In this paper the quadrotor dynamic model with nonlinear inputs is presented. Deadzone and saturation nonlinear inputs are considered for the quadrotor reflected to the actuators. The goal is to obtain a faithful mathematical representation of the mechanical system for system analysis and control design, not only in hover as presented in many works, but also in motion when take-off, land and flight for aerial navigation task. The model was implemented in Matlab/Simulink simulation model to optimize the design and to project control. Simulations of the model show that the nonlinear inputs must be considered in the control project.

Speech emotion recognition (SER) is widely applicable today, benefiting areas such as entertainment, robotics, and healthcare. This emotional understanding enhances user-machine interaction, making systems more responsive and providing more natural experiences. In robotics, SER is useful in home assistance devices, eldercare, and special education, facilitating effective communication. Additionally, in healthcare settings, it can monitor patients’ emotional well-being. However, achieving high levels of accuracy is challenging and complicated by the need to select the best combination of machine learning algorithms, hyperparameters, datasets, data augmentation, and feature extraction methods. Therefore, this study aims to develop a deep learning approach for optimal SER configurations. It delves into the domains of optimizer settings, learning rates, data augmentation techniques, feature extraction methods, and neural architectures for the RAVDESS, TESS, SAVEE, and R+T+S (RAVDESS+TESS+SAVEE) datasets. After finding the best SER configurations, meta-learning is carried out, transferring the best configurations to two additional datasets, CREMA-D and R+T+S+C (RAVDESS+TESS+SAVEE+CREMA-D). The developed approach proved effective in finding the best configurations, achieving an accuracy of 97.01% for RAVDESS, 100% for TESS, 90.62% for SAVEE, and 97.37% for R+T+S. Furthermore, using meta-learning, the CREMA-D and R+T+S+C datasets achieved accuracies of 83.28% and 90.94%, respectively.

The constant growth in the use of computer networks has demanded some concerns regarding disponibility, vulnerability and security. Intrusion Detection Systems (IDS) have been considered essential in keeping network security and therefore have been commonly adopted by network administrators. A possible disadvantage is the fact that such systems are usually based on signature systems, which make them strongly dependent on updated database and consequently inefficient against novel attacks (unknown attacks). The research presented in this paper proposes an IDS system based on artificial neural network (ANN) and the KDDCUP'99 dataset. Experimental results clearly show that the proposed system can reach an overall accuracy of 99.9% regarding the classification of pre-defined classes of intrusion attacks with, which is a very satisfactory result when compared to traditional methods.

In this paper the hexarotor dynamic model with nonlinear inputs and full state back stepping technique is presented. Dead zone and saturation nonlinear inputs are considered reflected to the rotors. The goal is to obtain a faithful mathematical representation of the mechanical system for analysis and control design, not only in hover, but also in motion when take-off, land and flight for aerial navigation tasks. The model was implemented in Matlab/Simulink to optimize the design of control system. Simulations of the hexarotor model shows the performance of the control law and stabilizes with good tracking.