Cross lingual speech emotion recognition via triple attentive asymmetric convolutional neural network

The application of cross‐corpus for speech emotion recognition (SER) via domain adaptation methods have gain high acknowledgment for developing good robust emotion recognition systems using different corpora or datasets. However, the issue of cross‐lingual still remains a challenge in SER and needs more attention to resolve the scenario of applying different language types in both training and testing. In this paper, we propose a triple attentive asymmetric convolutional neural network to address the recognition of emotions for cross‐lingual and cross‐corpus speech in an unsupervised approach. The proposed method adopts the joint supervision of softmax loss and center loss to learn high power discriminative feature representations for target domain via the use of high quality pseudo‐labels. The proposed model uses three attentive convolutional neural networks asymmetrically, where two of the networks are used to artificially label unlabeled target samples as a result of their predictions from training on source labeled samples and the other network is used to obtain salient target discriminative features from the pseudo‐labeled target samples. We evaluate our proposed method on three different language types (i.e., English, German, and Italian) data sets. The experimental results indicate that, our proposed method achieves higher prediction accuracy over other state‐of‐the‐art methods.     

Gain‐scheduled dynamic output feedback control for discrete‐time LPV systems

This paper presents synthesis conditions for the design of gain‐scheduled dynamic output feedback controllers for discrete‐time linear parameter‐varying systems. The state‐space matrix representation of the plant and of the controller can have a homogeneous polynomial dependency of arbitrary degree on the scheduling parameter. As an immediate extension, conditions for the synthesis of a multiobjective ??_∞ and ??₂ gain‐scheduled dynamic feedback controller are also provided. The scheduling parameters vary inside a polytope and are assumed to be a priori unknown, but measured in real‐time. If bounds on the rate of parameter variation are known, they can be taken into account, providing less conservative results. The geometric properties of the uncertainty domain are exploited to derive finite sets of linear matrix inequalities based on the existence of a homogeneous polynomially parameter‐dependent Lyapunov function. An application of the control design to a realistic engineering problem illustrates the benefits of the proposed approach. Copyright © 2011 John Wiley & Sons, Ltd.     

Asymptotic and robust stability of T‐S fuzzy genetic regulatory networks with time‐varying delays

In this paper, we propose and investigate a new general model of fuzzy genetic regulatory networks described by the Takagi–Sugeno (T‐S) fuzzy model with time‐varying delays. By using a Lyapunov functional approach and linear matrix inequality (LMI) techniques, the stability criteria for the delayed fuzzy genetic regulatory networks are expressed as a set of LMIs, which can be solved numerically by LMI toolbox in Matlab. Two fuzzy genetic network example are given to verify the effectiveness and applicability of the proposed approach. Copyright © 2011 John Wiley & Sons, Ltd.     

Simple method of characterizing the spatial luminance distribution at the user position for autostereoscopic 3‐D display

Abstract— The image quality of autostereoscopic 3‐D displays strongly depends on the user position. So, characterization of the spatial luminance distribution at the user position is important. For the measurement of the spatial luminance distribution, a method that places a diffuser screen at the user position and is illuminated by a 3‐D display has been investigated. By placing the diffuser screen and 3‐D display non‐parallel, the luminance distribution at the various distances can be determined. Though the accuracy of this measurement method is somewhat limited, the measuring procedure is fast and simple, compared with other time‐consuming methods.     

Delay‐dependent passivity and passification for uncertain Markovian jump systems with time‐varying delays

This paper deals with the problems of passivity analysis and passivity‐based controller design for Markovian jump systems with both time‐varying delays and norm‐bounded parametric uncertainties. Firstly, new delay‐dependent conditions for the considered system to be passive are obtained by using a mode‐dependent Lyapunov functional and by introducing some slack variables. These conditions are expressed by means of LMIs that are easy to check. It is shown through a numerical example that the obtained passivity conditions are less conservative than the existing ones in the literature. Secondly, the passification problem is investigated. On the basis of the obtained passivity conditions, dynamic output‐feedback controllers are designed, which ensure that the resulting closed‐loop system is passive. The effectiveness of the proposed design method is demonstrated by a numerical example. Copyright © 2011 John Wiley & Sons, Ltd.     

An Intelligent Robust Tracking Control for a Class of Electrically Driven Mobile Robots

This paper addresses the problem of designing robust tracking control for a class of uncertain wheeled mobile robots actuated by brushed direct current motors. This class of electrically‐driven mechanical systems consists of the robot kinematics, the robot dynamics, and the wheel actuator dynamics. Via the backstepping technique, an intelligent robust tracking control scheme that integrates a kinematic controller and an adaptive neural network‐based (or fuzzy‐based) controller is developed such that all of the states and signals of the closed‐loop system are bounded and the tracking error can be made as small as possible. Two adaptive approximation systems are constructed to learn the behaviors of unknown mechanical and electrical dynamics. The effects of both the approximation errors and the unmodeled time‐varying perturbations in the input and virtual‐input weighting matrices are counteracted by suitably tuning the control gains. Consequently, the robust control scheme developed here can be employed to handle a broader class of electrically‐driven wheeled mobile robots in the presence of high‐degree time‐varying uncertainties. Finally, a simulation example is given to demonstrate the effectiveness of the developed control scheme.     

焊接箱型截面构件在不同焊缝熔深下承载力性能试验研究

为了有效改善大跨度桥梁中管翼缘焊接箱型截面构件的耐久性的问题,提出采用耐候钢代替普通钢的管翼缘箱型截面梁。同时,为了研究耐候钢管翼缘焊接箱型截面构件填充混凝土后在全熔透和部分熔透条件下的单轴承载力性能,开展了焊接矩形截面在三种不同焊缝熔深下的耐候钢管混凝土截面轴压短柱试验研究。分别测试每个试件在单轴压力作用下的静态应变、动态应变,以及竖向位移和侧向位移。对比构件承载力的试验结果及理论分析结果,得出不同熔深下焊接箱型截面管翼缘组合构件的承载力性能。研究结果表明:1）耐候钢管翼缘焊接箱型截面构件的全熔透焊缝承载力高于部分熔透焊缝承载力。2）全熔透试件开裂时的竖向位移较部分熔透试件的位移值大,而不同熔深下构件的横向位移测点L4随轴压荷载的增大而有增加,L3测点横向位移规律不明显。3）不同耐候钢管翼缘焊接箱型截面构件横向整体受拉,局部在顶部角部位置受压。构件的混凝土内部和钢板表面应变情况复杂,规律不明显。     

不同变截面桩竖向承载特性的数值分析

基于现场试验,采用Abaqus有限元软件对等截面桩及变截面桩单桩竖向承载力测试实验过程进行数值模拟。结果表明:弹性变形阶段,竖向荷载-沉降曲线呈线性变化趋势,等截面桩比变截面桩桩身沉降较小;塑性屈服阶段,等截面桩与变截面桩单桩承载力几乎一致。变截面位置对桩侧摩阻力沿深度的分布有一定影响,最大侧摩阻力位置根据变截面的位置而变化。变截面桩的平均侧摩阻力较等截面桩的平均侧摩阻力大,变截面桩侧摩阻力效果较等截面桩更有优势。在相同承载力条件下,变截面桩所耗费的材料较等截面少,对于竖向承载特性,变截面桩与等截面桩表现基本一致,因此使用变截面桩能节约工程成本。     

基于多任务学习和知识图谱的面部表情识别

针对面部表情分类的模型中参数较复杂、识别准确率较低的问题,提出了一种基于知识图谱辅助识别的多任务学习算法模型（MLAM）,该模型由基于深度学习的识别模块与知识图谱嵌入模块两部分构成。首先从输入的数据中提取潜在的人脸局部表情特征,通过知识图谱实现局部表情和个体的复杂交互;然后在MLAM 模型中设计一个交叉压缩单元,关联这两个独立模块,自动学习局部表情和实体特征的高级交互,并在这两个任务之间传递交叉知识转移;最后,在FER2013和CK+的数据集上对比了同类算法,实验结果表明,该模型在上述数据集上分别得到了0.69和0.99的识别率,提高了面部表情识别准确率。     

基于水质模拟的水质在线监测站点布设研究

随着水质监测连续化的需求增加,河流水质在线监测站布设成为不可忽视的问题。本文采用水文模拟模型HSPF对台湾淡水河流域进行水量水质联合模拟。水文模拟以9个测站比对,纳什效率系数多数大于0.7;相关系数r皆大于0.7。水质模拟以27个测站比对,生化需氧量、氨氮、悬浮固体、溶氧的修正平均百分误差多数小于25%。基于水质变化率和水质超标率提出水质敏感河段概念,并以此确定为补充布设水质在线监测站点的优先河段。研究指出,淡水河流域水质在线监测站目前仍缺乏且位置不尽合理,应优先补充三峡河的三峡大桥、景美溪的宝桥、基隆河的江北桥水质在线监测站。