Papers by Abayomi O Agbeyangi
arXiv (Cornell University), Jan 7, 2024
Nigeria's remarkable information and communication technology (ICT) journey spans decades, playin... more Nigeria's remarkable information and communication technology (ICT) journey spans decades, playing a pivotal role in economic sustainability, especially as the nation celebrates its Republic at Sixty. This paper provides an overview of Nigeria's ICT journey, underscoring its central role in sustainable economic prosperity. We explore the potential of artificial intelligence, blockchain, and the Internet of Things (IoT), revealing the remarkable opportunities on the horizon. We stress the urgency of achieving digital inclusivity, bridging the urban-rural gap, and reducing the technological divide, all of which are critical as Nigeria marks its sixtieth year. We intend to prove the invaluable opportunities of ICT for policymakers, business leaders, and educational institutes as Nigeria looks towards enduring economic development in this digital age. Specifically, we envision a dynamic landscape where emerging technologies are set to redefine industries, supercharge economic growth, and enhance the quality of life for every Nigerian.
Integration of Blockchain Into Medical Data Security
Advances in healthcare information systems and administration book series, Jun 30, 2023
A Critical Analysis of Cloud Computing Adoption in Selected West African Countries
Impact of Blockchain on the Security and Privacy of IoT-Empowered Healthcare Systems
Advances in healthcare information systems and administration book series, Jun 30, 2023
Solving the House Numbering Problem in Nigeria: Internet of Things (IoT) As An Emerging Solution
2022 5th Information Technology for Education and Development (ITED)
Informatics in education, Dec 15, 2022
The aim of this study was to determine the predispositions of the studied groups of students to w... more The aim of this study was to determine the predispositions of the studied groups of students to work in the IT sector. The basis for predisposition assessment was their voluntary self-assessment of certain preferences, which are related to the theory of multiple intelligences of Professor Gardner. The study was conducted on a reference group of IT sector employees, assuming that they will be the model, to which the results of the study will be related. The method used to obtain data about the students' predispositions was a test carried out in an auditorium mode or online. More than 500 students from several countries were surveyed and interesting statistical material was obtained allowing for comparison between groups. The most important result was to find a way to sort the students into groups in order from most similar in their aptitude to the market pattern to least. This made it possible to determine the boundary beyond which students could be considered selected for a job in the IT sector. Statistical hypotheses about the similarity of the student groups to the reference group were verified. The results were both positive, confirming that a large percentage of students have predispositions to work in the IT market, and less promising. The authors are convinced that the method can be applied all over the world, as they examined groups in very diverse countries, taking into account, for example, location, education system, culture or religion.
Yorùbá numeral system has been seen to have the most unusual and complicated of any of the world&... more Yorùbá numeral system has been seen to have the most unusual and complicated of any of the world's natural language numeral systems due to the complexity involved in its derivation. In this paper, we present the development of an English to Yorùbá text-to-text number translation system. In our approach, we examined English and Yorùbá numerals to understand the concepts and techniques underlining their translation process. The theories, rules and computational processes underlying the numeral system were used to formulate the model for the work. The design, requirement and the specification for the system were done in Unified Modeling Language (UML) and Automata theory. The designed system was implemented using Python programming language and other modules (PyQt4 and NLTK). The experimental results showed that the system scored 98% on all the output considered.
Unmanned aerial vehicles (UAVs) known variously as drones or remotely piloted vehicles (RPVs) are... more Unmanned aerial vehicles (UAVs) known variously as drones or remotely piloted vehicles (RPVs) are small aircraft that can fly without an onboard human operator. They are either autonomous or semi-autonomous and can carry cameras, sensors, communication equipment or other payloads. Their uses have been seen as the most effective for aerial surveillance. In this paper, we review the various trends in their development vis-à-vis their application in aerial surveillance. The results gathered from our review shows that UAVs are very effective for aerial surveillance.
Automatic Identification of Vehicle Plate Number using Raspberry Pi
2020 International Conference in Mathematics, Computer Engineering and Computer Science (ICMCECS), 2020
Vehicle’s plate number is a unique identity by which individual vehicle can be identified. Vehicl... more Vehicle’s plate number is a unique identity by which individual vehicle can be identified. Vehicle plate recognition system helps to capture a vehicle plate number, extract the numbers on the plate and check the details of the car owner. As the number of car owners in a country increases, identifying and charging unlawful vehicles on the road has been a tedious work for law enforcement agents. In this paper, we present an automatic vehicle plate recognition system using Raspberry pi. A Camera was incorporated to help in capturing the plate number images and it is interfaced to a Raspberry pi processor for authentication. Using the Open Computer Vision (Open CV) and Optical Character Recognition (OCR), the system can extract numbers from the captured plate image and completely automate the license plate recognition. The experimental results from several testing in different locations and conditions show that the system performed better than most of the baseline studies considered.
The Yorùbá Numeral System:: A Review in Relation to other Numeral Systems
Ambiguity is a pervasive characteristic of natural language. The specific sense intended is mostl... more Ambiguity is a pervasive characteristic of natural language. The specific sense intended is mostly determined by the textual context in which an instance of the ambiguous word appears. In this paper, we examine how words which can be used as both nouns and verbs in a simple subject-verb-object (SVO) English sentence can be disambiguate. First, we collate words that are normally used in the home domain according to their different parts of speech. Next, their corresponding Standard Yorùbá translations were obtained. Phrase Structure Grammar was used to determine the structure of the sentence and the position of each parts of speech that make up the sentence. Rewrite rules were also written for the simple English sentences constructed from a combination of these ambiguous words; the words were then stored in a database designed to accept determiners, nouns and verbs. Thereafter, the system was implemented using Python programming language and SQLite3 for the database. The system was e...
Rule-based approach is a good approach for Machine Translation System used for language with lots... more Rule-based approach is a good approach for Machine Translation System used for language with lots of grammar which Yorùbá language is one. In this paper we present Rule-based approach to Yorúbà Machine Translation System. The popularity of Yorúbà language among the three main languages in Nigeria calls for the need to computerise the language. Transfer Rule-Based Machine Translation is use in the development of the System. It was used because it allows us to use manual tagging of the part of speech (POS). Rewrite rules was developed for the two languages (Yorùbá and English). The data was collected from home domain vocabularies. The re-write rule was verified using Natural Language Toolkits (NLTKs) and implement using python programming language. The system interface gives the user the opportunity to type simple English language sentence and the resulting Yorùbá Translation is displayed. The result shows that the system performance is close to the expert opinion, having considered t...
YorAA: An Authorship Attribution of Yorùbá Texts
Journal of Computer Science and Its Application, 2021
The process of establishing the most likely author of a collection of texts or documents whose au... more The process of establishing the most likely author of a collection of texts or documents whose authorship must be verified is known as authorship attribution. Several studies have been reported in the literature on the task, but rarely any reported work on Yorùbá language texts. In this paper, the development of an automatic Yorùbá written texts authorship attribution system (YorAA) is reported. The literary works of six Yorùbá authors were considered. Stylometry features were extracted from the texts using the BoW approach and lexical/syntactic word frequencies approach. The Support Vector Machine, Multilayer Perceptron and Random Forest algorithms were used for the classification analysis. The experimental results showed that the developed YorAA system achieved accuracy, recall, precision and F1 measures values of 95%, 83%, 84% and 84% respectively on the average, for all the six authors. The results demonstrate that with a database of written texts in Yorùbá language, that is eno...
An Autonomous Obstacle Avoidance Robot Using Ultrasonic Sensor
Journal of Computer Science and Its Application, 2020
The use of robot and its enormous technological applications in today‟s era of industrial and int... more The use of robot and its enormous technological applications in today‟s era of industrial and intelligent systems has been seen to be highly impactful. The ability of these robots to move freely with minimal control is posing a real challenge. In this paper, the development of an autonomous obstacle avoidance robot using ultrasonic sensors is presented. In the design, the ultrasonic sensor serves as the eye of the robot to aid its autonomous movement. The robot is a wheeled type which can either be control using a dedicated control application (Android App) or autonomously. The control application was an added feature in case there is need to manually control the robot. The accuracy of the robot obstacle avoidance is highly encouraging scoring 87.5%, although, there are other challenges which are noted for further study. Keywords: Robotic, Obstacle avoidance, Autonomous system, Ultrasonic sensor.
IAES International Journal of Artificial Intelligence (IJ-AI), 2017
Yorùbá numerals have been seen as one of the most interesting but quite complicated numeral syste... more Yorùbá numerals have been seen as one of the most interesting but quite complicated numeral system. In this paper we present the development of a web-based English to Yorùbá numeral translation system. The system translates English numbers both in figure and text to its standard Yorùbá form. The computational processes underlying both numerals were used to formulate the model for the work. Unified Modeling language (UML) and Automata theory was used for the system design and specification. The designed system was implemented using Google Web App Engine with support for python. The result of the system evaluation using mean opinion score approach shows that the system gives a recall of 100% on all the output considered.
IOSR Journal of Computer Engineering, 2017
Biometric technology has been seen as one of the most effective technology for human secured iden... more Biometric technology has been seen as one of the most effective technology for human secured identification systems. In this paper, we present the development of an automated fingerprint-based door control system to address the shortcomings of the manual door control systems. The developed system used fingerprint sensing device and an application to control the whole system. The fingerprint sensing device controls user identification, enrollment and verification while the application provides access to the system. The control application was implemented using C# programming language. The result shows that the system works as expected and scored 89% from the testing metrics used. There are other issues which can be taken as further research.
Authorship Verification of Yorùbá Blog Posts using Character N-grams
2020 International Conference in Mathematics, Computer Engineering and Computer Science (ICMCECS)
Predicting Mobile Portability Across Telecommunication Networks Using the Integrated-KLR
International Journal of Intelligent Information Technologies
Mobile number portability (MNP) across telecommunication networks entails the movement of a custo... more Mobile number portability (MNP) across telecommunication networks entails the movement of a customer from one mobile service provider to another. This, often, is as a result of seeking better service delivery or personal choice. Churning prediction techniques seek to predict customers tending to churn and allow for improved customer sustenance campaigns and the cost therein through an improved service efficiency to customer. In this paper, MNP predicting model using integrated kernel logistic regression (integrated-KLR) is proposed. The Integrated-KLR is a combination of kernel logistic regression and expectation-maximization clustering which helps in proactively detecting potential customers before defection. The proposed approach was evaluated with five others, mostly used algorithms: SOM, MLP, Naïve Bayes, RF, J48. The proposed iKLR outperforms the other algorithms with ROC and PRC of 0.856 and 0.650, respectively.
Predicting Mobile Portability Across Telecommunication Networks Using the Integrated-KLR
International Journal of Intelligent Information Technologies
Mobile number portability (MNP) across telecommunication networks entails the movement of a custo... more Mobile number portability (MNP) across telecommunication networks entails the movement of a customer from one mobile service provider to another. This, often, is as a result of seeking better service delivery or personal choice. Churning prediction techniques seek to predict customers tending to churn and allow for improved customer sustenance campaigns and the cost therein through an improved service efficiency to customer. In this paper, MNP predicting model using integrated kernel logistic regression (integrated-KLR) is proposed. The Integrated-KLR is a combination of kernel logistic regression and expectation-maximization clustering which helps in proactively detecting potential customers before defection. The proposed approach was evaluated with five others, mostly used algorithms: SOM, MLP, Naïve Bayes, RF, J48. The proposed iKLR outperforms the other algorithms with ROC and PRC of 0.856 and 0.650, respectively.
Predicting Mobile Portability Across Telecommunication Networks Using the Integrated-KLR
International Journal of Intelligent Information Technologies
Mobile number portability (MNP) across telecommunication networks entails the movement of a custo... more Mobile number portability (MNP) across telecommunication networks entails the movement of a customer from one mobile service provider to another. This, often, is as a result of seeking better service delivery or personal choice. Churning prediction techniques seek to predict customers tending to churn and allow for improved customer sustenance campaigns and the cost therein through an improved service efficiency to customer. In this paper, MNP predicting model using integrated kernel logistic regression (integrated-KLR) is proposed. The Integrated-KLR is a combination of kernel logistic regression and expectation-maximization clustering which helps in proactively detecting potential customers before defection. The proposed approach was evaluated with five others, mostly used algorithms: SOM, MLP, Naïve Bayes, RF, J48. The proposed iKLR outperforms the other algorithms with ROC and PRC of 0.856 and 0.650, respectively.
Uploads
Papers by Abayomi O Agbeyangi