Multi-sensor Hybrid Fusion Algorithm Based on Adaptive Square-root Cubature Kalman Filter

In the normal operation condition, a conventional square-root cubature Kalman filter （SRCKF） gives sufficiently good estimation results. However, if the measurements are not reliable, the SRCKF may give inaccurate results and diverges by time. This study introduces an adaptive SRCKF algorithm with the filter gain correction for the case of measurement malfunctions. By proposing a switching criterion, an optimal filter is selected from the adaptive and conventional SRCKF according to the measurement quality. A subsystem soft fault detection algorithm is built with the filter residual. Utilizing a clear subsystem fault coefficient, the faulty subsystem is isolated as a result of the system reconstruction. In order to improve the performance of the multi-sensor system, a hybrid fusion algorithm is presented based on the adaptive SRCKF. The state and error covariance matrix are also predicted by the priori fusion estimates, and are updated by the predicted and estimated information of subsystems. The proposed algorithms were applied to the vessel dynamic positioning system simulation. They were compared with normal SRCKF and local estimation weighted fusion algorithm. The simulation results show that the presented adaptive SRCKF improves the robustness of subsystem filtering, and the hybrid fusion algorithm has the better performance. The simulation verifies the effectiveness of the proposed algorithms.

An Improved Medical Image Fusion Algorithm for Anatomical and Functional Medical Images

In recent years,many medical image fusion methods had been exploited to derive useful information from multimodality medical image data,but,not an appropriate fusion algorithm for anatomical and functional medical images.In this paper,the traditional method of wavelet fusion is improved and a new fusion algorithm of anatomical and functional medical images,in which high-frequency and low-frequency coefficients are studied respectively.When choosing high-frequency coefficients,the global gradient of each sub-image is calculated to realize adaptive fusion,so that the fused image can reserve the functional information;while choosing the low coefficients is based on the analysis of the neighborbood region energy,so that the fused image can reserve the anatomical image's edge and texture feature.Experimental results and the quality evaluation parameters show that the improved fusion algorithm can enhance the edge and texture feature and retain the function information and anatomical information effectively.

A new PQ disturbances identification method based on combining neural network with least square weighted fusion algorithm

A new method for power quality (PQ) disturbances identification is brought forward based on combining a neural network with least square (LS) weighted fusion algorithm. The characteristic components of PQ disturbances are distilled through an improved phase-located loop (PLL) system at first, and then five child BP ANNs with different structures are trained and adopted to identify the PQ disturbances respectively. The combining neural network fuses the identification results of these child ANNs with LS weighted fusion algorithm, and identifies PQ disturbances with the fused result finally. Compared with a single neural network, the combining one with LS weighted fusion algorithm can identify the PQ disturbances correctly when noise is strong. However, a single neural network may fail in this case. Furthermore, the combining neural network is more reliable than a single neural network. The simulation results prove the conclusions above.

Analysis and Evaluation of IKONOS Image Fusion Algorithm Based on Land Cover Classification

Different fusion algorithm has its own advantages and limitations,so it is very difficult to simply evaluate the good points and bad points of the fusion algorithm. Whether an algorithm was selected to fuse object images was also depended upon the sensor types and special research purposes. Firstly,five fusion methods,i. e. IHS,Brovey,PCA,SFIM and Gram-Schmidt,were briefly described in the paper. And then visual judgment and quantitative statistical parameters were used to assess the five algorithms. Finally,in order to determine which one is the best suitable fusion method for land cover classification of IKONOS image,the maximum likelihood classification( MLC) was applied using the above five fusion images. The results showed that the fusion effect of SFIM transform and Gram-Schmidt transform were better than the other three image fusion methods in spatial details improvement and spectral information fidelity,and Gram-Schmidt technique was superior to SFIM transform in the aspect of expressing image details. The classification accuracy of the fused image using Gram-Schmidt and SFIM algorithms was higher than that of the other three image fusion methods,and the overall accuracy was greater than 98%. The IHS-fused image classification accuracy was the lowest,the overall accuracy and kappa coefficient were 83. 14% and 0. 76,respectively. Thus the IKONOS fusion images obtained by the Gram-Schmidt and SFIM were better for improving the land cover classification accuracy.

Anti-swarm UAV radar system based on detection data fusion

There is a growing body of research on the swarm unmanned aerial vehicle(UAV)in recent years,which has the characteristics of small,low speed,and low height as radar target.To confront the swarm UAV,the design of anti-UAV radar system based on multiple input multiple output(MIMO)is put forward,which can elevate the performance of resolution,angle accuracy,high data rate,and tracking flexibility for swarm UAV detection.Target resolution and detection are the core problem in detecting the swarm UAV.The distinct advantage of MIMO system in angular accuracy measurement is demonstrated by comparing MIMO radar with phased array radar.Since MIMO radar has better performance in resolution,swarm UAV detection still has difficulty in target detection.This paper proposes a multi-mode data fusion algorithm based on deep neural networks to improve the detection effect.Subsequently,signal processing and data processing based on the detection fusion algorithm above are designed,forming a high resolution detection loop.Several simulations are designed to illustrate the feasibility of the designed system and the proposed algorithm.

A novel image fusion algorithm based on bandelet transform

A novel image fusion algorithm based on bandelet transform is proposed. Bandelet transform can take advantage of the geometrical regularity of image structure and represent sharp image transitions such as edges efficiently in image fusion. For reconstructing the fused image, the maximum rule is used to select source images＇ geometric flow and bandelet coefficients. Experimental results indicate that the bandelet-based fusion algorithm represents the edge and detailed information well and outperforms the wavelet-based and Laplacian pyramid-based fusion algorithms, especially when the abundant texture and edges are contained in the source images.

Adaptive Multisensor Tracking Fusion Algorithm for Air－borne Distributed Passive Sensor Network

Single passive sensor tracking algorithms have four disadvantages: bad stability, longdynamic time, big bias and sensitive to initial conditions. So the corresponding fusion algorithm results in bad performance. A new error analysis method for two passive sensor tracking system is presented and the error equations are deduced in detail. Based on the equations, we carry out theoretical computation and Monte Carlo computer simulation. The results show the correctness of our error computation equations. With the error equations, we present multiple 'two station'fusion algorithm using adaptive pseudo measurement equations. This greatly enhances the tracking performance and makes the algorithm convergent very fast and not sensitive to initial conditions.Simulation results prove the correctness of our new algorithm.

Prediction and fusion algorithm for meat moisture content measurement based on loss-on-drying method

The loss-on-drying method has been widely used as a standard approach for measuring the moisture content of high-moisture materials such as solid and semi-solid foods.Loss-on-drying method provides reliable results,whilst usually labor-intensive and time-consuming.This paper presents a novel algorithm for predicting the moisture content of meats based on the loss-on drying method.The proposed approach developed a drying kinetics model of meats based on Fick’s Second Law and designed a prediction algorithm for meat moisture content using the least-squares method.The predicted results were compared with the official method recommended by the Association of Official Analytical Chemists(AOAC).When the moisture content of meat samples(beef and pork)was varied from 69.46%to 74.21%,the relative error of the meat moisture content(MMC)calculated by the proposed algorithm was 0.0017-0.0117,the absolute errors were less than 1%.The testing time was about 40.18%-56.87%less than the standard detection procedure.

Exploring on Hierarchical Kalman Filtering Fusion Accuracy

Aim To analyze the traditional hierarchical Kalman filtering fusion algorithm theoretically and point out that the traditional Kalman filtering fusion algorithm is complex and can not improve the tracking precision well, even it is impractical, and to propose the weighting average fusion algorithm. Methods The theoretical analysis and Monte Carlo simulation methods were ed to compare the traditional fusion algorithm with the new one,and the comparison of the root mean square error statistics values of the two algorithms was made. Results The hierarchical fusion algorithm is not better than the weighting average fusion and feedback weighting average algorithm The weighting filtering fusion algorithm is simple in principle, less in data, faster in processing and better in tolerance.Conclusion The weighting hierarchical fusion algorithm is suitable for the defective sensors.The feedback of the fusion result to the single sersor can enhance the single sensorr's precision. especially once one sensor has great deviation and low accuracy or has some deviation of sample period and is asynchronous to other sensors.

Optimizing slope safety factor prediction via stacking using sparrow search algorithm for multi-layer machine learning regression models

The safety factor is a crucial quantitative index for evaluating slope stability.However,the traditional calculation methods suffer from unreasonable assumptions,complex soil composition,and inadequate consideration of the influencing factors,leading to large errors in their calculations.Therefore,a stacking ensemble learning model(stacking-SSAOP)based on multi-layer regression algorithm fusion and optimized by the sparrow search algorithm is proposed for predicting the slope safety factor.In this method,the density,cohesion,friction angle,slope angle,slope height,and pore pressure ratio are selected as characteristic parameters from the 210 sets of established slope sample data.Random Forest,Extra Trees,AdaBoost,Bagging,and Support Vector regression are used as the base model(inner loop)to construct the first-level regression algorithm layer,and XGBoost is used as the meta-model(outer loop)to construct the second-level regression algorithm layer and complete the construction of the stacked learning model for improving the model prediction accuracy.The sparrow search algorithm is used to optimize the hyperparameters of the above six regression models and correct the over-and underfitting problems of the single regression model to further improve the prediction accuracy.The mean square error(MSE)of the predicted and true values and the fitting of the data are compared and analyzed.The MSE of the stacking-SSAOP model was found to be smaller than that of the single regression model(MSE=0.03917).Therefore,the former has a higher prediction accuracy and better data fitting.This study innovatively applies the sparrow search algorithm to predict the slope safety factor,showcasing its advantages over traditional methods.Additionally,our proposed stacking-SSAOP model integrates multiple regression algorithms to enhance prediction accuracy.This model not only refines the prediction accuracy of the slope safety factor but also offers a fresh approach to handling the intricate soil composition and other influencing factors,making it a precise and reliable method for slope stability evaluation.This research holds importance for the modernization and digitalization of slope safety assessments.

Chlorophyll-a Estimation in Tachibana Bay by Data Fusion of GOCI and MODIS Using Linear Combination Index Algorithm

This study discusses the fusion of chlorophyll-a (Chl.a) estimates around Tachibana Bay (Nagasaki Prefecture, Japan) obtained from MODIS and GOCI satellite data. First, the equation of GOCI LCI was theoretically calculated on the basis of the linear combination index (LCI) method proposed by Frouin et al. (2006). Next, assuming a linear relationship between them, the MODIS LCI and GOCI LCI methods were compared by using the Rayleigh reflectance product dataset of GOCI and MODIS, collected on July 8, July 25, and July 31, 2012. The results were found to be correlated significantly. GOCI Chl.a estimates of the finally proposed method favorably agreed with the in-situ Chl.a data in Tachibana Bay.

基于多模型融合的中长期径流集成预测方法

中长期水文预报是流域水资源规划与合理配置的重要依据。为提高中长期径流预测精度,提出了一种基于多模型融合的水库中长期径流集成预测方法。该方法将ARMA、BP、LSTM、RF和SVR等5个异质预测模型进行融合,同时采用超参数优化方法确定各模型的最优参数。将其用于青海省龙羊峡水库的中长期径流预报中,结果表明,通过Stacking融合算法建立的集成预测模型相较于单一模型,取得了更高的预测精度(R2值由0.71提升至0.82)。此方法可为提升流域中长期径流预测精度提供一定参考。

考虑风电不确定性的电气综合能源系统混合尺度调控

为改善电-气互联综合能源系统中风电出力不确定性和多能传输差异对调控过程的影响,提出了基于改进小波融合算法的混合尺度调控方法.首先采用区间数学的方法,对系统中风电功率不确定性进行表示并给出风电处理策略.其次,考虑到不同能源传输特性的差异,提出了改进的小波融合算法,即先对电力网络中传感器信号数据进行多个不同小波基的多尺度分解,再对天然气系统信号数据中使用相同小波基分解的信号在混合尺度上实施加权数据融合,进行不同小波基的逆变换后得到融合信号.最后基于所搭建仿真模型,对比分析了不同调控方法的调控效果.结果表明本文所提方法的调控结果优于DMPC(分布式模型预测控制)滚动优化调控结果,且在改善了系统运行经济性的同时也提高了系统稳定性.

改进RRT-Connect与DWA算法的巡检机器人路径规划研究

针对传统RRT-Connect算法在密集复杂环境中路径规划效率低、动态避障效果差等问题,提出一种改进RRT-Connect与DWA融合算法。该算法通过改进采样策略、动态步长优化和碰撞检测引导随机树生长;在随机树中采用贪心策略和角度约束优化路径。基于巡检机器人建立运动学模型,通过速度采样空间生成轨迹簇;建立模糊逻辑系统自适应调整DWA算法评价函数的权重系数,将全局最优路径点融入DWA算法中实现全局最优路径和实时避障。仿真结果表明,在油气站场密集复杂环境中,改进RRT-Connect算法较传统算法路径缩短约27.09%,平滑度提高约84.6%,碰撞距离提高约18.75%;改进融合算法路径减少约2.97%,平滑度提高约78.8%,碰撞距离提高约30.6%,验证了提出算法的有效性。

基于时空融合算法的水体叶绿素a反演研究

为了准确反演水体中叶绿素a浓度,以黄柏河东支流域为例,采用STNLFFM时空融合算法,对2017年GF-4和Sentinel-2反射率数据进行融合,以重构Sentinel-2影像的时间序列数据,并对应用算法前后获取的水质参数-光谱特征响应关系建立多元线性回归模型,比较模型对叶绿素a的预测效果以验证时空融合算法的可行性,利用重构后影像光谱特征与水质参数的响应关系建立人工神经网络模型,反演2017年黄柏河东支流域各水库水体叶绿素a浓度。结果表明:利用时空融合算法生成的影像接近真实影像,提高了多元线性回归模型预测叶绿素a的效果,R2从融合前0.659提高至融合后0.844,且基于时空融合算法获取的水质参数-光谱关系建立的人工神经网络模型模拟精度较好,R2和MRE达到0.925和9.461%,反演的叶绿素a浓度空间差异性明显。证明了时空融合算法在水质参数反演过程中具有较好的应用前景。

基于改进YOLOv网络的外观检测研究

外观检测涉及对图像或视频中的物体进行准确和高效的识别和定位,为了解决物体表面小尺寸目标检测的问题,研究通过优化YOLOv3网络模型,引入多尺度检测和深度可分离卷积技术来提高检测精度和模型效率,以增强对小尺寸目标的识别能力,再采用深度可分离卷积技术来减少计算量,并提高模型的训练效果;实验结果表明,研究模型在物体表面小尺寸检测方面取得显著提升;与其他金属表面损伤检测算法相比,优化后的YOLOv3实现了71.52%的检测精度,超越Faster R-CNN 6.83%;尽管Faster R-CNN在准确性方面优异但速度慢,SSD速度较快但不及YOLOv2;而YOLOv2虽速度快但精度稍低;相对于原始模型,研究算法的平均精度提升了7.77个百分点,达到了79.21%;虽然网络深度的提升稍增计算量,略有检测速率下降,但引入深度可分离卷积后,检测速度达到36.2帧/秒,仅较原模型稍低2.4帧/秒;研究可以优化算法,提高小尺寸目标检测的准确性和鲁棒性,推动其在计算机视觉领域的广泛应用。

改进的轻量级行人目标检测算法

针对行人目标数量密集、目标尺度小和目标周围背景光照强弱不一而导致的检测精度低的问题,提出一种基于特征融合的轻量化行人检测算法。以TinyYOLOv4为基础框架,首先,搭建新的主干特征提取网络(CSPDarknet53-S),在原主干网络的基础上加入新的特征提取模块(REM)来增强网络提取行人特征的能力。其次,改进特征融合结构,在主干网络提取高低层特征图后,先是在主干网络与特征融合网络间加入特征融合模块(RM-block)来增大感受野;然后引入浅层特征信息保留更多小目标特征,形成新的特征融合网络(IFFM)。最后,通过YOLO Head对融合来的特征图进行处理获得输出结果。实验结果表明,提出的算法在行人数据集(PASCAL VOC2007和VOC2012的person数据)上取得了较高的检测精度以及较好的检测效果。

肌电和足压信息融合的外骨骼步态识别

为解决基于单一信号识别步态相位不够精准的问题,开展了动态交互力激励下的人机协同行走的步态识别研究。设计了肌电和足压信息采集的多模态传感器检测硬件平台;分别对单一信号开展滤波降噪、特征提取与降维等预处理;将表征下肢生理信息的肌电信号与运动信息的足压信号相融合,构建了支持向量机-模糊C均值(support vector machine-fuzzy C-mean algorithm,SVM-FCM)多模信息融合的外骨骼助行步态识别算法;开展了人机协同助行实验,实验结果表明:信息融合后的人机步态相位平均识别率达到82.49%,优于使用单一信号的识别效果,验证了多模信息融合算法识别人机协同步态的有效性。本研究可用于下肢外骨骼机器人运动控制,为人机运动相融奠定基础。

站台门间隙异物自动检测系统设计与实现

[目的]站台门间隙异物检测环节对地铁运营安全有影响,故有必要研究一种新型的地铁站台门防夹检测系统,使未来的FAO(全自动运行)系统更加安全与高效。[方法]采用视频和激光雷达算法融合技术,提出了结合视频图片识别和雷达点云数据的双重判据AI检测策略,创新性地采用了PointNet算法架构来进行地铁站台门间隙异物的检测,实现摄像头视频辅助激光雷达工作模式。若被检测间隙出现异物,则报警和视频联动,第一时间捕捉报警现场视频。利用多维深度学习方法,降低误判概率。[结果及结论]在系统设计中,提出传感器交叉叠装分层安装方法,实现间隙异物冗余检测功能;通过交叉互检机制,有效提高了检测装置的冗余性和可靠性;使用2D传感器实现3D检测效果。所研制系统为地铁信号系统提供安全联锁信号,提供报警信息给综合监控系统,并推送手环报警信息给现场运行人员。使地铁站台门间隙异物检测更加准确可靠,为地铁的全自动运行提供安全保障。

基于改进A^(*)蚁群融合算法的路径规划研究

随着智能化技术的发展,无人车路径规划技术在未来无人战场上将发挥重要的作用。针对A^(*)算法易发生碰撞障碍物的问题,提出通过改进转弯机制进行避碰。针对路径较长和不够平滑的问题,提出一种改进A^(*)蚁群融合算法。仿真结果表明,使用改进A^(*)蚁群融合算法得到的路径长度和平滑度更优,简单地图中路径长度减少2.34%,总转弯角度减小5.62%;复杂地图中路径长度减少2.62%,总转弯角度减小26.3%。因此,该算法在保证无人车避障的基础上,有利于其快速完成相应任务。