分部加权的行道树检测网络构建     

沈雨  仇宇轩  于正浩 《测绘通报》2020,(2):77

基于深度学习目标检测框架，提出了一种端到端的训练网络，用于行道树的自动检测。由于行道树之间的遮挡问题，现有的通用物体检测框架无法直接应用于此任务，为此本文提出了一种树形分部加权模块，以减少严重遮挡造成的错误检测。然后对提出的神经网络进行训练和评估。结果显示，本文所建立的分部加权树木检测网络能够在遮挡条件下，有效地检测出街景图像中的行道树，该方法在各种条件下均具有较高的精度和良好的稳健性。  相似文献   

改进注意力机制的遥感地貌识别算法     

张朕通  单玉刚  袁杰 《测绘通报》2020,(10):93

对遥感地貌进行识别，近年来一直是遥感图像应用领域的研究热点。使用深度学习算法识别遥感影像具有比传统方法更高的准确率和稳健性。针对遥感影像中目标复杂度高、特征信息多等问题，本文提出了一种基于改进注意力机制的遥感图像识别算法，即将并联注意力机制（CS）和神经网络模型相结合，借助弱监督学习来辅助训练。同时采用双损失函数来缓解数据过拟合问题。试验结果表明，本文模型总精度为98.35%，Kappa系数达0.95，优于其他深度学习算法，能有效地识别出自然地貌。  相似文献   

Seismic reflections from the Moho - the effect of isostasy     

M. R. Warner 《Geophysical Journal International》1987,88(2):425-435

  相似文献   

Statistical Modelling of Lower-Crustal Reflections     

B. A. Raynaud 《Geophysical Journal International》1988,95(1):111-121

  相似文献   

改良的单台Z／H法     

陈伯舫 《华南地震》1995,15(2):16-21

改良的单台Ｚ／Ｈ法的原理是增加了次强项Ｐ＾ｍｍ＋３，但仍保留了原Ｚ／Ｈ法的优点：方法简单，只需单台资料，不需作球谐分析。  相似文献   

关联向量机及其在入侵检测中的应用探讨     

王帅伟  麦永浩  杨辉华  王勇 《成都信息工程学院学报》2005,20(3):270-274

介绍一种稀疏的贝叶斯学习算法——关联向量机(RVM)，它在再生核希尔伯特空间中学习，利用贝叶斯方法推理，推广能力好，与支持向量机相比不仅解更为稀疏而且不需要调整超参数。应用RVM的对小样本的良好分类能力，提出一种基于RVM的入侵检测原型系统。  相似文献   

五极纵轴测深法在郑州地区热水资源勘探中的应用     

王建庄 《河南国土资源》1995,(3)

郑州市区的地下热水来自增温地层，在使用电法勘探确定热水层位和埋深时，用五极纵轴测深法与对称四极测深法相结合，取得了良好的地质效果。  相似文献   

RecNet: a deep neural network for personalized POI recommendation in location-based social networks     

Ruifeng Ding 《International journal of geographical information science》2018,32(8):1631-1648

How to exploit various features of users and points of interest (POIs) for accurate POI recommendation is important in location-based social networks (LBSNs). In this paper, a novel POI recommendation framework, named RecNet, is proposed, which is developed based on a deep neural network (DNN) to incorporate various features in LBSNs and learn their joint influence on user behavior. More specifically, co-visiting, geographical and categorical influences in LBSNs are exploited to alleviate the data sparsity issue in POI recommendation and are converted to feature vector representations of POIs and users via feature embedding. Moreover, the embedded POIs and users are fed into a DNN pairwise to adaptively learn high-order interactions between features. Our method is evaluated on two publicly available LBSNs datasets and experimental results show that RecNet outperforms state-of-the-art algorithms for POI recommendation.  相似文献   

Mining transition rules of cellular automata for simulating urban expansion by using the deep learning techniques   总被引：3，自引：0，他引：3  

Jialv He  Yao Yao  Ye Hong  Zhang Jinbao 《International journal of geographical information science》2018,32(10):2076-2097

Along with the gradually accelerated urbanization process, simulating and predicting the future pattern of the city is of great importance to the prediction and prevention of some environmental, economic and urban issues. Previous studies have generally integrated traditional machine learning with cellular automaton (CA) models to simulate urban development. Nevertheless, difficulties still exist in the process of obtaining more accurate results with CA models; such difficulties are mainly due to the insufficient consideration of neighborhood effects during urban transition rule mining. In this paper, we used an effective deep learning method, named convolution neural network for united mining (UMCNN), to solve the problem. UMCNN has substantial potential to get neighborhood information from its receptive field. Thus, a novel CA model coupled with UMCNN and Markov chain was designed to improve the performance of simulating urban expansion processes. Choosing the Pearl River Delta of China as the study area, we excavate the driving factors and the transformational relations revealed by the urban land-use patterns in 2000, 2005 and 2010 and further simulate the urban expansion status in 2020 and 2030. Additionally, three traditional machine-learning-based CA models (LR, ANN and RFA) are built to attest the practicality of the proposed model. In the comparison, the proposed method reaches the highest simulation accuracy and landscape index similarity. The predicted urban expansion results reveal that the economy will continue to be the primary factor in the study area from 2010 to 2030. The proposed model can serve as guidance in urban planning and government decision-making.  相似文献   

Values shift in response to social learning through deliberation about protected areas     

《Global Environmental Change》2023

Salient, long-term solutions to address global environmental change hinge on management strategies that are inclusive of local voices and that recognize the array of values held by surrounding communities. Group-based participatory processes that involve deliberation of multiple stakeholders with varying perspectives—particularly social learning—hold promise to advance inclusive conservation by identifying and creating a shared understanding of the landscape. However, few studies have empirically investigated how the value basis of stakeholder deliberation changes over time in relation to social learning. This study provided a novel platform for local stakeholders from Interior Alaska to deliberate on landscape change and associated management practices in ways that shifted their value orientations. In particular, we used a pre-test, post-test experimental design involving mixed methods to measure how different types of values changed as a result of social learning through an online discussion forum. We found evidence that social learning: 1) activated shared values that were previously hidden through building a relational understanding of others, and 2) shifted values that spanned three levels of psychological stability. As hypothesized, social values that represented expressed preferences for landscape change were most likely to shift in association with social learning. Conversely, shifts in individual values towards self-transcendence required learning to go beyond the discussion forum and be situated within the participants’ broader communities of practice. Overall, this longitudinal study highlights how social learning facilitated through deliberation presents opportunities to identify shared values and spark value shifts across stakeholder groups, thus incorporating diverse viewpoints into decision-making about global environmental change.  相似文献