In both catastrophe prevention and disaster relief, humanitarian logistics is essential. Delivering aid as quickly as possible has an impact on the welfare of victims and the survivable rate in certain parts of the relief supply operation. In this study, the Traveling Salesman Problem (TSP) is employed to determine the optimal path for providing aid to alleviate the suffering of victims when a disaster strikes. When deciding on the route, the severity level is considered as well. The model also takes into account the total time to distribute relief supplies. The flood case study from Nakhon Ratchasima province of Thailand is used to examine the TSP's application. The results obtained help in determining the suitable scheme for distributing relief efforts, and the optimal path with the shortest overall distance is identified for use as a strategy for effectively managing the distribution network.

Social media is an important source of false news because of its accessibility, usability, and large community. Individuals who trust the fabricated news may be misinformed. Classifying true and false information among data is a challenging task for the ordinary person. Hence, machine learning is the best solution for supporting human judgment. In this study, eleven machine learning algorithms were employed to evaluate the performance of models utilizing a Thai fake news dataset. In addition, we designed experiments to demonstrate how stop words influence performance. This study found that stop words had no effect on the performance of the model while classifying Thai fake news, and that SVM with an RBF kernel provided the best performance.

A two dimensional graph is a powerful method for representing a set of objects that usually appears in many sources of literature. Numerous efforts have been made to discover image semantics based on contents of literature. However, conventional methods have not been fully able to satisfy users because a wide variety of techniques are being developed, and each is very useful for enhancing system capabilities in their own way. In this paper, we have developed a method to automatically extract relationships from graphs on the basic of their captions and image content, particularly from graph titles. Furthermore, we improved our idea by applying several technologies such as ontology and a dependency parser. The relationships discovered in a graph are presented in the form of a triple (subject, predicate, object). Our objectives are to find implicit and explicit information in the graph and reduce the semantic gap between an image and literature context. Accuracy was manually estimated to identify the most reliable triple. Based on our results, we concluded that the accuracy via our method was acceptable. Therefore, our method is dependable and worthy of future development.