@article { author = {Tawfik, Medhat and Bahgat, Ashraf and Keshk, Arabi and Torkey, F.}, title = {Artificial Bee Colony Algorithm for Cloud Task Scheduling}, journal = {IJCI. International Journal of Computers and Information}, volume = {4}, number = {1}, pages = {1-10}, year = {2015}, publisher = {Minufiya University; Faculty of Computers and Information}, issn = {1687-7853}, eissn = {2735-3257}, doi = {10.21608/ijci.2015.33956}, abstract = {Cloud computing services are becoming ubiquitous, and are becoming the primary source of computing power for both enterprises and personal computing applications. One of the fundamental issues in this environment is related to task scheduling. The scheduler should do the scheduling process efficiently in order to utilize the available resources. In this paper a cloud task scheduling policy based on artificial bee colony algorithm compared with different scheduling algorithms has been proposed. The main goal of the proposed algorithm is minimizing the makespan of a given tasks set. Artificial bee colony algorithm models the behavior of honey bees and can be used to find solutions for difficult or impossible combinatorial problems. Algorithms have been simulated using Cloudsim toolkit package. Experimental results showed that the artificial bee colony algorithm outperformed ACO, FPLTF and FCFS algorithms.}, keywords = {Cloud Computing,task scheduling,make span,artificial bee colony}, url = {https://ijci.journals.ekb.eg/article_33956.html}, eprint = {https://ijci.journals.ekb.eg/article_33956_00e14724271769d23b7067336027d6de.pdf} } @article { author = {Ahmed, Hatem and Salem, Rashed and Saleh, Safa'a}, title = {Clustering Algorithm for Distributed Real-Time Database sites}, journal = {IJCI. International Journal of Computers and Information}, volume = {4}, number = {1}, pages = {11-20}, year = {2015}, publisher = {Minufiya University; Faculty of Computers and Information}, issn = {1687-7853}, eissn = {2735-3257}, doi = {10.21608/ijci.2015.33957}, abstract = {The demand for real-time database is increasing. Indeed, most real-time systems are inherently distributed in nature andneed to handle data in a timely fashion. Obtaining data from remote sites may take long time making the temporal data invalid. This results in large number of tardy transactions with their catastrophic effect. Clustering the database sites nodes can help distributed real-time database systems to face the challenges meeting their time requirements. Reducing the large number of network sites into many clusters with smaller number of sites will effectively decrease the response time, resulting in better meeting of time constraints. In this paper, we introduce a clustering algorithm for distributed real-time database that depend on both the communication time cost and the timing properties of data. The results show the effectiveness of the proposed approach via achieving lower communication time, higher database performance and better meeting of timing requirements.}, keywords = {Clustering,Database,real-time distributed systems}, url = {https://ijci.journals.ekb.eg/article_33957.html}, eprint = {https://ijci.journals.ekb.eg/article_33957_2506b47d05c5cdbfa26a9bdaa0363dcb.pdf} } @article { author = {Elgendy, Ibrahim and Shams, M. and Keshk, Arabi}, title = {A lightweight Framework for Improving the Mobile Applications Performance}, journal = {IJCI. International Journal of Computers and Information}, volume = {4}, number = {1}, pages = {21-28}, year = {2015}, publisher = {Minufiya University; Faculty of Computers and Information}, issn = {1687-7853}, eissn = {2735-3257}, doi = {10.21608/ijci.2015.33958}, abstract = {In Recent years, the smartphones have exploded in popularity and set to become the fastest spreading technology. Thesedevices have wide range of capabilities like more processing, more storage, GPS, Wi-Fi, camera, and others. As a result, the developer trends to build a complex application such as augmented reality, face detection, image processing and speech recognition. Although the capabilities that smartphones support, these applications require more processing and consume more battery. Therefore, the researchers trend to solve this problem by using rich resources such as cloud computing to support the mobile devices for execution these application. Where the mobile device offload these applications or part of it to be executed remotely on the cloud. This paper will introduce a lightweight framework to improve the performance of mobile applications and save the battery consumption. This framework have a core module which so-called dynamic offloader. This module determines dynamically at run time the decision for the offloading process based on the current environment. The experimental results are applied on Gaussian blur filter application and thisresults proved that this lightweight framework improves the performance and saves energy of mobile applications.}, keywords = {Smartphones,Android,Computation Offloading,Mobile Cloud Computing,Battery Consumption,Lightwight Framework}, url = {https://ijci.journals.ekb.eg/article_33958.html}, eprint = {https://ijci.journals.ekb.eg/article_33958_6e8e13d0c37c9843918e291aaf50f739.pdf} } @article { author = {Malhat, M. and Mousa, Hamdy}, title = {Evaluating Parallel Ward Algorithm for Drug Discovery}, journal = {IJCI. International Journal of Computers and Information}, volume = {4}, number = {1}, pages = {29-35}, year = {2015}, publisher = {Minufiya University; Faculty of Computers and Information}, issn = {1687-7853}, eissn = {2735-3257}, doi = {10.21608/ijci.2015.33959}, abstract = {Millions of compounds are now available in chemical libraries and scientists have to test these compounds againstbiological targets in order to identify lead compounds. The identification of lead compounds is a key step in the drug discovery process. So, there are many hierarchical clustering algorithms are developed and modified for that purpose. Ward algorithm is one of the most popular hierarchical clustering algorithms that are used in many applications in the drug discovery process because of it is accuracy. But, it has limitation to handle large data sets within a reasonable time and memory resources. In this paper, we evaluate and compare two parallel approaches to run ward algorithm. The two approaches are parallel for loop and MapReduce framework. The results shows that parallel for loop failed to reduce computational time of ward algorithm due to overhead needed for data communications. But, MapReduce framework shows considerable reduction in computational time. The parallel ward algorithm saves 17% of time usingthree nodes and saves 58% of time using six nodes using MapReduce.}, keywords = {Drug Discovery,Hierarchical Clustering,Ward Clustering,Parallel for,MapReduce}, url = {https://ijci.journals.ekb.eg/article_33959.html}, eprint = {https://ijci.journals.ekb.eg/article_33959_fd9eb763c68464cb818995cbc9f5f3b9.pdf} } @article { author = {Samy, Ahmed and Semary, N. and Ahmed, Hatem}, title = {Comparative Study of Load Balancing Techniques in Mobile WiMAX IEEE 802.16e}, journal = {IJCI. International Journal of Computers and Information}, volume = {4}, number = {1}, pages = {37-47}, year = {2015}, publisher = {Minufiya University; Faculty of Computers and Information}, issn = {1687-7853}, eissn = {2735-3257}, doi = {10.21608/ijci.2015.33960}, abstract = {Mobile Worldwide Interoperability for Microwave Access (Mobile WiMAX) is a wireless Metropolitan Area Network technology based on IEEE 802.16e standard. Mobile WiMAX has been designed with the purpose of enabling mobile Internet from the physical layer to the network layer. In this paper, a comparative study between load balancing techniques in mobile WiMAX is presented. These techniques are Spare Capacity Procedure (SCP) and WiMAX QOS Aware Load Balancing Protocol (WQLP). These load balancing techniques used when network congestion occurred in Mobile WiMAX networks. These two techniques represent the major trends of load balancing in Mobile WiMAX IEEE 802.16e technology. These techniques use directed handovers for Load Balancing (LB) among cells; these handovers were initiated by the Serving Base Station. Performance of load balancing techniques have been analyzed and evaluated based on an extensive simulation. The simulation shows that the performance of WQLP is better than SCP in load distribution but SCP is faster than WQLP in handover process. The elaborated performance analysis shows a set of advantages and disadvantages of these techniques. This evaluation study represents an important entry point for choosing the besttechniques that can distribute load among BSs and guarantee QoS for all MSs using real-time applications. }, keywords = {Mobile WiMAX,Load Balancing,Forced Handover,Quality of service}, url = {https://ijci.journals.ekb.eg/article_33960.html}, eprint = {https://ijci.journals.ekb.eg/article_33960_eda6efb38cd500a1207b776f4017d698.pdf} }