arXiv subjects

Ismaila Idris

Publications and source records attributed to Ismaila Idris.

3 recordsLinked to original sources

arXiv2015

Tasks Scheduling Technique Using League Championship Algorithm for Makespan Minimization in IaaS Cloud

Makespan minimization in tasks scheduling of infrastructure as a service (IaaS) cloud is an NP-hard problem. A number of techniques had been used in the past to optimize the makespan time of scheduled tasks in IaaS cloud, which is propotional to the execution cost billed to customers. In this paper, we proposed a League Championship Algorithm (LCA) based makespan time minimization scheduling technique in IaaS cloud. The LCA is a sports-inspired population based algorithmic framework for global optimization over a continuous search space. Three other existing algorithms that is, First Come First Served (FCFS), Last Job First (LJF) and Best Effort First (BEF) were used to evaluate the performance of the proposed algorithm. All algorithms under consideration assumed to be non-preemptive. The results obtained shows that, the LCA scheduling technique perform moderately better than the other algorithms in minimizing the makespan time of scheduled tasks in IaaS cloud.

cs.DC↗

arXiv2014

Design Evaluation of Some Nigerian University Portals: A Programmer's Point of View

Today, Nigerian Universities feel pressured to get a portal up and running dynamic, individualized web systems have become essential for institutions of higher learning. As a result, most of the Nigerian University portals nowadays do not meet up to standard. In this paper, ten Nigerian University portals were selected and their design evaluated in accordance with the international best practices. The result was revealing.

cs.CY↗

arXiv2014

An Improved AIS Based E-mail Classification Technique for Spam Detection

An improved email classification method based on Artificial Immune System is proposed in this paper to develop an immune based system by using the immune learning, immune memory in solving complex problems in spam detection. An optimized technique for e-mail classification is accomplished by distinguishing the characteristics of spam and non-spam that is been acquired from trained data set. These extracted features of spam and non-spam are then combined to make a single detector, therefore reducing the false rate. (Non-spam that were wrongly classified as spam). Effectiveness of our technique in decreasing the false rate shall be demonstrated by the result that will be acquired.

cs.CR↗