درخت حوزه‌های تخصصی

Relying on the Area Under the Curve (AUC) measure, we compare the performance of the Logit regression model and the LightGBM algorithm. Despite these methods being common in the literature, our study emphasizes the role of statistical inference to evaluate and compare the results comprehensively. We use the training set of the Vesta (2018) dataset, provided by Vesta—a global fraud prevention company headquartered in the United States specializing in payment solutions and risk management. Originally released as part of a Kaggle competition focused on credit card fraud detection, this dataset comprises diverse transaction records, representing a rich source for exploring advanced fraud detection methods. Our analysis reveals that while the LightGBM algorithm generally yields higher predictive accuracy, the differences between the calculated AUCs of the two methods are not statistically significant. This underscores the importance of using inferential techniques to validate model performance differences in fraud detection.

Food production in controlled cultivation areas plays a crucial role in increasing productivity and offsetting supply shortages. Product yields, water consumption, and energy use are the main parameters determining the performance of food production in a greenhouse. Smart technology is an effective solution to improve these parameters. This study aimed to identify the components, challenges, and requirements for the development of smart agriculture in greenhouses. Our case study focused on Tehran province, which encompasses a significant portion of the total greenhouses in Iran. The statistical population consisted of 20 subject-matter experts with research or executive experience in greenhouse automation, selected purposefully. Questionnaires and semi-structured interviews were used in this study to collect data. First, we identified the variables affecting the development of smart agriculture in greenhouses by using a literature review and semi-structured interviews with experts, Then, the experts were asked to evaluate the cross-influence of the identified variables through pairwise comparison. Finally, data analysis was done using MICMAC software. The findings indicate that the identified requirements and challenges have had a significant influence on the lack of smart agriculture in greenhouses. Through network analysis of influence and dependence relationships, it was found that economic requirements and challenges, technical and infrastructural requirements and challenges, legal and regulatory requirements, and institutional requirements were the most influential variables in the development of smart agriculture in Tehran province.