基于JXTA的协同学习系统研究

随着计算机网络技术的迅速发展和计算机协同工作CSCW理论和技术研究的深入,计算机协同学习(Computer Supported Collaborative Learning)的思想逐渐被引入计算机网络教育的应用中.目前大多数的协同学习系统采用了C/S结构.提出的基于JXTA的协同学习系统采用了P2P(Peer-to-Peer)结构,满足了协同学习的一般需求,具有安全性、可伸缩性和可扩展性.     

基于超像元词包特征和主动学习的高分遥感影像变化检测

为解决高分辨率遥感影像变化检测中存在底层特征缺乏语义信息、像元级的检测结果存在“椒盐”现象以及监督分类中样本标注自动化程度较低,本文提出一种基于超像元词包特征和主动学习的变化检测方法。首先采用熵率分割算法获取叠加影像的超像元对象;其次提取两期影像像元点对间的邻近相关影像特征（相关度、斜率和截距）和顾及邻域的纹理变化强度特征（均值、方差、同质性和相异性）,经线性组合作为像元点对的底层特征;然后基于像元点对底层特征利用BOW模型构建超像元词包特征,并采用一种改进标注策略的主动学习方法从无标记样本池中优选信息量较大的样本,且自动标注样本类别;最后训练分类器模型完成变化检测。通过选用2组不同地区的GF-2影像和Worldview-Ⅱ影像作为数据源进行实验,实验结果中2组数据集的F1分数分别为0.8714、0.8554,正确率分别为0.9148、0.9022,漏检率分别为0.1681、0.1868,误检率分别为0.0852、0.0978。结果表明,该法能有效识别变化区域、提高变化检测精度。此外,传统主动学习方法与改进标注策略的主动学习方法的学习曲线对比显示,改进的标注策略可在较低精度损失下,有效提高样本标注自动化程度。     

滑坡变形预测灰色神经网络耦合模型的构建及适用性分析

结合灰色模型和神经网络的数据处理特点,提出串联、并联和混联式3种结构的灰色神经网络滑坡变形预测模型。串联式将滑坡变形位移时序分解为趋势项和随机项,采用灰色模型提取滑坡位移时序趋势,利用神经网络逼近随机波动;并联式以灰色模型和神经网络分别对滑坡预测,采用智能非线性组合,按照预测目标精度动态调整权重,从而获取最终组合预测结果;混联式通过增加灰白化层及灰模型群,对神经网络拓扑结构进行优化,达到弱化滑坡原始监测数据随机性、提高预测模型稳健性的目的。将3种模型应用于古树屋滑坡变形预测,并对其适用性进行讨论。结果表明,3种结构的灰色神经网络耦合模型均提高了预测精度,适用于复杂状况下滑坡体的变形预测。     

Climatology of Shear Line and Related Rainstorm over the Southern Yangtze River Valley Based on an Improved Intelligent Identification Method

Based on four reanalysis datasets including CMA-RA, ERA5, ERA-Interim, and FNL, this paper proposes an improved intelligent method for shear line identification by introducing a second-order zonal-wind shear. Climatic characteristics of shear lines and related rainstorms over the Southern Yangtze River Valley(SYRV) during the summers(June-August) from 2008 to 2018 are then analyzed by using two types of unsupervised machine learning algorithm,namely the t-distributed stochastic neighbor embeddin...     

基于迁移学习方法的山东冷云冰晶特征分布研究

为分析冷云中冰晶的分布特征,揭示冰晶增长演变机制,根据冰晶形状和尺度特征分为8类并进行标注,同时标注1类隔断栏进行数据质量控制,将9类标签图像整合并建立图像集,利用迁移学习VGGNet16方法进行识别训练,经训练模型分类准确率达98%。将模型应用到秋季冷云冰晶特征研究中,选取3次积层混合云和3次层状云降水过程,分析冰晶形状在不同温度区间的占比及冰晶谱变化特征,结果表明,温度通过影响冰晶基面与棱面的比值来决定冰晶初始形状分布,相同温度区间积层混合云内球状冰晶和线型冰晶占比高于层状云,低于-12℃后各类冰晶占比相对固定;积层混合云内线型冰晶直径集中在300~800 μm,冰晶谱呈多峰分布,聚合体直径大于600 μm,冰晶谱首尾两端浓度相当,球状冰晶直径集中在120～300 μm,冰晶谱呈单调下降趋势。     

基于注意力机制与自适应时序分解的气温预报模型

针对传统方法在捕捉气象序列长期依赖关系及泛化性能上的不足,提出了一种基于稀疏注意力与自适应时序分解的气温预报模型（ATFSAS）。该模型整体采用编码器 解码器架构,结合稀疏注意力机制以有效捕捉气象观测数据间的长期依赖性。为减少编码过程中造成的冗余,提出了一种信息蒸馏方法。通过结合多层解码器与自适应时序分解单元,逐步细化预报信号中的周期性和趋势性分量,实现了较为精准的气温预报。基于德国耶拿气象数据集,进行24 h精细化气温预报,其平均绝对误差为1.7108℃。基于中国地面气候资料日值数据集,进行中短期日平均气温预报和多地区单日平均气温预报,相比传统模型LSTM,ATFSAS模型预报结果的平均绝对误差分别提升了35.56%和23.66%。     

基于机器学习的格点气温预报订正方法

使用2017年9月至2021年3月国家级业务化运行的智能网格实况分析产品和欧洲中期天气预报中心全球模式(EC)产品,根据湖北省的地理分布特征构建6个分区,采用基于LightGBM机器学习算法建立的气温预报方法,生成湖北省0.05°×0.05°格点气温预报产品。利用2021年4—9月的预报产品和格点实况资料进行检验,结果表明:基于机器学习的气温预报方法(MLT)取得了较好的预报效果,其在0～72 h时效内优于中央气象台下发的气温精细化指导预报(SCMOC)和EC产品;MLT在山区的误差较平原大,但山区的订正幅度大于平原,日最高气温的订正幅度大于日最低气温的订正幅度;4—9月MLT、SCMOC、EC产品的平均绝对误差(MAE)日变化都呈现了白天偏高、夜间偏低、午后凸起的单峰特征,MLT的MAE值较SCMOC和EC产品的更低,并且在转折性天气中仍具有优势;站点检验与格点检验结论一致,基于格点建模的气温预报产品对站点预报同样得到了订正。机器学习在格点气温的模式订正方面可以作为一个行之有效的手段。     

地质统计学变差函数人机对话拟合

变差函数的研究在地质统计学中具有十分重要作用，本文运用界面图形图像处理强的Ｃ￣（＋＋）语言实现了界面友好汉化人机对话变差函数的拟合，主要包括管理菜单的生成，实验变差值的求解，变差图的图形显示，标准函数模型的计算及变差函数人机对话求解等部分。最后对比一下回归分析与人机对话拟合结果。     

Comparing Human and Neural Network Learning of Climate Categories

This study compares how humans and neural networks classify climate types. Human subjects were asked to classify climates from monthly temperature and precipitation patterns. To model their learning process, the same data were used to produce input vectors that trained a pattern associator neural network. Both human subjects and the neural network classified climates accurately after 10 rounds of supervised learning. The neural network successfully modeled the rate of human learning and the ability to learn specific climate categories. Moreover, the neural network weights used to classify climates correspond to distinct visual characteristics in temperature and precipitation. These results suggest that neural networks can model the formation of visual categories.     

An interactive system to assist mineral identification in ore microscopy

An interactive computer system has been developed to assist the mineral identification in ore microscopy. The reference file of the system consists of optical, mechanical, and chemical properties of about 130 ore minerals. The properties are name, chemical formula, color, bireflectance, anisotropism, internal reflection, reflectance at wavelengths of 470, 546, 589, and 650 nm, and polishing hardness and micro-indentation hardness. All the properties except reflectance and microindentation hardness are qualitative or semi-qualitative. Most of the properties are given as characters relative to the more common minerals. This implies that most of the identification processes advance on the basis of the comparison between a subject mineral and coexisting minerals. For this reason, the system asks a user at first to input already identified mineral names. This is quite different from the mineral identification procedures used in petrographic microscopy. To reduce the number of possible minerals, the system presents a series of questions to a user, and the user selects any of the prepared answers according to his observation. The user can also choose any desired question independently of the sequence. The user is expected to be able to recognize some common minerals, such as pyrite, chalcopyrite, galena, and hematite, without the assistance of the system.