AUTHOR=Rad Dana , Magulod Gilbert C. , Balas Evelina , Roman Alina , Egerau Anca , Maier Roxana , Ignat Sonia , Dughi Tiberiu , Balas Valentina , Demeter Edgar , Rad Gavril , Chis Roxana TITLE=A Radial Basis Function Neural Network Approach to Predict Preschool Teachers’ Technology Acceptance Behavior JOURNAL=Frontiers in Psychology VOLUME=Volume 13 - 2022 YEAR=2022 URL=https://www.frontiersin.org/journals/psychology/articles/10.3389/fpsyg.2022.880753 DOI=10.3389/fpsyg.2022.880753 ISSN=1664-1078 ABSTRACT=With the continual development of artificial intelligence and smart computing in recent years, quantitative approaches have become increasingly popular as an efficient modeling tool since they do not necessitate complicated mathematical models. The radial basis function neural network (RBFNN) is frequently utilized because of its clear structure and high nonlinear function approximation ability, particularly in data categorization and nonlinear system modeling. During the COVID-19 pandemic, ICT has become a major tool in the school system. Inspired by the demand of technology into early education, the present research uses a Radial Basis Function neural network modeling technique to predict preschool instructors' technology usage in class based on recognized determinant characteristics of technology acceptance. In this regard, this study designed an adapted version of Technology Acceptance Model with 8 dimensions. This study included 182 preschool teachers who were randomly chosen from a project-based national preschool teacher training program. In the model summary, we have obtained in the training sample a sum of squares error of 37.5 and a percent of incorrect predictions of 43.3%. In the testing sample we have obtained a sum of squares error of 14.88 and a percent of incorrect predictions of 37%. Thus, we can conclude that 63% of classified data are correctly assigned to models’ depended variable, actual technology use, which is a significant rate of correct predictions in the testing sample. This high significant percentage of correct classification represents an important result, mainly because this is one of the first study that applies neural networks prediction on psychological data, opening up a new interdisciplinary field of research. The findings show that perceived usefulness, perceived ease of use, self-efficacy, perceived enjoyment, intention to use, compatibility, and attitude, all have an impact on preschool teachers' behavioral intention. Our study adds to the literature by concentrating on the behavioral intentions of Romanian preschool instructors who were recently involved in online education activities. Our study contributes to the discovery of possible characteristics that influence preschool instructors' willingness to use educational technology. The data can be used to establish focused practical methods to increase the technological acceptability of preschool instructors.