DSpace Angular :: Browsing by Author "Oguntunde, Bosede"

Browsing by Author "Oguntunde, Bosede"

Now showing 1 - 20 of 30

An Adaptive Thresholding Algorithm-Based Optical Character Recognition System for Information Extraction in Complex Images
(Journal of Computer Science, 2020) Oguntunde, Bosede
Extracting texts from images with complex backgrounds is a major challenge today. Many existing Optical Character Recognition (OCR) systems could not handle this problem. As reported in the literature, some existing methods that can handle the problem still encounter major difficulties with extracting texts from images with sharp varying contours, touching word and skewed words from scanned documents and images with such complex backgrounds. There is, therefore, a need for new methods that could easily and efficiently extract texts from these images with complex backgrounds, which is the primary reason for this work. This study collected image data and investigated the processes involved in image processing and the techniques applied for data segmentation. It employed an adaptive thresholding algorithm to the selected images to properly segment text characters from the image’s complex background. It then used Tesseract, a machine learning product, to extract the text from the image file. The images used were coloured images sourced from the internet with different formats like jpg, png, webp and different resolutions. A custom adaptive algorithm was applied to the images to unify their complex backgrounds. This algorithm leveraged on the Gaussian thresholding algorithm. The algorithm differs from the conventional Gaussian algorithm as it dynamically generated the blocksize to apply threshing to the image. This ensured that, unlike conventional image segmentation, images were processed area-wise (in pixels) as specified by the algorithm at each instance. The system was implemented using Python 3.6 programming language. Experimentation involved fifty different images with complex backgrounds. The results showed that the system was able to extract English character-based texts from images with complex backgrounds with 69.7% word-level accuracy and 81.9% character-level accuracy. The proposed method in this study proved to be more efficient as it outperformed the existing methods in terms of the character level percentage accuracy.
Assessment of Selected Data Mining Classification Algorithms for Analysis and Prediction of Certain Diseases
(University of Ibadan Journal of Science and Logics in ICT Research (UIJSLICTR), 2020-03) Oguntunde, Bosede
Medical science generates large volumes of data stored in medical repositories that could be useful for extraction of vital hidden information essential for diseases diagnosis and prognosis. In recent times, the application of data mining to knowledge discovery has shown impressive results in disease analysis and prediction. This study investigates the performance of three data mining classification algorithms, namely decision tree, Naïve Bayes, and k-nearest neighbour in predicting the likelihood of the occurrence of chronic kidney disease, breast cancer, diabetes, and hypothyroid. The datasets which were obtained from the UCI Machine were split into 60% for training and 40% for testing on the one hand and 70% for training and 30% for testing on the other hand. The performance parameters considered include classification accuracy, error rate, execution time, confusion matrix, and area under the curve. Waikato Environment for Knowledge Analysis (WEKA) was used to implement the algorithms. The findings from the analysis showed that decision tree recorded the highest prediction accuracy followed by the Naïve Bayes and k-NN algorithm while k-NN recorded the minimum execution time on the four datasets. However, k-NN also has the largest average percentage error recorded on the datasets. The findings, therefore, suggest that the performance of these classification algorithms could be influenced by the type and size of datasets.
Boothstrap Method for Measures of Statistical Accuracy
(African Journal of Pure and Applied Sciences, 2008) Oguntunde, Bosede
We introduced bootsrap method for dependent data structure and emphasis is on the construction of efficient inferential procedures for an estimator as a measure of its statistical accuracy, such as standard error, bias, ratio, coefficient of variantion and root mean square error. it was illustaretd with real time series data structure.
Building Data-Driven Decision Support System for Pragmatic Leadership.
(EDUCERE - Journal of Educational research, 2006) Oguntunde, Bosede
Decision Support System (DSS) is an interactive software-based system that assists leaders (decision makers) compile, analyze and manipulate information from raw-data documents, knowlede frameworks and/or business models to identify and solve problems and make decisions. In general, DSS's design and implementations are classified as data-driven, model-driven, knowledge-driven, document-driven and communication driven. Taxonomically, DSS could be passive, active, cooperative. A passive DSS is a system that aids the process of decision making, but that cannot bring out decision, suggestion or solutions. an active DSS can bring out such. A cooperative DSS allows the decision maker modify, complete, or refine the decision suggestions provided by the system, before sending them back to the system for validation. This paper focused on cooperative Data Driven DSS. Data-Drive DSS emphasizes access to and manipulation of time-series of internal organizatinal data and at times external data using Database Queries and On-Line Analytical Processing (OLAP0 tools.Thus, help managers (leaders) make prompt decision from the available data and models easily. The methodology forthe research is IDEFIX approach, nomally referred to as BOTTOM_UP approach to project work. The DSS is to speed-up data analysis for prompt decision-making through data model of relational Database Management System (RDBMS). the implementation optimizes the use of Mathematical Relational Algebra model for various report generation. it is implementable at any level, for practical, reality and pragmatic leadership qualities.
Comparative Analysis of Some Programming Languages
(Transnational Journal of Science and Technology, 2012) Oguntunde, Bosede
Programming languages are used for controlling the behavior of computer machines. Several programming languages exist and new are being created always. These programming languages become popular with use to different programmers because there is always a tradeoff between ease of learning and use, efficiency and power of expression. In this work we examine six programming languages two from different groups of scientific, non scientific and object oriented programming languages. We present an algorithm for performing combination and permutation to implement the comparison. Two parameters, the memory consumption and running time requirement are tested and objected oriented programming languages perform better in term of their running times although same could not be said of them in term of memory requirements.
A Comparative Study of some Traditional and Modern Cryptographic Techniques.
(International Journal of Engineering & Management Research, 2017) Oguntunde, Bosede
In the era of Internet and networks applications with the attendant prevalence of virus attacks, and intrusion of various kinds and intensities, information security has become a major challenge. There is a demand for stronger encryption techniques which are very hard to crack. The role of cryptography in the field of network security has become very pivotal. There are a wide range of cryptographic algorithms that are used for securing networks. There are also continuous research efforts to formulate new cryptographic algorithms aimed at evolving more advanced techniques for more secured ommunication. This work analyses some cryptographic techniques based on programming approaches and performances using certain criteria such as the block size, key length, and encryption time and security issues. Blowfish technique was found to offer a better performance compared to AES and RSA in terms of average encryption time. However, DES and Blowfish share the smallest block size of 64 bit while DES has the least key length of 56 bits.
Design Issues in Mobile Application Development
(African Journal of Pure and Applied Sciences, 2008) Oguntunde, Bosede
This paper discusses design issues related to developing mobile applications for business users and for other user satisfaction. it shows that despite the many limitations mobile devices have, it is worthwhile considering developing them. Mobile commerce may become the key driving force for developing mobile applications, just as electronic commerce catalyzed the development of web applications. This paper puts special emphasis on goal-driven applications, and suggests seven key principles for developing highly goal-driven mobile applications. finally, the importance of mobile usability evaluation is emphasized.
The Design of a Hybrid Model-Based Journal Recommendation System
(Advances in Science, Technology and Engineering Systems Journal, 2020) Oguntunde, Bosede
There is currently an overload of information on the internet, and this makes information search a challenging task. Researchers spend a lot of man-hour searching for journals related to their areas of research interest that can publish their research output on time. In, this study, a recommender system that can assist researchers access relevant journals that can publish their research output on time based on their preferences is developed. This system uses the information provided by researchers and previous authors' research publications to recommend journals with similar preferences. Data were collected from 867 respondents through an online questionnaire and from existing publication sources and databases on the web. The scope of the research was narrowed down to computer science-related journals. A hybrid model-based recommendation approach that combined Content-Based and Collaborative filtering was employed for the study. The Naive Bayes and Random Forest algorithms were used to model the recommender. WEKA, a machine learning tool, was used to implement the system. The result of the study showed that the Naïve Bayes produced a shorter training time (0.01s) and testing time (0.02s) than the Random forest training time (0.41) and testing time (0.09). On the other hand, the classification accuracy of the Random forest algorithm outperformed the naïve Bayes with % correctly classified instance of 89.73 and 72.66; kappa of 0.893 and 0.714; True Positive of 0.897 and 0.727 and ROC area of 0.998 and 0.977, respectively, among other metrics. The model derived in this work was used as a knowledge-base for the development of a web-based application, named "Journal Recommender" which allowed academic authors to input their preferences and obtain prompt journal recommendations. The developed system would help researchers to efficiently choose suitable journals to help their publication quest.
Development of a Mobile Agent System for Monitoring Memory Usage in a Network.
(The International Journal of Engineering and Science (IJES), 2017) Oguntunde, Bosede
Memory management concerns the process of managing the computer memory, in particular, the main memory, which is an expensive resource of the computer system. In this study, a mobile agent was developed for monitoring memory usage in a network. Monitoring the memory usage of systems in a network is essential in a multiprocessing and multitasking environment due to fact that some processes invoked at startup or those running on the background can consume physical memory and reduce the available memory in their idle states; this way, they reduce the efficiency of the system. Monitoring memory helps to increase the performance of the system and enhance the efficiency of the network. The features of the mobile agent were modeled using the Unified Modelling Language. Programming was done in Java and implementation adopted the Java Agent Development Environment (JADE), a versatile mobile agent platform. A number of computer systems were paired and the monitoring agent system was successfully deployed.
Development of a Prototype Online System for Birth and Death Regsitration in Nigeria
(International Journal of the Application of Wireless and mobile Computing, 2018-12) Oguntunde, Bosede
Accurate population statistics is very importatnt for good development planning and economic management of any country. This can be achieved through adequate and close registration and monitoring of births, deaths and migration; many developing countries however do not have adequate facilities for these tasks. Where such facilities are available, the processes are tedious, slow and stressful, hence they are not widely used. This work is an attempt to bridge the gap, it presents an online information system for monitoring births and deaths rates in Nigeria. A database for registering births and deaths was created with SQlite at the backend, JavaScript - a lightweight, interpretive scripting language was used to ensure dynamic web pages and object-oriented Node JS for the server side language due to its efficiency as a server side language.
Embedded Mobile Agent (EMA) for Distributed Information Retrieval
(International Journal of Computer Science and Information Security, 2015) Oguntunde, Bosede
Mobile agent paradigm has been recognised as a viable approach for building distributed applications. Mobile agents migrate through the network, execute asynchronously and autonomously, conserve bandwidth, achieve better load balancing, adapt dynamically to changes in their environment, are robust and fault tolerant. Existing agents run and execute on agent platforms also called, the Mobile Agent System (MAS), which provides run-time execution and support facilitites for mobile agent to accomplish it tasks. These MASs from different vendors are different in laguage, design,and implementation and are not interoperateable, this impedes the achievement of the full potentials of mobile agent paradigm. This work is aimed at providing a robust structure for deploying mobile agents so they can execute independent of the MAS. We propose a lightweight agent to run in the kernel mode of the operating system as an operating system service, giving an impression of the agent directly communicating with the operating systems.
Emergence of More Female Role Models in the Sciences: The Case of Students’ Academic Performance in a Nigerian Private University
(International Journal of Science and Technoledge,, 2020) Oguntunde, Bosede
In this article, we present an empirical study to provide more evidence on the strength of the female gender in the sciences. It is on record that the percentage of women in the sciences is still low compared to the male counterpart. This paper is thus intended to make use of the performance of female undergraduates in the sciences to encourage more participation from this group. The study focused on six science courses that already graduated students from Redeemer’s university for at least 4 years as at the time of the research. We compared the average performance of female students with that of male students in each program over 5 years. The results obtained suggest that female students also have great potentials in the sciences, with better performance in some instances than male students. Consequently, we encourage more women participation in Science, Technology, Engineering and Mathematics (STEM) disciplines.
An Enhanced Encryption System Based on the Unison of Lossless Compression and a Tri-Hashing Algorithm
(International Journal of Advanced Science and Technology, 2020) Oguntunde, Bosede
In recent times, technological advancement in communications has made it essential to protect the ever-increasing amount of data and ensure the privacy of users. There is a lot of sensitive data present on the web, and it needs to be protected. Using conventional security methods like RSA, DES, AES algorithms, and others alone have become inadequate in protecting data from any kind of potential abuse. Complex algorithms are required to not only to encrypt the data but also to compress and distribute the data. This is due to the fact that some existing encryption techniques can be cracked given enough time and resources. This work attempts to resolve these flaws by combining a lossless compression technique with encryption in a single process or selective encryption of data. The proposed algorithm, tagged Enhanced Encryption System (EES), uses three different keys. One hashed from PBKDF2, the other from the PI sequence and finally DNA sequence, where each one is invariant of the user’s inputted key. Following this operation, there are infinite possible keys generated under every iteration. Lossless compression was applied to the test data based on the Lempel-Ziv-Welch (LZW) algorithm. Data encryption was implemented with the python programming language. The output produced different ciphertexts for the same plain text, thereby confusing any hacker that tries to brute-force the system. The experimental results showed that EES achieved better encryption and decryption run-time without losing data when compared to the AES, RSA and DES algorithms.
An Experimental Evaluation of Short-Term Stock Prediction in the Nigerian Stock Market using Multilayer Perceptron Neural Network
(African Journal Comping & ICT, 2020-12) Oguntunde, Bosede
Stock prices fluctuate, are unpredictable, and this has increased interest in the stock price prediction research. This work aims at predicting stock prices in the Nigerian Stock Market using Artificial Neural Network (ANN). Seven-year data obtained from the Investing Website for ten companies listed as the top gainers in the Nigerian Stock Market were used, having attributes High, Low, Close, Open. The data set was divided into a training dataset (70%), validating dataset (15%), testing dataset (15%), a Multilayer Perceptron Neural Network (MLP) using Levenberg Marquardt algorithm to build, train and test the model. The model generated was used for a short-term prediction, predicting the next days’ opening and closing prices. The results from the training model were used for comparison with the testing data to ascertain the accuracy of the model. Results from the data analysis carried out using MATLAB revealed that Multilayer Perceptron neural network technique gives satisfactory output with best validation performance mean square value of 0.0059445 at epoch 20, with R score of 0.94654, 0.92687, 0.8584 and 0.92997 respectively for training, validation, Test and combined set. It has Mean Square Error of 5.92336e-3, 5.94448e-3 and 7.98277e-3 for training, validation and testing respectively; and regression value of 9.97966e-1, 9.97813e-1 and 9.97351e-1 respectively for training, validation and testing.
Exploring the Performance Characteristics of Naive Bayes Classifier in the Sentiment Analysis of an Airline's Social Media Data
(Advances in Science, Technology and Engineering Systems Journal, 2020) Oguntunde, Bosede
Airline operators get much feedback from their customers which are vital for both operational and strategic planning. Social media has become one of the most popular platforms for obtaining such feedback. however, to analyze, catgorize and generate useful insight from the huge quantity of data on social media is not a trivial task. This study investigates the capability of the Naive bayes classifer for analyzing sentiments of airline image branding. it further examines the impact of data size on the accuracy of the classifier. We collected data about some online conversations relating to an incident where an airline's security operatives roughly handled a passenger as a case study. It was reported that the incident resulted in a loss of about $i billion of the company's corporate value. Data were extracted from twitter, preprocessed and analyzed using the Naive bayes classifier. the findings showed a 62.53% negative and 37.47% positive sentiments about the incident with a classification accuracy of over 0.97. To assess the impact of training size on the accuracy of the classifier, the training sets were varied into different sizes. A direct linear relationship between the training size and the classifier's accuracy was observed. this implies that large training data sets have the potentials for increasing the classification accuracy of the classifier. However, it was also observed that a continous increase in the classification size could lead to overfitting. Hence, there is a need to develop mechanisms for determining optimum training size for finest accuracy of the classifier. The negative perceptions of customer could have a damaging effect on a brand and ultimately lead to a catastrophic loss in the organization.
A Framework for an Operating System-based Mobile Agent Interoperability
(International Organization of Scientific Research Journal of Computer Engineering (IOSR-JCE), 2013) Oguntunde, Bosede
Mobile agent technology has grown in acceptance over the years for distributed applications, but it is yet to be adopted as ubiquitous solution technique. This is due to its complexity and lack of interoperability. Mobile agent executes on mobile agent platform, these platforms from different vendors are design, and language specific, and are thus non interoperable. In other words mobile agent built on one platform cannot interact with or execute on any other platform. There is a need to provide a common base on which agents from different vendors can interact and interoperate. This work presents a framework for mobile agent interoperability by providing an Embedded Mobile Agent (EMA) system into the Windows Operating System kernel so that it can run as a service; this was done to eliminate the overheads associated with the agent platforms and enhance mobile agents’ interoperability. The targeted OS were Windows XP, Windows Vista and Windows7.
A Framework for Evaluative Results Integration for Information Retrieval System
(The Journal of Computer Science and its Application, 2013-06) Oguntunde, Bosede
Information Retrieval (IR) systems are evaluated fro two levels, namely the system-centric and user-centric levels. these two levels are made up of three perspectives (aspect) each. the problem with this arrangement is that evaluating the system from any of these perspectives leads to independent evalative results. Therefore, using these results to improve IR systems remains a major challenge. This paper presents an integrative framework for integrating evaluative results from each of the perspectives of the user-centric levels.The integrative framework was used to provide Decision variables (DVs) that were harnessed into a Survey Instrument (SI)used in elliciting data from a total of 250 respondents between years 2010 and 2011. The Crombach Alpha (CA) test was used to test the Dvs. the result of the CA showed that the DVs were internally consistent since their scores range from 0.70 and above, WHile the results indicate that the framework to be proposed would serve its purpose, it also confirm that it needs more testing. The technique of factor analysis was used to test the framework further based on the data elicited using the SI. the purpose was to find out if there is any reasonable correlation between user satisfaction and other factors. The correlation obtained revealed that the use of an integrative agent would assist in harnessing the three perspectives of the user-centric levels. This provided a new way of exploiting the three perspectives at once instead of individually as has been the case. Thus, we propose base on this result that the problem of individual and independent evaluative results that are not usable can be eliminated,
A Framework for Multi-Tier Internet Service Architecture for Doctors’ Directory
(International Journal of Computer and Technology, 2013) Oguntunde, Bosede
The rapid advancements in technology and telecommunications, especially the Internet, have led to an explosive growth of Web-based Internet Applications. This work presents a framework for the development of a web based information system for doctor’s directory. The system connects patients with medical specialists (consultants) in diverse areas of medicine. It does not only provide information about the specialists; the patient can as well secure an appointment with the specialists. We propose a three-tier Internet Service architecture for the directory.
Hybridized Deep Convolutional Neural Network and Fuzzy Support Vector Machines for Breast Cancer Detection
(SN Computer Science, 2021) Oguntunde, Bosede
A cancerous development that originates from breast tissue is known as breast cancer, and it is reported to be the leading cause of women death globally. previous researches have proved that the application of Computer-Aided Detection (CADs) in screeening mammography can assist the radiologist in avoiding missing breast cancer cases. However, many existing systems are prone to false detection or misclassification and are majorly tailored towards either binary classification or theer-class classification. Therefore, this study seeks to develop both two-class and three-class models for breast cancer detection and classification employing a dep convolutional neural network (DCNN) with fuzzy support vector machines. The models were developed using mammograms downloaded from the digital databse for screening mammogragraphy (DDSM) and curated breast imaging subset CBISDDSM data repositories. The datasets were preprocessed, and feature extracted for classification with DCNN and fuzzy support vector machine (SVM). The system was evaluated using accuracy, sensitivity, AUC, Fi-score, and confusion matrix. The 3-class model gave an accuracy of 81.43% for DCNN and 85.00% accuracy for the fuzzy SVM. the first layer of the serial 2-layer DCNN with fuzzy SVM for binary prediction yielded 99.61% and 100.00% accuracy, respectively. However, the second layer gave 86.60% and 91.65, respectively. This study's contribution to knowledge includes the hybridization of deep convolutional neural network with fuzzy support vector machines to improve the detection and classification of cancerous and non-cancerous breast tumours in both binary classification and three-class classification scenarios.
Impact of Social Networking Media Usage on the Academic Performance of Students of Redeemer's University.
(International Journal of Engineering Research and Development, 2017-10) Oguntunde, Bosede
Online social networking has taken the centre stage among the many services offered by the Internet. Young people and students of higher institutions in particular have taken keen interest in interactions on the social media. In view of perceived decline in students' academic performances, pundits have suggested taht unbridled indulgences in social media could have a major role in their poor performances. in this study, we investigate the impact of the social media networking on the academic performances of students of the Redeemer's University. A sample f 200 students were drawn across departments on proportional basis. A structured questionaire was administered, processed and analysed. From the results, it was discovered that only the size of friendship on the social media has significant impacts on students' performances. Factors such as daily time spent and hourly time spent on social media have no signifcant effect on the students' academic performance.

Browsing by Author "Oguntunde, Bosede"

Results Per Page

Sort Options