The need for more and more accurate simulations of groups of autonomous beings directs the attention of researchers towards the ways of parallelizing simulation algorithms. Parallel execution of discrete simulation models update methods requires their division between workers. Existing methods used for grid division aim at providing equal areas of fragments and minimizing the length of created borders. However, in real life simulations, other factors also have to be considered. In this paper we present a method for grid partitioning, which also allows defining indivisible areas, considers complex shapes of real-life environments and supports division suitable for defined architecture of nodes and cores. The method is evaluated using several scenarios, providing satisfactory results.

In recent years, model-based design and automatic code generation have gained popularity in various applications. However, using this approach in some specialized safety-critical applications is still challenging because the code must fulfill rigorous requirements. In this paper, the methodology of development of the software autopilot for the surface-to-surface guided projectile is presented in detail. The missile is actuated only with 32 solid propellant lateral motors, which makes the control task challenging. MATLAB and Simulink were used to develop the detailed simulation of the missile together with the control software. A Model-in-the-Loop testing was evaluated to achieve appropriate autopilot performance. Embedded Coder was applied to generate production-ready C code from the model. A custom test framework was created to accelerate the design process. The numerical equivalency of the Simulink model and C code was investigated extensively using Software-in-the-Loop and Processor-in-the-Loop simulations. The developed control algorithm was implemented on real hardware with ARM Cortex M4 microcontroller. The integrated prototype of the projectile control system was successfully tested in laboratory conditions by Hardware-in-the-Loop simulation. The scientific significance of this paper lies in a comprehensive description of the methodology that might be used in the external ballistics area.

In the present era, maintaining a healthy and disease-free life is complex due to multiple personal and environmental impacts. Early identification and diagnosis will help human beings lead a sustainable life. However, to achieve this, health care data has to be processed in an efficient manner with more accuracy. Thus, the impacts of diseases or future impacts can be predicted or detected and proper medication can be provided by the physicians. Handling medical data over conventional data analysis is quite different due to data diversity. Efficient feature extraction techniques must be employed with minimum computation cost so that the extracted features can be classified in a better way. Machine learning models perform well in healthcare data analysis. However, the performance can be improved if deep learning models replace machine learning models. Thus, in this research work, a hybrid deep learning approach is proposed using convolutional neural networks (CNN) and the random forest algorithm. The final classifier block in the CNN architecture is replaced with a random forest classifier to enhance the prediction accuracy and overall performance. Standard benchmark healthcare datasets are employed in the proposed model simulation analysis and the performances are compared to existing techniques such as MNN (Multi Neural Network), CNN-Multilayer Perceptron (CNN-MLP), CNN-Long Short-Term Memory (CNN-LSTM), and Support Vector Machines (SVM), KNN to validate the superior performance.

The Research focuses on the real-time identification of emergency vehicles using the YOLOv8 algorithm in the context of IoT. The aim is to develop an efficient and accurate emergency vehicle detection system to improve emergency service response times. The proposed system utilizes the YOLOv8 algorithm trained and tested with a dataset from a camera placed on a busy road. The results demonstrate that the system can detect emergency vehicles at a speed of 31 frames per second with a 95% accuracy rate. The system is implemented using a Raspberry Pi as an edge device, processing the live video stream from an IoT device equipped with a camera. Once an emergency vehicle is detected, an alert is sent to the emergency services for prompt action. The study highlights the potential of the YOLOv8 algorithm and IoT in creating effective and reliable emergency vehicle detection systems. The proposed solution is cost-effective, easy to implement, and adaptable to existing infrastructure. It has the capability to save lives and enhance emergency response by reducing response times. Future improvements can include the incorporation of more advanced machine learning algorithms and additional sensors to identify other emergency vehicles like ambulances and fire engines. The research emphasizes the potential of IoT and machine learning in developing innovative solutions for emergency services, particularly in the realm of intelligent transportation systems.

In this paper we present a grey wolf algorithm for a concurrent real time optimization problem in searching for optimal game solving solution. There are many solutions to solve the game. Each solution can demand different optimal values of different parameters. However some ways in which the players try to solve the game do not lead to success. The optimization problem consists of two phases. Each phase Impacts the second one in real time. The first phase is responsible for the optimization parameters choice. The second phase validates the choice and makes the optimization of the parameters. As a optimizing method we chose grey wolf optimization. At the beginning the algorithm generates some number of solutions. The solution which has the value of the parameters the closest to maximum is a position of an alfa wolf. The rest of solutions are, according to the values of the parameters, split to be the positions of beta, delta and omega wolfs.

The paper presents a comprehensive approach to design and implementation of a multidimensional nonlinear control system for a 3D crane. For design purposes, a simulation model of the crane is developed and verified. Proposed are two structures of the control system, which are based on PID controller and predictive control system. The synthesis process is presented. The designed systems are verified in terms of their effectiveness, based on the judgement on the obtained waveforms of controlled variables and integral control indicators. Finally, the two systems are compared with each other, and the conclusions regarding their applicability for this type of system are presented.

In this paper, the use of a highly sensitive acoustic emission method for studying the deformation and failure processes of composite materials is considered, which provides a substantial amount of information about phenomena occurring at the sub-micro, micro, and macro levels. However, the additional influence of various factors leads to the problem of interpreting and identifying the recorded information. Addressing this problem involves determining the influence of different factors on acoustic emission signal parameters and their sensitivity to the influencing factor. In this study, during the failure of a composite material under transverse force according to the Mises criterion, an analysis is conducted on the impact of changes in the number of composite material elements (damage area) on the amplitude-time parameters of the acoustic emission signal based on a developed signal model. The results of the simulation allowed for the identification and description of patterns in the changes of amplitude-time parameters of acoustic emission signals (maximum amplitude, area under the signal curve, and signal duration) with variations in the number of composite material elements. These patterns enable the determination of the sensitivity of acoustic emission signal parameters to the influencing factor. The findings of this study may be of interest in the development of methods for monitoring, diagnosing, and predicting the failure of composite materials and products through the registration and analysis of acoustic emission signals.

This paper presents the concept of hierarchical extremely modular systems (EMS). The biology-inspired nomenclature, genetic encoding, and operations for this class of structures is introduced and illustrated with various examples. Four mutation types are introduced and briefly analyzed. A relatively good convergence of the evolution strategy-based algorithm applied for optimization of EMS is shown.

In this paper a fuzzy Proportional (PD) Controller was designed and implemented for dynamically adapting the velocity and motion parameters in a quadruped robot for autonomously following a goal. The FNK0050 Freenove quadruped robot was utilized for the experiments, which has 12 degrees of freedom and this is why it has higher complexity. Experimental results show that the proposed fuzzy PD controller surpasses the standard PID controller provided as default by the manufacturer of the robot.