We develop the classification part of a system that analyses transmitted light microscope images of dispersed kerogen preparation. The system automatically extracts kerogen pieces from the image and labels each piece as either inertinite or vitrinite. The image pre-processing analysis consists of background removal, identification of kerogen material, object segmentation, object extraction (individual images of pieces of kerogen) and feature calculation for each object. An expert palynologist was asked to label the objects into categories inertinite and vitrinite, which provided the ground truth for the classification experiment. Ten state-of-the-art classifiers and classifier ensembles were compared: Naïve Bayes, decision tree, nearest neighbour, the logistic classifier, multilayered perceptron (MLP), support vector machines (SVM), AdaBoost, Bagging, LogitBoost and Random Forest. The logistic classifier was singled out as the most accurate classifier, with an accuracy greater than 90. Using a 10 times 10-fold cross-validation provided within the Weka software, we found that the logistic classifier was significantly better than five classifiers (p<0.05) and indistinguishable from the other four classifiers. The initial set of 32 features was subsequently reduced to 6 features without compromising the classification accuracy. A further evaluation of the system alerted us to the possible sensitivity of the classification to the ground truth that might vary from one human expert to another. The analysis also revealed that the logistic classifier made most of the correct classifications with a high certainty. 相似文献
This article aims to study Web use and Web-based co-operation and collaboration in geographical and environmental education
at the primary and secondary level around the world. Recent trends and future opportunities and challenges are taken into
account. The theoretical part of the study considers Web use and different forms of Web-based co-operation. Web use and co-operation
in education are classified as co-operative learning, collaborative learning or communal learning. Web use in geographical
and environmental education is noted to be growing in significance. Web-based co-operation at any level of intensity is associated
with many opportunities and challenges. The empirical part of this study involves a survey of geographical and environmental
education researchers in various countries about their views of Web use in education. The results of this survey indicate
that the Web in general finds minimal use in geographical and environmental education. As access to the Web is limited and
only some pupils can use it, co-operation, particularly collaborative learning on the Web, is still rare in geographical and
environmental education. The most often used application is e-mail. Researchers recognise the potential of the Web to enhance
local, national and international co-operation, and to facilitate a better understanding of geographical and environmental
issues at the grass-root level. Web-based learning can also help to increase and deepen the pupils' cultural understanding.
Before that, however, problems in access, costs and teacher training must be solved.
This revised version was published online in August 2006 with corrections to the Cover Date. 相似文献
道路场景理解是自动驾驶领域中重要模块之一,它可以提供关于道路更丰富的信息,对于建立高精度地图和实时规划都具有重要作用。其中,语义分割可以为图像每个像素赋予类别信息,是自动驾驶场景理解中最常用的方法。但是,目前常用的语义分割算法在速度和精度上大都不能达到很好的平衡。本文在Mobile Net V2的基础上,提出了一种多层次特征融合的方法,使得网络可以在实时运行的同时保证精度满足实际应用的需求,并在Cityscapes数据集上进行了试验验证和分析。 相似文献