Design And Build Virtual Reality Photography Web-Based To Support Tourism

Abstract

<p class="Abstract"><span lang="EN-US">Tourism is the activity of visiting tourist objects for recreational and leisure purposes. Along with developments in the world of technology and information, there is a technology that can be used to promote a tourist attraction called Virtual Reality. Virtual Reality is a technology designed to allow users to interact with a computer-simulated environment. The problem is that there are still very few travel websites that provide this feature. Virtual Reality technology in the world of photography is known as Virtual Reality Photography. Virtual Reality Photography can produce images in 360</span><sup>o</sup><span lang="EN-US">, so people can see the image as a whole and as if they were in place when the photographer was taking pictures. The purpose of this research is to design and build a website that provides information for tourists who want to visit tourist objects. The development method used is the Multimedia Development Life Cycle. The output of his research is a Virtual Reality Photography website that provides information in the form of 360<sup>o</sup> images equipped with location maps and static images. Augmented Reality technology can be applied on this website as a form of information presented as well as Virtual Reality technology.<em></em></span></p><p class="Keywords"><span lang="EN-US">Keywords— Information, Multimedia, Tourism, Virtual Reality, Web</span>.</p>

Development of virtual tour reality using 360-degree panoramic images and Leaflet JavaScript

“…VR photography is processed to allow users to interact directly with virtual places. This VR photography, also called immersive photography or 360° panoramic photography, shows a location continuously, smoothly, and seamlessly at a 360-degree viewing angle in the horizontal and vertical directions [23]. Virtual tours provide an overview of places that correspond to the original tour.…”

Improvement of Data Mining Models using Forward Selection and Backward Elimination with Cryptocurrency Datasets

“…The results showed that the Backward Elimination model on the KNN Algorithm had an accuracy of 92.8% and AUC of 0.942, the Naïve Bayes algorithm had an accuracy of 88.0% and AUC of 0.912, the C4.5 algorithm had an accuracy of 96.7% and AUC of 0.956, while the results of the model after optimization is the KNN algorithm with an accuracy of 97.6% and AUC of 0.973, the Naïve Bayes algorithm with an accuracy of 89.4% and AUC of 0.958, the C4.5 algorithm has an accuracy of 97.5% and AUC of 0.988. To make it clearer in understanding previous research, a comparative analysis of the previous technique is presented [5], [18], as shown in Table 1. This research fills in the gaps with previous research by using four Supervised Learning Algorithms and using two Feature Selection-Wrapper methods, namely Forward Selection and Backward Elimination.…”