Hypertension Detection via Tree-Based Stack Ensemble with SMOTE-Tomek Data Balance and XGBoost Meta-Learner DOI Creative Commons
Christopher Chukwufunaya Odiakaose,

Fidelis Obukohwo Aghware,

Margaret Dumebi Okpor

et al.

Journal of Future Artificial Intelligence and Technologies, Journal Year: 2024, Volume and Issue: 1(3), P. 269 - 283

Published: Dec. 1, 2024

High blood pressure (or hypertension) is a causative disorder to plethora of other ailments – as it succinctly masks ailments, making them difficult diagnose and manage with targeted treatment plan effectively. While some patients living elevated high can effectively their condition via adjusted lifestyle monitoring follow-up treatments, Others in self-denial leads unreported instances, mishandled cases, now rampant cases result death. Even the usage machine learning schemes medicine, two (2) significant issues abound, namely: (a) utilization dataset construction model, which often yields non-perfect scores, (b) exploration complex deep models have yielded improved accuracy, requires large dataset. To curb these issues, our study explores tree-based stacking ensemble Decision tree, Adaptive Boosting, Random Forest (base learners) while we explore XGBoost meta-learner. With Kaggle retrieved, prediction accuracy 1.00 an F1-score that correctly classified all instances test

Language: Английский

StreamBoostE: A Hybrid Boosting-Collaborative Filter Scheme for Adaptive User-Item Recommender for Streaming Services DOI Open Access

R.R. Atuduhor,

Margaret Dumebi Okpor,

R. E. Yoro

et al.

Advances in Multidisciplinary & Scientific Research Journal Publication, Journal Year: 2024, Volume and Issue: 10(2), P. 89 - 106

Published: May 31, 2024

With home entertainment, selecting the perfect movie is a pervasive challenge, amplified by many streaming platforms like Netflix and Amazon Prime. This study advances recommender system with collaborative filtering approach as implemented in Python titled StreamBoostE. We used user-based item-based similarity schemes on feature embedding to aid faster model construction training for tree-based gradient boosting ensemble. Employing both user- cosine ease embedding, assesses movies inter-relations via personalized user interest preferences submitted titles focus genre classification. Results shows ensemble yields prediction accuracy of 0.9984 F1 0.996. The major contribution StreamBoostE its capability expedite selection process when integrated using flask API streamlit cross-channel integration web-based platforms. It presents users list top-10 recommended similarity. XGBoost performed best user-/item-based scheme fused sampling method. Keywords: Random Forest, SMOTE, credit card fraud detection, selection, imbalanced dataset Aims Research Journal Reference Format: Atuduhor, R.R., Okpor, M.D., Yoro, R.E., Odiakaose, C.C., Emordi, F.U., Ojugo, A.A., Ako, Geteloma, V.O., Ejeh, P.O., Abere, R.A., Ifioko, A.M., & Brizimor, S.E. (2024): StreamBoostE: A Hybrid Boosting-Collaborative Filter Scheme Adaptive User-Item Recommender Streaming Services. Advances Multidisciplinary Scientific Vol. 10. No. 2. Pp 89-106. www.isteams.net/aimsjournal. dx.doi.org/10.22624/AIMS/V10N2P8

Language: Английский

Citations

2
WiSeCart: Sensor-based Smart-Cart with Self-Payment Mode to Improve Shopping Experience and Inventory Management DOI Open Access

S.E Brizimor,

Margaret Dumebi Okpor, Rume Elizabeth Yoro

et al.

Advances in Multidisciplinary & Scientific Research Journal Publication, Journal Year: 2024, Volume and Issue: 10, P. 53 - 74

Published: March 30, 2024

Superstores are often rippled with people from a variety of the pyramid structure lower, middle and higher-levels pyramid. These malls transform onto busy-bee hub wishing to explore merits discounted product prices special offers. This, however causes surge in traffic coupled enticing promotions that then lead endless queues at various cash-sales point check-out counters. This case poses inherent challenges both for business owners customers due time constraint, substitution quantity tracking such malls. The study proposes WiSeCart – wireless sensor-based shopping cart near feature compatibility feat. Result shows integration self-payment system via NFC tech provisions with: (a) reduced queue so can finish their quicker fast-paced checkout process, (b) yields increase inventory management efficiency errors customer data entry using communication stickers, (c) improved capability allow further behaviour experience service delivery, which will turn equip owner better managerial decision support. Keywords: sensor-networks, smart-carts, trolley, experience, superstores Journal Reference Format: Brizimor, S.E., Okpor, M.D., Yoro, R.E., Emordi, F.U., Ifioko, A.M., Odiakaose, C.C., Ojugo, A.A., Ejeh, P.O., Abere, R.A., Ako, Geteloma, V.O., (2024): WiSeCart: Sensor-based Smart-Cart Self-Payment Mode Improve Shopping Experience Inventory Management. Social Informatics, Business, Politics, Law, Environmental Sciences & Technology Journal. Vol. 10, No. 1. Pp 53-74. www.isteams/socialinformaticsjournal. dx.doi.org/10.22624/AIMS/SIJ/V10N1P7

Language: Английский

Citations

1
NiCuSBlockIoT: Sensor-based Cargo Assets Management and Traceability Blockchain Support for Nigerian Custom Services DOI Open Access

D. Obasuyi,

Rume Elizabeth Yoro, Margaret Dumebi Okpor

et al.

Advances in Multidisciplinary & Scientific Research Journal Publication, Journal Year: 2024, Volume and Issue: 15(2), P. 45 - 64

Published: May 31, 2024

As competitive market and globalization continue to ripple a range of issues across the asset chain (i.e. safety, quality, tracing, overall management efficiency). Pandemics are bound occur without warning has revealed unpreparedness many nations. Thus, Nigerian Government aiming shore up revenue/monetization via customs exercise duties augment nosedive in revenue oil sector – must formulate policies adapt technology harness its inherent benefits therein. Study advances sensor-based blockchain NiCuSBlockIoT, which will provision decision-support scheme for cargo goods traceability movement on value-chain by first ensuring that accurate records registered, tagged reported using units. These then broadcasted NiCuSBlockIoT as record and/or blocks P2P network decentralized framework executed distributed hyper-ledger fabric smart-contract transaction logic. Result show model eliminate fraud often accompanies centralized sensor-layered reports all such errors data supply value chain. Keywords: BlockChain, Food chain, Customs Service, NISBlockIoT CISDI Journal Reference Format Obasuyi, D.A., Yoro, R.E., Okpor, M.D., Ifioki, A.., Brizimor, S.., Ojugo, A.A., Odiakaose, C.C., Emordi, F.U., Ako, Geteloma, V.C., Abere, R.A., Atuduhor, R.R. & Akiakeme, E. (2024): NiCuSBlockIoT: Sensor-based Cargo Assets Management Traceability Blockchain Support Custom Services. Computing, Information Systems, Development Informatics Allied Research Journal. Vol 15 No 2, Pp 45-64. dx.doi.org/10.22624/AIMS/CISDI/V15N2P4. Available online at www.isteams.net/cisdijournal

Language: Английский

Citations

1
Pilot Study on Consumer Preference, Intentions and Trust on Purchasing-Pattern for Online Virtual Shops DOI Open Access

Sebastina Nkechi Okofu,

Kizito Eluemunor Anazia,

Maureen Ifeanyi Akazue

et al.

International Journal of Advanced Computer Science and Applications, Journal Year: 2024, Volume and Issue: 15(7)

Published: Jan. 1, 2024

User behaviour about an item is a choice predicated on their perception of the in order to satisfy intent such purchase pattern/choice as made. With virtual stores improve consumer coverage, monetization and ease product delivery, users' trust lowered with non-delivery advertised products items purchased are often replaced new/similar products. To resolve issues preference for via online shops – each transaction reflects user buying behaviour. This, if harnessed will aid businesses reshape inventory handle various challenges arising from feature evolution, drift, replacement, concept evolution. Our study seeks these Bayesian network trust, features store investigate effectiveness design usefulness promote e-commerce Nigeria. Data consists 8,693 records collected Google Play Scraper Library Jumia retrieved over 586 respondents. Expert evaluation ranked use parameters high.

Language: Английский

Citations

1
CoDuBoTeSS: A Pilot Study to Eradicate Counterfeit Drugs via a Blockchain Tracer Support System on the Nigerian Frontier DOI Open Access

Ayo Michael Ifioko,

Rume Elizabeth Yoro, Margaret Dumebi Okpor

et al.

Advances in Multidisciplinary & Scientific Research Journal Publication, Journal Year: 2024, Volume and Issue: 10(2), P. 53 - 74

Published: May 31, 2024

The pharma-sector has maintained improved productivity and profitability via a concerted effort to address critical issues such as an unorganized regulatory system, lack of safety data, no standards in manufacture process, non-adaptation pharma-chain, no-harmony inventory supports. Study proposes blockchain trace-support ensure drugs quality, consumer safety, its trading asset. It uses radio-frequency identification sensor register administration provide databank trace drug records. Results notes: (a) presents roadmap for adoption by the National Agency Food Drug Administration Control (NAFDAC) traceable pharmaceutical blockchain, (b) show ensemble is scalable up-to 7500users yield performance 1138-transactions per seconds with response time 88secs page retrieval 128secs queries respectively, (c) yields slightly longer increased number users world-state stored permissionless hyper-fabric ledger. Thus, framework can directly query retrieve data without it traversing whole This, turn, improves efficiency effectiveness traceability system. Keywords: Blockchain, Counterfeit drugs, Healthcare, Nigeria, CORDA, hyper-ledger fabric, HIPPA Journal Reference Format: Ifioko, A.M., Yoro, R.E., Okpor, M.D., Brizimor, S.E, Obasuyi, D., Emordi, F.U., Odiakaose, C.C., Ojugo, A.A., Atuduhor, R.R, Abere, R.A., Ejeh, P.O., Ako, R.E. & Geteloma, V.O. (2024): CoDuBoTeSS: A Pilot Eradicate Drugs Blockchain Tracer Support System on Nigerian Frontier. Behavioural Informatics, Digital Humanities Development Rese Vol. 10 No. 2. Pp 53-74 https://www.isteams.net/behavioralinformaticsjournal dx.doi.org/10.22624/AIMS/BHI/V10N2P6

Language: Английский

Citations

0
CoDuBoTeSS: A Pilot Study to Eradicate Counterfeit Drugs via a Blockchain Tracer Support System on the Nigerian Frontier DOI Open Access

Ayo Michael Ifioko,

Rume Elizabeth Yoro, Margaret Dumebi Okpor

et al.

Advances in Multidisciplinary & Scientific Research Journal Publication, Journal Year: 2024, Volume and Issue: 10(2), P. 53 - 74

Published: May 31, 2024

The pharma-sector has maintained improved productivity and profitability via a concerted effort to address critical issues such as an unorganized regulatory system, lack of safety data, no standards in manufacture process, non-adaptation pharma-chain, no-harmony inventory supports. Study proposes blockchain trace-support ensure drugs quality, consumer safety, its trading asset. It uses radio-frequency identification sensor register administration provide databank trace drug records. Results notes: (a) presents roadmap for adoption by the National Agency Food Drug Administration Control (NAFDAC) traceable pharmaceutical blockchain, (b) show ensemble is scalable up-to 7500users yield performance 1138-transactions per seconds with response time 88secs page retrieval 128secs queries respectively, (c) yields slightly longer increased number users world-state stored permissionless hyper-fabric ledger. Thus, framework can directly query retrieve data without it traversing whole This, turn, improves efficiency effectiveness traceability system. Keywords: Blockchain, Counterfeit drugs, Healthcare, Nigeria, CORDA, hyper-ledger fabric, HIPPA Journal Reference Format: Ifioko, A.M., Yoro, R.E., Okpor, M.D., Brizimor, S.E, Obasuyi, D., Emordi, F.U., Odiakaose, C.C., Ojugo, A.A., Atuduhor, R.R, Abere, R.A., Ejeh, P.O., Ako, R.E. & Geteloma, V.O. (2024): CoDuBoTeSS: A Pilot Eradicate Drugs Blockchain Tracer Support System on Nigerian Frontier. Behavioural Informatics, Digital Humanities Development Rese Vol. 10 No. 2. Pp 53-74 https://www.isteams.net/behavioralinformaticsjournal dx.doi.org/10.22624/AIMS/BIJ/V10N1P6

Language: Английский

Citations

0
Hypertension Detection via Tree-Based Stack Ensemble with SMOTE-Tomek Data Balance and XGBoost Meta-Learner DOI Creative Commons
Christopher Chukwufunaya Odiakaose,

Fidelis Obukohwo Aghware,

Margaret Dumebi Okpor

et al.

Journal of Future Artificial Intelligence and Technologies, Journal Year: 2024, Volume and Issue: 1(3), P. 269 - 283

Published: Dec. 1, 2024

High blood pressure (or hypertension) is a causative disorder to plethora of other ailments – as it succinctly masks ailments, making them difficult diagnose and manage with targeted treatment plan effectively. While some patients living elevated high can effectively their condition via adjusted lifestyle monitoring follow-up treatments, Others in self-denial leads unreported instances, mishandled cases, now rampant cases result death. Even the usage machine learning schemes medicine, two (2) significant issues abound, namely: (a) utilization dataset construction model, which often yields non-perfect scores, (b) exploration complex deep models have yielded improved accuracy, requires large dataset. To curb these issues, our study explores tree-based stacking ensemble Decision tree, Adaptive Boosting, Random Forest (base learners) while we explore XGBoost meta-learner. With Kaggle retrieved, prediction accuracy 1.00 an F1-score that correctly classified all instances test

Language: Английский

Citations

0