Real-time driver state detection A vision system for controlling an industrial robot with hand movements Integration of a camera and virtual reality with a robotic arm Application of computer vision in the recognition and interpretation of sign letters Mapping of characteristic points of the human face using machine learning and Blender software Six-legged robotic insect Two-way communication based on the MQTT protocol within the virtual and real environment

Real time driver state detection

Student: Šimun Kordiš

This paper explores the possibilities of facilitating the use of artificial intelligence and deep learning, technologies that are increasingly being used in various fields. The motivation for this paper is to develop a tool that will provide users with intuitive interface for developing deep learning models without the need for technical knowledge in this domain.

As a result, a web application was developed that allows users to easily create and customize deep learning models. The system is implemented using modern technologies. The user interface is developed in the Next.js framework, while the backend logic is built using the Flask framework. The application uses PyTorch to train neural networks, allowing users to customize the network architecture and visualize the results and performance of the model.

The application testing and evaluation was conducted on a well-known dataset for iris flower classification. The model demonstrated high precision, achieving 100% prediction accuracy on a test dataset.