一种改进的进化树构建算法

邻接法是最有效的距离建树法的一种,但邻接法的聚类过程总是选择距离最近的进行聚类,容易忽略一些更为合理的拓扑结构,这是邻接法准确性不够理想的一个重要原因。为了提高邻接法的准确性,本文结合最大似然法提出一种改进的进化树构建算法。该算法在邻接法基础上,结合最大似然法搜索最优的拓扑结构,通过模拟实验将改进算法与邻接法等进化树构建算法进行比较,实验结果表明,改进算法的准确性明显优于邻接法。     

两种方法对泰莱盆地河流水质评价的分析

采用加权欧式距离法和模糊综合评价法对泰莱盆地地表水体环境质量进行评价的结果表明,全区地表水以Ⅱ和Ⅲ类为主;东部河流水质稍差,牟汶河和柴汶河的上游水质超过Ⅳ类;西部的大汶河和汇河水质要好于东部地区河流,水质以Ⅱ类和Ⅲ类为主。加权欧式距离法在给出评价断面水质级别的同时给出评价断面对于某一水质标准的贴近度以及水质的变化趋势,评价结果显示的信息相对真实多元,在水质评价中的表现要优于模糊综合评价法。     

基于深度神经网络的高位滑坡范围预测

以贵州尖山营滑坡为工程背景,通过对深度学习的总结与分析,建立多层感知器模型以对该滑坡危险区范围进行非线性预测研究。通过对深度神经网络算法的优化,构建64-128-32-1四层多层感知器模型,并以滑坡最大高差、滑坡体积、滑源区坡度、坡脚坡度、地层倾角作为输入量,以滑坡最大水平运动距离作为输出量对该模型进行训练,实现影响因素与运动距离的非线性映射。根据对贵州省尖山营滑坡调查和研究,尖山营滑坡区域面积约648 700 m2,体积约1 200万 m3,属于特大型滑坡。依据最优模型对该滑坡进行滑距预测,滑坡平面直线距离1 769 m区域内为危险区域。     

Promoting the integration of technology in teaching: An analysis of the factors that increase the intention to use technologies among Italian teachers

Background: The rapid spread of COVID-19 forced many countries to adopt severe containment measures, transferring all didactic activities into virtual environments. However, the integration of technology in teaching may present difficulties, especially in some countries, such as Italy. Objectives: The present study analyzed how the two main factors of the Technology Acceptance Model (TAM), namely perceived usefulness and perceived ease of use, combined with online teaching self-efficacy, were associated with the intention to use technology to teach. We posited a moderated moderation model in which perceived usefulness represented the main predictor, with self-efficacy and perceived ease of use as moderators of intention to use technology to teach. Method: The model was tested through multiple regressions, using the PROCESS macro on SPSS 26 with a sample of 178 upper secondary school teachers in Italy. Results and conclusions: Regressions showed that each variable significantly predicted the intention to use technology. In addition, a moderation effect of self-efficacy on the perceived usefulness of using technology was found for medium and high-level of perceived ease of use of technology. Implications: The present study provides targeted implications for distance education policy and practice to promote its adoption (or the blended modality) in Italian upper schools.     

视觉测量中多光学靶点亮度自适应控制

提出了一种面向大视场高精度视觉测量的多红外目标靶点（红外LED）亮度自适应控制方法。以微控制器PIC16F873A和LED驱动芯片MAX6964作为核心器件,设计了可满足大空间范围内靶点亮度控制需求的多目标靶点控制驱动器。为了使LED在近距测量时的调节精度和远近距离测量时的发光亮度都能满足要求,根据MAX6964输出特点设计了PWM信号输出电路,并采用推挽电路驱动LED。实验证明,目标靶点在CCD相机上成像光斑稳定一致。     

Evaluating a color-based active basis model for object recognition

Wu and coworkers introduced an active basis model (ABM) for object recognition in 2010, in which the learning algorithm tends to sketch edges in textures. A grey-value local power spectrum was used to find a common template and deformable templates from a set of training images and to detect an object in new images by template matching. In this paper, we propose a color-based active basis model (color-based ABM for short), which incorporates color information. We adopt the framework of Wu et al. in the learning, detection, and classification of the color-based ABM. However, in order to improve the performance in object recognition, we modify the framework of Wu et al. by using different color-based features in both the learning and template matching algorithms. In this color-based ABM approach, two types of learning (i.e., supervised learning and unsupervised learning) are also explored. Moreover, the usefulness of the color-based ABM for practical object recognition in computer vision applications is demonstrated and its significant improvement in recognizing objects is reported.     

角点距离矩阵和同心圆划分的曲线描述与匹配

曲线匹配对于物体识别、目标跟踪、碎片拼接等有着重要的意义。针对曲线匹配的效率与鲁棒性问题,提出了一种基于角点距离矩阵和同心圆划分的曲线描述与匹配算法。该算法分为粗略匹配和精确匹配两个阶段。粗略匹配阶段首先采用角点距离矩阵来描述曲线;然后通过子矩阵的方法来匹配曲线。精确匹配阶段首先采用同心圆划分的方法描述曲线;然后通过两条曲线同心圆描述集的差异度度量函数来度量他们的相似性。算法不仅具有平移、旋转、缩放不变性,而且具有较强的鲁棒性,可用于遮挡物体的匹配以及基于轮廓的图形拼接。实验结果表明了该算法的有效性和可行性。     

非相似度保持投影

由主成分分析(PCA)可知任何一幅人脸图像都可以通过一组特征脸的线性加权来重构,PCA是最小均方误差意义下图像的最优表示,但是传统的PCA最终只通过比较加权系数的欧氏距离来进行识别,没有考虑残差。因此,提出非相似尺度的概念,将两个样本同时投影到相同向量上,在确定它们关系时既考虑投影系数,也考虑重构所产生的残差。两者的投影系数和残差相差越大,说明这两个样本越不相似。和保局投影(LPP)有所不同,非相似度保持投影算法不必预先设定近邻个数,它是利用非相似度的概念,创建非相似度散布矩阵,最终通过最大化目标函数获取最优子空间。在AR库和Feret库上的实验结果证明了该方法的有效性。     

基于像素差异的金属腐蚀区域分割仿真研究

研究基于图像的金属腐蚀区域分割问题,提高分割区域的准确性。针对传统基于金属本身与腐蚀颜色的区别,利用像素差异的变化进行腐蚀区域的分割,因当腐蚀颜色与金属的本体颜色相差不是很大,或者在边沿发生像素的混淆时,利用差异边缘像素相减的方法很难完整分割腐蚀区域的问题。为了解决上述问题,提出利用空间像素差异距离聚类的金属腐蚀区域图像分割算法。通过计算差异像素之间的差异距离概率,将差异像素特征进行严格划分,对划分后的结果进行排序计算,详细描述混淆边沿信息,对腐蚀区域进行完整分割。实验证明,改进方法能够对金属腐蚀造成的细微区域完整分割,取得了满意的效果,为金属腐蚀区检测提供了参考。     

基于叶片形态特征的葡萄品种自动识别

葡萄在全世界种植范围较广,葡萄品种识别对葡萄资源统计、新品种鉴定及遗传资源保护都有重要意义。以成熟叶片为基本材料,不变矩、面积、周长、主叶脉长度和叶柄长度等11维特征向量为基础数据,采用叶片特征选择、图像处理、特征值提取、建立分类模型等方法,运用国际葡萄与葡萄酒组织形态分类方法和改进的欧式距离等技术开发一个基于葡萄叶片数字图像的葡萄品种自动识别软件。共测试17种酿酒和3种野生葡萄,识别率达87%。该方法具有自动化、识别速度快、花费低、省时省力等特点,可应用于葡萄病虫害的识别、杂交新品种双亲的判定等。