Network security is defined as a set of policies and actions taken by a network administrator in order to prevent unauthorized access, penetrated the defenses and infiltrated the network from unnecessary intervention. The network security also involves granting access to data using a pre-defined policy. A network firewall, on the other hand, is a network appliance that controls incoming and outgoing traffic by examining the traffic flowing through the network. This security measure establishes a secure wall [firewall] between a trusted internal network and the outside world were a security threat in shape of a hacker or a virus might have existed

In this paper we describe several different training algorithms for feed forward neural networks(FFNN). In all of these algorithms we use the gradient of the performance function, energy function, to determine how to adjust the weights such that the performance function is minimized, where the back propagation algorithm has been used to increase the speed of training. The above algorithms have a variety of different computation and thus different type of form of search direction and storage requirements, however non of the above algorithms has a global properties which suited to all problems.

Feature selection algorithms play a big role in machine learning applications. There are several feature selection strategies based on metaheuristic algorithms. In this paper a feature selection strategy based on Modified Artificial Immune System (MAIS) has been proposed. The proposed algorithm exploits the advantages of Artificial Immune System AIS to increase the performance and randomization of features. The experimental results based on NSL-KDD dataset, have showed increasing in performance of accuracy compared with other feature selection algorithms (best first search, correlation and information gain).

In this paper, we established a mathematical model of an SI1I2R epidemic disease with saturated incidence and general recovery functions of the first disease I1. Considering the basic reproduction number, we obtained conditions for both disease-free and co-existing cases. The equilibrium points local stability is verified by using the Routh-Hurwitz criterion, while for the global stability, we used a suitable Lyapunov function to analyze the endemic spread of the positive equilibrium point. Moreover, we carried out the local bifurcation around both equilibrium points (disease-free and co-existing), where we obtained that the disease-free equilibrium point undergoes a transcritical bifurcation. We conduct numerical simulations that suppo

Joint diseases, such as osteoarthritis, induce pain and loss of mobility to millions of people around the world. Current clinical methods for the diagnosis of osteoarthritis include X-ray, magnetic resonance imaging, and arthroscopy. These methods may be insensitive to the earliest signs of osteoarthritis. This study investigates a new procedure that was developed and validated numerically for use in the evaluation of cartilage quality. This finite element model of the human articular cartilage could be helpful in providing insight into mechanisms of injury, effects of treatment, and the role of mechanical factors in degenerative
conditions, this three-dimensional finite element model is a useful tool for understanding of the stress d

Introduction: This study was designed to examine the effects of addition of the combination of polymerized polymethyl methacrylate (PMMA) and zirconia (ZrO2) particles to heat cure PMMA resin on impact strength, surface hardness, and roughness. Methods: The 70% (w/w) of polymerized PMMA powder (particle size: 0.70mm) was mixed with 30% (w/w) of zirconia powder (ZrO2) (1mm) to produce PMMA-ZrO2 filler. Ninety acrylic specimens created were divided into three groups containing 0% wt (Control group), 2% wt, and 4% wt, PMMA-ZrO2 filler. Ten specimens were used for impact strength, surface hardness and roughness test, blindly. Data were analyzed via oneway ANOVA and the Tukey post hoc test using R 3.6.3. Results: There was statistically signific

Codes of red, green, and blue data (RGB) extracted from a lab-fabricated colorimeter device were used to build a proposed classifier with the objective of classifying colors of objects based on defined categories of fundamental colors. Primary, secondary, and tertiary colors namely red, green, orange, yellow, pink, purple, blue, brown, grey, white, and black, were employed in machine learning (ML) by applying an artificial neural network (ANN) algorithm using Python. The classifier, which was based on the ANN algorithm, required a definition of the mentioned eleven colors in the form of RGB codes in order to acquire the capability of classification. The software's capacity to forecast the color of the code that belongs to an ob

Codes of red, green, and blue data (RGB) extracted from a lab-fabricated colorimeter device were used to build a proposed classifier with the objective of classifying colors of objects based on defined categories of fundamental colors. Primary, secondary, and tertiary colors namely red, green, orange, yellow, pink, purple, blue, brown, grey, white, and black, were employed in machine learning (ML) by applying an artificial neural network (ANN) algorithm using Python. The classifier, which was based on the ANN algorithm, required a definition of the mentioned eleven colors in the form of RGB codes in order to acquire the capability of classification. The software's capacity to forecast the color of the code that belongs to an object under de