E-learning platforms support education systems worldwide, transferring theoretical knowledge as well as soft skills. In the present study high-school pupils’, and adult students’ opinions were evaluated through a mo...E-learning platforms support education systems worldwide, transferring theoretical knowledge as well as soft skills. In the present study high-school pupils’, and adult students’ opinions were evaluated through a modern structured MOODLE interactive course, designed for the needs of the laboratory course “Automotive Systems”. The study concerns Greek secondary vocational education pupils aged 18 and vocational training adult students aged 20 to 50 years. The multistage, equal size simple random cluster sample was used as a sampling method. Pupils and adult students of each cluster completed structured 10-question questionnaires both before and after attending the course. A total of 120 questionnaires were collected. In general, our findings disclosed that the majority of pupils and adult students had significantly improved their knowledge and skills from using MOODLE. They reported strengthening conventional teaching, using the new MOODLE technology. The satisfaction indices improved quite, with the differences in their mean values being statistically significant.展开更多
针对无人机在光伏组件巡检任务中红外故障图像识别准确率低、检测速度慢的问题,提出一种特征增强的YOLO v5s故障检测算法。首先对损失函数进行优化,将原有的回归损失计算方法由GIOU(generalized intersection over union)改为功能更加...针对无人机在光伏组件巡检任务中红外故障图像识别准确率低、检测速度慢的问题,提出一种特征增强的YOLO v5s故障检测算法。首先对损失函数进行优化,将原有的回归损失计算方法由GIOU(generalized intersection over union)改为功能更加强大的EIOU(efficient intersection over union)损失函数,并自适应调节置信度损失平衡系数,提升模型训练效果;随后,在每个检测层前分别添加InRe特征增强模块,通过丰富特征表达增强目标特征提取能力。最后,用创建的红外光伏数据集进行对比验证。实验结果表明:本文方法均值平均精度(mean average precision,mAP)为92.76%,检测速度(frame per second,FPS)达到42.37 FPS,其中热斑、组件脱落两种故障类型平均精度分别为94.85%、90.67%,完全能够满足无人机自动巡检的需求。展开更多
文摘E-learning platforms support education systems worldwide, transferring theoretical knowledge as well as soft skills. In the present study high-school pupils’, and adult students’ opinions were evaluated through a modern structured MOODLE interactive course, designed for the needs of the laboratory course “Automotive Systems”. The study concerns Greek secondary vocational education pupils aged 18 and vocational training adult students aged 20 to 50 years. The multistage, equal size simple random cluster sample was used as a sampling method. Pupils and adult students of each cluster completed structured 10-question questionnaires both before and after attending the course. A total of 120 questionnaires were collected. In general, our findings disclosed that the majority of pupils and adult students had significantly improved their knowledge and skills from using MOODLE. They reported strengthening conventional teaching, using the new MOODLE technology. The satisfaction indices improved quite, with the differences in their mean values being statistically significant.
文摘针对无人机在光伏组件巡检任务中红外故障图像识别准确率低、检测速度慢的问题,提出一种特征增强的YOLO v5s故障检测算法。首先对损失函数进行优化,将原有的回归损失计算方法由GIOU(generalized intersection over union)改为功能更加强大的EIOU(efficient intersection over union)损失函数,并自适应调节置信度损失平衡系数,提升模型训练效果;随后,在每个检测层前分别添加InRe特征增强模块,通过丰富特征表达增强目标特征提取能力。最后,用创建的红外光伏数据集进行对比验证。实验结果表明:本文方法均值平均精度(mean average precision,mAP)为92.76%,检测速度(frame per second,FPS)达到42.37 FPS,其中热斑、组件脱落两种故障类型平均精度分别为94.85%、90.67%,完全能够满足无人机自动巡检的需求。