Studies have shown that the application of gamification has positive effects on motivation and learning. However, various meta-studies indicate that there is high volatility in the published results. The purpose of this study is to analyze whether the student’s activity as gamers is related to these differences. A comparative study was conducted with undergraduates’ students in a database course. Students were divided into two instructional approaches: flipped learning (n = 47), and flipped with gamification (n = 49). Gamers were identified in each class using three methods: game frequency, spending money on videogames and most played game genre. The results showed that students in gamified class obtained significantly better results in learning, but there were no differences in motivation and satisfaction. When comparing gamers with non-gamers in the gamified class, the results using the three methods coincide with respect to motivation but show differences in satisfaction and learning. In the same way, when the effects of gamification on non-gamers were analyzed, there are coincidences in which those of the gamified class have better performance, but there are no coincidences regarding motivation and satisfaction. The results obtained show that the conclusions when comparing between gamers and non-gamers depend on the method used to identify them.
1 June 2020 in Computer Applications in Engineering Education
Deep learning has gained popularity in recent years for reconstructing hyperspectral and multispectral images, offering cost-effective solutions and promising results. Research on hyperspectral image reconstruction feeds deep learning models with images at specific wavelengths and outputs images in other spectral bands. Although encouraging results of previous works, it should be determined to what extent the reconstructed information can lead to an advantage over the captured images. In this context, the present work inspects whether or not reconstructed spectral images add relevant information to segmentation networks for improving urban tree identification. Specifically, we generate red-edge (ReD) and near-infrared (NIR) images from RGB images using a conditional Generative Adversarial Network (cGAN). The training and validation are carried out with 5770 multispectral images obtained after a custom data augmentation process using an urban hyperspectral dataset. The testing outcomes reveal that ReD and NIR can be generated with an average Structural Similarity Index Measure of 0.93 and 0.88, respectively. Next, the cGAN generates ReD and NIR information of two RGB-based urban tree datasets (i.e., Jekyll, 3949 samples, and Arbocensus, 317 samples). Subsequently, DeepLabV3 and SegFormer segmentation networks are trained, validated, and tested using RGB, RGB+ReD, and RGB+NIR images from Jekyll and Arbocensus datasets. The experiments show that reconstructed multispectral images might not add information to segmentation networks that enhance their performance. Specifically, the p-values from a T-test show no significant difference between the performance of segmentation networks.
20 July 2024 in Computer Applications in Engineering Education