Browsing by Author "Akintola, Abimbola Ganiyat"
Now showing 1 - 8 of 8
Results Per Page
Sort Options
Item Comparative Analysis of Selected Heterogeneous Classifiers for Software Defects Prediction Using Filter-Based Feature Selection Methods(Faculty of Engineering, Federal University Oye-Ekiti, Ekiti., 2018-03-31) Akintola, Abimbola Ganiyat; Balogun, Abdullateef Oluwagbemiga; Lafenwa-Balogun, Fatimah; Mojeed, Hameed AdeleyeClassification techniques is a popular approach to predict software defects and it involves categorizing modules, which is represented by a set of metrics or code attributes into fault prone (FP) and non-fault prone (NFP) by means of a classification model. Nevertheless, there is existence of low quality, unreliable, redundant and noisy data which negatively affect the process of observing knowledge and useful pattern. Therefore, researchers need to retrieve relevant data from huge records using feature selection methods. Feature selection is the process of identifying the most relevant attributes and removing the redundant and irrelevant attributes. In this study, the researchers investigated the effect of filter feature selection on classification techniques in software defects prediction. Ten publicly available datasets of NASA and Metric Data Program software repository were used. The topmost discriminatory attributes of the dataset were evaluated using Principal Component Analysis (PCA), CFS and FilterSubsetEval. The datasets were classified by the selected classifiers which were carefully selected based on heterogeneity. Naïve Bayes was selected from Bayes category Classifier, KNN was selected from Instance Based Learner category, J48 Decision Tree from Trees Function classifier and Multilayer perceptron was selected from the neural network classifiers. The experimental results revealed that the application of feature selection to datasets before classification in software defects prediction is better and should be encouraged and Multilayer perceptron with FilterSubsetEval had the best accuracy. It can be concluded that feature selection methods are capable of improving the performance of learning algorithms in software defects prediction.Item Design and Implementation of Ayo Olopon Game(2015) Babatunde, Akinbowale Nathaniel; Abikoye, Oluwakemi Christiana; Mabayoje, Medinat Abolore; Akintola, Abimbola Ganiyat; Oderemi, ChristianaThe difficulty encountered with the present manual mode of the “Ayo olopon” game is majorly on the tools used in playing it. The game utilizes the earth as the board of the game and uses stones, leaves as other parameters in playing it. Though some still use boards carved from wood and seeds but there is still a problem with portability. This research which is centred on automating the “Ayo olopon” game is inevitable because of the increasing need for system automation. There are many difficulties associated with the existing manual approach of playing the “Ayo olopon” game which ranges from loss or misplacing of seeds to inaccuracy in scores calculation due to human errors. This system is designed to efficiently handle the entire process of the game play. Two algorithms were implemented for the game manipulation. The first for handling the incrementing of the next cell while the other an entire play turn. Out of the diverse rules for the game play, one was selected and implemented. With the proposed system, “Ayo olopon” game playing is more efficient when compared to its present mode of play. The study outlined the concepts of the analysis and design methodology of the proposed system, compares it with the existing system and explains the design and implementation of the system using Microsoft C# as its programming language on the Visual Studio.NET platform serving as the Integrated Development Environment (IDE). The research was tested using the Windows operating system and worked successfulItem Design and Implementation of Yoruba Language Cryptosystem(Published by Faculty of Physical Sciences, University of Ilorin, 2014) Abikoye, Oluwakemi Christiana; Akintola, Abimbola Ganiyat; Ibrahim, SSecurity has always been a bedrock for transaction and protection of human lives and until the existence of artificial intelligence, humans have learned to trust themselves for each other safety or safety of information except for few times where security was threatened by breach of trust or betrayal by persons which often led to enormous crisis. Recent research works have been able to achieve some high level of success in security of information. However, communication in Yoruba language using the Yoruba alphabet and symbols is still at its infancy. In other to achieve acceptable quality of information security of Yoruba alphabet and symbols in text, there is need for a robust security system. There are multiple layers of security, requirements and features which need automated technicality for assurance of effective security. In this paper, encryption and decryption of information written in Yoruba as text is achieved using Caesar Cipher Algorithm to carry the Yoruba people along in the advancement taking place in the world of information technology. It adopted a symmetric encryption algorithm that uses one key for both encryption and decryption and used digits as its ciphertext which is a novel means of ensuring difficulty in breaking the codes as patterns with digits are not easily recognizable.Item Gain Ratio and Decision Tree Classifier for Intrusion Detection(Foundation of Computer Science (FCS), NY, USA, 2015) Mabayoje, Modinat Abolore; Akintola, Abimbola Ganiyat; Balogun, Abdullateef Oluwagbemiga; Ayilara, OpeyemiWith the evident need for accuracy in the performance of intrusion detection system, it is expedient that in addition to the algorithms used, more activities should be carried out to improve accuracy and reduce real time used in detection. This paper reviews how data mining relates to IDS, feature selection and classification. This paper proposes architecture of IDS where GainRatio is used for feature selection and decision tree for classification using NSL-KDD99 dataset, It also includes the evaluation of the performance of the Decision tree on the dataset and also on the reduced dataset.Item Hybridization of El-Gamal and Blow-Fish Algorithm for Data Security(Faculty of Communication and Information Sciences, University of Ilorin, Ilorin, Nigeria., 2017) Bajeh, Amos Orenyi; Olatunde, Yusuf Olanrewaju; Akintola, Abimbola Ganiyat; Balogun, Abdullateef Oluwagbemiga; Wasiu, M. O; Sulaiman, A. T.The internet connects all part of the world together and thus, makes it very easy and fast to communicate from different location. Reports by internet user on security issues such as hacking of e-mail account, SQL injection, unauthorized access to transaction details makes users to migrate from one platform to another. The increasing activities of hackers to overcome the existing security measures have raised the need for more and improving security technique.Therefore,this study demonstrates hybridization of Blowfish and El-Gamal algorithm to improve data security and improve the performance of El-Gamal algorithm. In the hybrid system, Blowfish is used to encrypt message containing private data using a secret key after which the secret key is encrypted by El-Gamal algorithm using public and private key which are mathematically related.The cipher text produced contains the mixture of private data and secret key. A simulation program is developed using java in order to experiment the difference between the hybrid system, blowfish and El-Gamal algorithm. The result showed that the developed hybrid system is more secure and faster compared to El-Gamal algorithm.Item A K-means and fuzzy logic-based system for clinical diagnosis (staging) of cervical cancer(Inderscience, 2017) Abikoye, Oluwakemi Christiana; Olajide, Emmanuel Oluwaseun; Babatunde, Akinbowale Nathaniel; Akintola, Abimbola GaniyatIn cases of the burden arising from cancer world, cervical cancer is the most common type of gynaecological cancer, accounting 8% (527,624 cases in 2012) of all female malignancies, second only to breast and colorectal cancer. Women with cervical cancer constitute patient populations that are in need of ongoing, person-centred supportive care. The unavailability of technologies that can determine the stage of cervical cancer constitutes a problem in the actual diagnosis. Previously physician predict the cancer stage on the basis of their experience in the field, however this is prone to error because man’s judgement are sometimes clouded by emotions. This research seeks to address this problem with the design of a k-means and fuzzy logic based system for clinical diagnosis (staging) of cervical cancer. The K-means algorithm was used for the grouping of data and fuzzy logic for the rule based prognosis of cervical cancerItem Social Media Preference by Secondary Schools’ Computer Science Teachers(Faculty of Physical Sciences, 2015) Mabayoje, Medinat Abolore; Ajia, Ismaeel S; Tella, A; Abikoye, Oluwakemi Christiana; Akintola, Abimbola GaniyatThis research explores the preference for social media by secondary schools teacher for the teaching of computer science in Ilorin metropolis. Questionnaires were administered to two hundred (200) respondents randomly selected from ten different secondary schools in Ilorin metropolis. A total of 174 questionnaires were returned completely filled which serve as the overall sample which gives 87% return rate. Findings from the study reveals that commonly used social media are Facebook, Twitter, Skype, Whatsapp, Blackberry Messenger, 2go, Eskimi and LinkedIn. There is a low usage of these services in most of the public and private schools due to the financial implication of procurement and installation of these facilities. Interestingly, level of awareness and acceptability based on the numerous benefits of social media on teaching and learning functions and productivity was of a high proportion. It was concluded that school administrators and parents should collaborate with educational agencies to aid in the effective implementation and funding for the procurement of sophisticated ICTs for better dissemination of social media in both public and private schools in Ilorin metropolis.Item Text to Text Translation of English Language to Yorùbá Language(ISTEAMS., 2015) Abikoye, Oluwakemi Christiana; Ojo, I. Mayowa; Akintola, Abimbola GaniyatTranslation of languages from one form to another has never taken its full shape till today, since when there was confusion in man’s language at the tower of Babel. There are various approaches and techniques through which several scholars and linguists have provided, as a general standard for translating any language texts to another. In this paper, several translating techniques are reviewed, and finally the English language is translated into its equivalent Yorùbá languages using the direct and oblique (indirect) translation technique, with literal, modulation and transposition set as the main key point, the English words were documented into the database for referencing and efficient translation into Yorùbá. The result shows that about 80% of any source language texts can be translated into another language efficiently using this three key module of translation technique.