Ziegler and Nichols proposed the well-known Ziegler-Nichols method to tune the coefficients of PID controller. This tuning method is simple and gives fixed values for the coefficients which make PID controller have weak adaptabilities for the model parameters variation and changing in operating conditions. In order to achieve adaptive controller, the Neural Network (NN) self-tuning PID control is proposed in this paper which combines conventional PID controller and Neural Network learning capabilities. The proportional, integral and derivative (KP, KI, KD) gains are self tuned on-line by the NN output which is obtained due to the error value on the desired output of the system under control. The conventional PID controller in the robot manipulator is replaced by NN self tuning PID controller so as to achieve trajectory tracking with minimum steady-state error and improving the dynamic behavior (overshoot). The simulation results showed that the proposed controller has strong self-adaptability over the conventional PID controller.
Background: Early detection of subclinical left ventricular (LV) systolic dysfunction is crucial and could influence patients' prognosis by aiding the clinician to candidate patients for better management.
Objective: To detect early LV systolic dysfunction in asymptomatic patient with chronic aortic regurgitation by two dimensional speckle tracking echocardiography.
Methods: Sixty one asymptomatic patients with chronic aortic regurgitation, with no ischemic heart diseases (by coronary angiography) or conductive heart diseases, no diabetes mellitus, no hypertension, and no other valvular heart diseases (group 1) and fifty age and sex-matched healthy subjects (
... Show More
Imitation learning is an effective method for training an autonomous agent to accomplish a task by imitating expert behaviors in their demonstrations. However, traditional imitation learning methods require a large number of expert demonstrations in order to learn a complex behavior. Such a disadvantage has limited the potential of imitation learning in complex tasks where the expert demonstrations are not sufficient. In order to address the problem, we propose a Generative Adversarial Network-based model which is designed to learn optimal policies using only a single demonstration. The proposed model is evaluated on two simulated tasks in comparison with other methods. The results show that our proposed model is capable of completing co
... Show More
* مشكلة البحث والحاجة اليه:
تأتي أهمية هذا العلم وقوته ومدى الحاجة اليه لكل الناس وخاصة اللذين يريدون أن يغيروا عاداتهم السيئة ويأثروا في غيرهم ، أذ اكد المفكرون والقادة والمصلحون ورجال التربية أنه يجب على الإنسان ان يكون مثابراً ومجتهداً ومتقناً لعمله ، ومنظماً لوقته الى اخر القائمة الطويلة من مفردات الجودة ولم يقولوا كيف يمكن للانسان ان يفعل ذلك ؟ أن علم الهندسة النفسية استطاع ان يجيب. 
... Show MoreThe research focuses on determination of best location of high elevated tank using the required head of pump as a measure for this purpose. Five types of network were used to find the effect of the variation in the discharge and the node elevation on the best location. The most weakness point was determined for each network. Preliminary tank locations were chosen for test along the primary pipe with same interval distance. For each location, the water elevation in tank and pump head was calculated at each hour depending on the pump head that required to achieve the minimum pressure at the most weakness point. Then, the sum of pump heads through the day was determined. The results proved that there is a most economical lo
... Show More
(1)
In this paper, the process for finding an approximate solution of nonlinear three-dimensional (3D) Volterra type integral operator equation (N3D-VIOE) in R3 is introduced. The modelling of the majorant function (MF) with the modified Newton method (MNM) is employed to convert N3D-VIOE to the linear 3D Volterra type integral operator equation (L3D-VIOE). The method of trapezoidal rule (TR) and collocation points are utilized to determine the approximate solution of L3D-VIOE by dealing with the linear form of the algebraic system. The existence of the approximate solution and its uniqueness are proved, and illustrative examples are provided to show the accuracy and efficiency of the model.
Mathematical Subject Classificat
... Show More
(5)
(1)
Passive optical network (PON) is a point to multipoint, bidirectional, high rate optical network for data communication. Different standards of PONs are being implemented, first of all PON was ATM PON (APON) which evolved in Broadband PON (BPON). The two major types are Ethernet PON (EPON) and Gigabit passive optical network (GPON). PON with these different standards is called xPON. To have an efficient performance for the last two standards of PON, some important issues will considered. In our work we will integrate a network with different queuing models such M/M/1 and M/M/m model. After analyzing IPACT as a DBA scheme for this integrated network, we modulate cycle time, traffic load, throughput, utilization and overall delay
... Show MoreThe integration of gender in urban studies is considered a goal and objective to build a society characterized by justice and equality. It further allows all its residents to enjoy the opportunities to live in a safe urban life. Based on the that, the limitations of the research and its field of interest related to the relationship between gender and urban studies have become clear. The insufficient knowledge in this regard considers gender as a concept that does not exist in itself, but rather overlaps and intersects with several concepts and studies, including urban studies. Thus, it has become necessary to adopt a descriptive methodology that helps reach a theoretical framework to explain the beginnings of such an interaction and inte
... Show More
In this paper, we derive and prove the stability bounds of the momentum coefficient µ and the learning rate ? of the back propagation updating rule in Artificial Neural Networks .The theoretical upper bound of learning rate ? is derived and its practical approximation is obtained
Artificial Neural Networks (ANN) is one of the important statistical methods that are widely used in a range of applications in various fields, which simulates the work of the human brain in terms of receiving a signal, processing data in a human cell and sending to the next cell. It is a system consisting of a number of modules (layers) linked together (input, hidden, output). A comparison was made between three types of neural networks (Feed Forward Neural Network (FFNN), Back propagation network (BPL), Recurrent Neural Network (RNN). he study found that the lowest false prediction rate was for the recurrentt network architecture and using the Data on graduate students at the College of Administration and Economics, Univer
... Show More
The aim of this paper is to approximate multidimensional functions f∈C(R^s) by developing a new type of Feedforward neural networks (FFNS) which we called it Greedy ridge function neural networks (GRGFNNS). Also, we introduce a modification to the greedy algorithm which is used to train the greedy ridge function neural networks. An error bound are introduced in Sobolov space. Finally, a comparison was made between the three algorithms (modified greedy algorithm, Backpropagation algorithm and the result in [1]).