Article Per Year (5 Year)
p-Index From 2020 - 2025
0.702
P-Index
This Author published in this journals
All Journal International Journal of Informatics and Communication Technology (IJ-ICT) Applied Engineering and Technology Journal of Computing Theories and Applications
Okpor, Margareth Dumebi
Unknown Affiliation
Automotive Engineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Industrial & Manufacturing Engineering Materials Science & Nanotechnology

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
BloFoPASS: A blockchain food palliatives tracer support system for resolving welfare distribution crisis in Nigeria Aghware, Fidelis Obukohwo; Adigwe, Wilfred; Okpor, Margareth Dumebi; Odiakaose, Christopher Chukwufunaya; Ojugo, Arnold Adimabua; Eboka, Andrew Okonji; Ejeh, Patrick Ogholorunwalomi; Taylor, Onate Egerton; Ako, Rita Erhovwo; Geteloma, Victor Ochuko
International Journal of Informatics and Communication Technology (IJ-ICT) Vol 13, No 2: August 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijict.v13i2.pp178-187

Abstract

With population rising to approximately 200 million Nigerians – fast-paced, urbanization has continued to advent food insecurity with maladministration, corruption, internal rife, and starvation. These, threatened the nation's unity with the lockdown of 2020; and consequently, have now become the trend. Nigeria must as a nation, re-examine her methods in the administration of palliatives (in lieu of food and relief) distribution – as the above-listed issues have become of critical need in the equitable distribution of reliefs, both from the humanitarian agency view, and the Government (State and Federal). They have noticed non-transparency, corruption, and data inadequacies, as major drawbacks in its management. Our study presents a blockchain ensemble for the administration of food palliatives distribution in Nigeria that first ensures, that all beneficiaries be registered, and the food palliatives are sensor-tagged and recorded on the blockchain. Results show the number of transactions per second and page retrieval abilities for the proposed chain were quite low with 30-TPS and 0.38seconds respectively – as compared to public blockchain. Proposed ensemble eliminates fraud that is herein rippled across the existing system, minimizes corrupt practices via sensor-based model, provides insight for stakeholders, and minimize the error in reported data on the supply chain.
Enhancing the Random Forest Model via Synthetic Minority Oversampling Technique for Credit-Card Fraud Detection Aghware, Fidelis Obukohwo; Ojugo, Arnold Adimabua; Adigwe, Wilfred; Odiakaose, Christopher Chukwufumaya; Ojei, Emma Obiajulu; Ashioba, Nwanze Chukwudi; Okpor, Margareth Dumebi; Geteloma, Victor Ochuko
Journal of Computing Theories and Applications Vol. 1 No. 4 (2024): JCTA 1(4) 2024
Publisher : Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62411/jcta.10323

Abstract

Fraudsters increasingly exploit unauthorized credit card information for financial gain, targeting un-suspecting users, especially as financial institutions expand their services to semi-urban and rural areas. This, in turn, has continued to ripple across society, causing huge financial losses and lowering user trust implications for all cardholders. Thus, banks cum financial institutions are today poised to implement fraud detection schemes. Five algorithms were trained with and without the application of the Synthetic Minority Over-sampling Technique (SMOTE) to assess their performance. These algorithms included Random Forest (RF), K-Nearest Neighbors (KNN), Naïve Bayes (NB), Support Vector Machines (SVM), and Logistic Regression (LR). The methodology was implemented and tested through an API using Flask and Streamlit in Python. Before applying SMOTE, the RF classifier outperformed the others with an accuracy of 0.9802, while the accuracies for LR, KNN, NB, and SVM were 0.9219, 0.9435, 0.9508, and 0.9008, respectively. Conversely, after the application of SMOTE, RF achieved a prediction accuracy of 0.9919, whereas LR, KNN, NB, and SVM attained accuracies of 0.9805, 0.9210, 0.9125, and 0.8145, respectively. These results highlight the effectiveness of combining RF with SMOTE to enhance prediction accuracy in credit card fraud detection.
AQuamoAS: unmasking a wireless sensor-based ensemble for air quality monitor and alert system Geteloma, Victor Ochuko; Aghware, Fidelis Obukohwo; Adigwe, Wilfred; Odiakaose, Chukwufunaya Chris; Ashioba, Nwanze Chukwudi; Okpor, Margareth Dumebi; Ojugo, Arnold Adimabua; Ejeh, Patrick Ogholuwarami; Ako, Rita Erhovwo; Ojei, Emmanuel Obiajulu
Applied Engineering and Technology Vol 3, No 2 (2024): August 2024
Publisher : ASCEE

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31763/aet.v3i2.1409

Abstract

The increased awareness by residents of their environment to maintain safe health states has consequently, birthed the integration of info tech to help resolve societal issues. These, and its adopted approaches have become critical and imperative in virtualization to help bridge the lapses in human mundane tasks and endeavors. Its positive impacts on society cannot be underestimated. Study advances a low-cost wireless sensor-based ensemble to effectively manage air quality tasks. Thus, we integrate an IoT framework to effectively monitors environment changes via microcontrollers, sensors, and blynk to assist users to monitor temperature, humidity, detect the presence of harmful gases in/out door environs. The blynk provides vital knowledge to the user. Our AQuaMoAS algorithm makes for an accurate and user-friendly mode using cloud services to ease monitor and data visualization. The system was tested at 3 different stages of rainy, sunny and heat with pollutant via alpha est method. For all functions at varying conditions, result revealed 70.7% humidity, 29.5OC, and 206 ppm on a sunny day. 51.5% humidity, 20.4OC and 198ppm on a rainy, and 43.1 humidity, 45.6OC, 199ppm air quality on heat and 66.5% humidity, 30.2 OC and 363 ppm air quality on application of air pollutant were observed
Enhanced data augmentation for predicting consumer churn rate with monetization and retention strategies: a pilot study Geteloma, Victor Ochuko; Aghware, Fidelis Obukohwo; Adigwe, Wilfred; Odiakaose, Chukwufunaya Chris; Ashioba, Nwanze Chukwudi; Okpor, Margareth Dumebi; Ojugo, Arnold Adimabua; Ejeh, Patrick Ogholuwarami; Ako, Rita Erhovwo; Ojei, Emmanuel Obiajulu
Applied Engineering and Technology Vol 3, No 1 (2024): April 2024
Publisher : ASCEE

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31763/aet.v3i1.1408

Abstract

Customer retention and monetization have since been the pillar of many successful firms and businesses as keeping an old customer is far more economical than gaining a new one – which, in turn, reduce customer churn rate. Previous studies have focused on the use of single heuristics as well as provisioned no retention strategy. To curb this, our study posits the use of the recen-cy-frequency-monetization framework as strategy for customer retention and monetization impacts. With dataset retrieved from Kaggle, and partitioned into train and test dataset/folds to ease model construction and training. Study adopt a tree-based Random Forest ensemble with synthetic minority oversampling technique edited nearest neighbor (SMOTEEN). Various benchmark models were trained to asssess how well each performs against our proposed ensemble. The application was tested using an application programming interface Flask and integrated using streamlit into a device. Our RF-ensemble resulted in a 0.9902 accuracy prior to applying SMOTEENN; while, LR, KNN, Naïve Bayes and SVM yielded an accuracy of 0.9219, 0.9435, 0.9508 and 0.9008 respectively. With SMOTEENN applied, our ensemble had an accuracy of 0.9919; while LR, KNN, Naïve Bayes, and SVM yielded an accuracy of 0.9805, 0.921, 0.9125, and 0.8145 respectively. RF has shown it can be implemented with SMOTEENN to yield enhanced prediction for customer churn prediction using Python
Co-Authors Adigwe, Wilfred Aghware, Fidelis Obukohwo Ako, Rita Erhovwo Ashioba, Nwanze Chukwudi Eboka, Andrew Okonji Ejeh, Patrick Ogholorunwalomi Ejeh, Patrick Ogholuwarami Geteloma, Victor Ochuko Odiakaose, Christopher Chukwufumaya Odiakaose, Christopher Chukwufunaya Odiakaose, Chukwufunaya Chris Ojei, Emma Obiajulu Ojei, Emmanuel Obiajulu Ojugo, Arnold Adimabua Taylor, Onate Egerton