Journal of Artificial Intelligence in Electrical Engineering
Volume:7 Issue: 25, Spring 2018

The occurrence of catastrophic earthquakes necessitates further researches in the structure engineering for retrofitting construction structures. In this paper, the application of the active control in the structures’ seismic response has been addressed. A single degree of freedom nonlinear structure has been studied. The nonlinear dynamic of the structure is considered in which, the nonlinear part of the dynamic is modeled by Bouc-Wen model. The sliding mode controller is used to stabilize the system. The results show the effectiveness of the proposed method.

Sometimes conventional feedback controllers may not perform well online because of the variation in process dynamics due to nonlinear actuators, changes in environmental conditions and variation in the character of the disturbances. To overcome the above problem, this paper deals with the designing of a controller for a second order system with Model Reference Adaptive Control (MRAC) scheme using the MIT rule for adaptive mechanism. In this rule, a cost function is defined as a function of error between the outputs of the plant and the reference model, and controller parameters are adjusted in such a way so that this cost function is minimized. The designed controller gives satisfactory results, but is very sensitive to the changes in the amplitude of reference signal. It follows from the simulation work carried out in this paper that adaptive system becomes unstable if the value of adaptation gain or the amplitude of reference signal is sufficiently large. This paper also deals with the use of MIT rule along with the normalized algorithm to handle the variations in the reference signal, and this adaptation law is referred as modified MIT rule. The performances of the proposed control algorithms are evaluated and shown by means of simulation on MATLAB and Simulink

Cells grow and then need a very neat method to create new cells that work properly to maintain the health of the body. When the ability to control the growth of the cells is lost, they are unconsidered and often divided without order. Exemplified cells form a tissue mass called the tumor. In fact, brain tumors are abnormal and uncontrolled cell proliferations. Segmentation methods are used in biomedical image processing and examines the methods used for better segmentation. Critical assessment of the current state of the automated and automated methods for categorizing anatomical medical pictures with emphasis on the benefits and disadvantages. In this project, we recognize brain tumors and classify tumor stages using database testing and training. Segmentation is used for testing purpose by FCM space. Neural networks are also used for its segmentation, which yields acceptable results in PNN neural networks.

3D printers are tools utilized to create real 3D samples using the 3D files within your computer. The first feasibility and idea of such tools dates back to 1950. The very first sketch of 3D printers was presented in 1980s called "Rapid Prototyping" and the first sample was developed by Charles Hall and it was recorded with the name of the same scientist. But the current 3D printers were first made in 1986 using SLA method and entered the market two years later.

The electromechanical analysis of a piezoresistive pressure microsensor with a square-shaped diaphragm for low-pressure biomedical applications is presented. This analysis is developed through a novel model and a finite element method (FEM) model. A microsensor with a diaphragm 1000 „m length and with thickness=400 µm is studied. The electric response of this microsensor is obtained with applying voltage into senseor in p-type piezoresistors located on the diaphragm surface. The diaphragm that is 10 „m thickexhibits a maximum deflection of 3.74 „m using the designed model, which has a relative difference of 5.14 and 0.92% with respect to the comsol model, respectively. The maximum sensitivity and normal stress calculated using the this model are 1.64 mV/V/kPa and 102.1 MPa, respectively. The results of the polynomial model agree well with the Timoshenko model and FEM model for small deflections. In addition, the designed model can be easily used to predict the deflection, normal stress, electric response and sensitivity of a piezoresistive pressure microsensor with a square-shaped diaphragm under small deflections.

Magnetic Resonance Imaging (MRI) is a noninvasive imaging method widely used in medical diagnosis. Data in MRI are obtained line-by-line within the K-space, where there are usually a great number of such lines. For this reason, magnetic resonance imaging is slow. MRI can be accelerated through several methods such as parallel imaging and compressed sensing, where a fraction of the K-space lines is obtained. According to the advanced mathematical theories about compressed sensing, images entailing sparse representation within a certain area can be restored through a random sub sampling of K-space data. MRI images are often sparse in an appropriate conversion range, where imaging speed can be significantly improved through the compressed sensing theory. The complete random sub sampling of K-space creates an extremely high degree of incoherent artifacts for simplifying the mathematical calculations. Random sampling of K-space points is generally impractical in all dimensions, because the K-space paths will be smooth only when hardware and physiological considerations have been met. Our goal is to design practical decoherence sub sampling models simulating the interference properties of the pure random sub sampling until it is possible to quickly gather information. This paper introduces 3 sub sampling techniques for K-space data, providing the best efficiency in the production of sparse incoherent artifacts based on the compressed sensing theory. All the proposed methods were simulated on real-life data compared against the MRI results.