arXiv subjects

SeyedMehdi Abtahi

Publications and source records attributed to SeyedMehdi Abtahi.

3 recordsLinked to original sources

arXiv2022

An adaptive neuro-fuzzy model for attitude estimation and 2 control a 3 DOF system

In recent decades, one of the scientists' main concerns has been to improve the accuracy of satellite attitude, regardless of the expense. The obvious result is that a large number of control strategies have been used to address this problem. In this study, an adaptive neuro-fuzzy integrated (ANFIS) satellite attitude estimation and control system was developed. The controller is trained with the data provided by an optimal controller. A pulse modulator is used to generate the right ON/OFF commands of the thruster actuator. To evaluate the performance of the AN-FIS controller in closed-loop simulation, an ANFIS observer is used to estimate the attitude and angular velocities of the satellite using magnetometer, sun sensor and data gyro data. In addition, a new ANFIS system will be proposed and evaluated that can jointly control and estimate the system. The performance of the ANFIS controller is compared to the optimal PID controller in a Monte Carlo simulation with different initial conditions, disturbance and noise. The results show that the ANFIS controller can surpass the optimal PID controller in several aspects, including time and smoothness. In addition, the ANFIS estimator is examined and the results demonstrate the high ability of this designated observers. Both the control and estimation phases are simulated by a single ANFIS subsystem, taking into account the high capacity of ANFIS, and the results of using the ANFIS model are demonstrated.

eess.SY↗

arXiv2020

Machine Learning Method Used to find Discrete and Predictive Treatment of Cancer

Cancer is one of the most common diseases worldwide, posing a serious threat to human health and leading to the deaths of a large number of people. It was observed during the drug administration in chemotherapy that immune cells, cancer cells and normal cells are killed or at least seriously injured and also in order to keep dosage of the drug at specific level in body, drug should be delivered in specific time and dosage. Therefore, to address these problems, a decision-making process is needed to identify the most appropriate treatment for cancer cases which causes killing of cancer cells by considering the number of healthy cells that would be killed. Despite the latest technological developments, the current methods need to be improved to suggest the most optimized a dose of the drug for tumor cells discretely. It is expected that our proposed ANFIS model be able to suggest the specialists the most optimum dose of the drug, which considers all key factors including cancer cells, immune and health cells. The results of the simulations exhibit the high accuracy of the proposed intelligent controller during the treatment in predicting the behavior of all key factors and minimize the usage dose of the drug with regard this significant point that the proposed controller gives discrete data for treatment which can fill the gap between engineering and medical science.

q-bio.QM↗

arXiv2020

Machine Learning Method to Control and Observe for Treatment and Monitoring of Hepatitis B Virus

Hepatitis type B is one of the most common infectious disease worldwide that can pose severe threats to human health up to the point that may contribute to severe liver damage or cancer. Over the past two decades a large number of dynamic models have been presented based on experimental data to predict the HBV infection behavior. Besides, several kinds of controllers have been employed to obtain effective solutions from the HBV treatment. In this essay we consider the nonlinear HBV dynamic model which subjected to both parametric and non-parametric uncertainties without using any linearization. In previous control methods three HBV dynamic states should be measured virus safe, and infected cells. However in most of the biological systems, the amount of virus is experimentally measured. Accordingly, the necessity to seek a method that can estimate the amount of required drug by receiving the virus data emerges. An ANFIS method is developed in this work to provide an intelligent controller for the drug dosage based on the number of viruses together with an estimator for the amount of infected and uninfected cells. This controller is trained first using the data provided from a previous adaptive control strategy. After that to improve the closed-loop system capabilities two unmeasured state variables of fundamental dynamics are estimated through the training phase of the ANFIS observer. The results of simulations demonstrated that the accuracy of the proposed intelligent controller is high in the tracking of the desired descending virus population.

q-bio.QM↗