Publication Title Improving User Interface Design and Efficiency Using Graphic Design and Animation Techniques Download PDF
Publication Type journal
Publisher NIPES-Journal of Science and Technology Research 6(3) 2024 pp. 67-86 ISSN-2682-5821
Paper Link https://doi.org/10.5281/zenodo.13765451
Publication Authors 1Akwukwuma, V.V.N., 1Chete F.O., 2Okpako A.E and 1Irabor F.E.
Year Published 2024-09-15
Abstract User interface (UI) design has undergone a significant evolution, integrating graphic design and animation techniques that have redefined digital experiences. This evolution, driven by technological advancements and a deeper understanding of user behaviour, has emphasized the fusion of aesthetics and functionality as a cornerstone in modern UI design. This research explores the integration of graphic design and animation techniques to enhance user interface (UI) design and user experience (UX) within digital environments. The study includes a detailed analysis of user perception regarding functional enhancements, impact on accessibility, and efficiency of task completion through data collected from respondents. A prototype of car booking and rental App was designed using Figma as the primary design tool which facilitated collaborative design processes, leading to the creation of engaging user experiences such as Landing Page Animation and Circular Navigation Animation. The research approach employed in this study involves a combination of survey and direct observation. The findings reveal a positive reception among users regarding functional enhancements, with a majority strongly agreeing (63.20%) and a minority expressing dissent (5.01%). Similarly, the impact on accessibility garnered high satisfaction levels, with approximately 60.7% strongly agreeing and minimal dissent (3.66%). Efficiency in task completion also received positive feedback, with 55.46% strongly agreeing and dissent at 2.94%. The design and data analysis journey highlight the significance of integrating visually appealing and interactive elements in UIs. This research work underscores the importance of design innovation and data-driven decision-making in optimizing UI design for enhanced user experiences and satisfaction.
Publication Title Usability Analysis of E-Commerce Mobile Applications Download PDF
Publication Type journal
Publisher NIPES-Journal of Science and Technology Research 6(3) 2024 pp. 46-66 ISSN-2682-5821
Paper Link https://doi.org/10.5281/zenodo.13765436
Publication Authors Akwukwuma, V.V.N., 1Chete F.O., 2Okpako A.E and 1Nkwor U.M
Year Published 2024-06-03
Abstract E-commerce has completely transformed the way people purchase; it is therefore expedient to prioritize methods for enhancing the userfriendliness of e-commerce applications. Despite the development of ecommerce mobile applications, there exists a substantial vacuum in comprehensive usability evaluations, impeding the improvement of user experiences. Users confront different hurdles, ranging from navigation issues and inadequate search functionality to arduous checkout procedures, which might potentially dissuade them from completing transactions. Due to lack of extensive work on e-commerce apps used by Nigerians, there is lack of understanding regarding how to effectively tackle the usability difficulties observed in e-commerce mobile apps in Nigeria. This research aims to address these gaps by measuring three key usability metrics: Efficiency, Effectiveness, and User Satisfaction on three commonly used e-commerce apps in Nigeria which are Konga, Jumia, and AliExpress. The research approach employed in this study involves a combination of survey and direct observation. The findings indicated that the Jumia e-commerce app is rated better than the AliExpress and Konga app in terms of efficiency, effectiveness, and user satisfaction due to its user-friendly interface, effective data handling and smooth navigation. AliExpress also demonstrated exceptional performance while the Konga app received the lowest ratings across the three usability metrics. In summary, the study underscores the need for user-centric design and ongoing improvement in e-commerce mobile applications in Nigeria. It stresses the value of investing in usability advancements to retain and ensure consumer satisfaction
Publication Title Taxonomy of Software Agents Download PDF
Publication Type journal
Publisher International Journal of Novel Research in Computer Science and Software Engineering
Paper Link www.noveltyjournals.com
Publication Authors Omoghenemuko Greg Imoniyovwe , Okpako Abugor Ejaita
Year Published 2018-06-04
Abstract Agent is an old concept in human civilisation, and it comes from the word agency. Physical agents that act as facilitators in discharging duties unbehalf of their owners or clients are no more in vogue, since the invention of the programmable electronic device called computer, human activities have been influenced greatly and productivity has been on the increase because of the application of softwares to undertake most human activities. These softwares now act as agents for their owners or users to facilitate transactions in this present information age; to birth what is popular known as software agents. The Internet, which is a global computer networked environment, is the physical platform for ubiquitous computation where people of different domains of human specialisation, use software agents for business transactions. The researchers define an agent, software agents and take a panoramic overview of characteristics of software agents, and present a robust taxonomy of software agents for proper understanding, highlight some importance of software agents
Publication Title An Analysis of Machine Learning Techniques for Verifying and Improving Veracity in Big Data Download PDF
Publication Type journal
Publisher International Journal of Scientific Research and Engineering Development-
Paper Link www.ijsred.com
Publication Authors Dr. Anazia Eluemunor Kizito , Dr. Okpako Abugo Ejaita
Year Published 2022-06-04
Abstract Veracity is one of the characteristics of big data that deals with the quality, trustworthiness, accuracy, authenticity, truthfulness, provenance, unbiasness, and completeness of big data. It is observed that one of the major problems associated with big data at point of generation and storage, is usually itspoor veracity rate. Veracity problems in big data are due to activities like wilful falsity, domain negligence, value misrepresentation, deliberate biasness, inaccuracy in device measurement, computing errors, hacking, social engineering and other security breaches. In order to reduce and manage these veracity problems in big data so many methods and techniques have been proposed. In this research work, Machine Learning Techniques and Algorithms is proposed as the means of improving and verifying the Veracity in big data. We understudied the various techniques, algorithms, advantages and disadvantages of Machine Learning Techniques applications of improving and verifying the Veracity in big data classification.
Publication Title A FUZZY LOGIC RISK CONTROL AND SELFASSESSMENT METRICS FOR e-BANKING OPERATIONAL RISK ANALYSIS Download PDF
Publication Type journal
Publisher THE JOURNAL OF COMPUTER SCIENCE AND ITS APPLICATIONS Vol. 27, No. 2 December 2020
Publication Authors Ako, R. E., 2 Oghorodi, D. and 3 Okpako, A. E.
Year Published 2020-12-12
Abstract Operational risk is the risk of losses arising from the failure or inadequate internal processes, human resources, systems, and external events that affect the bank's operations as defined by Basel Committee on Banking Supervision. Defining a suitable set of risk measurement metrics is considered one of the most important issues for any risk analysis. It enables the quantitative evaluation of the risk exposure level and the effectiveness of internal control system. Risk measurement is needed to provide an effective means to quantify the risk of existing or planned systems to enable understanding of the overall security level and to guide decision making. Given the number of successful attacks against financial Institutions and the sophistication of the tactics used by attackers, existing classical measurement approaches are no longer enough. This study focuses on fuzzy logic-based metric identification to measurement of the risk exposure level, to enable financial institutions to see the overall risk level and security state of their E-banking systems and to assist with decision making. This will provide a newer dimension to risk management by shifting from risk measurement based on probability and classical set theory to Fuzzy Logic (FL) measurement. In this paper fuzzy logic-based metrics is presented and expressed as a function of six factors (triggering events, avoidance, recovery, Undesirable Operational State (UOS), cost of Undesirable Operational State (UOS) occurrence and severity of risk occurrence) as proposed by [1].
Publication Title A Fuzzy Logic-Based Framework for E-banking Operational Risk Assessment Download PDF
Publication Type journal
Publisher Journal of Digital Innovations & Contemp Res. In Sc., Eng & Tech. Vol. 7, No. 1. Pp 59-74
Paper Link DOI: dx.doi.org/10.22624/AIMS/DIGITAL/V7N1P6
Publication Authors Ako, Rita Erhovwo & Okpako, Abugor Ejaita
Year Published 2019-03-28
Abstract Emerging realities in assessing operational risk (OR) specifically in the context of E-banking which is poised with heightened technical complexities, has raised the need for a paradigm shift from risk models based on probability and classical set theory to Fuzzy Logic (FL). Threat(s) /threat sources continue to defy probability analysis, due to uncertainties of categorizing the risks in any well-established patterns. These uncertainties which comes in different shapes and flavours such as infrequent but very large financial losses, ever changing nature of internal controls, lack of long historical data, entangled cause-and-effect relationship etc. makes it difficult to assess the exact degree of exposures to OR. Therefore it is essential to develop valid and reliable framework for effective OR assessment. Fuzzy Logic (FL) models are built upon fuzzy logic and fuzzy set theory which is suitable for analysing risks with uncertainties, incomplete data and expert opinions. In this paper, a new Operational Risk Assessment (ORA) framework for E-banking was developed using Fuzzy Logic. In addition, a new ORA factor was identified to determine the magnitude of impact and the risk exposure level.
Publication Title Implementation of Neutrosophic-Based Decision Support System for Effective Diagnosis of Liver Disease Download PDF
Publication Type journal
Publisher International Journal of Research and Scientific Innovation (IJRSI) | Volume VIII, Issue IV, April 2021 | ISSN 2321–2705
Paper Link https://dx.doi.org/10.51244/IJRSI.2021.8403
Publication Authors Okpako, A.E1* , Omoghenemuko, G.I.2 , Odikwa, H.N3
Year Published 2021-04-04
Abstract Liver diseases have been shown to be highly correlated to excessive consumption of alcohol and other harmful or injurious substances such as drugs and toxins. The Nigeria social milieu cannot do away with excessive consumption of alcoholicrelated substances and drugs, which are predominantly consumed on weekends either in parties or clubs. Most Nigeria teenagers and adults alike who are supposedly considered as socially correct indulge in excessive consumption of alcohol and other harmful substances leaving the alcoholic companies and shops smiling to the banks. This unpalatable trend has dire consequences as it raises the figure of liver disease patients, which is mostly confused with other tropical diseases like malaria and as such its manifestation cannot be predicted on time with certainty. Timely diagnosis is a panacea to the management of the disease but this is not the case most times as there are handful of hepatologists that can adequately diagnose this disease since General practitioner might not be able to diagnose them on time. This research seeks to comparatively analyze the performance of Neutrosophic-based Decision Support System and Multilayer Neural Network (Traditional Neural Network) in the classification of Indian Liver Patient Dataset (ILDP) as well as articulate its suitability in the classification or diagnosis of liver disease (ILPD). Object Oriented Analysis and Design methodology was used while the implementation was done using WEKA and Java on a Netbeans platform. Experimental results show that Neutrosophic-Based Decision Support System (NBDSS) with an accuracy of 96.41% using a confusability measurement threshold of 0.003278 performed better than the conventional neural network with an accuracy of 72.45%. This clearly shows that Neutrosophic-based Decision Support System is suitable for the diagnosis of liver diseases.
Publication Title A Framework for Diagnosing Confusable Diseases using Neutrosophic based Neural Network Download PDF
Publication Type journal
Publisher International Journal of Computer Applications (0975 – 8887)
Publication Authors Okpako Abugor Ejaita, Asagba P. O
Year Published 2017-06-06
Abstract The two major motivations in medical science are to prevent and diagnose diseases. Diagnosis of disease must be done with care since it is the first stage of therapeutic actions towards eventual management of the disease; a mistake at this stage is disastrous and such adequate care must be ensured. Diagnosis becomes difficult in medical domain due to influence of medical uncertainties that arises from confusability in disease symptomatic presentation between two diseases. This confusability of these diseases stems from the overlaps in the disease symptomatic presentation and has led to misdiagnosis with various degrees of associated costs and in worst cases led to death. In this research, we present the analysis of the existing systems and finally present a framework for the diagnosis of confusable disease using neutrosophic-based neural network.
Publication Title Development of Water Billing System: A Case Study of Akwa Ibom State Water Company Limited, Eket Branch Download PDF
Publication Type journal
Publisher The International Journal Of Science &Technoledge (ISSN 2321 – 919X)
Publication Authors James, Gabriel Gregory, Okpako Abugor Ejaita, Inam, I. A.
Year Published 2016-07-07
Abstract Computers are now taking over virtually every field of human endeavours and most functions. Computers affect our daily lives more and more and hopefully, can be used to improve the quality of our lives by releasing us from dull, repetitive tasks and allowing us to expand our minds. Thispaper explains how the old Water Billing System can be improved in AkwaIbom State Water Company Limited (AKSWCL), Eket. The research work aims at designing and developing a Water Billing System for AKSWCL. The formation of the system was approached using a requirement, analysis and capturing methodology that consist of four main phases, namely domain understanding, requirements capturing, classification, and validation. A tool called the Visual Basic was used for validating the syntax of the system while a prototype with test scripts was used for validating the system as a whole.
Publication Title Development of Hybrid Intelligent based Information Retreival Technique Download PDF
Publication Type journal
Publisher International Journal of Computer Applications
Publication Authors Gregory Gabriel James, Abugor Ejaita Okpako, C. Ituma, J.E. Asuquo
Year Published 2022-10-10
Abstract To find information over the internet to a certain level, depends on our capacity to track all related subjects and classify them into bunches of comparative themes. As the domain of information is enlarging over the internet , the time consumption and the difficulties experienced by researchers to find a relevant material that meets the user’s specified request increases, thereby putting the researchers into a state of dilemma at the cause of searching for relevant information that meets their need. The pursuit to trim down the challenges of impasse faced by researchers as well as time exhausted to filter relevant materials in the pools of irrelevant materials have motivated this research. The work aims at developing a Neurofuzzy intelligent search framework for tracking and recovery of web archives. The method used was Object-Oriented analysis and Design (OOAD). A hybrid intelligent framework – based tracking system was utilized as the finest choice for tracking archives, since the shortcomings of Neural Network and Fuzzy Logic based tracking system were complemented while their individual qualities are upgraded. This paper expands prior Fuzzy-based information retrieval approaches through increasing the Fuzzy variables and their linguistic values by utilizing distinctive rules and functions that characterized the record. The mapping of input to output parameters was achieved by applying the triangular membership’s functions. Adaptive neural fuzzy inference system model also utilized the Takagi Sugeno inference mechanism. It was observed that using ANFIS improved the hybrid intelligent framework – based tracking system performance slightly with 0.22641 representing 22.64% over the Fuzzy Inference System (FIS) results, thereby guarantee retrieval of most relevant documents that met the user’s request.
Publication Title Fake News and Threat to Democracy: The Nigeria perspective Download PDF
Publication Type journal
Publisher Innovations, Number 69 June 2022
Publication Authors Ojobo Ogheneruemu Lucky, Okpako Abugor Ejaita, Irori Okiemute Queenett
Year Published 2022-03-07
Abstract The focus of this study is to investigate fake news and its threat on Nigeria’s democracy. The study is anchored on three objectives which are to: examine the rate of the spread of fake news among Nigerians, on both social and traditional media; find out the effect of fake news on Nigeria’s democracy and determine actions that can be appropriate in combating it. The study used purposive sampling and surveyed 60 social media users from Delta and Edo states (using 30 respondents from each of the two states) and administered questionnaire appropriately. The study found that despite the awareness of fake news among respondents, there is still increase of fake news because; majority of people do not take time to verify the source of information before sharing and acting on it, hence, they unintentionally propel the spread of fake news. Most respondent feel fake news circulates and ends only in social media and does not have any effect on democracy. The study also found that politics and crisis often suffer more fake news than any other issue. To guard against the spread of it, the study submits that awareness creation and enlightenment of people should be carried out so that one can be knowledgeable about the catastrophe fake news can cause. Furthermore, government should put an end to the hoarding of public information as well as the creation of penalty for the initiators and circulators of fake news
Publication Title An Improved Framework for Diagnosing Confusable Diseases Using Neutrosophic Based Neural Network Download PDF
Publication Type journal
Publisher Neutrosophic Sets and Systems, Vol. 16, 2017
Paper Link https://digitalrepository.unm.edu/nss_journal?utm_source=digitalrepository.unm.edu/nss_journal/vol16/iss1/7&utm_medium=PDF&utm_campaign=PDFCoverPages
Publication Authors Okpako Abugor Ejaita Asagba P.O.
Year Published 2017-06-16
Abstract The two major motivations in medical science are to prevent and diagnose diseases. Diagnosis of disease must be done with care since it is the first stage of therapeutic actions towards eventual management of the disease; a mistake at this stage is disastruous, and such, adequate care must be ensured. Diagnosis becomes difficult in medical domain due to influence of medical uncertainties that arises from confusability in disease symptomatic presentation between two diseases. This confusability of these diseases stems from the overlaps in the disease symptomatic presentation and has led to misdiagnosis with various degrees of associated costs and in worst cases led to death. In this research, we present the analysis of the existing systems and finally present a framework for the diagnosis of confusable disease using neutrosophic-based neural network.
Publication Title Adaptive Learner-CBT with Secured Fault-Tolerant and Resumption Capability for Nigerian Universities Download PDF
Publication Type journal
Publisher (IJACSA) International Journal of Advanced Computer Science and Applications,
Publication Authors Bridget Ogheneovo Malasowe 1 , Maureen Ifeanyi Akazue 2 , Ejaita Abugor Okpako 3 , Fidelis Obukohwo Aghware 4 , Arnold Adimabua Ojugo 5 , Deborah Voke Ojie 6
Year Published 2023-08-08
Abstract The post covid-19 studies have reported significant negative impact witnessed on global education and learning with the closure of schools’ physical infrastructure from 2020 to 2022. Its effects today continues to ripple across the learning processes even with advances in e-learning or media literacy. The adoption and integration therein of e-learning on the Nigerian frontier is yet to be fully harnessed. From traditional to blended learning, and to virtual learning – Nigeria must rise, and develop new strategies to address issues with her educational theories as well as to bridge the gap and negative impact of the post covid-19 pandemic. This study implements a virtual learning framework that adequately fuses the alternative delivery asynchronous- learning with traditional synchronous learning for adoption in the Nigerian Educational System. Result showcases improved cognition in learners, engaged qualitative learning, and a learning scenario that ensures a power shift in the educational structure that will further equip learners to become knowledge producer, help teachers to emancipate students academically, in a framew
Publication Title DEVELOPMENT OF AN IOT-BASED HUMIDITY, TEMPERATURE, AND AIR QUALITY MONITORING SYSTEM Download PDF
Publication Type journal
Publisher Scientia Africana, Vol. 23 (No. 1), February, 2024. Pp 131-142 © Faculty of Science, University of Port Harcourt, Printed in Nigeria
Paper Link https://dx.doi.org/10.4314/sa.v23i1.11
Publication Authors Ukadike, I.D1 , Okpako, A.E2 , Isitor, N.D
Year Published 2024-02-02
Abstract Monitoring the environment has become of great importance as it helps individuals keep tabs on their environment. Air pollution is very dangerous to human health and it is known to cause deadly health conditions. This research presents an IoT-based design that will effectively monitor the humidity, temperature, and air quality of a given environment. NodeMCU humidity, temperature, and gas sensors were deployed in the design of the system. The output interface was designed using the Blynk IoT platform. The system was tested in two stages using application of gas pollutants and heat on one hand, whilereadings were taken from a cool evening and sunny afternoon on the other hand. After testing all the functions of the system under various conditions, it revealed 76% humidity, 26.8oC temperature, and 461ppm on the application of gaseous air pollutants, 43.1% humidity, 45.6OC temperature, and 199ppm of air quality on the application of heat, 51.1 humidity, 20.4% temperature, 198ppm of air quality on a cool evening and 70.7% humidity, 29.5OC of temperature and 206ppm of air quality on a sunny afternoon. The system showed improved performance in terms of monitoring of humidity, temperature and air quality and can be deployed suitably in homes, schools, and industries.
Publication Title Theoretical Utility of Data Value Metric and Genetic Algorithms for Variable Clustering in an Unsupervised Learning Environment Download PDF
Publication Type journal
Publisher Caliphate Journal of Science & Technology (CaJoST)
Paper Link https://dx.doi.org/10.4314/cajost.v6i1.13
Publication Authors Okpako A. Ejaita1 and Ojie D. Voke2
Year Published 2024-01-01
Abstract Cluster analysis is regarded as one of the most important unsupervised learning tasks, with its natural application in dividing data into meaningful groups, also known as clusters, based on the information in the data by describing the objects in terms of their relationships and capturing the data's natural structure. Many traditional performance evaluation metrics for clustering algorithms abound in the literature, treating various attributes or variables equally when measuring similarity; however, different attributes or variables may contribute differently due to the amount of information they contain, which can vary greatly. Data Value Metric (DVM) is an information theoretic measure based on the concept of mutual information that has been shown to be a good metric for validating data quality and utility in a big data ecosystem and in traditional data. Because it uses a forward selection search strategy, Data Value Metric (DVM) suffers from local minima and loss of diversity in the population; however, hybridizing it with Genetic Algorithm will overcome the problem of local minima because there will be a blend of evolutionary search to ensure a balance between exploration and exploitation of the search space. This paper proposed a hybrid model of the Genetic Algorithm and the Data Value Metric (DVM) as an informationtheoretic metric for quantifying the quality and utility of variable clustering selection that can be applied to traditional data.
Publication Title FePARM: The Frequency-Patterned Associative Rule Mining Framework on Consumer Purchasing-Pattern for Online Shops Download PDF
Publication Type journal
Publisher Computing, Information Systems, Development Informatics & Allied Research Journal Vol. 15 No. 2, 2024 - www.cisdijournal.net
Publication Authors 1Malasowe, Bridget Ogheneovo,, 2Okpako, Abugor Ejaita, 3 Okpor, Margaret Dumebi, 4Ejeh, Patrick Ogholuwarami, 5Ojugo, Arnold Adimabua & 6Ako, Rita Erhovwo
Year Published 2024-02-02
Abstract Transaction data often is a true presentation of consumers’ buying behavior, stored as a set of relational records, which properly harnessed via mining – can help businesses improve their sales volume as a decision support system. Managing such a system can pose many issues to biz such as feature evolution, concept evolution, concept drift, and infinite data length – and often makes it impractical to effectively store such big-data. To curb this, previous studies have assumed data to be stationary in using associative rule mining. This has deprived such systems of the flexibility and adaptiveness required to handle the dynamics of concept drift that characterizes transaction datasets. Our study thus proposes a basket frequent pattern growth trained associative rule mining model to handle large data. The dataset was retrieved from the Delta-Mall Asaba and consists of 556,000 transaction consumer records. The model consists of six-layers, and yields the best result with a 0.1 value for both the confidence and support level(s) at a 94% accuracy, sensitivity of 87%, and a specificity of 32% with a 20-second convergence and processing time.
Publication Title Online Media Audience Awareness and Response to Political Cyberbullying and its Implication to Development in Nigeria
Publication Type journal
Publisher FUPRE JOURNAL 8(3): 196-214 (2024)
Paper Link http://fupre.edu.ng/journal
Publication Authors IKPEGBU, E. 1,* , OKPAKO, E. A. 2 , CHIEMEKE, S. 3 , OMOROGIUWA, O. 4
Year Published 2024-06-30
Abstract Tensions are usually high during political campaign periods in Nigeria as politicians seek to influence the electorates to their favour. In the process, they express sentiments that sometimes threaten or disparage their opponents. Online media platforms have been one of the most adopted means for politicians, leading to political cyberbullying. This study focused on online media audience awareness and response to political cyberbullying and its implication to development in Nigeria. The study had two objectives on the awareness level and response to the issue. The researchers anchored the study on the Selective Processes Theory, and approached it through qualitative survey research design. There were 224 respondents drawn from online media users in Nigeria. A Google designed form was administered through emails and WhatsApp platforms. The study adopted the four-point Likert scale format with 2.5 as the criterion for decision. The researchers found out that online media audience is averagely aware (3.26 AWMS) of political cyberbullying in Nigeria. Secondly, the respondents have a high negative perception (3.56 AWMS) about political cyberbullying, which is good for development. It was therefore concluded that with the knowledge and perception, politicians may not benefit from political cyberbullying in the future. The study recommends that mainstream media should increase anti-political cyberbullying campaign through its online media platforms.
Publication Title Text Encryption Using Advanced Encryption Standard (AES) Algorithm
Publication Type journal
Publisher Journal of Science and Technology Research 6(2) 2024 pp. 214-228 ISSN-2682-5821
Paper Link https://doi.org/ 10.5281/zenodo.12558923
Publication Authors 1Akwukwuma, V.V.N., 1Chete F.O., 1Oshioluamhe, M.N. and 2Okpako A.E.
Year Published 2024-06-05
Abstract With the increasing importance of data security in the digital age, the need for robust encryption techniques has become paramount. The Advanced Encryption Standard (AES) is regarded as one of the safest encryption techniques currently in use. The AES encryption algorithm is a symmetric block cipher algorithm with a block/chunk size of 128 bits. These distinct blocks are converted using keys that are 128, 192, and 256 bits long. The ciphertext is created by joining these blocks together once they have been encrypted. The decryption is done in the reverse order. This study discusses the implementation of text encryption using the AES algorithm. The Graphical User Interface of the text encryption system was built using python library Tkinter while the encryption and decryption algorithm were programmed using python and its libraries. The tools used for the implementation were the text editor and python Integrated Development Environment (IDE).
Publication Title Quest for Empirical Solution to Runoff Prediction in Nigeria via Random Forest Ensemble: Pilot Study
Publication Type journal
Publisher Journal of Behavioral Informatics
Publication Authors Malasowe, B.O.1, Edim, E.B.2, Adigwe, W.3, Okpor, M.D.4, Ako, R.E5, Okpako, A.E6, Ojugo, A.A.7, & Ojei E. O
Year Published 2024-03-04
Abstract Environmental factors and features often change to result in either harsh weather conditions or rainfall, which often calms the weather as well as provides fast, significant downstream hydrology known as runoff with a variety of implications such as erosion, water quality, and infrastructures. These, in turn, impact the quality of life, sewage systems, agriculture, and tourism of a nation, to mention a few. It chaotic, complex and dynamic nature has necessitated studies in the quest for future direction of such runoff via prediction models. With little successes in use of knowledge driven models – many studies have now turned to data-driven models. Dataset is retrieved from Metrological Center in Lagos, Nigeria for the period 1999–2023. The retrieved dataset was split: 70% for train dataset, and 30% for test dataset. Our study used the Random Forest ensemble. Result yields a sensitivity of 0.9, specificity 0.19, accuracy of 0.74, and improvement rate of 0.12. Other ensembles underperformed as compared to proposed model. Study reveals annual rainfall is an effect of variation cycle. Models will help simulate future floods and provide, lead time warnings in flood management.
Publication Title The Use of Artificial Intelligence and Human-Computer Interaction (AI-HCI) to Improve Children’s Learning Outcomes in Nigeria Download PDF
Publication Type journal
Publisher International Journal Of Engineering And Computer Science Volume 13 Issue 08 August 2024, Page No. 26351-26358
Paper Link 10.18535/ijecs/v13i08.4842
Publication Authors Unique Onyenmeli Epunam 1., Osaremwinda Omorogiuwa2., Ejaita Abugor Okpako3
Year Published 2024-08-08
Abstract This study investigates the impact of AI on human-computer interaction patterns among Nigerian children, focusing on accessibility, usage, and educational outcomes. The research encompasses both parental and teacher perspectives, analyzing demographic data and AI technology integration. Results reveal significant discomfort among parents regarding unsupervised AI use by children, yet highlight the potential benefits of AI in enhancing academic performance and motivation. Teachers report varied frequency in incorporating AI into lessons, influenced by accessibility and educational context. Cultural and social factors play a crucial role in AI adoption, presenting challenges such as device availability and internet access. This comprehensive analysis underscores the need for balanced AI integration, considering both educational advantages and potential discomforts, to optimize learning experiences and foster responsible AI usage in academic settings.
Publication Title Cross-Platform Android App Gateway Payment System using Xamarin Download PDF
Publication Type journal
Publisher International Journal of Computer (IJC) ISSN 2307-4523 (Print & Online)
Paper Link https://ijcjournal.org/index.php/InternationalJournalOfComputer/index
Publication Authors Osaremwinda Omorogiuwaa*, Ejaita Abugor Okpakob, Juliana Ndunaguc
Year Published 2023-05-13
Abstract Most mobile applications lacks cross platforms portability and capabilities. As such, developers tend to use specific code base that runs only on a native android application built using Java or a native iOS application built using Swift. In developing mobile application, same application is therefore required to be developed using the appropriate native app required software development. This leads to duplication of efforts, more cost, time consumption and maintenance. Although, the applications are the same, mobile application has to be developed separately because of platform independence. This paper proposes the use of Xamarin in developing mobile apps due to its cross-platform capabilities. Using Xamarin save cost, create a single code base for faster development and less maintenance while still maintaining native app performance and user experience. To substantiate Xamarin suitability, a gateway payment system was development and tested, the results showed actual cross platform functionalities in a seamless manner.
Publication Title Machine Learning Survival Analysis Model for Diabetes Mellitus Download PDF
Publication Type journal
Publisher International Journal of Innovative Science and Research Technology ISSN No:-2456-2165
Publication Authors Maureen I. Akazue1, Geofrey A. Nwokolo1, Clement O. Ogeh1 Emmanuel Ufiofio1, Okpako A. Ejaita2
Year Published 2023-04-04
Abstract Developing effective survival analysis models would help guide the decision-making in managing major health challenges. Model development can be achieved through various approaches. Diabetes is a health challenge in Nigeria that has attracted the interest of researchers thus much research has been carried out as regards its management necessitating the development of models. This study carried out a machine learning analysis on diabetes data collected from Central Hospital, Warri, Delta State implementing Cox-PH Model due to the role both play in survival analysis. A dataset of 100 diabetic patients' records was collected. The dataset was used for training multiple machine learning algorithms, namely, SupportVector (SVM), K- nearestneighbors (KNN) classifier, etc., and the proposed model (Cox-PH Hybrid or CPH-SML). The performance evaluation of the machine learning algorithms and the proposed model gave accuracy levels as follows: KNN- 47%, SVM; 74%, and Cox-PH Hybrid-96%. The concordance index was used to evaluate the proposed model and it had an index of 0.7204, on several covariates such as Age, Gender, Education, Marital Status, history of smoking, SBP, DBP, etc. From this study's analysis of the diabetic data, it was able to conclude that the variables associated with diabetes mortality are; the age of the patient and diabetes types. The patients' hazard ratio reduces when they are young compared to when they are old. The patient's hazard ratio is also dependent on the diabetes type. Thus, early diagnosis and proper health management of diabetics can prolong the age of diabetic patients.
Publication Title Development of Hybrid Intelligent based Information Retreival Technique Download PDF
Publication Type journal
Publisher International Journal of Computer Applications (0975 – 8887) Volume 184– No.34, October 2022
Publication Authors Gregory Gabriel James, Abugor Ejaita Okpako, C. Ituma, J.E. Asuquo
Year Published 2023-10-10
Abstract To find information over the internet to a certain level, depends on our capacity to track all related subjects and classify them into bunches of comparative themes. As the domain of information is enlarging over the internet , the time consumption and the difficulties experienced by researchers to find a relevant material that meets the user’s specified request increases, thereby putting the researchers into a state of dilemma at the cause of searching for relevant information that meets their need. The pursuit to trim down the challenges of impasse faced by researchers as well as time exhausted to filter relevant materials in the pools of irrelevant materials have motivated this research. The work aims at developing a Neuro- fuzzy intelligent search framework for tracking and recovery of web archives. The method used was Object-Oriented analysis and Design (OOAD). A hybrid intelligent framework – based tracking system was utilized as the finest choice for tracking archives, since the shortcomings of Neural Network and Fuzzy Logic based tracking system were complemented while their individual qualities are upgraded. This paper expands prior Fuzzy-based information retrieval approaches through increasing the Fuzzy variables and their linguistic values by utilizing distinctive rules and functions that characterized the record. The mapping of input to output parameters was achieved by applying the triangular membership’s functions. Adaptive neural fuzzy inference system model also utilized the Takagi Sugeno inference mechanism. It was observed that using ANFIS improved the hybrid intelligent framework – based tracking system performance slightly with 0.22641 representing 22.64% over the Fuzzy Inference System (FIS) results, thereby guarantee retrieval of most relevant documents that met the user’s request.
Publication Title Covid-19 pandemic misinformation and disinformation on social media: a study of Abraka metropolis Download PDF
Publication Type journal
Publisher 1.Misinformation, 2.Disinformation, 3.Social Media, 4.COVID-19, 5.Focus group.
Publication Authors Ojobo Ogheneruemu Lucky, Okpako Abugor Ejaita, Ivwighren, Hannah Emuobosa
Year Published 2022-09-09
Abstract The outbreak of Coronavirus disease has birthed a lot of fictitious stories. With the unexpected outbreak of the pandemic in 2019, there followed a tsunami of misinformation and disinformation all over the world including Nigeria. This study is anchored on the hypodermic needle theory and the agenda-setting theory to act as the stimulus in response to misinformation and disinformation that is detrimental to the management of the dreadful pandemic. Focus group interview was conducted that elicited responses from 120 teaching and non-teaching staff of six primary and secondary schools in Abraka and environs. Data analyzed indicates that many believed in the misinformation and disinformation about COVID-19.Findings affirmed that generally, misinformation and disinformation can influence negatively. One of the recommendations of this study encourages the general public to watch against misinformation and disinformation by checking the credibility of any information received to guard against the misleading citizens about issues of health. The public health authorities such as the NCDC, WHO, UN, cooperate bodies, NGOs, should be relentless in initiating proper measures against disastrous information at all times especially during a pandemic.
Publication Title An Evaluation of Smartphone Usage and Social Interaction of Delta State University Students, Abraka Download PDF
Publication Type journal
Publisher Journal of Information Engineering and Applications www.iiste.org ISSN 2224-5782 (print) ISSN 2225-0506 (online) Vol.13, No.1, 2023
Paper Link 10.7176/JIEA/13-1-02
Publication Authors OJOBOH, Lucky Ogheneruemu*, OKPAKO, Abugor Ejaita
Year Published 2023-01-01
Abstract Information and Communication Technology has woven into human lives as it is nearly inseparable from it. It has drastically affected the way things are done either by reinventing or increasing their efficiency. Inevitably, Information technologies have also reinvented how social interactions are carried out and in extreme cases introduced myriads of modernized and globalized forms of communication. The study evaluated Smartphone usage and social interaction of Delta State University students. A survey method was used to collect responses from 450 respondents from the Faculty's whole student body. The data collected was analyzed using linear regression (ANOVA). The Technology Acceptance Model and Symbolic Interaction theories were used to guide the research. The research shows that the frequency and pattern of smartphone use by students at the Faculty of Social Sciences is influenced their social interactions with family and friends; there was no significant effect of smartphone use on students' academic activities; and the brands of phones owned by students influenced their social interactions. It is recommended that students should utilize their smartphones for academic activity more; students should strike a balance between using smartphones for personal and academic objectives and University administration should give internet access for students.
Publication Title WEB BASED DAILY OPERATIONAL E-TICKETING SYSTEM FOR ROAD TRANSPORTERS IN NIGERIA Download PDF
Publication Type journal
Publisher International Journal of Scientific Development and Research (IJSDR)
Publication Authors 1)Okpako Abugor Ejaita (2)Anazia Eluemunor Kizito
Year Published 2022-06-06
Abstract There is an increase in the number of vehicles plying our roads in Nigeria which will significantly increase the revenue generation to the government as the vehicles normally pay for operational tickets on daily basis which has also brought to light issue of security on our roads. Regrettably, there are several revenue leakage points inherent in the manual system of daily operational ticketing which is making the government not to realize the supposed increased revenue from the road transportation, more so, when there is a dwindling revenue generation from the oil sector. The aim of this paper is to develop a system that will handle daily operational tickets for road transport workers to ensure proper recording and monitoring of ticket revenue. Object oriented analysis and design was used as the methodology for this work. The front end was developed using a HTML, JAVASCRIPT and CSS while the backend is PHP and Mysql for experimental purpose. Test procedures showed that the application passed all the requirements needed for the application to be published and sold in the open market. This application will improve the manual ticketing method, making it necessary to get information about ticketing at real time and eliminate the extra effort and time wastage during such transaction/ticket processing.
Publication Title Implementation of Neutrosophic-Based Decision Support System for Effective Diagnosis of Liver Disease Download PDF
Publication Type journal
Publisher International Journal of Research and Scientific Innovation (IJRSI) | Volume VIII, Issue IV, April 2021 | ISSN 2321–2705
Paper Link https://dx.doi.org/10.51244/IJRSI.2021.8403
Publication Authors Okpako, A.E1* , Omoghenemuko, G.I.2, Odikwa, H.N3
Year Published 2021-04-04
Abstract Liver diseases have been shown to be highly correlated to excessive consumption of alcohol and other harmful or injurious substances such as drugs and toxins. The Nigeria social milieu cannot do away with excessive consumption of alcoholic- related substances and drugs, which are predominantly consumed on weekends either in parties or clubs. Most Nigeria teenagers and adults alike who are supposedly considered as socially correct indulge in excessive consumption of alcohol and other harmful substances leaving the alcoholic companies and shops smiling to the banks. This unpalatable trend has dire consequences as it raises the figure of liver disease patients, which is mostly confused with other tropical diseases like malaria and as such its manifestation cannot be predicted on time with certainty. Timely diagnosis is a panacea to the management of the disease but this is not the case most times as there are handful of hepatologists that can adequately diagnose this disease since General practitioner might not be able to diagnose them on time. This research seeks to comparatively analyze the performance of Neutrosophic-based Decision Support System and Multilayer Neural Network (Traditional Neural Network) in the classification of Indian Liver Patient Dataset (ILDP) as well as articulate its suitability in the classification or diagnosis of liver disease (ILPD). Object Oriented Analysis and Design methodology was used while the implementation was done using WEKA and Java on a Netbeans platform. Experimental results show that Neutrosophic-Based Decision Support System (NBDSS) with an accuracy of 96.41% using a confusability measurement threshold of 0.003278 performed better than the conventional neural network with an accuracy of 72.45%. This clearly shows that Neutrosophic-based Decision Support System is suitable for the diagnosis of liver diseases.
Publication Title A Fuzzy-Based Chat-bot Messenger for Home Intelligent System with Multiple Sensors Download PDF
Publication Type journal
Publisher International Journal of Advanced Trends in Computer Science and Engineering
Paper Link https://doi.org/10.30534/ijatcse/2021/771022021
Publication Authors Ndubuisi Henry Odikwa1, Anietie Peter Ekong2,Ejaita Okpako3
Year Published 2021-04-03
Abstract The integration of chatbot engines and home automation systems is an area that is seeing a lot of development and resources dedicated to in recent years. Many devices nowadays are constantly connected to the Internet (IoT) and this is a huge opportunity to create a software application that can manage an area of our everyday life. This paper was aimed at the design and implementation of a low-cost fuzzy-based system which converts fuzzy values to Crips values that uses weather conditions of a particular environment to function as an intelligent system in a smart home. The functions of this system is made possible with the integration of multiple sensors of Pewatron zirconia in a circuit in conjunction with fuzzy values in a chatbot messenger environment with the aid of the Telegram Bot service to control the state of electrical devices in the house based on atmospheric weather conditions. The commands to the control of electrical appliances was done by creating user interface that interfaces with the mobile devices that provides intelligent response programmed on to the Freescale S32K microcontroller with wireless fidelity. The main focus was to create a chat interface that allows the users to interact with their systems at home in their convenience(reaching the users where they already are, like Telegram, Facebook etc.), creating a system that not only allows you to control and manage your home electrical systems but also a networking system that gives you leverage of ease and faster network in terms of operation in controlling your home devices through decisions. The outcome of this fuzzy-based smart home intelligent system proved reliable and efficient more than the previously designed smart home systems based on relay and microcontroller. More so, the system reduces power consumption from electrical appliances as the application generally employed fuzzy Crips values based on the weather conditions.
Publication Title The Triadic Interplay Of Culture, Globalization And Cybercrime Trajectory In Nigeria Through A Sociocultural Lens Download PDF
Publication Type journal
Publisher Researchjournali’s Journal of Computer Science Vol. 5 | No. 4 March | 2020 ISSN 2349-5391
Publication Authors Okpako Abugor Ejaita, Oghorodi Duke, Ako R.E
Year Published 2020-03-03
Abstract The rapid penetration and acceptability of information and communication technology into every area of human endeavor have lent its influence to culture in recent times through globalization. Inevitably, it has also modernized how terrestrial crimes are perpetuated and propagated, consequently introducing new forms of crimes known as cybercrimes. Cybercrimes are valid indicators of economic and societal failures that have culminated into a sociological menace in the 21st century. However, globalization is not only the connection of cities and towns but also the interplay of various cultural embodiments that can positively or negatively affect the behavior of person(s) living in that society. It is a known fact that nobody speaks or acts from nowhere except from cultural background. This paper proposes a sociocultural analysis of cybercrime in Nigeria as an emerging trend after taking a detailed look at the advances made using sociological analysis. We concluded the paper by recommending sociocultural approach that uses a community-based strategy which will engender development of effective and multidisciplinary approach in understanding and combatting cybercrime in Nigeria.
Publication Title A Roadmap to a Nigeria Digital Knowledge Economy: Trends and Implications Download PDF
Publication Type journal
Publisher Digital Innovations & Contemporary Research in Science, Engineering and Technology
Paper Link dx.doi.org/10.22624/AIMS/DIGITAL/V7N3P2
Publication Authors 1Oghorodi, D., 2Okpako, A.E. & 3Ako, R.
Year Published 2019-10-10
Abstract Countries all around the world today are moving towards and actively embracing a new and evolving type of economy known as Digital Knowledge Based Economy. It is an economy where there is a high dependence on knowledge, information and high skill levels, and the increasing need for ready access to all of these by the business and public sectors. It is “an economy in which the production, exchange, distribution and use of knowledge are main drivers of economic growth, employment generation and wealth creation”. However, Nigeria with her inherent multifaceted challenges has made no serious progress in embracing this new form of economy. There is need to appraise our readiness that would x-ray and give the country a direction toward surmounting some major challenges holding her down in this regard. The paper identified certain factors that are needed to ensure that Nigeria evolve into a ‘knowledge driven economy’ and compared Nigeria preparedness towards digital Knowledge based economy with other ‘developed countries’ around the world. This study seeks to provide motivation for academics, researchers, the Nigeria Government (security agencies related to cybercrime and other crime related issues) to discover mechanism, frameworks, metrics and protocols to deal with challenges to the country’s readiness to embrace digital knowledge based economy. The study therefore concludes by recommending some policy guidelines such as minimizing ICT/digital literacy gap between academic and industry; ‘power and energy’ problems must be sorted out as quickly as possible; cybercrime and other allied act of electronic crime should be discouraged through stringent legislation; our educational system needs to be reevaluated and adequate steps taken for a working education sector; more grants should be given to research and should be adequately monitored. In addition, adequate measure should be taken for the welfare of staff both academics and other allied institutions to prevent or curb knowledge drift other countries of the world.
Publication Title 3(5)250$1&($1$/<6,62)25,*,1$/'.3&9(568602',),(''.3& $/*25,7+0686,1*$57,),&,$/$17$1'75$9(//,1*6$/(60$1 352%/(06
Publication Type journal
Publisher ????:Ž?????Ž??????????Ž??????^?????????????????Ž?? sŽ????EŽ???/?????—???????? :^
Publication Authors 2JKRURGL'XNH, Okpako Ejaita, Ako, Rita
Year Published 2019-12-12
Abstract &RGH%ORDWUHPDLQVDQXQUHVROYHGSUREOHPLQ*HQHWLFSURJUDPPLQJ*3(IIRUWVE\UHVHDUFKHUVWR UHVROYHWKHFRGHEORDWSUREOHPLQ*3KDVQRWEHHQVXFFHVVIXOVRIDU7KLVSDSHULVDQRWKHUDWWHPSWWR ILQGDEHWWHUPHWKRGWRFRQWUROFRGHEORDWXVLQJWKHPRGLILHG'.3&DOJRULWKP7KHSDSHUFRPSDUHV SHUIRUPDQFHRIWKHRULJLQDO '.3&DOJRULWKPZLWKWKHPRGLILHG'.3&DOJRULWKPXVLQJQXPEHUVRI WLPHVEORDWRFFXUDQGUXQWLPHRIWKHDOJRULWKPV(YROXWLRQDU\0HWKRGRORJ\ZLWKLQFOLQDWLRQWRREMHFW 2ULHQWDWLRQZDVXVHG
Publication Title A Causality Learning of E-banking Operational Risk using Tree Augmented Naïve Bayes Classifier Download PDF
Publication Type journal
Publisher International Journal of Soft Computing and Engineering (IJSCE) ISSN: 2231-2307, Volume-8 Issue-4, November 2018
Publication Authors Ako Rita Erhovwo, Okpako Ejaita Abugor
Year Published 2018-11-11
Abstract E-banking systems have been shown to increase and modify particularly Operational Risk (OR). It has increased the technical complexity of the banks operational and security issues. The mode of occurrence, magnitude, and consequences often takes on new dimensions. It has become increasingly important to effectively identify potential OR issues underlying the E-banking operations, their causal relationships, the effectiveness of controls implemented, the inherent risk exposure level, and the residual risk. This research work seeks to propose Tree Augmented Naïve Bayes (TAN) Classifier in the modeling of the causal relationships among operational risks factors. To validate the proposed use of TAN classifier, we comparatively analyzed the performance of the TAN classifier with three other soft computing tools; C4.5 Decision Tree, Naïve Bayes (NB) and Artificial Neural Networks (ANN). These soft computing tools were evaluated in terms of the CPU training time complexity, classification measured by prediction accuracy, ranking measured by AUROC, and the Mean and Relative absolute error rate. The dataset was pre-processed and transformed by conducting a factor analysis procedure using SPSS statistical measurement tool, to identify risks that may require urgent actions and to reduce the dimensionality of the dataset into a smaller subset of most significant measurable variables. WEKA was then used as the developmental tool for training and testing the soft computing classifiers. Through causality learning from the collected E-banking Customers’ data, we demonstrated that the proposed classifier cannot only discover causalities but also perform better in prediction than other algorithms, such as C4.5, NB, and ANN. The TAN network structure revealed the interdependencies among operational risk factors.
Publication Title A Novel Framework for Predicting and Managing Comorbid Diseases using Neutrosophic Logic and Machine Learning Download PDF
Publication Type journal
Publisher International Journal of Computer Applications (0975 – 8887) Volume 175 – No.4, October 2017
Publication Authors A. E. Okpako, R. E. Ako
Year Published 2017-10-10
Abstract Emerging realities in medical research had advocated for a shift from single disease diagnosis mostly in clinical diagnosis of geriatric patients since most geriatric patients presents more than one disease complications. Comorbidity is visibly a phenomenon predominantly seen in elderly patients thus has made the management of diseases in such patients’ complex. A metric is needed which would be an indispensable tool for prioritizing treatment or developing clinical guidelines so as to handle the blizzards of risks of overtreatment and inappropriate prescription. This metric would provide an evidence about how both conditions and care processes interact and as such would assist and/or complement human practitioners mostly in areas where there are only General Practitioners to handle comorbid disease diagnosis , treatment and management. In this paper, we present a framework using Artificial Neural Network whose inference mechanism is driven by Neutrosophic logic, all being mechanism employed in soft computing so as to ensure intelligent capability in handling comorbidity. This framework is generic and could be used for any comorbid disease of interest.
Publication Title A Theoretic Utility of Augmenting Generalized Regression Neural network with Expert System for Hepatitis B Diagnosis Download PDF
Publication Type journal
Publisher Journal of Computing, Science &Technology.Vol.1, Issue 2 2024
Paper Link https://focjournal.unidel.edu.ng/
Publication Authors Ojie D. V. 1, Ogala Onyarin Justin2, & Okpako Abugor Ejaita
Year Published 2024-02-02
Abstract The inclusion of computing devices in the diagnostic phase in medical care has received a disturbing publicity owing to its inherent benefits: practicality, reproducibility, efficiency, and immunity to disturbance variables unique to humans (fatigue, stress, diminished attention). Technology does not replace human professionals in this area of medical support; instead, it aims to aid them by developing systems that can pick up or create appropriate data. In medicine, diagnosis is defined as "the detection of a disease or condition based on its outward signs and symptoms" or "the investigation of the underlying physiological, biochemical cause." Hepatitis B, which includes chronic liver disease, is quite widespread worldwide and can harm hepatocytes. Cirrhosis can range in severity from healthy carriers to decompensated cirrhosis. We have developed an intelligent framework for identifying hepatitis B viral illness in this research. Hepatitis is a dangerous disease that requires expensive treatment and severe side effects. The generalized regression neural network is a suitable and promising approach to detection and prediction of severity of Hepatitis B in patients.
Publication Title Analysis of Emerging Cybercrime Entrepreneurship and Its Implication in Nigeria Download PDF
Publication Type journal
Publisher Covenant Journal of Entrepreneurship (CJoE) Vol. 7 No.1, June 2023
Publication Authors 1Okpako A. Ejaita, 2Malasowe O. Bridget, 3 Mormah F. Ofuma & 4Chiemeke C. Stella
Year Published 2023-06-06
Abstract Emerging realities in our society have glorified, celebrated and romanticized cybercriminals and their proceeds. This ugly and immoral societal acceptance of such criminal tendencies and their proceeds has extended the frontiers of Entrepreneurship due to its elastic nature to what is recently known as Cybercrime Entrepreneurship. Cybercrime Entrepreneurs on one hand, are experienced cybercriminals that sets up centers (virtual and physical) for teaching them while on the second hand, they are successful, experienced and well- connected cyber criminals that set up ventures with enabling environment for less experienced individual to learn and efficiently carry out their criminal activities. This paper presents a review of theories of Entrepreneurship and their validity in understanding the recent disturbing publicity of Cybercrime Entrepreneurs and its subsequent indulgence by teenagers in Nigeria. The theories used are Economic factors theory by Joseph Schumpeter, Psychological factor theory by David Mccleland, Sociological factors theory by Thomas Cochranis and Alert Theory. It was observed that there are significant discontinuities and continuities in the configuration of cybercrime Entrepreneurship and traditional Entrepreneurship. The study concludes that Cyber Entrepreneurship is a function of psychological, sociological, criminological and economic factors and has negative implication to human capacity development of Nigeria. The research recommends amongst others that policy should be enacted to discourage the influx of youth into Cybercrime Entrepreneurship; punishment be explicitly spelt out in the law. Furthermore, government should also try to help our youths by engaging them positively to believe that there is dignity in labour.
Publication Title SYSTEM PERFORMANCE METRICS IN AN AGILE COMPUTING ENVIRONMENT (A CASE STUDY OF INTEGRATED DATA SERVICE LIMITED) Download PDF
Publication Type journal
Publisher Nigerian Journal of Scientific Research, 19 (1): 2020; January -February; njsr.abu.edu.ng; ISSN-0794-0319
Publication Authors ODIKWA, H.N.1*, UZOARU, G.C.2 AND OKPAKO, E.
Year Published 2020-01-01
Abstract This paper is aimed at determining the best system performance metrics that will quickly respond to changes in an agile computing environment. This paper designed an architectural model for determining the best performance metrics in an agile computing environment such as Integrated Data Services Limited. The research work was based on six (6) system performance metrics; execution time, QUIPS, SPECs, Clock rate, MFLOPS and MIPS. MATLAB as a mathematical tool was used in the analysis of the various performance metrics to determine the best metrics. The experiments performed showed that execution time is the best performance metrics having execution time of 0.95, 0.97 and 1.01 followed by QUIPS and SPEC that has values of 6, 3 and 1.2 seconds in completing processes in the three experimental servers, while MFLOPS, MIPS and Clock Rates were found to be of poor performance metrics in any agile computing environment.
Publication Title Improved Diagnosis of Dental Caries Using Expert System Download PDF
Publication Type journal
Publisher Journal of Computing, Science &Technology
Publication Authors Okoh Ogechukwu Lucky1, Okpako Abugor Ejaita2, Mughele Ese Sophia3, Rosemary Ewere Iwegbu4
Year Published 2024-02-02
Abstract There is no doubt that computing and its associated technologies have also transformed the medical domain with introduction of tools that help in medical diagnosis and prognosis of diseases. The field of medical dentistry has received a disturbing publicity in recent times as there are cases of dental problems in Nigeria which has put a burden on the limited number of dentists we have in the country. Studies have shown that many general hospitals in Delta state and in Nigeria do not have dentist that are primarily stationed on duty in the hospital and where there are one or two, the pressure on them in terms of service is enormous which ultimately leads to poor service delivery and eventual progression of dental problems such as caries to more complicated medical posture before they actually meet an expert. This consequently results in over working conditions for the dentists in attending to patients. The Expert system for diagnosis of dental caries gives real time result, fast without or with minimal error and is hoped to be integrated to the health-care system to enable general medical practitioners attend to some dental cases that are not so complicated and even complement the dental expert in diagnosis and management of caries disease.
Publication Title Detection of Cues in Malicious Web-Content using a Sentiment-targeted Extreme Gradient Boosting Tree-based Ensemble Download PDF
Publication Type journal
Publisher Journal of Computing, Science &Technology
Paper Link https://focjournal.unidel.edu.ng/
Publication Authors Rume Elizabeth Yoro1 , Okpako Abugor Ejaita2 , & Edun Ogechi Peace3
Year Published 2024-05-13
Abstract Mobility, ease of accessibility, and portability have continued to grant ease in the adoption rise of smartphones; while, also proliferating the vulnerability of users that are often susceptible to phishing. With some users classified to be more susceptible than others resulting from media presence and personality traits, many studies seek to unveil lures and cues as employed by these attacks that make them more successful. Web content has been often classified as genuine and malicious. Our study seeks to effectively identify cues and lures using the sentiment analysis targeted tree-based gradient boosting algorithm on dataset divided into train/test sets that are scraped from client/user online presence and activity over social networking sites. The dataset is scraped using the Python Google Scrapper. The essence of which is to effectively help users to classify contents from social networking sites as either malicious phishing attacks, or as genuine contents for use using sentiment analysis. The machine learning of choice is the XGBoost. Results show that the ensemble yields a prediction accuracy of 97-percent with an F1-score of 98.19% that effectively correctly classified 2089-instances with 85-incorrectly classified instances for the test-dataset.
Publication Title A Framework for Diagnosing Confusable Diseases using Neutrosophic based Neural Network Download PDF
Publication Type journal
Publisher International Journal of Computer Applications (0975 – 8887) Volume 167 – No.1, June 2017
Publication Authors Okpako Abugor Ejaita, Asagba P. O.
Year Published 2017-06-06
Abstract The two major motivations in medical science are to prevent and diagnose diseases. Diagnosis of disease must be done with care since it is the first stage of therapeutic actions towards eventual management of the disease; a mistake at this stage is disastrous and such adequate care must be ensured. Diagnosis becomes difficult in medical domain due to influence of medical uncertainties that arises from confusability in disease symptomatic presentation between two diseases. This confusability of these diseases stems from the overlaps in the disease symptomatic presentation and has led to misdiagnosis with various degrees of associated costs and in worst cases led to death. In this research, we present the analysis of the existing systems and finally present a framework for the diagnosis of confusable disease using neutrosophic-based neural network.
Publication Title A Conceptual Framework for the Adoption of IoT in the Energy Sector: Technology-Organization- Environment Framework Approach Download PDF
Publication Type journal
Publisher Authorized licensed use limited to: University of Johannesburg. Downloaded on August 17,2024 at 09:10:19 UTC from IEEE Xplore. Restrictions apply
Publication Authors 1 st Snow Ngozi Monye Department of Information Communication Technology University of Delta Agbor, Delta State, Nigeria ngozi.monye@unidel.edu.ng 2 nd Stella Isioma Monye Department of Mechanical and Mechatronics Afe Babalola University Ado Ekiti, Nigeria 7 th Kazeem Bello Aderemi Department of Mechanical Engineering Federal University of Oye Ekiti Ekiti State, Nigeria kazeem.bello@fuoye.edu.ng Sunday Adeniran Afolalu 2,3 Department of Mechanical Mechatronics monyeis@abuad.edu.ng 2Department of Mechanical Engineering Afe Babalola University Ado Ekiti, Nigeria 3Department of Mechanical Engineering Science University of Johannesburg Johannesburg, South Africa adeniran.afolalu@abuad.edu.ng 4 th Imhade Princess Okokpujie Department of Mechanical and Mechatronics Afe Babalola University Ado Ekiti, 360001, Nigeria Department of Mechanical and Industrial Engineering Technology University of Johannesburg University of Johannesburg Johannesburg, 2028, South Africa ip.okokpujie@abuad.edu.ng 5 th Adedotun O. Adetunla Department of Mechanical and Mechatronics Afe Babalola University Ado Ekiti, Nigeria adetunla.adedotun@abuad.edu.ng 6 th Omolayo M. Ikumapayi Department of Mechanical and MechatronicsAfe Babalola University Ado Ekiti, Nigeria ikumapayi.omolayo@abuad.edu.ng 8 th Samuel Obinna Nwankwo Department of Mechanical and Mechatronics Afe Babalola University Ado Ekiti, Nigeria nwankwso@abuad.edu.ng 9 th Ejaita Abugor Okpako Department of Information Communication Technology University of Delta Agbor Delta State, Nigeria ejaita.okpako@unidel.edu.ng
Year Published 2024-08-17
Abstract The major role played by Internet of Things (IoT) in the energy sector cannot be overemphasized. Its application encompasses the development of smart grid, development of electric buildings and integration of grid and renewable energy such as wind turbines, solar panels, hydropower systems, and photovoltaic cells. However, amidst of all these prospects lie some pressing challenges facing the application of IoT technology in the energy sector. This work studied on the recent prospects of IoT in the energy sector and its challenge. Recent works related to the study have it that the most pressing challenges facing the application of IoT in the energy sector are the adoption and the security issues. It is on this light that the work has proposed a conceptual framework using the Technology-organization-environment framework for a sustainable application of IoT in the energy sector in future. Some recommendations for leveraging IoT in the energy industry are also stated in the work.
Publication Title Utilizing Amazon Web Services Tools for Efficient Multilingual Omnichannel Contact Centres Download PDF
Publication Type journal
Publisher Faculty of Natural and Applied Sciences Journal of Computing and Applications Print ISSN: 3026-8133 www.fnasjournals.com Volume 2; Issue 1; September 2024; Page No. 51-57
Paper Link http://www.fnasjournals.com/
Publication Authors Mughele, E.S., Ogala. J.O., & Okpako, E.A.
Year Published 2024-09-09
Abstract A contact centre may face difficulties when there are language barriers between a customer and an agent. To improve customer experience, this study demonstrates how to instantly translate chat conversations between users in real-time, in their preferred language, across multiple channels. The paper used some essential Amazon Web Services (AWS) to implement this solution. At the core of the demo is our machine learning models, which help to auto-connect, evaluate and translate the customer experience. Researchers used Amazon Connect to modernize the information technology (IT) service desk with omnichannel contact centre capabilities. Customers could utilize Amazon Connect's flexible chat APIs to enable multilingual conversations. Developers can use Amazon serverless and API-based artificial intelligence/machine learning (AI/ML) services to incorporate machine learning capabilities into their apps.
Publication Title DISRUPTIVE TECHNOLOGIES FOR EDUCATIONAL INNOVATION IN DELTA STATE AND ITS CYBER SECURITY IMPLICATIONS: A POST COVID-19 ASSESSMENT Download PDF
Publication Type journal
Publisher FUDMA Journal of Sciences (FJS) ISSN online: 2616-1370 ISSN print: 2645 - 2944 Vol. 8 No. 6, December, 2024, pp 36 - 43
Paper Link https://doi.org/10.33003/fjs-2024-0806-
Publication Authors * 1Okpako, Abugor Ejaita, 1 Isitor, Nkechi , 2Ojie, Deborah Voke and 2Ukadike, Destiny
Year Published 2024-12-06
Abstract Technology is everywhere and it’s changing the way things work, hence it is disruptive depending on its application and context. Disruptive technology introduces new markets and modifies existing ones, providing end users with better access, convenience, empowerment, choice, and value as well as competing with established models and practically transforming products and services. The COVID-19 pandemic necessitated a rapid shift to remote learning and the adoption of disruptive technologies in educational institutions worldwide, including Nigeria. Despite this, there is limited evidence investigating how different disruptive technologies and configurations associate with cyber security within the educational sector. This research work examines the association of disruptive technology and cyber security implications in the Delta State educational system during the post COVID 19 pandemic period. A cross sectional approach was used for data collection through questionnaires where 55 responses out of 80 respondents from some selected schools in Delta State were used. The results confirm some cyber threats on using disruptive technology in e-learning as phishing and identity theft. The respondent’s level of online satisfaction, cyber security awareness and performance was significantly associated with various independent variables such as e-learning platforms, online interaction, and privacy concerns. An understanding of these relationships will help educators and other stakeholders to prioritize legislation and regulations that will address such developments. The aim should not to over-regulate and consequently strangle them, but to envisage change, prepare for it, and set up appropriate regulatory frameworks to ensure societal balance.