Browsing by Author "Ameen, Ahmed Oloduowo"
Now showing 1 - 4 of 4
Results Per Page
Sort Options
Item Design and Analysis of Network Models for QoS Routers on UDP and CBR(Georgian Technical University and St. Andrew the First Called Georgian University of The Patriarchy of Georgia, 2017) Ameen, Ahmed Oloduowo; Olatinwo, D.D.; Alamu, F.O; Olatinwo, S.O.; Balogun, Abdullateef OluwagbemigaTo address the issues of packet delay and unfairness among multimedia UDP flows, this paper presents the design and evaluation of network models to study different parameters for quality-of-service (QoS) provisioning in differentiated service (DiffServ) routers using user datagram protocol (UDP) as network traffic agent and constant bit rate (CBR) as traffic generator. Traffic marker algorithms are used to define the treatment an incoming traffic (packet streams) receives at the edge routers in a DiffServ domain. In order to implement the TSW2CM and TSW3CM marker algorithms, a network model was designed. The designed models were simulated, analysed and evaluated. For the purpose of evaluation, packet delay and fairness index were considered. The obtained evaluation results were analysed based on a ranking system approach to showcase the strengths and weaknesses of the TSW2CM and TSW3CM algorithms for multimedia UDP flows. The adopted approach showed that the TSW3CM algorithm was ranked first with a packet delay value of 0.237704 while TSW2CM algorithm was marked second (with 0.431778), and the TSW3CM algorithm was ranked first with a fairness rate value of 0.3823960 while TSW2CM algorithm was ranked second (with 0.2817353). The obtained results indicate that applications that requires low packet delay can be deployed on UDP protocol using TSW3CM algorithm while applications that requires high fairness rate values can be deployed on UDP protocol using TSW3CM algorithmItem Heterogeneous Ensemble Methods Based On Filter Feature Selection(Research Nexus Africa’s Networks in Conjunction with The African Institute of Development Informatics & Policy (AIDIP) Ghana & The International Centre for Information Technology & Development (ICITD), USA, 2016) Ameen, Ahmed Oloduowo; Balogun, Abdullateef Oluwagbemiga; Usman, Ganiyat; Fashoto, Gbenga StephenWhile certain computationally expensive novel methods can construct predictive models with high accuracy from high dimensional data, it is still of interest in many applications to reduce the dimension of the original data prior to any modeling of the data. Hence, this research presents a précis of ensemble methods (Stacking, Voting and Multischeme) and Multilayer perceptron, K Nearest Neighbour and NBTree with a framework on the performance measurement of base classifiers and ensemble methods with and without feature selection techniques (Principal Component Analysis, Information Gain Attribute Selection and Gain Ratio Attribute Selection). The enhancement is based on performing feature selection on dataset prior to classification. The notion of this study is to evaluate the performances of the ensemble methods on original and reduced datasets. A 10-fold cross validation technique is used for the performance evaluation of the ensemble methods and base classifiers (Root to Local) R2L KDD cup 1999 dataset and UCI Vote dataset using Waikato environment for knowledge analysis (WEKA) tool. The experiment revealed that the reduced dataset yielded improved results than the full dataset after using the ensemble methods based on stacking, voting and multischeme. On the R2L dataset, Multischeme ensemble method gave accuracy of 98.76% with PCA as feature selection on R2L dataset while 98.58% accuracy was given without feature selection. Using the gain ratio attribute selection, the Multischeme gave 98.93% accuracy over 98.76% without feature selection while using information gain attribute selection gave accuracy 98.85% over 98.76% without feature selection. For the Vote Dataset, Multischeme ensemble method proved best with an accuracy of 92.18% with PCA feature selection over 89.88% without feature selection, 95.40% accuracy with information gain as feature selection over 93.10% without feature selection and 95.40% accuracy with gain ratio as feature selection over 93.10% without feature selection. In arguably, it can be concluded that ensemble methods works well with feature selection.Item Influence of Feature Selection On Multi-Layer Perceptron Classifier for Intrusion Detection System(Research Nexus Africa’s Networks in Conjunction with The African Institute of Development Informatics & Policy (AIDIP) Ghana & The International Centre for Information Technology & Development (ICITD), USA., 2016-12-15) Mabayoje, Modinat Abolore; Balogun, Abdullateef Oluwagbemiga; Ameen, Ahmed Oloduowo; Adeyemo, Victor ElijahThe usage of the most popular neural network – Multilayer perceptron, as gained ground for the purpose of detecting intrusion. A lot of researchers had used it judiciously but there exist problem of slow training time and data over-fitting. This paper reviews the various data mining techniques for applied in the area intrusion detection, categories of attacks, and techniques for feature selection. This paper proposes an architecture where information gain is used for feature selection and multilayer perceptron (MLP) for classification on KDD’99 dataset. Evaluation of the performance of the MLP classifier on the KDD’99 dataset and also on the reduced dataset was conducted.Item PERFORMANCE EVALUATION OF SELECT DATA MINING SOFTWARE TOOLS FOR DATA CLUSTERING(Federal University Wukari, Taraba State, Nigeria., 2018-09-10) Ameen, Ahmed Oloduowo; Bajeh, Amos Orenyi; Adesiji, Boluwatife Aderinsola; Balogun, Abdullateef Oluwagbemiga; Mabayoje, Modinat AboloreData mining is used to discover knowledge from information system. Clustering is one of the techniques used for data mining. It can be defined as a technique of grouping un-labelled data objects such that objects belonging to one cluster are not similar to the objects belonging to another cluster. Data mining tools refer to the software that are used for the process of efficiently analysing, summarizing and extracting useful information from different perspectives of data. This paper presents a comparative analysis of four open-source data mining software tools (WEKA, KNIME, Tanagra and Orange) in the context of data clustering, specifically K-Means and Hierarchical clustering methods. The results of the performance analysis based on the execution time and quality of clusters showed that WEKA tool outperforms the other tools with the lowest SSE of 199.7308 with an average execution time of 1.535 seconds. Knime has SSE of 222.217 but with an average execution time of 7.13 seconds, and then Tanagra with SSE of 269.3902 and average execution time of 2.01 seconds, Orange has the poorest performance with SSE of 388.78.