"Annals. Computer Science Series" Journal Romania, 300559 Timişoara, 6 Lascăr Catargiu str. Phone: 004 0256 220 687  Fax: 004 0256 220 690 Email: conference.fcia [@] tibiscus [.] ro  conference.fcia [@] gmail [.] com 



» Some Results on the Numerical Simulation of SEIRS Epidemic Model with Saturated Incidence Rate Considering the Saturation Term for the Susceptible Individual » M. K. Kolawole and M. O. Olayiwola ABSTRACT:
In this research paper, the numerical simulation of a SusceptibleExposedInfectedRecovered Susceptible (SEIRS) epidemic model with saturated incidence rate with the saturated terms for the susceptible individuals was analyzed. We established the diseasefree equilibrium and endemic equilibrium states of the model. We also investigated the local and global stabilities of the disease free equilibrium using matrix and Lyapunov function methods when the basis reproduction number 1 Reproductive number, SEIRS, saturated incidence rate, susceptible individual. » Received: 30 November 2016» Accepted: 10 January 2017 
9  18



» Effect of Negligibility of Known Auxiliary Variable Coefficient of Variation in Product Estimation » A. A. Adewara ABSTRACT: If the auxiliary variable coefficient of variation c_{x} is known but negligible, then what comes of the mean square error (mse) of our conventional product and mean per unit estimators. In this study, if c_{x} is known but negligible, that is, if it tend towards zero (c_{x}→0), the mse of both the conventional product and mean per unit estimator becomes equal. The question that will quickly come to mind here is, how often does known becomes negligible?. It at times do occur in sample survey, so there must be statistical awareness on this in case we experience such in our researches, just like when the population size (N) is large, then, the finite population correction (fpc) becomes negligible and hence, it tends towards zero (f=n/N→0). If c_{x}→0, then virtually the mse of some of the existing proposed alternatives may tend towards the mse of the mean per unit estimator. When this occur, over estimation problem in product estimation does not arise but if known c_{x} is not negligible, Adewara (2016) proposed an alternative product estimator, ӯ_{aaap}, which utilizes c_{x} which was found to minimize over estimation of ӯ_{p} on ӯ whenever ρ_{xy} < [c_{y}^{2}*(1α^{2}*(Ẍ/(Ẍ+c_{x})^{2})α^{2}*(Ẍ/(Ẍ+c_{x}))^{2}*c_{x}^{2}]/[2*c_{y}*c_{x}*α^{2}*(Ẍ/(Ẍ+c_{x}))^{2}], 0.1 <= α <0.7. KEYWORDS:product, coefficient of variation, estimator, mean square error, bias. » Received: 26 January 2017» Accepted: 27 February 2017 
19  22



» Numerical Results of Some Initial and Boundary Value Problems in Mechanics » M.O. Olayiwola and M. K. Kolawole ABSTRACT: In this research article, the Variational Iteration method coupled with the polynomial approximation is used to find numerical solution to some homogenous and nonhomogenous ordinary differential equations arising in mechanics. KEYWORDS:variational iteration method, boundary value problem, polynomial. » Received: 03 February 2017» Accepted: 13 March 2017 
23  30



» Robustness of Modified FactorType Estimators under NonResponse Model » A. Audu and A. A. Adewara ABSTRACT: In this paper, robustness of suggested modified factortype estimators have been study under nonresponse model in relation to other existing related estimators of population mean. Mean square error (MSE) of suggested estimators under nonresponse model has been obtained and empirical study was done using Data 1, 2, 3 and 4. The robustness of the considered estimators were obtained by averaging their expected MSE and ranked accordingly to their level of efficiency. The results revealed that the efficiency of all the estimators considered increases as the proportion of nonrespondent who responded after been reinterviewed increases and the suggested estimators compete favourably with almost the estimators considered in the study. KEYWORDS:Estimator, Robustness, Mean square error (MSE), Efficiency. » Received: 26 January 2017» Accepted: 13 March 2017 
31  40



» Developing Students’ Metacognitive Skills in Mathematics Classroom » Phi Van Thuy ABSTRACT: Twentyfirst century mathematics education is about facing novel realworld problems, nurturing creative thinking skills and cultivating productive ways of learning. In attempting to innovate teaching and learning in order to prepare a new generation for the demands of this new era, many educators have discovered the value of metacognition. This paper presents the importance of metacognition to the learning of mathematics, employed metacognitive skills in the process of solving mathematics problems. KEYWORDS:Metacognitive skills, higherorder thinking skill, mathematics problem solving, mathematics teaching methods. » Received: 12 January 2017» Accepted: 27 Februyary 2017 
41  46



» An Asymptotic Comparison of Dynamic Panel Data Estimators with Autocorrelated Error Terms » K. T. Uthman and B. A. Oyejola ABSTRACT: This paper investigates properties of some dynamic panel data estimators including Ordinary Least Squares (OLS), the AndersonHsiao IV (AH), ArellanoBond Generalized Method of Moment (GMM) firststep, Blundell Bond System (SYS1) firststep, M and MM estimators in the presence of serial correlation. Absolute Bias and Root Mean Squares Error were used to evaluate finite properties of the estimators and revealed improving performances asymptotically under different sample sizes and varying degrees of autocorrelation. The results showed that in small and large sample situations, irrespective of time dimension, Anderson–Hsiao IV estimator (AH) outperforms all other estimators. ArellanoBond Generalized Method of Moment (GMM) onestep proves to be relatively superior among the estimators when the time period (T) is small, though it may not be the best but performance improved drastically as the number of crosssectional units increases. However, Ordinary Least Squares estimator has least performance among all the estimators considered in this study. KEYWORDS:Dynamic Panel Data, Serial Correlation, CrossSections, Time Periods, Absolute Bias and Root Mean Squares Error. » Received: 28 January 2017» Accepted: 16 March 2017 
47  54



» Student’s Performance Analysis using Decision Tree Algorithms » Abdulsalam Sulaiman Olaniyi, Saheed Yakub Kayode, Hambali Moshood Abiola, SalauIbrahim Taofeekat Tosin and Akinbowale Nathaniel Babatunde ABSTRACT: Educational Data Mining (EDM) is concerns with developing and modeling methods that discover knowledge from data originating from educational environments. This paper presents the use of data mining approach to study students’ performance in CSC207 (Internet Technology and Programming I) a 200 level course in the department of Computer, Library and Information Science. Data mining provides many approaches that could be used to study the students’ performance, classification task is used in this work to evaluate the student’s performance and as there are numbers of approaches that can be used for data classification, including decision tree method. In this work, decision trees were used which include BFTree, J48 and CART. Students’ attribute such as Attendance, Class test, Lab work, Assignment, Previous Semester Marks and End Semester Marks were collected from the students’ management system, to predict the performance at the end of semester examination. This paper also investigates the accuracy of different Decision tree algorithms used. The experimental results show that BFtree is the best algorithm for classification with correctly classified instance of 67.07% and incorrectly classified instance of 32.93%. KEYWORDS:Classification, Decision tree, Students’ Performance, Educational Data Mining. » Received: 24 January 2017» Accepted: 13 March 2017 
55  62



» Modified FactorType Estimators with Two Auxiliary Variables under TwoPhase Sampling » A. Audu and A. A. Adewara ABSTRACT: In this paper, two modified factortype estimators with two auxiliary variables for population mean have been suggested. Bias and MSE of the suggested estimators have been derived up to first order approximation using Tailor’s series expansion and the conditions for their efficiency over some existing estimators have been established theoretically. Empirical study was conducted using three dataset and the results revealed that the suggested estimators are more efficient. KEYWORDS:Estimator, Auxiliary variable, Mean square error (MSE), Twophase sampling. » Received: 27 January 2017» Accepted: 16 March 2017 
63  76



» Modelling of Gross Domestic Product of Some Sectors of Nigeria Economy in the Presence of Autocorrelation » Osuolale Peter Popoola, Adekunle A. Araromi, Adesina A. Rafiu and Mattew T. Odusina ABSTRACT: The research work examined the statistical modelling of Nigeria GDP of some selected sectors in the presence of autocorrelation. It examines the effects and contribution of some economic sectors to the Gross Domestic Production of Nigeria. The data set in (N million) covered a period of 20 years from 1990 to 2009 for the economic variables of interest. The statistical methods employed were regression analysis, correlation and residual analysis. The estimated regression equation is given as: Y = 77203 + 6.43816X1 + 1.26391X2 + 6. 99025X3 1. 01914X4.The Coefficient of Determination (R2) of 0.9806 showed that the four economic variables considered explained about 98% of the variation in the nations GDP. A further analysis revealed the Variance Inflation Factor with the independent variables been highly correlated which denotes the presence of multicollinearity. DurbinWatson and GoldfeldQuandt tests revealed that there was no autocorrelation in the error terms but there was evidence of heteroscedasticity respectively. It was found that Agriculture sector contribute the highest to the growth of the economy, follow by the manufacturing and oil sector respectively, while the least contribution was experienced from building and construction. The work therefore advice the government to invest more on the agriculture sector and non oil sector in order to increase GDP. KEYWORDS:GDP, DurbinWatson, Multiple. » Received: 24 March 2017» Accepted: 29 April 2017 
77  81



» An Ensemble Approach Based on Decision Tree and Bayesian Network for Intrusion Detection » Balogun A. O., Balogun A. M., Sadiku P. O. and Amusa L. B. ABSTRACT: This paper presents an overview of intrusion detection and a hybrid classification algorithm based on ensemble method (stacking) which uses decision tree (J48) and Bayesian network as base classifiers and functional tree algorithm as the metalearner. The data set is passed through the decision tree and node Bayesian network for classification. The metalearner (Functional tree classifier) will then select the value of the base classifier that has the higher accuracy based on majority voting. The key idea here is to always pick the value with higher accuracy since both base classifier (decision tree and Bayesian network) will always classify all instances. A performance evaluation was performed using a 10fold cross validation technique on the individual base classifiers (decision tree and Bayesian network) and the ensemble classifier (DTBN) using the KDD Cup 1999 dataset on WEKA tool. Experimental results show that the hybrid classifier (DTBN) gives the best result in terms of accuracy and efficiency compared with the individual base classifiers (decision tree and BN). The decision tree gave a result of (99.9974% for DoS, 100% for Normal, 98.8069% for probing, 97.6021% for U2R and 73.0769% for R2L), the Bayesian network (99.6410% for DoS, 100% for Normal, 97.1756% for probing, 97.0693% for U2R and 69.2308% for R2L),while the ensemble method gave a result of (99.9977% for DoS, 100% for Normal, 98.8069% for probing, 97.6909% for U2R and 73.0769% for R2L). KEYWORDS:Network security, Intrusion detection system, classifiers, Bayesian network, Functional tree Decision Tree, metalearner. » Received: 25 January 2017» Accepted: 13 March 2017 
82  91



» Heterogeneous Ensemble Models for Generic Classification » Balogun A. O., Balogun A. M., Sadiku P. O. and Adeyemo V. E. ABSTRACT: This paper presents the application of some data mining techniques in the field of health care and computer network security. The selected classifiers were used individually and also, they were ensemble methods using four different combinations for the purpose of classification. Naïve Bayes, Radial Basis Function and Ripper algorithms were selected and the ensemble methods were majority voting, multischeme, stacking and Minimum Probability. The KDDCup’99 dataset was used as the benchmark for computer network security, while for the health care, breast cancer and diabetes dataset from the WEKA repository were used. All experiments and simulations were carried out, analyzed and evaluated using the WEKA tool. The Multischeme ensemble method gave the best accuracy result for the KDD dataset (99.81%) and the breast cancer dataset (73.08%) but its value of (75.65%) on breast cancer is the least of them all. Ripper algorithm gave the best result accuracy (99.76%) on KDD dataset amongst the base classifier but it was slightly behind in the breast cancer and diabetes dataset. KEYWORDS:Ensemble, Data mining, Classification, KDD Dataset, Machine Learning. » Received: 20 March 2017» Accepted: 29 April 2017 
92  98



» A Review on Data Mining Techniques for Heart Disease Prediction » Taye Oladele Aro, Besiru Jibrin Muhammed, Olufisayo Babatope Ayoade and Idowu Dauda Oladipo ABSTRACT: Data mining is an important stage in knowledge discovery in database (KDD) of clinical data due to its ability to extract concealed (hidden) patterns from huge amount of datasets to produce more useful and understandable information. One of the most important applications of data mining is the prediction of heart disease. Techniques in data mining can be employed for management, diagnosis and prediction of heart disease in healthcare establishments. This paper discusses review on different approaches in data mining that have been employed by several researchers to predict heart disease. KEYWORDS:Prediction, Data mining, Diagnosis, Healthcare, Knowledge discovery in database. » Received: 25 March 2017» Accepted: 29 April 2017 
99  103



» A 2Dimensional GaborFilters for Face Recognition System: A Survey » Taye Oladele Aro, Bamidele Oluwade, Oluwakemi Abikoye and Amos Bajeh ABSTRACT: An efficient recognition algorithm for human face is a technique discovered to be based on good facial feature representation. A twodimensional Gabor represents a group of wavelets which capture optimally frequency information and local orientation from a digital image. Gabor filters have been employed greatly and highly considered to be one of the best performing techniques for feature extraction in face recognition owing to its invariant against local distortion initiated by changes in expression, lighting and pose. This paper discusses some reviews on 2Dimensional Gaborbased facial recognition techniques. The huge feature dimensionality problem associated with Gabor feature is stated and several techniques to reduce this problem are suggested. KEYWORDS:Gaborfilters, face recognition, feature extraction, wavelets, Gabor feature, dimensionality. » Received: 13 March 2017» Accepted: 29 April 2017 
104  112



» Proves of the Existence and Determination of Blocks Size of Pairwise Balanced Designs » Osuolale Peter Popoola, Benjamine A. Oyejola, Ayanniyi W. Ayanrinde and Adekunle A.Araromi ABSTRACT: A pairwise balanced design of index λ is a way of selecting blocks from a set of treatments (support set) such that any two treatments have covalency λ. If there are v treatments and if every block size is a member of some set K of positive integers, the design is designated a PB (v;K; λ).{5} Therefore, this research research work attempts to proof the existence of PBDs, shows the relationship that exists among the PBDs parameters (v, b, r, k, λ), and specify conditions for the construction of PBDs when λ > 0, k is odd and λ = 1.Thus, v − k and r − λ are proved to be nonnegative therefore, r − k ≥ 0, and b ≥ v. Also, a PBD(15; {4, 3}; 3) was constructed from the PBD(15; {5, 3}; 1). KEYWORDS:Regular Design, Balanced Designs, Blocks Designs and Pairwise Balanced Designs. » Received: 24 March 2017» Accepted: 29 April 2017 
113  118



» Automated Voting System Using Bimodal Identification And Verification Technique » Joseph Bamidele AWOTUNDE ABSTRACT: Nigeria voting system is characterized with violence and malpractices, where some people used another person voting card to vote and many have more than one voter’s card in their possession, which allow them to vote more than one time. These problems does not peculiar to Nigeria alone but includes other countries that are using manual method of voting system. In order to combat the aforementioned problems the paper therefore proposed a secure voting system using bimodal identification and verification system for voting and registration of voters. The purpose is to uniquely identify voters and to eliminate the possibility of double registration at the polling booth by the voters. Also the issue of double voting will also be abolished. Further study can look into web based and mobile based automated voting system, which allow voter to catch their vote anywhere and anytime. KEYWORDS:Voting system, automated, recognition, Verification, Bimodal. » Received: 6 April 2017» Accepted: 17 June 2017 




» Construction of (k^{2}, b, r, k, 1) Resolvable Balanced Incomplete Block Designs (RBIBD) using Nim Addition Tables of Order 2^{n}, 2 ≤ n ≤ 5 » Oluwaseun A. Otekunrin and Kehinde O. Alawode ABSTRACT:
Resolvable Balanced Incomplete Block Designs (RBIBDs) are important combinatorial designs that have useful applications in various fields of human endeavour. In this paper, Nim addition tables, from the game of Nim, of order 2^{n}, 2≤n≤5 were used as the basis for the construction of some (k^{2}, b, r, k, 1) RBIBDs. Nim addition tables of order 2^{n}, 2≤n≤5 were constructed. These tables were special Latin squares that obeyed the Finite Groups theory and closed nnimregularity conditions for closed nnimregular games. The Bose’s generalized method of constructing Mutually Orthogonal Latin Squares (MOLS) was used to obtain 2^{n}1 MOLS for each n. The MOLS were superimposed on one another and successive diagonalization algorithm was used to obtain the RBIBDs from the superimposed MOLS. The RBIBDs constructed were (16, 20, 5, 4, 1), (64, 72, 9, 8, 1), (256, 272, 17, 16, 1) and (1024, 1056, 33, 32, 1) RBIBDs. These RBIBDs are all in existence and a link was thus established between the game of Nim and RBIBDs. Mutually Orthogonal Latin Squares; Successive diagonalization algorithm; Impartial Combinatorial games; closed nnimregular matrix; Finite groups. » Received: 16 April 2017» Accepted: 17 June 2017 



» www.fcia.tibiscus.ro  » www.ccsitia.tibiscus.ro  » www.geogebra.tibiscus.ro  » www.tibiscus.ro   © 20032017, Last update: 23.06.2017 / 11:32 