Data Automation with Deep Learning: A Systematic Review

Abstract

The instructions give the basic guidelines for This research addresses the application of Deep Learning techniques in data automation, highlighting its benefits and areas of implementation. A comprehensive search of academic databases was conducted using the PRISMA methodology, selecting relevant studies according to specific inclusion and exclusion criteria. The analysis focused on two main categories: predictive models and convolutional neural networks (CNN). In the area of predictive models, applications such as text sentiment analysis and IoT systems for predicting school dropout were evaluated. For CNNs, methods for 3D localization and smart factory management were explored. The findings indicate that Deep Learning significantly improves accuracy and efficiency in data automation, with applications in sectors such as technology, healthcare, agriculture and energy. Despite the limitations of the study, such as time coverage and database selection, future challenges are identified, including improving model scalability and efficiency, data security and privacy, and adaptability to new contexts with limited data. These findings provide a solid foundation for future research and practical applications in the field of Deep Learning.