构建“多态融合、互利共生”的乡村新型人地关系——以宁夏稻渔空间为例

在我国全面建设社会主义现代化的进程中,中国农村传统的人地关系正在转变。主要的变化是农民从粘着于土地,土地应用的单一性,变成农民与土地逐渐有了距离,土地应用立体化、多元化。宁夏“稻渔空间”乡村生态产业观光园,在农业发展现代化进程中,构建了稻田画空间艺术形态、稻作农耕生态、复合产业业态和城乡文化融合生态等“多态融合、互利共生”的发展模式,初步实现了农业高质高效、保持生态平衡,助力农民市民化,但存在建设用地和耕地的平衡、企业与农民收益平衡、产业和生态平衡等问题,需进一步探索和完善。

State Estimation Method for GNSS/INS/Visual Multi-sensor Fusion Based on Factor Graph Optimization for Unmanned System

With the development of unmanned driving technology,intelligent robots and drones,high-precision localization,navigation and state estimation technologies have also made great progress.Traditional global navigation satellite system/inertial navigation system(GNSS/INS)integrated navigation systems can provide high-precision navigation information continuously.However,when this system is applied to indoor or GNSS-denied environments,such as outdoor substations with strong electromagnetic interference and complex dense spaces,it is often unable to obtain high-precision GNSS positioning data.The positioning and orientation errors will diverge and accumulate rapidly,which cannot meet the high-precision localization requirements in large-scale and long-distance navigation scenarios.This paper proposes a method of high-precision state estimation with fusion of GNSS/INS/Vision using a nonlinear optimizer factor graph optimization as the basis for multi-source optimization.Through the collected experimental data and simulation results,this system shows good performance in the indoor environment and the environment with partial GNSS signal loss.

多模态影像融合在颅底肿瘤的诊断、治疗中的应用价值

目的探讨多模态影像融合在颅底肿瘤的诊断、治疗中的应用价值。方法 9例颅底肿瘤术前均行DynaCTA检查及MRI薄层(2 mm)增强扫描检查,将多组影像数据输入工作站,采用"双容积重建"技术进行脑血管及MRI的影像融合,通过静态及动态融合影像观察肿瘤与脑结构、血管及颅骨的毗邻关系,并对肿瘤的诊断、手术治疗及预防血管并发症进行分析。结果 9例均获得满意的影像融合、具有很好的空间一致性,在一张影像上可以清晰显示病变及其周围脑结构、血管及颅骨解剖关系,提高精准性诊断,并应用于指导治疗策略、设计手术划及预防并发症。9例均恢复满意出院。结论多模态影像融合对提高颅底肿瘤的诊断精准性、提高肿瘤全切除率、降低病死率和残疾率效果肯定,对血管损伤并发症治疗疗效肯定。

磁共振多模态成像及融合技术在脑胶质瘤术后放疗剂量优化中的应用

研究核磁共振多模态成像及融合技术在脑胶质瘤术后放疗剂量优化当中的效果。方法:此次研究中共选取了在我院接受脑胶质瘤手术的120例患者进行实验,实验均在患者知情的情况下进行,再分别对两组患者进行不同模式的扫描后,对结果进行了对比和分析。结果:通过研究结果,分析组患者的扫描图像体积明显大于研究组患者,从数据的对比上来看,P<0.05,因此,两组数据间的差异具有统计学价值。但在勾画靶区的剂量上,p>0.05,两组数据之间的差异并不具有统计学价值。结论:磁共振多模态成像及融合技术的应用能够在很大程度上提升对于靶区勾画的精确性,减小误差,从而使放疗中的计量更加精确,在临床中具有推广价值,值得借鉴。

基于知网句子相似度计算的主观题阅卷技术研究

提出了一种基于多态融合的句子相似度计算方法,用该方法能得到学生答案与标准答案之间的最佳相似度值,从而可大大提高主观题阅卷的准确率。

Test method of laser paint removal based on multi-modal feature fusion

Laser cleaning is a highly nonlinear physical process for solving poor single-modal(e.g., acoustic or vision)detection performance and low inter-information utilization. In this study, a multi-modal feature fusion network model was constructed based on a laser paint removal experiment. The alignment of heterogeneous data under different modals was solved by combining the piecewise aggregate approximation and gramian angular field. Moreover, the attention mechanism was introduced to optimize the dual-path network and dense connection network, enabling the sampling characteristics to be extracted and integrated. Consequently, the multi-modal discriminant detection of laser paint removal was realized. According to the experimental results, the verification accuracy of the constructed model on the experimental dataset was 99.17%, which is 5.77% higher than the optimal single-modal detection results of the laser paint removal. The feature extraction network was optimized by the attention mechanism, and the model accuracy was increased by 3.3%. Results verify the improved classification performance of the constructed multi-modal feature fusion model in detecting laser paint removal, the effective integration of acoustic data and visual image data, and the accurate detection of laser paint removal.

Adaptive multi-modal feature fusion for far and hard object detection

In order to solve difficult detection of far and hard objects due to the sparseness and insufficient semantic information of LiDAR point cloud,a 3D object detection network with multi-modal data adaptive fusion is proposed,which makes use of multi-neighborhood information of voxel and image information.Firstly,design an improved ResNet that maintains the structure information of far and hard objects in low-resolution feature maps,which is more suitable for detection task.Meanwhile,semantema of each image feature map is enhanced by semantic information from all subsequent feature maps.Secondly,extract multi-neighborhood context information with different receptive field sizes to make up for the defect of sparseness of point cloud which improves the ability of voxel features to represent the spatial structure and semantic information of objects.Finally,propose a multi-modal feature adaptive fusion strategy which uses learnable weights to express the contribution of different modal features to the detection task,and voxel attention further enhances the fused feature expression of effective target objects.The experimental results on the KITTI benchmark show that this method outperforms VoxelNet with remarkable margins,i.e.increasing the AP by 8.78%and 5.49%on medium and hard difficulty levels.Meanwhile,our method achieves greater detection performance compared with many mainstream multi-modal methods,i.e.outperforming the AP by 1%compared with that of MVX-Net on medium and hard difficulty levels.

The two-factor model of evaluating mining rights of coal resources based on options

MRCR could be regarded as a multi-stage compounding real option,based on option theory,assuming the convenience yield of coal reserves to be constant,built a one-factor model of valuating MRCR with the stochastic value of coal reserves.On the basis of our one-factor model,set up a two-factor model of evaluating MRCR assuming the convenience yield follows the mean-reverting process.When applied to valuate the MRCR of a coalmine,this model gives higher values than the one-factor model and the NPV.This is because the increase of convenience yield can improve the executive oppor- tunity of MRCR.

Applications of state estimation in multi-sensor information fusion for the monitoring of open pit mine slope deformation

The traditional open pit mine slope deformation monitoring system can not use the monitoring information coming from many monitoring points at the same time, can only using the monitoring data coming from a key monitoring point,and that is to say it can only handle one-dimensional time series.Given this shortage in the monitoring, the multi-sensor information fusion in the state estimation techniques would be intro- duced to the slope deformation monitoring system,and by the dynamic characteristics of deformation slope,the open pit slope would be regarded as a dynamic goal,the condi- tion monitoring of which would be regarded as a dynamic target tracking.Distributed In- formation fusion technology with feedback was used to process the monitoring data and on this basis Klman filtering algorithms was introduced,and the simulation examples was used to prove its effectivenes.

Smart Human Computer Interface with EMG and Vision Based on Multi-modal Information Fusion

A smart Human Interface （HCI） replacing conventional mouse interface is proposed. The interface is able to control and command action with only hand. Four finger motions （left click, right dick, hold, drag） are used to command the interface. Also the authors materialiae cursor movement control using image processing The measure what they use for inference is entropy of Electromyogram （EMG） signal, Gaussian modeling and likelihood estimation. In image processing for cursor control, they use color recognition to get the center point of finger tip from marker, and map the point onto cursor. Accuracy of finger movement inference is over 95% and cursor control works naturally without delay. They materlalize whole system to check its performance and utility.

Multimodality image registration and fusion using neural network

Multimodality image registration and fusion are essential steps in building 3-D models from remotesensing data. We present in this paper a neural network technique for the registration and fusion of multimodali-ty remote sensing data for the reconstruction of 3-D models of terrain regions. A FeedForward neural network isused to fuse the intensity data sets with the spatial data set after learning its geometry. Results on real data arepresented. Human performance evaluation is assessed on several perceptual tests in order to evaluate the fusionresults.

Carbon Emission Evaluation in Jinan Western New District based on Multi-source Data Fusion

Carbon emissions caused by human activities are closely related to the process of urbanization,and urban land utilization,function vitality and traffic systems are three important factors that may influence the emission levels.For clarifying the space structure of a low-carbon eco-city,and combining the concept of"Combining Assessment with Construction"to track and contrast the construction of the low-carbon eco-city,this research selects quantifiable low-carbon eco-city spatial characteristics as indicators,and evaluates and analyzes the potential carbon emissions.Taking the Jinan Western New District as an example,diversity of construction land,travel carbon emission potential,and density and accessibility of adjacent road networks in the overall urban planning were measured.After the completion of the new urban area,the evaluation mainly reflected certain factors,such as the mixed degree of urban functions,the density of urban functions,the walking distance to bus stops and the density and number of bus stops.Dividing the levels and adding equal weights after index normalization,the carbon emission potential is evaluated at the two levels of the overall and fragmented areas.The results show that:(1)The low-carbon emission potential areas in the planning scheme basically reached the planned goals.(2)There is inconsistency between districts and indicators in the planning scheme.The diversity of construction land and the accessibility of the adjacent road network are relatively small;however,there is a large difference between the travel carbon emission potential and the road network accessibility.(3)Carbon emission potential after completion did not reach the planned expectation,and the low-carbon emission potential plots were concentrated in the Changqing Old City Area and Central Area of Dangjia Town Area.(4)The carbon emission indicators varied greatly in different areas,and there were serious imbalances in the density of public transportation lines and the mixed degree of urban functions.