A robust locating multi-optima approach for damage identification of plate-like structures

This paper proposes a robust optimization approach for multiple damage identification of plate-like structures. Different from traditional particle swarm optimizations (PSOs), a combined PSO and niche technique (NPSO) is proposed to solve multimodal optimization problems, with the full consideration of subswarm creation, merging and absorbing mechanism. As a hypersensitive parameter to damage, the curvature mode shape is adopted to construct the objective function. Case studies are conducted to investigate the effectiveness and robustness of the algorithm on multi-damage identification. Simulation results show that the proposed algorithm exhibits robust search performance on identifying damage locations accurately with good convergence behavior. It is hoped that this study can provide guidance on robust damage detection, especially when the structure is subject to multiple damages and external disturbances.     

一种基于改进NMS的牛脸检测方法

针对牲畜牛身份认证的多牛脸检测场景，本文给出一种基于改进Faster R-CNN的牛脸检测方法。使用Inception v2替换ZF网络作为Faster R-CNN的基础网络，模型精度得到显著提升；针对多牛检测场景对NMS（Non-Maximum Suppression）进行相应优化，使模型的召回率得到显著提升。通过和其他目标检测模型对比实验，本文的改进模型在精确率和召回率上均优于其他模型。     

Distributed two‐stage state estimation with event‐triggered strategy for multirate sensor networks

This paper investigates the state estimation issue for a class of wireless sensor networks (WSNs) with the consideration of limited energy resources. First, a multirate estimation model is established, and then, a new event‐triggered two‐stage information fusion algorithm is developed based on the optimal fusion criterion weighted by matrices. Compared with the existing methods, the presented fusion algorithm can significantly reduce the communication cost in WSNs and save energy resources of sensors efficiently. Furthermore, by presetting a desired containment probability over the interval [0,1] with the developed event‐triggered mechanism, one can obtain a suitable compromise between the communication cost and the estimation accuracy. Finally, a numerical simulation for the WSN tracking system is given to demonstrate the effectiveness of the proposed method.     

采用信息增益率的混合入侵检测模型设计

针对现有混合入侵检测模型仅定性选取特征而导致检测精度较低的问题，同时为了充分结合误用检测模型和异常检测模型的优势，提出一种采用信息增益率的混合入侵检测模型.首先，利用信息增益率定量地选择特征子集，最大程度地保留样本信息；其次，采用余弦时变粒子群算法确定支持向量机参数构建误用检测模型，使其更好地平衡粒子在全局和局部的搜索能力，然后，选取灰狼算法确定单类支持向量机参数构建异常检测模型，以此来提高对最优参数的搜索效率和精细程度，综合提高混合入侵检测模型对攻击的检测效果；最后，通过两种数据集进行仿真实验，验证了所提混合入侵检测模型具有较好的检测性能.     

结合MNF变换和Canny算子的遥感影像变化检测

针对大面积区域的多时相遥感影像变化检测的需求，提出了一种基于最小噪声分离（MNF）的Canny边缘检测提取影像变化信息的检测方法。对多时相影像采用多种变换组合成具有多维波段信息的影像，采用最小噪声分离法分离噪声并得到单波段差异图，通过Canny边缘检测法计算梯度幅值，采用高低双阈值法细化边缘，从而提取差异图变化边缘，有效突出了变化信息。以1995年和2003年加扎勒河的两期遥感影像为例，利用两时相影像进行土地覆被变化检测。实验结果表明，该方法适用于监测大面积区域内地物的突变情况。在数据基础上进行最小噪声分离可以有效解决传统Canny边缘检测提取边缘时造成的伪边缘现象，同时采用高低双阈值法有效去除伪边缘点，从而获得更加精确、直观的变化检测效果，在自然地理变化监测、地理国情灾害监测等有很好的应用价值。     

Improved CCM for variable causality detection in complex systems

Convergent cross-mapping (CCM), has been largely implemented for variable causality detection in complex systems like chemical process. However, this method is susceptible to problems regarding parameter selection and threshold determination. The synchronization phenomenon and the Moran effect, which are two interference terms in causality detection, must also be addressed. Therefore, an improved CCM is proposed to overcome these limitations in this paper. In the improved CCM, the optimal embedding dimension is selected based on the pseudo-nearest-neighbor theory. Also, Monte Carlo simulation is adopted to evaluate the convergence threshold. Next, by using the defined time delay detection function, the synchronization phenomenon and the Moran effect are identified to reduce the interference terms and further improve the accuracy. Finally, the improved CCM method is applied in a numerical example and a hydrocracking process to demonstrate its feasibility and superior performance than other methods.     

Computer aided automated detection and classification of brain tumors using CANFIS classification method

The development of abnormal cells in human brain leads to the formation of tumors. This article proposes an efficient approach for brain tumor detection and segmentation using image fusion and co-active adaptive neuro fuzzy inference system (CANFIS) classification method. The brain MRI images are fused and the dual tree complex wavelet transform is applied on the fused image. Then, the statistical features, local ternary pattern features and gray level co-occurrence matrix features. These extracted features are classified using CANFIS classification approach for the classification of source brain MRI image into either normal or abnormal. Further, morphological operations are applied on the abnormal brain MRI image for segmenting the tumor regions. The proposed methodology is evaluated with respect to the performance metrics sensitivity, specificity, positive predictive value, negative predictive value, tumor segmentation accuracy with detection rate. The proposed image fusion based brain tumor detection and classification methodology stated in this article achieves 96.5% of average sensitivity, 97.7% of average specificity, 87.6% of positive predictive value, 96.6% of negative predictive value, and 98.8% of average accuracy.     

一种基于压缩感知的运动目标检测技术

运动目标检测是计算机视觉、图像处理等相关领域的研究热点，其核心就是对视频图像中的每一帧图像进行相应的研究和处理。本文主要研究思路是从压缩感知技术采样信号的角度出发，将每一帧的二维图像压缩采样成具有少量信息的一维信号，再通过信号重构用少量数据量将图像重构出来，最后通过目标检测技术对每一帧的图像进行运动目标提取。仿真实验表明该方法是可行和有效的，同时可以大大减少目标检测中所记录的数据量，解决海量数据的存储与传输问题。     

基于边图的线性流重叠社区发现算法

重叠网络的社区发现是复杂网络研究中的重要问题。为了提高网络中重叠社区发现的时间效率，提出一种基于边图的线性流重叠社区发现算法LBSA。算法首先对于边图网络中的边进行随机的依次处理，完成节点的初步社区划分，再将其中重叠小社区合并到相似度最大的其他大社区中得到最终的社区。通过以上步骤，算法能够以接近线性的时间复杂度得到网络的重叠结构。从最终的实验结果来看，与其他算法相比，该算法能够在更短的时间有质量地发现网络中的重叠社区。