@article { author = {AL-Sammarraie, N and Alrahmawy, M and Rashad, M}, title = {A SCHEDULING ALGORITHM TO ENHANCE THE PERFORMANCE AND THE COST OF CLOUD SERVICES}, journal = {International Journal of Intelligent Computing and Information Sciences}, volume = {15}, number = {1}, pages = {1-14}, year = {2015}, publisher = {Ain Shams University, Faculty of Computer and Information Science}, issn = {1687-109X}, eissn = {2535-1710}, doi = {10.21608/ijicis.2015.10906}, abstract = {Cloud computing is based on the pay-per-use; hence, the price of usage is one of the mainfactors for cloud services’ customers when selecting the cloud provider to rent the service from. Hence,cloud providers need to provide competitive costs of the services for the users. Therefore, the cloudproviders, in addition to optimize the utilization of the resources, aim to provide the service with thecompetitive cost at the same time. In order to achieve this, there is a need for a new set of economicaltask scheduling algorithms for the cloud. This paper introduces an algorithm for task scheduling basedon assigning priorities for tasks according to their profits, where we provided examples of usage of thealgorithm and compared it to some of the traditional cloud scheduling algorithms.}, keywords = {}, url = {https://ijicis.journals.ekb.eg/article_10906.html}, eprint = {https://ijicis.journals.ekb.eg/article_10906_199142afe733104bab8fbf659dcd4497.pdf} } @article { author = {Mohammed, F and ALdaidamony, E and Raid, A}, title = {IRIS AND FINGER VEIN MULTI MODEL RECOGNITION SYSTEM BASED ON SIFT FEATURES}, journal = {International Journal of Intelligent Computing and Information Sciences}, volume = {15}, number = {1}, pages = {15-24}, year = {2015}, publisher = {Ain Shams University, Faculty of Computer and Information Science}, issn = {1687-109X}, eissn = {2535-1710}, doi = {10.21608/ijicis.2015.10907}, abstract = {Individual identification process is a very significant process that resides a large portion ofday by day usages. Identification process is appropriate in work place, private zones, banks …etc.Individuals are rich subject having many characteristics that can be used for recognition purpose suchas finger vein, iris, face …etc. Finger vein and iris key-points are considered as one of the most talentedbiometric authentication techniques for its security and convenience. SIFT is new and talentedtechnique for pattern recognition. However, some shortages exist in many related techniques, such asdifficulty of feature loss, feature key extraction, and noise point introduction. In this manuscript a newmethod named SIFT-based iris and SIFT-based finger vein identification with normalization andenhancement is proposed for achieving better performance. In evaluation with other SIFT-based iris orSIFT-based finger vein recognition algorithms, the suggested technique can overcome the difficulties ofaccurate extraction of key-points and clear the noise points without feature loss. Experimentaloutcomes demonstrate that the normalization and improvement steps are critical for SIFT-based irisrecognition and SIFT-based finger vein recognition , the recommended method can accomplishsatisfactory recognition performance.}, keywords = {}, url = {https://ijicis.journals.ekb.eg/article_10907.html}, eprint = {https://ijicis.journals.ekb.eg/article_10907_ad418805435df11f6cf5c44723d82c87.pdf} } @article { author = {El Houby, E and Yassin, N}, title = {METHODOLOGY FOR SELECTING MICROARRAY BIOMARKER GENES FOR CANCER CLASSIFICATION}, journal = {International Journal of Intelligent Computing and Information Sciences}, volume = {15}, number = {1}, pages = {25-39}, year = {2015}, publisher = {Ain Shams University, Faculty of Computer and Information Science}, issn = {1687-109X}, eissn = {2535-1710}, doi = {10.21608/ijicis.2015.10908}, abstract = {In the analysis of microarray gene expression data, it is very difficult to obtain a satisfactoryclassification result by machine learning techniques because of the dimensionality problem. That is thegene expression data are very high dimensional, while datasets usually contain a few tens samples.Microarray data includes many redundant, noisy genes and numerous genes contain inappropriateinformation for classification.The best combination of gene selection and classification is required toidentify biomarker genesfrom thousands of genes. In this research, a methodology has been developedto eliminate noisy, irrelevant and redundant genes and find a small setof significant informativebiomarker genes which can classify cancer dataset with high accuracy. The process consists of twophases which are gene selection and classification. In gene selection phase, the genes have been rankedaccording to their ranking scores; two statistical approaches which are class separability and T-testhave been used. Then from the highest ranked genes, different subsets of genes have been used toclassify dataset until reach the highest possible accuracy. Two data mining techniques have been usedfor classifications which are K-Nearest Neighbor and Support Vector Machine. The proposed methodhas been used to classify 7 benchmarkgene expression cancer datasets. The results showed that theproposed methodology can identifysmall subsetof relevant predictive genes and can achieve highprediction accuracy with this small subset of genes for different datasets.The accuracyand subset ofbiomarker genes have been identified for different cancer datasets.}, keywords = {}, url = {https://ijicis.journals.ekb.eg/article_10908.html}, eprint = {https://ijicis.journals.ekb.eg/article_10908_52b1f6aef83aa6f6c3c07ef4f0dcc364.pdf} } @article { author = {Hameed, B and Elfetouh, A and Abu_Elkheir, M}, title = {DATA CLEANINGTOOL: USAGEOFFUZZYROUGHSETTHEORY AS MACHINE LEARNINGPRE-PROCESSING}, journal = {International Journal of Intelligent Computing and Information Sciences}, volume = {15}, number = {1}, pages = {41-54}, year = {2015}, publisher = {Ain Shams University, Faculty of Computer and Information Science}, issn = {1687-109X}, eissn = {2535-1710}, doi = {10.21608/ijicis.2015.10909}, abstract = {Real-world data is often incomplete, inconsistent, and/or lacking in certain behaviors ortrends, and is likely to contain many errors. Data preprocessing is a crucial phase in the data miningprocess that involves techniques toresolve such issues. Feature selection is a popular datapreprocessing procedure that is focused on omitting attributes from decision systems while stillmaintain the ability of those decision systems to distinguish different decision classes. A popular way toevaluate attribute subsets with respect to this criterion is based on the notion of dependency degree. Inthis paper, we conduct an experimental study using the generalized classical rough set framework fordata-based attribute selection and reduction, based on the notion of fuzzy decision reducts to evaluatethe viability of using Fuzzy rough subset feature. Experimental results shows that, general optimizationcan be achieved under average accuracy reduction, ±10.7 %, against high reduction rate overattributesranging from 36% to 97% and over instances from 1.7% to 44%.}, keywords = {}, url = {https://ijicis.journals.ekb.eg/article_10909.html}, eprint = {https://ijicis.journals.ekb.eg/article_10909_051cd596a486aa129173b4f502cf9991.pdf} } @article { author = {Elawady, R and Barakat, S and Elrashidy, N}, title = {SENTIMENTANALYSIS FOR ARABIC AND ENGLISH DATASETS}, journal = {International Journal of Intelligent Computing and Information Sciences}, volume = {15}, number = {1}, pages = {55-70}, year = {2015}, publisher = {Ain Shams University, Faculty of Computer and Information Science}, issn = {1687-109X}, eissn = {2535-1710}, doi = {10.21608/ijicis.2015.10911}, abstract = {Sentiment analysis is an important topic that has tracked attention since 2001. It basically istext classification based on analyzing opinions that expressed by writing (e.g., social media, blogs,discussion groups, etc). The widespread use of social networks has, also, led to a widespreadavailability of opinionated posts, making research in the area more viable and important. We need tomake sentiment analysis to calculate the percentage of user acceptance or rejection according to theircomments.Although Arabic is the native language of hundreds of millions of people in twenty countriesacross the Middle East and North Africa, the research in the area of Arabic sentiment analysis isprogressing at a very slow pace compared to that being carried out in English[2].In this paper, wepresnet our work in which we start by testing on English texts that wrere collected from Amazon (book,DVD, and electronics).Then, we applied the same process on Arabic dataset that we collect fromYouTubeArabic pages. We applied more than one machine learning on algorithms both (Arabic.English) (Decision trees, Navie Bayes, functions, and support vector machines. We also createdaSentiword Lexicon based on the Corpus that we gathered. Then we evaluated each method andcompared their accuracies.}, keywords = {}, url = {https://ijicis.journals.ekb.eg/article_10911.html}, eprint = {https://ijicis.journals.ekb.eg/article_10911_a5cb1c4b77e7693b04c844b543c2533d.pdf} } @article { author = {Ali, H and Elmogy, M and ALdaidamony, E and Atwan, A}, title = {MRI BRAIN IMAGE SEGMENTATION BASED ON CASCADED FRACTIONAL-ORDER DARWINIAN PARTICLE SWARM OPTIMIZATION AND MEAN SHIFT}, journal = {International Journal of Intelligent Computing and Information Sciences}, volume = {15}, number = {1}, pages = {71-83}, year = {2015}, publisher = {Ain Shams University, Faculty of Computer and Information Science}, issn = {1687-109X}, eissn = {2535-1710}, doi = {10.21608/ijicis.2015.10912}, abstract = {Image segmentation is an initiative with massive interest in many imaging applications, suchas medical images and computer vision. It is considered as a challenging problem, so we need todevelop an efficient, fast technique for medical image segmentation. In this paper, the proposedframework is based on two segmentation methods: Fractional-order Darwinian Particle SwarmOptimization (FODPSO) and Mean Shift segmentation (MS). FODPSO is a favorable method forspecifying a predefined number of clusters and it can find the optimal set of thresholds with a higherbetween-class variance in less computational time. In the pre-processing phase,the MRI image isfiltered and the skull is removed. In the segmentation phase, the result of FODPSO is used as the inputto MS. Finally, we make a validation to thesegmented image. We compared our proposed system withsome state of the art segmentation techniques using brain benchmark data set. The experimental resultsshow that the proposed system enhances the accuracy of the MRI brain image segmentation.}, keywords = {}, url = {https://ijicis.journals.ekb.eg/article_10912.html}, eprint = {https://ijicis.journals.ekb.eg/article_10912_f5d8a478bb3b1eb630c2d3be47ccb209.pdf} }