Pannee Suanpang, Pitchaya Jamjuntr & Phuripoj Kaewyong
Tourism route optimization will become a very substantial method of improving tourism planning for more appropriate matching with the travelers’ needs and budget especially in next normal tourism. This study aimed to support the tourist route planning of 50 scenic spots based on the researchers’ prototype of a recommendation system for considering the route’s distance, which was related to the transportation costs of the travel period. Optimal tourist routes in the tourist planning were suggested based on personal tourists’ level of satisfaction. The data for each location, distance, and transportation costs were collected. The obtained result was that the distance between the 50 attractions was 5272.51 kilometers when only considering the price. Moreover, this paper is linkage tourism route optimization on malware detection with convolutional neural network because of the increasing threats from malicious software in terms of both the numbers and complexity, security researchers have developed novel approaches for automatic detection and classification of malware instead of analyzing methods for malware files manually, which can be a time-consuming process. Furthermore, techniques were developed to avoid signature-based detection used by several antivirus companies. Therefore, deep learning techniques for malware classification were applied to identify the families of malware. In this paper, a convolutional neural network model was used for classifying static malware classification, and experiments were performed using the Malimg data set, which had malware images that were converted from portable executable malware binaries. The data set was divided into 25 malware families that had an accuracy of 96.46%.