Modeling and control of COVID-19 disease using deep reinforcement learning method.

The prevalence of epidemics has been studied by researchers in various fields. In the last 2 years, the outbreak of COVID-19 has affected the health, economy, and industry of communities around the world and has caused the death of millions of people. Therefore, many researchers have tried to model and control the prevalence of this disease. In this article, the new SQEIAR model for the spread of the COVID-19 disease is provided, which, compared to previous models, explores the effects of additional interventions on the outbreak and incorporates a wider range of variables and parameters to enhance its accuracy and alignment with reality. These modifications in the model lead to a more rapid eradication and control of the disease. This model includes six variables of the group of susceptible, quarantined, exposed, symptomatic, asymptomatic, and recovered individuals and includes three control inputs such as quarantine of susceptible, vaccination, and treatments. In order to minimize symptomatic infectious individuals and susceptible individuals and also to reduce treatment, vaccination, and quarantine costs, an optimal control approach using the Deep Deterministic Policy Gradient (DDPG) method has been applied to the system. This algorithm is applied to the model in different cases of control inputs, and for each case, optimal control inputs are obtained. In the following, the number of deaths due to the disease and the total number of symptomatic infectious individuals for each of these optimal control cases has been calculated. The results of the implemented control structure demonstrated a reduction of 60% in the number of deaths and 74% in the number of symptomatically infected individuals compared to the uncontrolled model. Finally, to test the performance of the control system, noise was applied to the system in various ways, including three methods: applying noise to observer variables, applying noise to control inputs, and applying uncertainty to model parameters. Therefore, we found that this control system was robust and performed well in different conditions despite the disturbance.

Tracking ankle joint movements during gait cycle via control of functional electrical stimulation.

Functional electrical stimulation (FES) is an effective method to induce muscle contraction and to improve movements in individuals with injured central nervous system. In order to develop the FES systems for an individual with gait impairment, an appropriate control strategy must be designed to accurate tracking performance. The goal of this study is to present a method for designing proportional-derivative (PD) and sliding mode controllers (SMC) for the FES applied to the musculoskeletal model of an ankle joint to track the desired movements obtained by experiments on two healthy individuals during the gait cycle. Simulation results of the developed controller on musculoskeletal model of the ankle joint illustrated that the SMC is able to track the desired movements more accurately than the PD controller and prevents oscillating patterns around the experimentally measured data. Therefore, the sliding mode as the nonlinear method is more robust in face to unmodeled dynamics and model errors and track the desired path smoothly. Also, the required control effort is smoother in SMC with respect to the PD controller because of the nonlinearity.

Optimal control methods for drug delivery in cancerous tumour by anti-angiogenic therapy and chemotherapy.

There are numerous mathematical models simulating the behaviour of cancer by considering variety of states in different treatment strategies, such as chemotherapy. Among the models, one is developed which is able to consider the blood vessel-production (angiogenesis) in the vicinity of the tumour and the effect of anti-angiogenic therapy. In the mentioned-model, normal cells, cancer cells, endothelial cells, chemotherapy and anti-angiogenic agents are taking into account as state variables, and the rate of injection of the last two are considered as control inputs. Since controlling the cancerous tumour growth is a challenging matter for patient's life, the time schedule design of drug injection is very significant. Two optimal control strategies, an open-loop (calculus of variations) and a closed-loop (state-dependent Riccati equation), are applied on the system in order to find an optimal time scheduling for each drug injection. By defining a proper cost function, an optimal control signal is designed for each one. Both obtained control inputs have reasonable answers, and the system is controlled eventually, but by comparing them, it is concluded that both methods have their own benefits which will be discussed in details in the conclusion section.

Fluttering and divergence instability of functionally graded viscoelastic nanotubes conveying fluid based on nonlocal strain gradient theory.

In this paper, a size-dependent viscoelastic pipe model is developed to investigate the size effects on flutter and divergence instability of functionally graded viscoelastic nanotubes conveying fluid. The nonlocal strain gradient theory and the Kelvin-Voigt model are used to consider the significance of nonlocal field, strain gradient field, and viscoelastic damping effects. The dimensionless equation of transverse motion and related classical and non-classical boundary conditions are derived using the variational approach. The partial differential equations are discretized to a system of ordinary differential equations by the use of Galerkin's method. The frequency equation is obtained as a function of dimensionless flow velocity, small-scale parameters, damping coefficient, and power-law parameter. Numerical results are presented to study the dynamical behavior of the system and are compared with experimental and theoretical results reported by other researchers. Coupled and single mode fluttering related to higher vibration modes of fluid-conveying nanotubes supported at both ends are studied for the first time. It is found that coupled mode fluttering can be seen for different vibration modes by increasing the flow velocity in the absence of structural damping. Structural damping changes the dynamical behavior of the system, in which by increasing the flow velocity, single mode fluttering occurs instead of coupled mode fluttering. In addition, the presence of structural damping increases the critical flow velocity and, as a result, increases the stability of the system. The results also show that increasing the nonlocal parameter will have a stiffness-softening effect, while increasing the strain gradient length scale has an opposing effect.

Optimal sliding mode control of drug delivery in cancerous tumour chemotherapy considering the obesity effects.

Different control strategies have been proposed for drug delivery in chemotherapy during recent years. These control algorithms are designed based on dynamic models of various orders. The order of the model depends on the number of effects considered in the model. In a recent model, the effect of obesity on the tumour progression and optimal control strategy in chemotherapy have been investigated in a fifth-order state-space model. However, the optimal controller is open loop and not robust to the common uncertainties of such biological system. Here, the sliding surface is obtained by the optimal trajectory and by considering uncertainties of some parameters, the robust-sliding control law is formulated in a way to slid on the optimal surface. Then, a sliding mode controller is designed to determine the drug dose rate such that the system follows the optimal desired trajectory. The stability of the control system is proved and the simulation results indicate that three states track the trajectory and the remaining two states satisfy the constraints.

Autoregressive-moving-average hidden Markov model for vision-based fall prediction-An application for walker robot.

Population aging of the societies requires providing the elderly with safe and dependable assistive technologies in daily life activities. Improving the fall detection algorithms can play a major role in achieving this goal. This article proposes a real-time fall prediction algorithm based on the acquired visual data of a user with walking assistive system from a depth sensor. In the lack of a coupled dynamic model of the human and the assistive walker a hybrid "system identification-machine learning" approach is used. An autoregressive-moving-average (ARMA) model is fitted on the time-series walking data to forecast the upcoming states, and a hidden Markov model (HMM) based classifier is built on the top of the ARMA model to predict falling in the upcoming time frames. The performance of the algorithm is evaluated through experiments with four subjects including an experienced physiotherapist while using a walker robot in five different falling scenarios; namely, fall forward, fall down, fall back, fall left, and fall right. The algorithm successfully predicts the fall with a rate of 84.72%.