Face expression recognition technology is one of the most recently developed fields in machine learning and has profoundly helped its users through forensic, security, and biometric applications. Many researchers and program developers have allocated their time and energy to figure out various techniques which would add to the technology’s functionality and accuracy. Face expression recognition is a complicated computational process in which is implemented via analyzing changes in facial traits that follow different emotional reactions. This paper endeavors to inspect accuracy ratio of six classifiers based on Relief-F feature selection method, relying on the utilization of the minimum quantity of attributes. The classifiers in which the paper attempts to inspect are Multi-Layer Perceptron, Random Forest, Decision Tree, Support Vector Machine, K-Nearest Neighbor, and Radial Basis Function. The experiment illustrates that K-Nearest Neighbor is the most accurate classifier with the total accuracy ratio of 94.93% amongst the rest when applied on CK+ Dataset.

The demand for setting up a wireless LAN internet connectivity is almost mandatory for every commercial building, home, company, and educational institutions. With the growing number and height of buildings as well as the number of users, it has become essential to apply new techniques to provide better wireless network services, especially for security issue with many applications used by an attacker that can decrypt the traditional password to use network resources, that’s lead to poor network performance for providing network services for people authorized to use it. All of that is almost a very challenge issue when applying outdated techniques. In this research a wireless network has been created considering a large number of users in a multi-floor building using a new control system which can solve the problems by setting up RADIUS authentication via that wireless network with a webpage that automatically appears to the user immediately after connecting to the wireless radio signal and automatically gaining an IP address, lead user directly to the temporary page asking him for  authentication, if the user has the right username and password or even sometimes a code called Voucher, he will get a package assigned to his priority. This technology will eliminate the vulnerability on the wireless connection and the unauthorized user will be discarded from the router, in addition of that authorized users will get authenticated to make better use of network resources.

In this research, a (RADC-AO) tool was constructed and implemented for the requirements analysis, design and stub-code generation according to aspect-oriented (AO) concepts based on theme approach. RADC-AO automatically identifies crosscutting concerns in natural language requirements text by using natural language processing (NLP), analyze requirements and apply a set of operations on themes got in the analysis process, design classes and aspects, draw class diagram, and generates stubcode. RADC-AO tested by input complete informal text requirements for payroll system (that contains security, logging, authorization, in addition to its core functionality which includes employees information entering, loans information entering, and payment calculation), RADC-AO successes in the test and gives good results.