果表明,SVR方法能获得更准确的预测结果.     

A Statistical Parameter Analysis and SVM Based Fault Diagnosis Strategy for Dynamically Tuned Gyroscopes

Gyro's fault diagnosis plays a critical role in inertia navigation systems for higher reliability and precision. A new fault diagnosis strategy based on the statistical parameter analysis (SPA) and support vector machine (SVM) classification model was proposed for dynamically tuned gyroscopes (DTG). The SPA, a kind of time domain analysis approach, was introduced to compute a set of statistical parameters of vibration signal as the state features of DTG, with which the SVM model, a novel learning machine based on statistical learning theory (SLT), was applied and constructed to train and identify the working state of DTG. The experimental results verify that the proposed diagnostic strategy can simply and effectively extract the state features of DTG, and it outperforms the radial-basis function (RBF) neural network based diagnostic method and can more reliably and accurately diagnose the working state of DTG.     

基于层次集成学习的高光谱图像分类

为提高高光谱图像（HSI）分类精度,基于集成学习方法提出高光谱图像分类的层次集成学习新框架。采用两种集成学习策略：外部集成及内部集成。在外部集成阶段,构造多种高光谱图像的光谱和空间特征,使外部集成呈高度多样性,有利于提高分类精度;内部集成阶段,针对关联多特征集中的个体,Adaboost算法实现个体分类性能的提高。两组高光谱数据的实验结果表明,与原始的Adaboost和单分类器相比较,该方法在整体精度方面有更好的性能。     

边坡变形时序分析的进化-自适应神经模糊推理模型

变形监测与预报是保证边坡工程施工安全与工程质量的重要措施,但由于位移时间序列的强非线性,边坡变形预报成为非常困难的问题．自适应模糊神经推理系统（ANFIS）有优越的学习和泛化性能,而遗传算法（GA）是优秀的全局优化工具．采用遗传算法优化ANFIS参数,并编制了相应的计算程序．结合三峡工程永久船闸施工变形监测和新滩滑坡变形监测,建立了边坡变形时序分析的GA-ANFIS智能模型．为了对比该模型的预测精度,采用GA优化支持向量回归（SVR）和BP神经网络的模型参数,编制了GA-SVR及GA-BP程序,对相同的算例进行了变形预测分析．按滚动预测法对三峡永久船闸高边坡和新滩滑坡的计算结果表明,文中提出的GA-ANFIS模型能够获得比GA-SVR和GA-BP模型更高的预测精度,可以应用于边坡工程变形监测预报分析,并为类似工程提供参考．     

Branch-Activated Multi-Domain Convolutional Neural Network for Visual Tracking

Convolutional neural networks (CNNs) have been applied in state-of-the-art visual tracking tasks to represent the target. However, most existing algorithms treat visual tracking as an object-specific task. Therefore, the model needs to be retrained for different test video sequences. We propose a branch-activated multi-domain convolutional neural network (BAMDCNN). In contrast to most existing trackers based on CNNs which require frequent online training, BAMDCNN only needs offline training and online fine-tuning. Specifically, BAMDCNN exploits category-specific features that are more robust against variations. To allow for learning category-specific information, we introduce a group algorithm and a branch activation method. Experimental results on challenging benchmark show that the proposed algorithm outperforms other state-of-the-art methods. What’s more, compared with CNN based trackers, BAMDCNN increases tracking speed.     

铁路风屏障防风效果代理模型优化

为确定铁路风屏障的最优参数,基于代理模型方法对风屏障防风效果进行了优化.首先,改进了网格搜索法以优化支持向量机回归模型的参数,并通过算例进行了验证.其次,以设置风屏障时的车辆气动特性为目标函数,建立了风屏障防风效果的优化模型.最后,利用风屏障的风洞试验结果,采用支持向量机回归建立了目标函数的代理模型,对风屏障的高度和透风率进行了优化.研究结果表明:改进的网格搜索法提高了支持向量机模型参数选择的准确性,当风屏障高度为1.91~2.90 m时,最优的风屏障透风率为0.00~0.17;当风屏障高度超过2.50 m后,增加风屏障的高度对防风效果的提高较为有限.      

Adaptive illumination normalization approach based on denoising technique for face recognition

A novel adaptive illumination normalization approach is proposed to eliminate the effects caused by illumination variations for face recognition. The proposed method divides an image into blocks and performs discrete cosine transform (DCT) in blocks independently in the logarithm domain. For each block-DCT coefficient except the direct current (DC) component, we take the illumination as main signal and take the reflectance as “noise”. A data-driven and adaptive soft-thresholding denoising technique is employed in each block-DCT coefficient except the DC component. Illumination is estimated by applying the inverse DCT in the block-DCT coefficients, and the indirectly obtained reflectance can be used in further recognition task. Experimental results show that the proposed approach outperforms other existing methods. Moreover, the proposed method does not need any prior information, and none of the parameters can be determined by experience.     

基于SVR的区域交通碳排放预测研究

基于STIRPAT模型,选择旅客周转量、货物周转量、人均GDP、机动车保有量、碳排放强度、能源结构和城市化率7项指标作为我国区域交通碳排放影响因素,建立基于支持向量回归机的碳排放预测模型,并以1990-2016年北京市交通碳排放相关数据为基础数据做实例分析.结果表明：训练样本交叉验证均方误差仅为 0.008 040,得到参数C和γ的最优值;模型预测值与真实值的拟合回归效果良好,训练集和测试集的相关系数分别为0.984 2和0.995 0,即模型具有良好的学习和推广能力;未来区域交通碳排放增长趋势逐渐变缓,但总量将继续呈上升趋势,社会仍然面临较大的温室气体减排压力.     

Dynamic Measurement of Task Scheduling Algorithm in Multi-Processor System

It is important to evaluate function behaviors and performance features of task scheduling algorithm in the multi-processor system.A novel dynamic measurement method(DMM)was proposed to measure the task scheduling algorithm's correctness and dependability.In a multi-processor system,task scheduling problem is represented by a combinatorial evaluation model,interactive Markov chain(IMC),and solution space of the algorithm with time and probability metrics is described by action-based continuous stochastic logic(aCSL).DMM derives a path by logging runtime scheduling actions and corresponding times.Through judging whether the derived path can be received by task scheduling IMC model,DMM analyses the correctness of algorithm.Through judging whether the actual values satisfy label function of the initial state,DMM analyses the dependability of algorithm.The simulation shows that DMM can effectively characterize the function behaviors and performance features of task scheduling algorithm.     

基于支持向量分类机和回归机的综合评价方法

采用支持向量多值分类机和回归机进行综合评价排序,以提高机器学习方法的综合评价排序能力,并以管理信息系统综合评价为例,与人工神经网络（ANN）方法进行了对比研究.试验结果表明,基于支持向量多值分类机综合评价得分之间的差异比ANN更明显,而且基于支持向量回归机综合评价得分的相对误差明显小于ANN.     

大数据背景下基于特征学习的机械设备剩余寿命预测

传统数据驱动剩余寿命的预测方法是通过信号处理从监测数据中手动提取特征并构建健康指标，而在大数据背景下，手动提取特征需要特定专家知识并耗费大量人力，为解决该问题，提出了一种基于特征学习的机械设备剩余寿命预测方法——自适应特征学习寿命预测方法（AFLRULP）. 该方法构建移动窗口数据矩阵解决单次采样中的数据波动问题，并建立了多层一维卷积神经网络将数据矩阵映射为机械设备的健康状态；根据失效阈值可以计算出机械设备的剩余寿命；采样轴承全寿命周期数据集合对提出的AFLRULP进行验证，并且与传统基于手动提取特征的方法进行寿命预测准确性的对比. 研究结果表明:AFLRULP不需要人工提取特征，可从原始监测数据映射为机械设备的性能状态与剩余寿命，相对于现有的基于手动提取特征的寿命预测方法，提出的方法在轴承寿命预测累积相对准确率上平均提高了0.20.      

An efficient approach for solving yard crane scheduling in a container terminal

An efcient approach for yard crane（YC）scheduling is proposed in this paper.The definition of task group for YC scheduling is proposed.A mixed integer programming（MIP）model is developed.In the model,objective functions are subject to the minimization of the total delay of complete time for all task groups and the minimization of block-to-block movements of YCs.Due to the computational scale of the non-deterministic polynomial（NP）complete problem regarding YC scheduling,a rolling-horizon decision-making strategy is employed to solve this problem,by converting the MIP model into another MIP model in the scheduling of each rolling period.Afterwards,a heuristic algorithm based on modified A＊search is developed to solve the converted model and obtain near optimal solution.Finally,the computational experiments are used to examine the performance of the proposed approach for YC scheduling.     

Automatic semantic analysis of software requirements through machine learning and ontology approach

Nowadays, software requirements are still mainly analyzed manually, which has many drawbacks (such as a large amount of labor consumption, inefficiency, and even inaccuracy of the results). The problems are even worse in domain analysis scenarios because a large number of requirements from many users need to be analyzed. In this sense, automatic analysis of software requirements can bring benefits to software companies. For this purpose, we proposed an approach to automatically analyze software requirement specifications (SRSs) and extract the semantic information. In this approach, a machine learning and ontology based semantic role labeling (SRL) method was used. First of all, some common verbs were calculated from SRS documents in the E-commerce domain, and then semantic frames were designed for those verbs. Based on the frames, sentences from SRSs were selected and labeled manually, and the labeled sentences were used as training examples in the machine learning stage. Besides the training examples labeled with semantic roles, external ontology knowledge was used to relieve the data sparsity problem and obtain reliable results. Based on the SemCor and WordNet corpus, the senses of nouns and verbs were identified in a sequential manner through the K-nearest neighbor approach. Then the senses of the verbs were used to identify the frame types. After that, we trained the SRL labeling classifier with the maximum entropy method, in which we added some new features based on word sense, such as the hypernyms and hyponyms of the word senses in the ontology. Experimental results show that this new approach for automatic functional requirements analysis is effective.