Abstract:The timetabling is a difficult problem, which is an element of the widen field of Scheduling. The scheduling problems belong to NP hard problems and are defined as an allocation problem of resources over time. The classes or lectures timetabling problem is usually solved by hand and taking several days or weeks of repair after feedback from staff and students in departments. This paper proposed an improved algorithm to solve lectures timetabling problem using genetic algorithm (GA), which has enhanced performance especially because the modification of genetic algorithm behavior. This paper also shows implementation details of timetabling software solution, which employs GA for finding an optimal solution of timetabling problem and generating lectures timetables by using real datasets and constraints from the departments at University of Science and Technology, IBB branch (hinted in the paper as college), Yemen. This software was developed by using C# to program genetic algorithm interface and using SQL Server database to store optimal timetables and college information.

No abstract

This paper introduces two new forms of the hidden discrete logarithm problem defined over a finite non-commutative associative algebras containing a large set of global single-sided units. The proposed forms are promising for development on their base practical post-quantum public key-agreement schemes and are characterized in performing two different masking operations over the output value of the base exponentiation operation that is executed in framework of the public key computation. The masking operations represent homomorphisms and each of them is mutually commutative with the exponentiation operation. Parameters of the masking operations are used as private key elements. A 6-dimensional algebra containing a set of p3 global left-sided units is used as algebraic support of one of the hidden logarithm problem form and a 4-dimensional algebra with p2 global right-sided units is used to implement the other form of the said problem. The result of this paper is the proposed two methods for strengthened masking of the exponentiation operation and two new post-quantum public key-agreement cryptoschemes. Mathematics subject classification: 94A60, 16Z05, 14G50, 11T71, 16S50.

Drug interactions prediction is one of the health critical issues in drug producing and use. Proposing computational model for classifying and predicting interactions of drugs with high precision is a difficult problem. Medicines are classified into two classes: overlapping, non-overlapping. It was suggested an expert system for classifying and predicting interactions of drugs using various information about drugs, interference reasons and common factors between patients and active substance that causes interference, such as: effective dose of the drug, maximum dose, times of use per day and age of patients considering that only adult category selected. The proposed model can classify and predict interactions of drugs through patient's state taking into consideration that when changing one of mentioned factors, the effect of drugs will be changed and it may lead to appear new symptoms on the patients. There is a desktop application related with the mentioned model, which helps users to know drugs and drugs families and its interactions. Proposed model will be implemented in Python using following classifiers: Logistic Regression (LR), Support Vector Machine (SVM) and Neural Network (NN), which divided data according to their similarity related to the factors of occurrence of drug interference. As these techniques showed good results, NN technology is considered one of the best techniques in giving results where MLPClassifier achieved superior performance with 97.12%.