多传感器融合在倾角测量抗振动中的应用

倾角传感是通过加速度计敏感重力加速度分量,反求出平面倾斜的角度。当倾角传感元件在振动的载体上工作时,由于载体的加速和减速会被加速度计敏感,从而对倾角的检测带来不能忽略的影响。对这种情况通过引入陀螺仪作为角度测量的重要互补器件,综合加速度计和陀螺仪两类传感器的数据来抑制振动对角度动态测量的干扰。最后的测试数据表明,这种设计方法在很大程度上消除了由于载体振动带来的干扰。     

卡尔曼滤波语音增强算法的CUDA实现

提出一种卡尔曼滤波语音增强算法的统一计算设备架构并行实现方案。该方案通过离散余弦变换把含噪语音分解为不相关的DCT系数,使原来的时域串行处理转化为统一计算设备架构并行处理,只需较少的线性预测阶数,节省运算时间。实验结果表明:与时域卡尔曼滤波比较,该方法有更高的输出分段信噪比,其统一计算设备架构加速方案可有效缩短语音增强运算的时间。     

基于注意力机制和卡尔曼滤波的多目标跟踪

为了解决目前多目标跟踪算法在行人遮挡后无法再次准确跟踪的问题,提出了一种融入注意力机制和改进卡尔曼滤波的多目标跟踪算法,选用联合检测和重识别框架提取特征,同时完成目标检测和重识别任务.设计了并行支路注意力机制,包括空间注意力和通道注意力两个部分,每个部分都采用并行支路的方式完成池化和卷积操作.在跟踪阶段,本文提出了速度先验卡尔曼滤波,实现对行人运动状态更精确的预测.采用CUHK-SYSU数据集对算法进行训练,并在MOT16数据集上做算法的验证和测试.本算法的多目标跟踪准确度(MOTA)达到了65.1％,多目标跟踪精确度(MOTP)达到了78.8％,识别F1值(IDF1)达到62.3％.实验表明,提出的跟踪算法可以有效地提高跟踪的整体性能,实现对目标的持续跟踪.     

基于Kalman滤波的GSC改进语音增强算法

针对广义旁瓣相消器（Generalized sidelobe canceller,GSC）存在非相干噪声消除性能不佳的缺陷,提出了采用后置Kalman滤波器改进的GSC去噪算法。该算法通过归一化最小均方算法校正自适应噪声对消器,并将滤除方向性干扰噪声后的语音信号输出到Kalman滤波器中,对残余背景噪声进行迭代最小均方误差（Minimum mean square error,MMSE）估计,抑制非相干噪声与麦克风阵元所产生的热噪声。经过在不同信噪比条件下客观语音质量评估（Perceptual evaluation of speech quality,PESQ）及语谱图分析后证明,与传统的GSC以及后置谱减法的改进GSC相比,本算法在噪声消除上的表现更为优越,且增强后信号也更接近目标信号。     

Hierarchical inversion‐based output tracking control for uncertain autonomous underwater vehicles using extended Kalman filter

In this study, a hierarchical inversion‐based output tracking controller (HIOTC) is developed for an autonomous underwater vehicle (AUV) subject to random uncertainties (e.g., current disturbances, unmodeled dynamics, and parameter variations) and noises (e.g., process and measurement noises). The proposed HIOTC respectively utilizes a combination of feedforward and feedback controls in a hierarchical structure based on the kinematic and dynamic models of the system. Moreover, to obtain uncontaminated or unavailable states for implementing the proposed control law, the extended Kalman filter (EKF) is employed to estimate the system states. Then, the position outputs, orientation, and velocity of the AUV are reached with guaranteed asymptotic stability. The robustness of the proposed HIOTC is verified through injection of random uncertainties into the system model. The closed‐loop stability of the proposed individual subsystems is respectively guaranteed to have uniformly ultimately bounded (UUB) performance based on the Lyapunov stability criteria. In addition, the asymptotic tracking of the overall system is demonstrated using Barbalat's lemma. Finally, the feasibility and effectiveness of the proposed control scheme are evaluated through computer simulations and it is shown that the overall system achieves good asymptotic tracking performance.     

A joint introduction to Gaussian Processes and Relevance Vector Machines with connections to Kalman filtering and other kernel smoothers

The expressive power of Bayesian kernel-based methods has led them to become an important tool across many different facets of artificial intelligence, and useful to a plethora of modern application domains, providing both power and interpretability via uncertainty analysis. This article introduces and discusses two methods which straddle the areas of probabilistic Bayesian schemes and kernel methods for regression: Gaussian Processes and Relevance Vector Machines. Our focus is on developing a common framework with which to view these methods, via intermediate methods a probabilistic version of the well-known kernel ridge regression, and drawing connections among them, via dual formulations, and discussion of their application in the context of major tasks: regression, smoothing, interpolation, and filtering. Overall, we provide understanding of the mathematical concepts behind these models, and we summarize and discuss in depth different interpretations and highlight the relationship to other methods, such as linear kernel smoothers, Kalman filtering and Fourier approximations. Throughout, we provide numerous figures to promote understanding, and we make numerous recommendations to practitioners. Benefits and drawbacks of the different techniques are highlighted. To our knowledge, this is the most in-depth study of its kind to date focused on these two methods, and will be relevant to theoretical understanding and practitioners throughout the domains of data-science, signal processing, machine learning, and artificial intelligence in general.     

融合UWB与INS的消防员室内定位与NLOS检测算法

融合超宽带（UWB）和惯性导航系统（INS）能够实现消防员室内精确定位。为实现UWB的非视距（NLOS）误差检测,设计一种双级EKF框架。该框架以松耦合形式实现UWB/INS的数据融合,通过INS获取的初始位置估计坐标以检测UWB测量值的NLOS误差,根据检测结果计算残差矩阵来动态调整融合滤波器的测量噪声矩阵,以达到缓解NLOS误差的目的。实验结果表明,与三角不等式原理检测算法和无NLOS检测的UWB/INS简单融合算法相比,所提NLOS检测算法具备良好的检测能力、较强的稳定性及较高的定位精度。     

双天线测向信息辅助捷联惯导快速对准算法

为解决捷联惯导的快速高精度对准问题,给出了一种双天线测向信息辅助的惯导快速对准算法.介绍了双天线测向的基本原理,在此基础上给出了双天线基线安装误差的补偿方法.基于速度、位置、航向观测量,设计了快速对准卡尔曼滤波器,给出了具体航向量测方程.根据实测双天线测向误差特性进行了仿真分析.仿真结果验证了方法的有效性,4 min航向精度优于0.05°,可满足通常0.8 nm/h机载捷联惯导的对准精度要求.双天线测向信息辅助快速对准算法相对传统基于罗经效应的速度、位置量测对准方式,对准时间可极大地缩短,但具体对准航向精度受双天线测向误差影响大.     

有适应力的分布式状态估计方法

为提高智能体系统对攻击的免疫力,研究了测量攻击下的适应力分布式状态估计方法。每个智能体对系统状态进行连续的本地线性测量。由于不同智能体的本地测量模型相互异构,对系统状态可能不具有本地可观测性,且攻击者能够操控部分智能体的测量数据,随意改变其测量结果。而智能体的目标是协同处理本地测量数据,并正确估计出未知的系统状态。因此,该问题的挑战在于在不对真实测量数据和恶意智能体的测量数据进行分辨时,如何设计算法估计得到真实的系统状态。为了解决这个问题,设计了适应性分布式最大后验概率估计算法。在该算法中,只要恶意智能体的数量小于某个特定值,所有智能体都能够收敛到系统状态。首先,根据卡尔曼滤波给出集中式最大后验概率(Maximum A Posteriori,MAP)估计方法,并与分布式一致性结合,进而得到分布式最大后验概率估计方法。然后,考虑到测量攻击,从估计一致性的角度,利用自适应饱和度增益设计了适应性分布式最大后验概率估计方法。最后,通过仿真实验验证算法的有效性。     

大数据融合模型的智能化网络安全检测方法

针对传统智能化网络安全检测平台处理数据效率低、误差大等问题,文章提出一种新型的解决方案;该方案基于大数据融合模型构建新型的智能化网络安全检测平台,采用卡尔曼滤波算法、采用数据融合分类算法和模糊推理算法3种方法结合构建出数据融合模型来对网络安全检测数据进行运算与处理;其中,采用卡尔曼滤波算法进行改进,对原始网络安全检测数据进行滤波降低噪声干扰,提高数据的精准度;通过SAE稀疏自动编码器自主提取网络安全检测数据的特征信息,之后K-means聚类算法对SAE稀疏自动编码器输出的数据进行处理,通过模糊推理算法调整权值;试验表明,文章所提方案克服了现有技术存在的不足,显著提高了处理数据效率和精准度,在数据量为2 TB的环境下,本研究方法的误差低至6.9％.