No abstract

No abstract

This paper presents a neural network based positioning control system of a piezo-ceramic actuator which exhibits hysteretic behavior. Proposed control system utilizes two neural networks with radial basis function (RBF) as their activation functions: one is used for modeling hysteretic behavior of the actuator and the other is assigned the role of a feedback controller for hysteresis compensation and tracking. The particle swarm optimization algorithm has been applied to the training of RBF-NN for modeling PZT dynamics to achieve high precision, whereas back propagation has been used for online controller parameters update. An internal model control (IMC) structure is employed which combines aforementioned two neural networks for positioning control of the actuator. Results of the positioning control simulation of PZT will be shown to indicate the validity of the proposed two RBF-NN internal model control system.

The objective of this study was to evaluate the brain function characteristics of carbon monoxide poisoning patients using resting-state functional magnetic resonance imaging (fMRI) method. For this purpose, 12 carbon monoxide poisoning patients and healthy controls were subjected to resting-state fMRI scans separately. A regional homogeneity (ReHo) approach was used to analyze the brain function in carbon monoxide poisoning patients. Compared with control group, the value of ReHo in carbon monoxide poisoning group showed distinct decrease in bilateral superior frontal gyrus, middle frontal gyrus, right cuneus, left middle temporal gyrus, right insula, and cerebellum. Therefore, it was concluded that the brain functions in carbon monoxide poisoning patients were abnormal under the resting-state. The cuneate lobe function may indicate the degree of brain hypoxia and strengthening the cerebellar function training may promote the rehabilitation process.

No abstract

Under the influence of artificial intelligence (AI), Internet of Things (IOT) and big data technology, V2X vehicle infrastructure cooperative technology is rapidly applied to intelligent traffic management and road condition services. However, the existing roadside traffic control equipment has difficulty in data aggregation and processing, that cannot meet the application requirements of the intelligent connection and edge calculation of the V2X vehicle infrastructure cooperative device. In this paper, the “edge computing + end-edge-cloud collaboration” mode is used to construct the roadside intelligent information interaction system. As an intelligent connection node between roadside traffic management system and V2X vehicle infrastructure cooperative system, the design makes roadside video analysis and real-time data fusion and push function come true. Because of its lightweight intersection deployment mode, regional-level road condition diagnosis and optimization control capabilities, it has broad application prospects.

No abstract

No abstract