期刊：
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING,2024年11(3):2510-2523 ISSN：2327-4697
通讯作者：
Yang, LT
作者机构：
[Zeng, Jiuzhen; Ruan, Yiheng; Yang, Laurence T.; Zhu, Chenlu] Huazhong Univ Sci & Technol, Hubei Engn Res Ctr Big Data Secur, Sch Cyber Sci & Engn, Hubei Key Lab Distributed Syst Secur, Wuhan 430074, Peoples R China.;[Zeng, Jiuzhen; Wang, Chao] Univ South China, Sch Elect Engn, Hengyang 421001, Peoples R China.;[Yang, Laurence T.] Zhengzhou Univ, Sch Comp & Artificial Intelligence, Zhengzhou 450001, Peoples R China.;[Yang, Laurence T.] St Francis Xavier Univ, Dept Comp Sci, Antigonish, NS B2G 2W5, Canada.;[Ruan, Yiheng] Hubei Chutian Smart Commun Co Ltd, Wuhan 430074, Peoples R China.
通讯机构：
[Yang, LT ] H;Huazhong Univ Sci & Technol, Hubei Engn Res Ctr Big Data Secur, Sch Cyber Sci & Engn, Hubei Key Lab Distributed Syst Secur, Wuhan 430074, Peoples R China.;Zhengzhou Univ, Sch Comp & Artificial Intelligence, Zhengzhou 450001, Peoples R China.
关键词：
Network traffic;anomaly pursuit;low-rank decomposition;tensor theories and methods
摘要：
Accurately pursuing network traffic anomalies is crucial to network maintenance and management. However, existing methods generally focus on detecting uniformly distributed sparse noises and therefore fail to deal with non-uniform or sequential anomalies with effect. In this article, a novel corruption-robust low-rank tensor decomposition (Cr-LTD) method is proposed for accurate and efficient structured-anomaly pursuit even in presence of sparse corruptions. For the intrinsically low-rank network traffic observation, Cr-LTD models it as a three-way tensor and formulates the traffic anomaly pursuit as a low-rank tensor decomposition problem. The intrinsically low-rank structure of network traffic tensor is depicted via a novel tensor nuclear norm which is a tight convex surrogate of tensor tubal rank. ${{\ell }_{2,1}}$ -norm and ${{\ell }_{1}}$ -norm are also introduced in Cr-LTD respectively for effective characterization on structured-anomaly and strong robustness to sparse corruption. Equipped with tensor nuclear norm and two regularizations, Cr-LTD achieves the low-rank tensor decomposition via solving and accelerating a convex program, thereby pursuing structured-anomaly robustly. Extensive experiments are conducted using a set of synthetic data and real-world network traffic datasets. Experiment results verify the superior performance of Cr-LTD over the state-of-the-art methods in terms of pursuit accuracy and corruption robustness.
摘要：
Visual inspection techniques for rail surface defects have become prevalent approaches to obtain information on rail surface damage. However, uneven illumination leads to illegibility of local information, and the change of the wheel-rail area results in the changeful background of the rail surface, both of which pose challenges to the visual inspection. This paper proposes a novel algorithm that detects rail surface defects via partitioned edge features (PEF). PEF eliminates the effect of uneven illumination by effectively extracting edge features and building homogeneous background on the rail surface. In the process of edge feature extraction, the thresholding based on adaptive partition of rail surface (APRS) plays an indispensable role. In APRS, the rail surface is adaptively partitioned into three types of regions according to the wheel-rail contact degree. After that, the dynamic threshold is set adaptively for each region type on the basis of the prior information of defect proportion. Subsequently, based on neighborhood information and fuzzy decision, the spatial information of adjacent pixels and the direction information of fracture edges are utilized to realize the effective recovery of incomplete defect contours. In addition, defect contours are precisely filled via a flexible combination of morphological hole filling operation and defect region extraction based on improved background difference. The accuracy of this PEF algorithm was confirmed by experiments and comparisons with related algorithms. The experiment results show that PEF detects defects with 92.03% recall and 88.49% precision, which achieves higher accuracy than the established detection algorithms for rail surface defects.
摘要：
Combination-chord model (CCM), specially designed to broaden the range of rail corrugation measurement, still faces two troubles including the measuring point deviation and the inverse filter parameters optimization. In this paper, a triple-line structured-light vision (SLV) based CCM is introduced to address these issues. Two solutions respectively for rectification of the measuring points deviation and optimization of the inverse filter parameters are presented. The former, based on the horizontal spacing constraint, detects the exact measuring point from a true rail profile which is reconstructed and rectified by the triple-line SLV. The latter, based on the minimum cumulative recovery error, defines the optimized numbers of frequency sampling and filter order, together with a splicing wavelength. Employing these optimized parameters, our CCM yields the overall amplitude-frequency response being nearly one whether for longwave corrugation or for shortwave corrugation. Both of the proposed solutions aim at enhancing the ordinary CCM in terms of the validity for rail corrugation measurement. Experimental assessments verify the availability and repeatability of our scheme.
摘要：
Dynamically measuring rail profile using the structured-light vision suffers from random vibrations on the line laser projector, which would cause distorted rail profiles. This paper presents a simple and effective distortion rectifying method to address this issue. The distorted rail profile is rectified by easily projecting it onto an auxiliary plane which is parallel to the cross section of rail. In order to establish the auxiliary plane, three profiles formed by radiating multiline structured light on rail are used to fit the rail longitudinal axis. More importantly, only one of the light planes is required to be calibrated beforehand. The others are calibrated online with the proposed self-calibration method, which is based on collinearity and parallelity constraints on the scene points of different rail profiles and requires only one image of the scene. Apart from evaluating the implementation with comprehensive experiments, we compare our method against other published works. The results exhibit its effectiveness and superiority in terms of the dynamic measurement of the rail profile.
摘要：
Structured-light vision (SLV) is a standard approach for inspecting rail wear. However, it is incompetent for dynamic inspection due to the random vibrations in the line laser projector. In this paper, a three-step distortion rectifying method is introduced to address this issue. Given an image with two rail profile stripes, the first step involves parallelity constraint-based establishment of an auxiliary plane whose normal vector is parallel with the rail longitudinal axis. The establishment is only dependent on the intrinsic camera parameters, which improves the robustness of the auxiliary plane to the random vibrations in the line laser projector. In step two, this auxiliary plane is utilized for the autonomous calibration of the line structured lights. The proposed self-calibration is achieved by minimizing the point set mapping errors on triple matching primitives such as rail jaw, railhead inner, and rail foot and requires only two laser stripes. After these two steps, two rail profiles are reconstructed from the double-line SLV without known poses, and the distorted one is projected onto the auxiliary plane for distortion rectifying. It is able to deliver more precise rectifying than the parallel-line SLV and cross-line SLV, even if the inspecting task is performed dynamically. With the comprehensive experiments, we test our scheme and compare it with the related methods. The experimental results verify that the proposed method outperforms the previous works in terms of the accuracy and robustness for the dynamic wear inspection.
摘要：
针对具有较大多普勒扩展和时延扩展的车载通信环境,利用后训练序列信道响应携带的信道变化信息,提出一种结合后训练序列的判决反馈信道估计方法。该方法采用最小二乘算法估计后训练序列的信道响应;对前一个正交频分复用(orthogonal frequency division multiplexing, OFDM)符号和后训练序列的信道响应估计值进行系数加权求和来估计当前OFDM符号的信道响应,并利用其4个导频子载波的信道频率响应关系自动获取加权系数;最后,对获得的信道响应估计值进行判决反馈和低通滤波以降低噪声影响。仿真结果表明,与目前取得较好性能的STA(spectral temporal averaging)方法、CDP(constructing data pilot)方法和结合平滑滤波的判决反馈信道估计方法相比,所提方法具有更优的误包率性能。
摘要：
针对多用户配对虚拟MIMO（multiple input multiple output）安全性差、对信道估计器依赖性强的问题,在分析理想MIMO系统和多径SISO（single input single output）系统本质关系的基础上,提出一种基于空时分组编码STBC（space-time block coding）和正交频分复用（orthogonal frequency division multiplexing,OFDM）的非协作式虚拟MIMO传输策略.在发送端,为了获得最佳发射分集增益,利用信道循环矩阵奇异值分解（singular value decomposition,SVD）后得到的左酉矩阵进行预编码;在接收端,为了获得平行子信道传输效果,提出一种基于低复杂度线性STBC译码和傅里叶变换预解码的非协作虚拟MIMO接收方案.该虚拟MIMO在收发两端均无需信道瞬时信息,以非协作方式在单天线内模拟多天线收发效果.仿真分析结果表明该虚拟MIMO系统能有效逼近实际理想MIMO的系统容量和误比特率性能,显著降低了虚拟MIMO系统的检测门限.该结果验证了其有效性和优越性.
摘要：
针对多用户配对虚拟MIMO (multiple input multiple output)安全性差,对信道估计器依赖性强的问题,提出一种基于非相干空频码(non-coherent space frequency code, NSFC)和正交频分复用(orthogonal frequency division multiplexing, OFDM)的非协作式虚拟MIMO。在分析NSFC成对错误概率的基础上,给出能满足全分集阶数和最大编码增益的编码准则。为了获得平行子信道传输效果,利用信道循环矩阵奇异值分解(singular value decomposition, SVD)后得到的酉矩阵分别进行预编码和预解码。基于最优NSFC和OFDM预编解码,提出一种新颖的虚拟MIMO策略。该虚拟MIMO在收发两端均无需信道瞬时信息,以非协作方式在单天线内模拟多天线收发效果。理论和仿真分析结果表明,虚拟MIMO系统能有效逼近实际理想MIMO的系统容量和误比特率性能,显著降低了虚拟MIMO系统的检测门限。
