Research on Dem Construction Methods With Effective Integration of Topographic Feature Lines

In cities and other human activity areas, the implementation of various ground projects has resulted in significant changes in natural surface morphology, a prominent feature of which is the formation of a variety of discontinuous terrains, such as roads and building basements. In the process of DEM modeling of these landforms, traditional modeling methods produce obvious topographic distortions at topographic prominences, which limits the application depth of DEMs in these areas. To solve these problems, this paper proposes a DEM modeling method to enhance the expression of discontinuous terrain from the perspective of simplicity and convenience for application. The method is based on terrain data such as topographic feature lines, altimetric points, and contour lines. First, parallel feature lines are generated according to a certain distance. Then, vertices are inserted into the topographic feature line and the parallel feature line according to the specified step length, and the known altimetric points are selected from both sides of the original topographic feature line to estimate the height value of the vertices. Finally, by combining the topographic feature line, parallel feature line and other available topographic data for TIN construction, the result can effectively express the special topography of discontinuous terrain. In this study, a region in Nanjing City, Jiangsu Province, China, was selected as the study area to conduct a DEM construction experiment. The experimental results showed that the DEM constructed by this method could well express the morphological characteristics of discontinuous terrain, and the height accuracy of the construction results was also significantly improved compared with that of the conventional method.

The Effects of Online Learning during the Outbreak of Coronavirus Disease 2019 (COVID-19) towards Grade 10-12 Thai Students’ Opinions

This study aimed to study the effects of integrating online learning in schools during the outbreak of COVID-19 in Thailand from mid-March to July 2020. The participants were 508 students consisting of grade 10-12 levels from five different schools in each province of Thailand. The questionnaire employed via “Poll Feature Line Group” was separated into three categories; 1) The general informations of the students, 2) The advantages of online learning, and 3) The limitations of online learning. 508 students gave the feedback by checking the items of the questionnaires via “Poll Feature Line Group”. The researchers took two weeks to complete the survey in October 2020. The results of the questionnaire were calculated into the statistical values in Percentage, Mean Range and Standard Deviation. The results revealed that the majority of the students studying online studied in grade 12 in science-mathematics program, and Thai and English subjects were primarily available online. The most three advantages were – 1) Online learning promotes the social distancing., 2) Online learning helps students save time and cut on expenses especially transport costs., and 3) Students can communicate via various platforms like Line, Email, Facebook, and Google Classroom. On the contrary, the most limitations were – 1) Students have no chance to participate in extracurricular activities in school., 2) The mere presence of a smartphone reduces students' ability to focus on the lessons., and 3) It can be hard to find answers to questions or resolve difficulties, especially when discussion forum participation is low.

Feature Line Embedding Based on Support Vector Machine for Hyperspectral Image Classification

In this paper, a novel feature line embedding (FLE) algorithm based on support vector machine (SVM), referred to as SVMFLE, is proposed for dimension reduction (DR) and for improving the performance of the generative adversarial network (GAN) in hyperspectral image (HSI) classification. The GAN has successfully shown high discriminative capability in many applications. However, owing to the traditional linear-based principal component analysis (PCA) the pre-processing step in the GAN cannot effectively obtain nonlinear information; to overcome this problem, feature line embedding based on support vector machine (SVMFLE) was proposed. The proposed SVMFLE DR scheme is implemented through two stages. In the first scatter matrix calculation stage, FLE within-class scatter matrix, FLE between-scatter matrix, and support vector-based FLE between-class scatter matrix are obtained. Then in the second weight determination stage, the training sample dispersion indices versus the weight of SVM-based FLE between-class matrix are calculated to determine the best weight between-scatter matrices and obtain the final transformation matrix. Since the reduced feature space obtained by the SVMFLE scheme is much more representative and discriminative than that obtained using conventional schemes, the performance of the GAN in HSI classification is higher. The effectiveness of the proposed SVMFLE scheme with GAN or nearest neighbor (NN) classifiers was evaluated by comparing them with state-of-the-art methods and using three benchmark datasets. According to the experimental results, the performance of the proposed SVMFLE scheme with GAN or NN classifiers was higher than that of the state-of-the-art schemes in three performance indices. Accuracies of 96.3%, 89.2%, and 87.0% were obtained for the Salinas, Pavia University, and Indian Pines Site datasets, respectively. Similarly, this scheme with the NN classifier also achieves 89.8%, 86.0%, and 76.2% accuracy rates for these three datasets.