认证导向下基于翻转课堂和混合教学模式的软件构造课程教学实践
Teaching Practice of Software Construction Course Based on Flipped Classroom and Blending Teaching Mode Under Engineering Education Accreditation Orientation
- Authors:
- Keywords: Engineering education accreditation; Software construction; Flipped classroom; Blending learning; Software engineering; Changjiang Rain Classroom工程教育认证; 软件构造; 翻转课堂; 混合式教学模式; 软件工程; 长江雨课堂
- Abstract: This paper combines the actual teaching process, integrates the concepts of engineering education accreditation and ideological and political theories to design teaching contents and organize teaching activities in the reverse direction of students’ learning outcomes, and proposes a studentoriented, teacher-led, teacher-assisted and supervised flipped and blended teaching mode with the assistance of the modern information-based teaching tool Changjiang Rain Classroom. According to the results of students’ performance, feedback and survey, the method has improved students’ enthusiasm for learning and their teamwork spirit, promoted students’ better understanding and practice of software construction knowledge, and helped cultivate students’ professional engineering ability and ideological morality in a comprehensive manner.针对“软件构造”课程内容多、难度大等特点，本文结合实际教学过程，融合工程教育认证和课程思政理 念，以学生学习成果为导向反向设计教学内容、组织教学活动，借助现代信息化教学工具长江雨课堂，提出了以学生为主体，教师引导、协助和监督的翻转课堂混合教学模式。从学生成绩、反馈与调研结果来看，该方法提高了学生学习的积极性和学生的团队合作精神，能够促进学生更好地理解、实践软件构造知识，有助于全面培养学生的工程专业能力和思想品德。
-
面向滨海生态监管的多尺度目标语义分割研究
Multi-scale Objectives Semantic Segmentation for Coastal Ecological Supervision
- Authors:
- Keywords: Coastal ecological supervision; Artificial intelligence; Mangroves; Mariculture; Benchmark dataset; Multi-scale feature fusion; Semantic segmentation滨海生态监管; 人工智能; 红树林; 海水养殖; 基准数据集; 多尺度特征融合; 语义分割
- Abstract: To improve the lack of deep learning dataset of coastal ecological scenes and low accuracy of multi-scale objectives semantic segmentation for remote sensing image classification, we take three types of coastal typical ecological supervision multi-scale objectives of mangrove, raft cultivation and pond aquaculture as research objects, constructs a benchmark dataset for coastal ecological supervision, improves the UNet feature fusion by integrating batch normalization and spatial dropout modules, and proposes a multi-scale deep convolutional semantic segmentation model. The model has an overall accuracy of 92% on the test set, a kappa coefficient of 0.87, and a mIoU of 82%. The experimental results show that the coupled stacking of batch normalization and feature fusion spatial dropout can effectively suppress multiscale objectives semantic segmentation overfitting and improve the model accuracy and generalization performance. The proposed model and the constructed semantic segmentation dataset for coastal ecological supervision can provide decision support for ecological restoration, mapping and comprehensive management in coastal areas.针对缺少滨海生态场景深度学习数据集，面向遥感影像分类的多尺度目标语义分割精度不高等问题，研究以红树林、浮筏养殖和围塘养殖三类滨海典型生态监管多尺度目标为研究对象，构建了面向滨海生态监管的多目标语义分割数据集，通过集成批归一化和空间置弃算法，改进UNet 特征融合策略，提出了一种多尺 度深度卷积语义分割模型。模型在测试集上总体精度92%，Kappa 系数0.87，平均交并比82%。实验结果表明批归一化与特征融合空间置弃的耦合堆叠可有效抑制多尺度目标语义分割过拟合，提高模型精度和泛化性能。研究提出的模型及构建的面向滨海生态环境监管的多目标语义分割数据集可为滨海区域生态修复、测绘和综合治理提供决策支持。
-
科研立项
