No abstract

No abstract

Data pre-processing is a crucial phase prior to analytic task and yet rarely been discussed especially for e-learning data which has multilevel data. Providing a reliable data pre-processing is important to provide quality dataset. Therefore, this study investigates the problems arise in data pre-processing and in this case, for identifying the implement prediction task. A MOOC dataset is selected for the data pre process in generating the summary of dataset is explained and the ultimate aim is to produce a dataset with features that are ready for data model and suggestions, which can be applied to support more comprehensible tools for educational domain who is the end user. Subsequently, the data pre efficient for predicting student's

No abstract

Abstract. Videogrammetry is a technique to generate point clouds by using video frame sequences. It is a branch of photogrammetry that offers an attractive capabilities and make it an interesting choice for a 3D data acquisition. However, different camera input and specification will produce different quality of point cloud. Thus, it is the aim of this study to investigate the quality of point cloud that is produced from various camera input and specification. Several devices are using in this study such as Iphone 5s, Iphone 7+, Iphone X, Digital camera of Casio Exilim EX-ZR1000 and Nikon D7000 DSLR. For each device, different camera with different resolution and frame per second (fps) are used for video recording. The videos are processed using EyesCloud3D by eCapture. EyesCloud3D is a platform that receive input such as videos and images to generate point clouds. 3D model is constructed based on generated point clouds. The total number of point clouds produced is analyzed to determine which camera input and specification produce a good 3D model. Besides that, factor of generating number of point clouds is analyzed. Finally, each camera resolution and fps is suggested for certain applications based on generated number of point cloud.