基于高阶累积量和DNN模型的井下信号识别方法

针对矿井复杂异构的无线环境,提出一种基于高阶累积量和DNN模型的井下信号识别方法,实现了井下BPSK,QPSK,8PSK,2FSK,4FSK,8FSK,32QAM,64QAM,OFDM等数字信号的自动调制识别。分析得到9种数字信号的高阶累积量理论值,并通过傅里叶变换提高信号辨识度;分析井下小尺度衰落信道对高阶累积量的影响,推导出经过井下衰落信道后信号的高阶累积量计算表达式,根据高阶累积量理论值构造特征参数并训练DNN模型,实现信号识别。仿真分析结果表明,该方法在矿井Nakagami-m衰落信道下有出色的调制识别性能,信噪比为-5 dB时平均正确识别率为89.2%以上,信噪比为5 dB以上时平均正确识别率为100%。该方法为在特殊复杂环境下的信号识别检测提供了新思路。     

基于LDA的表面肌电信号分类研究

研究了一种基于LDA分类器的模式识别方法,比较了五种特征参数组合方式,分析了无关联线性判别分析ULDA和PCA两种降维方法,通道数量和窗口长度对肌电信号分类的影响,最后应用LDA分类器对降维后的数据进行分类。实验结果表明:均方根和四阶AR系数两种特征组合在4通道和8通道下的准确率分别可以达到90%和96%,增加通道数量或特征数量可以进一步提高准确率;通过ULDA将特征矢量的维数降低到6维时,仍可以保证较高的准确率;6种手势的识别率超过了94%,其中4种手超过了97%,分类出错的窗口主要集中在过渡阶段。     

An automated approach to information systems decomposition

A method for automating the process of system decomposition is described. The method is based on a formal specification scheme, formal definition of good decomposition, heuristic rules governing the search for good candidate decompositions, and a measure of complexity that allows ranking of the candidate decompositions. The decomposition method has been implemented as a set of experimental computerized systems analysis tools and applied to a standard problem for which other designs already exist. The results are encouraging, in that decompositions generated using other methodologies map easily into those suggested by the computerized tools. Additionally, the use of the method indicates that when more than one `good' decomposition is suggested by the system, the specifications might have been incomplete. That is, the computerized tools can identify areas where more information should be sought by analysis     

An unconstrained optimization approach to empirical mode decomposition

Empirical mode decomposition (EMD) is an adaptive (data-driven) method to decompose non-linear and non-stationary signals into AM-FM components. Despite its well-known usefulness, one of the major EMD drawbacks is its lack of mathematical foundation, being defined as an algorithm output. In this paper we present an alternative formulation for the EMD method, based on unconstrained optimization. Unlike previous optimization-based efforts, our approach is simple, with an analytic solution, and its algorithm can be easily implemented. By making no explicit use of envelopes to find the local mean, possible inherent problems of the original EMD formulation (such as the under- and overshoot) are avoided. Classical EMD experiments with artificial signals overlapped in both time and frequency are revisited, and comparisons with other optimization-based approaches to EMD are made, showing advantages for our proposal both in recovering known components and computational times. A voice signal is decomposed by our method evidencing some advantages in comparison with traditional EMD and noise-assisted versions. The new method here introduced catches most flavors of the original EMD but with a more solid mathematical framework, which could lead to explore analytical properties of this technique.     

An approach to automated decomposition of volumetric mesh

Mesh decomposition is critical for analyzing, understanding, editing and reusing of mesh models. Although there are many methods for mesh decomposition, most utilize only triangular meshes. In this paper, we present an automated method for decomposing a volumetric mesh into semantic components. Our method consists of three parts. First, the outer surface mesh of the volumetric mesh is decomposed into semantic features by applying existing surface mesh segmentation and feature recognition techniques. Then, for each recognized feature, its outer boundary lines are identified, and the corresponding splitter element groups are setup accordingly. The inner volumetric elements of the feature are then obtained based on the established splitter element groups. Finally, each splitter element group is decomposed into two parts using the graph cut algorithm; each group completely belongs to one feature adjacent to the splitter element group. In our graph cut algorithm, the weights of the edges in the dual graph are calculated based on the electric field, which is generated using the vertices of the boundary lines of the features. Experiments on both tetrahedral and hexahedral meshes demonstrate the effectiveness of our method.     

基于小波变换的表面肌电信号的情感识别

情感识别是情感计算的一个关键问题。针对表面肌电信号（EMG）的非平稳性,采用小波变换方法对表面肌电信号进行分析,提取小波系数最大值和最小值构造特征矢量输入用L-M算法改进的BP神经网络分类器进行情感状态识别。实验表明,用表面肌电信号对joy、anger、sadness、pleasure 4种情感识别效果较好。也说明用小波变换方法提取特征,用神经网络作分类器的方法用于情感识别有很大的应用前景。     

An analogue approach to surface definition

This note describes a method for producing cubic curves made up from Bézier functions on an oscilloscope screen using simple analogue techniques. Ruled surface patches are illustrated in a simple extension of the method. It also indicates how generalized Bézier patches could be produced.     

An approach to closed-loop subspace identification by orthogonal decomposition

A method of identifying closed-loop systems is developed by using the orthogonal decomposition (ORT) method. The idea is to project the input and output data onto the space of exogenous inputs by using the LQ decomposition to obtain their deterministic components. The ORT-based method is then applied to deterministic components like the direct approach in order to derive state-space models of the plant. We also show that the present method is a subspace version of the two-stage method for transfer function estimation from closed loop data. Some simulation results are included to show the applicability of the present method.     

基于多元经验模态分解-传递熵的脑肌电信号耦合分析

皮层肌肉功能耦合是大脑皮层和肌肉组织间的相互作用,脑肌电信号的多尺度耦合特征可以体现皮层-肌肉间多时空的功能联系.将多元经验模态分解(MEMD)与传递熵(TE)结合,构建出MEMD-TE模型,应用于脑、肌间耦合分析.首先对同步采集的脑电(EEG)和肌电(EMG)信号进行预处理,然后采用多元经验模态分解算法对信号进行时-频尺度化,最后计算不同尺度上的传递熵值,分析各个尺度不同耦合方向(EEG→EMG及EMG→EEG)上的非线性耦合特征.采集了10名受试者静态握力(5 kg、10 kg、20 kg)下脑、肌电信号,实验结果表明:脑电对肌电的MEMD-TE值在高频段(40 Hz~75 Hz)上高于肌电对脑电的MEMD-TE值,皮层肌肉功能耦合具有双向性,且不同方向和频段上的耦合强度有所差异,显著性校验反映了不同力度下脑电对肌电的MEMD-TE值没有显著性差别.     

基于表面肌电信号小波包熵的情感识别

情感识别是情感计算的一个关键问题。针对表面肌电信号（EMG）的非平稳性,根据小波包变换在不同时频段均能精确的刻画信号,并提供丰富模式信息的特点,提出利用小波包熵方法对不同情感状态下的表面肌电信号进行分析。实验表明,该方法对情感的唤醒度识别效果较好。     

基于卷积神经网络的表面肌电信号手势识别

运用卷积神经网络原理,实现一维多通道的表面肌电信号的手势识别,避免了复杂的前期表面信号的预处理,以及手工特征提取阶段。文中分别采集右手的握拳、向左、向右和展拳4种手势的表面肌电信号。然后将采集的四种不同手势的肌电信号进行切割与标记,生成不同信号长度的八通道信号的训练集与测试集,运用卷积神经网络的原理,分别对其进行卷积、下采样。经过试验研究发现,运用卷积神经网络处理一维多通道表面肌电信号,从而实现手势识别的算法是可行的,并且能够得到较高的识别率。     

An approach to surface retouching and mesh smoothing

In this paper, we discuss a novel, fast, practical algorithm for surface modification of geometric objects. A space-mapping technique is used to transform a given or damaged part of a surface into a different shape in a continuous manner. The proposed approach is used for surface-retouching and mesh-smoothing problems. The technique, in fact, is based on a local processing of polygonal data that can be applied to the fairing of 3D meshes. We consider shape transformation as a general type of operation for surface modification and attempt to approach the problem from a single point of view, namely, that of the space-mapping technique based on the implementation of radial-basis functions. Experimental results are included to demonstrate the functionality of our mesh-modeling tool.     

An approach to in-process surface texture condition monitoring

Surface textures formed in the machining process have a great influence on parts’ mechanical behaviours. Normally, the surface textures are inspected by using the images of the machined and cleaned parts. In this paper, an in-process surface texture condition monitoring approach is proposed. Based on the grey-level co-occurrence matrices, some surface texture image features are extracted to describe the texture characteristics. On the basis of the empirical model decomposition, some sensitive features are also extracted from the vibration signal. The mapping relationship from texture characteristics to texture image features and vibration signal features is found. A back propagation neural network model is built when the signal features and the texture conditions are respectively inputs and outputs. The particle swarm optimization is used to optimise the weights and thresholds of the neural network. Experimental study verifies the approach's effectiveness in monitoring the surface texture conditions during the machining process. The approach's accuracy and robustness are also verified. Then, the surface texture condition can be monitored efficiently during the machining process.     

An oblique-extrema-based approach for empirical mode decomposition

It has been found that envelopes established by extrema in the empirical mode decomposition cannot always depict the local characteristics of a signal very well. This is due in part to the slight oscillations characterized as hidden scales which are almost left untreated during the sifting process. When involving hidden scales, the intrinsic mode function usually contains at a given instance multiple oscillation modes. In view of this, based on inflection points this paper presents a new decomposition algorithm called ‘oblique-extrema empirical mode decomposition’ to settle these problems. With this algorithm, any signal can be decomposed into a finite number of ‘oblique-extrema intrinsic mode functions’ which may possess better-behaved Hilbert transforms and produce more accurate instantaneous frequencies. It can suppress the effect of hidden scales and gets one step further in extracting finer scales. Experimental results demonstrate good performances of this new method.     

Diagnosing time-varying misbehavior: an approach based on model decomposition

The analysis of time-varying systems is attracting a lot of attention in the model-based diagnosis community. In this paper we propose an approach to the diagnosis of such systems, relying on a component-oriented model; we provide separately a behavioral model, that is, knowledge about the consequences of differentbehavioral modes of the components, and a model of the possible temporal evolution of such modes (mode transition graphs). In the basic approach, we assume that the consequences of behavioral modes are instantaneous with respect to the transition between two modes; this allows us to decompose the solution of a temporal diagnostic problem into two subtasks: determining solutions of atemporal problems in different time points and assembling the solution of the temporal problem from those of the atemporal ones. Most of the definitions and machinery developed for static diagnosis can be re-used in such a framework. We then consider the consequences of some extensions. Even allowing for very simple temporal relations in the behavioral model leads to a more complex interference between reasoning on the behavioral models and the consistency check with respect to possible temporal evolutions. We also briefly analyze the case of adding quantitative temporal knowledge or probabilistic knowledge to the mode transition graphs.This work was partially supported by CNR under grants 91.00916.PF69 and 91.02351.CT12.     

A novel multi-focus image fusion approach based on image decomposition

Multi-focus image fusion is an effective technique to integrate the relevant information from a set of images with the same scene, into a comprehensive image. The fused image would be more informative than any of the source images. In this paper, a novel fusion scheme based on image cartoon-texture decomposition is proposed. Multi-focus source images are decomposed into cartoon content and texture content by an improved iterative re-weighted decomposition algorithm. It can achieve rapid convergence and naturally approximates the morphological structure components. The proper fusion rules are constructed to fuse the cartoon content and the texture content, respectively. Finally, the fused cartoon and texture components are combined to obtain the all-in-focus image. This fusion processing can preserve morphological structure information from source images and performs few artifacts or additional noise. Our experimental results have clearly shown that the proposed algorithm outperforms many state-of-the-art methods, in terms of visual and quantitative evaluations.     

A BMI approach for H 2 based decomposition

The problem of static precompensator design for uncertain system to reduce the coupling is considered in this paper. Diagonal dominant is redefined using the H ₂ norm of the system. Based on this definition, the necessary and sufficient conditions for system diagonal dominant, which are described by Linear Matrix Inequalities (LMIs), are derived. These conditions are extended to design static precompensator for both nominal system and uncertain system. The conditions are in the form of Bilinear Matrix Inequalities (BMIs), and the combined bisection and path-following algorithm is developed to solve the BMIs. An example is given to show the effectiveness of the proposed method.     

An approach to active spatial data mining based on statisticalinformation

Spatial data mining presents new challenges due to the large size of spatial data, the complexity of spatial data types, and the special nature of spatial access methods. Most research in this area has focused on efficient query processing of static data. This paper introduces an active spatial data mining approach that extends the current spatial data mining algorithms to efficiently support user-defined triggers on dynamically evolving spatial data. To exploit the locality of the effect of an update and the nature of spatial data, we employ a hierarchical structure with associated statistical information at the various levels of the hierarchy and decompose the user-defined trigger into a set of subtriggers associated with cells in the hierarchy. Updates are suspended in the hierarchy until their cumulative effect might cause the trigger to fire. It is shown that this approach achieves three orders of magnitude improvement over the naive approach that reevaluate the condition over the database for each update, while both approaches produce the same result without any delay. Moreover, this scheme can support incremental query processing as well