Machine vision is an active branch of artificial intelligence. An important problem in this area is the trade-off among efficiency, accuracy and computation complexity. The human visual system can keep watchfulness to...
详细信息
Machine vision is an active branch of artificial intelligence. An important problem in this area is the trade-off among efficiency, accuracy and computation complexity. The human visual system can keep watchfulness to the perimeter of a viewing field while at the same time focus on the center of the field for fine information processing. This mechanism of appropriate assignment of computing resources can reduce the demand for huge and complex hardware structure. Therefore, the design of a computer model based on the biological visual mechanism is an effective approach to resolve problems in machine vision. In this paper, a multi-layer neural model is developed based on the features of receptive field of ganglion in retina to simulate multi-scale perceptive fields of ganglion cell. The neural model can maintain alert on the outer area of the image while capturing and processing more important information in the central part. It may provide valuable inspiration for the implementation of real-time processing and avoidance of huge computation in machine vision.
This paper presents modeling and simulation of a multi-input multi-output (MIMO) adaptive control system (ACS) for human arterial blood pressure (HASP) by multiple drug inputs -infusion speed (IS) control of inotropic...
详细信息
This paper presents modeling and simulation of a multi-input multi-output (MIMO) adaptive control system (ACS) for human arterial blood pressure (HASP) by multiple drug inputs -infusion speed (IS) control of inotropic agent (IA) and vasoactive agent (VA). The MIMO ACS is able to choose the most appropriate IS of IA and VA at good IS in order to maintain the aortic pressure (AOP) and central vain pressure (CAP) at desired levels, and at the same time to increase the cardiac output (CO). This ACS simulation consists of 3 parts: the system model (SM), the identifier (ID), and the explicit multivanable self-turning controller (MSC). The SM is a 2-input 2-output bilinear model with nonwhite system noise. The variable ID is capable of estimating the variable onset delay model (BNVD). The ID is capable of estimating the variable onset delay online by compressing the value in gaining the unbiased parameter estimation with an improved generalized least-squares (LS) algorithm. The MSC employs the minimum variance one-step-ahead control law. These three parts make a closed-loop control system successfully for heart disease patients during and after the operation.
暂无评论