ENHANCED FINGER VEIN BASED RECOGNITION SYSTEM
M. h
Jumaah
Faculty of Computers & Information, Mansoura University, Egypt
author
S.
Hussein
Faculty of Engineering, Mansoura University, Egypt
author
M.
Rashad
Faculty of Computers & Information, Mansoura University, Egypt
author
text
article
2016
eng
Robust Recognition systems become more complicated over time. These systems are derived from features which can be extracted from different body members using extractor methods. Finger vein is suitable member that could be used to violate the weakness of finger print. Conventional extractor methods like matched filter and morphological methods can extricate patterns if the widths of veins are steady whereas repeated line tracking method extract vein patterns from a hazy picture. These strategies can't remove veins that are smaller extensive than the accepted widths which corrupts the precision of the individual recognizable proof or can't adequately extricate flimsy veins on the grounds. In turn, we have proposed a system that tackles these issues by checking the shape of the picture profiles and stressing just the centerlines of veins. Our system for distinguishing the most extreme bend positions is hearty against transient vacillations in vein width and splendor. This paper introduces a finger vein recognition system based on using histogram of gradient and multi class support vector machine and finger vein recognition is powered by using Gabor filter with classifier powered by multi class support vector machine. The proposed have great enhancement impact over relative to accuracy, sensitivity, F-measure and precision during evaluation.
International Journal of Intelligent Computing and Information Sciences
Ain Shams University, Faculty of Computer and Information Science
1687-109X
16
v.
3
no.
2016
1
14
https://ijicis.journals.ekb.eg/article_19832_49ea596d8403b791c919ff185a076035.pdf
dx.doi.org/10.21608/ijicis.2016.19832
FOORC: A FUZZY ONTOLOGY-BASED REPRESENTATION FOR OBESITY RELATED CANCER KNOWLEDGE
M.
Elhefny
Information Systems Dept.,Faculty of Computers and Information,
author
M.
Elmogy
Information Technology Dept.,
Faculty of Computers and information
author
A.
Elfetouh
Information Systems Dept.,Faculty of Computers and Information,
author
F.
Badria
PharmacognosyDept.,Faculty of Pharmacy,
Mansoura University, Egypt
author
text
article
2016
eng
Obesity has a tight relationship with increased risks of different cancer types, such as Colorectal, Ovarian, Female Breast, Gallbladder, Adenocarcinoma, Kidney (Renal-Cell), Liver, and Pancreatic. It can also lead to some other diseases like diabetes and heart diseases. This paperproposes a fuzzy ontology that is based on OWL 2to represent the Obesity Related Cancer (ORC) domain knowledge. The diseases taxonomy isconstructed using the standard Disease Ontology. The presented FuzzyOntology includes more concepts than in crisp one and copes with the domain linguistic variables. It allows the users to query the Fuzzy Dl reasoner for element and get them back the fuzzy ontology for that element. It is expected to be good practice for ontologists and knowledge engineers in medical field aiding them to solve the overlapping concepts, linguistic variables, and reasoning problems by building their fuzzy ontologies. Building FOORC as an open ontology is a first attempt to organize information related to the obesity and cancer diseases in a formalized, structured manner that both physicians and intelligent systems can exploit it in knowledge sharing, reusability, and reasoning.
International Journal of Intelligent Computing and Information Sciences
Ain Shams University, Faculty of Computer and Information Science
1687-109X
16
v.
3
no.
2016
15
36
https://ijicis.journals.ekb.eg/article_19833_b62db55b74c9ea49302876b974016d6a.pdf
dx.doi.org/10.21608/ijicis.2016.19833
OPPONENT MODELS PREPROCESSING IN REAL-TIME STRATEGY GAMES
M.
Mourad
Computer Science and Basic Sciences Department, Faculty of Computer and Information Sciences, AM Shams University,
author
M.
Aref
Computer Science and Basic Sciences Department, Faculty of Computer and Information Sciences, AM Shams University,
author
M.
Abd-Elaziz
Computer Science and Basic Sciences Department, Faculty of Computer and Information Sciences, AM Shams University,
author
text
article
2016
eng
Creating a human-like computer player in real-time strategy games requires huge number of opponent models, these models must be preprocessed to either focus on accuracy or performance according to our needs. In order to preprocess these models accurately, we need to detect their type. Opponent models' type can be complex or simple. Complex opponent models are low variance models whose differences in features' values are low, so in order to accurately separate between these models, we need to preprocess them by increasing their dimensions. Simple opponent models are high variance models whose differences in features' values are high, so in order to separate between these models in a reasonable time, we need to preprocess them to decrease their dimensions, if possible, without accuracy or data loss.
International Journal of Intelligent Computing and Information Sciences
Ain Shams University, Faculty of Computer and Information Science
1687-109X
16
v.
3
no.
2016
37
45
https://ijicis.journals.ekb.eg/article_19835_fe44d7c9e8bd8619390e6a2489e93f20.pdf
dx.doi.org/10.21608/ijicis.2016.19835
REGISTRATION OF REMOTE SENSING IMAGES BASED ON FEATURE FUSION TECHNIQUES
M.
Asker
Faculty of Computers and Information, Mansoura University, Egypt
author
O.
Abu —ElNasr
Faculty of Computers and Information, Mansoura University, Egypt
author
B.
Shabana
Faculty of Computers and
and Computer Science, Information,
Mansoura-Egypt.
author
S.
Elmougy
Faculty of Computers and
and Information
author
text
article
2016
eng
Geometric correction is used to correct the registration errors in remotely sensed images. These images are often compared to ground control points (GCPs) either by using an accurate map (image to map) or using another geo-referenced image (image to image) and then resampled. Accordingly, the exact locations and the appropriate pixel values can be calculated in more accurate, time-wise and effortless manner. In the traditional methods, the GCPs are manually selected and then the transformation models are applied which yield time consuming and less accurate processes. The objective of this work is to develop an automatic approach for image registration based on another geo-referenced image using five feature extraction models. They are Scale Invariant Feature Transform (SIFT), Speeded Up Robust Features (SURF), Discrete Wavelet Transforms (DWT), (SIFT & DWT), and (SURF & DWT). The GCPs were selected based on the least-squares adjustments as the basis for improving the spatial accuracy of all the linking points in both images. The obtained results showed that models have higher accuracy in image registration with Root Mean Square Error (RMSE) less than 0.5. The developed automated image registration method provides more accurate results and saves time, money and effort.
International Journal of Intelligent Computing and Information Sciences
Ain Shams University, Faculty of Computer and Information Science
1687-109X
16
v.
3
no.
2016
47
66
https://ijicis.journals.ekb.eg/article_19838_530a5c851cc02372bb92e9952307dc43.pdf
dx.doi.org/10.21608/ijicis.2016.19838
USING ACTIONSCRIPT 3.00 TO DEVELOP AN ANDROID APPLICATION FOR MATHEMATICS COURSE
M.
Amasha
Department of computer preparing teacher, Dumyat University.
author
text
article
2016
eng
This study aims at designing an android application for mathematics course in primary schools. This application is mainly designed to help learners to learn and examine their cognitive and performance skills in mathematics. It also provides them with a chance to compete with their classmates. Through this application, learning mathematics will be available anytime and everywhere. This research is built on a case study to show how an android application can be helpful. Actioscript 3.00 code snippets by adobe for air is used to build the application. This research represents a case study that shows how this application was used effectively to support the activities in undergraduate level classes. Results indicate the effectiveness of using this current application in developing cognitive and performance skills in mathematics for students.
International Journal of Intelligent Computing and Information Sciences
Ain Shams University, Faculty of Computer and Information Science
1687-109X
16
v.
3
no.
2016
67
79
https://ijicis.journals.ekb.eg/article_19839_5f7df12b44bead0d6788aad84b710876.pdf
dx.doi.org/10.21608/ijicis.2016.19839
AUTOMATIC DETECTING AND REMOVAL DUPLICATE CODES CLONES
Z.
Al-Saffar
Department of Computer Science, Faculty of Computers and Information, Mansoura University, Mansoura 35516, Egypt.
author
S.
Sarhan
Department of Computer Science, Faculty of Computers and Information, Mansoura University, Mansoura 35516, Egypt.
author
S.
Elmougy
Department of Computer Science, Faculty of Computers and Information, Mansoura University, Mansoura 35516, Egypt
author
text
article
2016
eng
Code clones is considered now an important part of improving the overall design of software structure and software maintenance through making the source code more readable and more capable for maintenance. To remove code clones from a written code, refactoring technique could be used. Copying and pasting fragments of codes is a type of code clones that should be handled and has many practical applications such as software and project plagiarism detection clones and copyright infringements. To overcome this problem, we propose a computerized refactoring system to remove duplicate code clones. The simulation results of applying the proposed system showed that it increases the maintainability and quality of software system based on the total lines of code, blank lines and total methods count for the four used Java open source projects.
International Journal of Intelligent Computing and Information Sciences
Ain Shams University, Faculty of Computer and Information Science
1687-109X
16
v.
3
no.
2016
81
93
https://ijicis.journals.ekb.eg/article_19841_8073b308f38619b88465070635360154.pdf
dx.doi.org/10.21608/ijicis.2016.19841
MULTITHREAD IN NAMED ENTITY RECOGNITION
Z.
Rabea
Faculty of Computer and Information Sciences, Mansoura University, - Egypt
author
M.
Abu Elsoud
Faculty of Computer and Information Sciences, Mansoura University, - Egypt
author
M.
Rashed
Faculty of Computer and Information Sciences, Mansoura University, - Egypt
author
text
article
2016
eng
According to Gordon Earle Moore, Every two years, the number of core on a CPU chip is doubling. So we change our program to use threads for different reasons, program will run faster and make better use of the multiple CPU/core architecture that you are running on. This paper introduces a multithreading named entity recognition (NER) approach in Open American National Corpus. Named entity can be name of person, location, organization, number, date, e-mail, and so on . Using the pooling technique and get benefits of its computation time in the NER.
International Journal of Intelligent Computing and Information Sciences
Ain Shams University, Faculty of Computer and Information Science
1687-109X
16
v.
3
no.
2016
95
103
https://ijicis.journals.ekb.eg/article_19842_924b077bc67427e4092dc7a70fec1dc1.pdf
dx.doi.org/10.21608/ijicis.2016.19842