Search

Viral and bacterial infection diseases are the most common things caused by microbes. Infection diseases are serious issues because of the growth of COVID‐19. Because of the current living situation, clinical pathogens are difficult to identify. Therefore, biosensors have been widely utilized to sense the biomolecules relevant to viruses and bacteria. The biosensors observe the nanoparticles from the pathogens and help improve the infection analysis. The sensor information is processed using machine learning techniques because it consists of several learning patterns. However, the existing methods have multi‐objective optimization problems while analysing the changes in the nanoparticles. This work utilizes a mayfly optimized convoluted neural network (MOCNN) to overcome this research issue. The grid uses the fully convolution layer that processes the extracted biosensor features to determine the infections. The network performance is optimized by applying the exploitation and exploration properties of nuptial dance that help to escape from the local optima solutions. The effective utilization of the optimized training patterns improves the convergence speed and convergence rate compared to traditional methods. From the results, MOCNN ensures 98.97% accuracy, 0.388 error rate, and 0.322833 convergence rate on various iterations with different learning rates. [ABSTRACT FROM AUTHOR]

The real-time obstacle avoidance strategy remains an important technical demand in robotic navigation. Although some progress has been achieved in recent years, existing works cannot handle unknown background inference in complex contexts. To deal with this challenge, this paper proposes a dynamic obstacle avoidance method in robotic navigation control through YOLOv5-based object detection. Specifically, an attention mechanism-based YOLOv5 algorithm is introduced to enhance the expression capability of small target channel features and spatial features. A P2 small target detection layer is added to strengthen the fusion of feature information between high and low layers. This is expected to address the problem that some detailed features of small targets are lost due to multiple down-sampling operations. For the navigation control part, an abstract potential field is introduced to guide the robots to move toward the target position while avoiding obstacles. Finally, we conduct some experiments on a real-world simulation scenario to make a comparative analysis. The obtained results show that the proposal can improve the obstacle avoidance effect compared with some baseline methods. [ABSTRACT FROM AUTHOR]