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

Enhancing the Random Forest Model via Synthetic Minority Oversampling Technique for Credit-Card Fraud Detection DOI Creative Commons

Fidelis Obukohwo Aghware,

Arnold Adimabua Ojugo, Wilfred Adigwe

et al.

Journal of Computing Theories and Applications, Journal Year: 2024, Volume and Issue: 1(4), P. 407 - 420

Published: March 26, 2024

Fraudsters increasingly exploit unauthorized credit card information for financial gain, targeting un-suspecting users, especially as institutions expand their services to semi-urban and rural areas. This, in turn, has continued ripple across society, causing huge losses lowering user trust implications all cardholders. Thus, banks cum are today poised implement fraud detection schemes. Five algorithms were trained with without the application of Synthetic Minority Over-sampling Technique (SMOTE) assess performance. These included Random Forest (RF), K-Nearest Neighbors (KNN), Naïve Bayes (NB), Support Vector Machines (SVM), Logistic Regression (LR). The methodology was implemented tested through an API using Flask Streamlit Python. Before applying SMOTE, RF classifier outperformed others accuracy 0.9802, while accuracies LR, KNN, NB, SVM 0.9219, 0.9435, 0.9508, 0.9008, respectively. Conversely, after achieved a prediction 0.9919, whereas attained 0.9805, 0.9210, 0.9125, 0.8145, results highlight effectiveness combining SMOTE enhance detection.

Language: Английский

Citations

14
Deep Learning Framework for Advanced De-Identification of Protected Health Information DOI Creative Commons
Ahmad Aloqaily, Emad E. Abdallah,

Rahaf Al-Zyoud

et al.

Future Internet, Journal Year: 2025, Volume and Issue: 17(1), P. 47 - 47

Published: Jan. 20, 2025

Electronic health records (EHRs) are widely used in healthcare institutions worldwide, containing vast amounts of unstructured textual data. However, the sensitive nature Protected Health Information (PHI) embedded within these presents significant privacy challenges, necessitating robust de-identification techniques. This paper introduces a novel approach, leveraging Bi-LSTM-CRF model to achieve accurate and reliable PHI de-identification, using i2b2 dataset sourced from Harvard University. Unlike prior studies that often unify Bi-LSTM CRF layers, our approach focuses on individual design, optimization, hyperparameter tuning both components, allowing for precise performance improvements. rigorous architectural design tuning, underexplored existing literature, significantly enhances model’s capacity tag detection while preserving essential clinical context. Comprehensive evaluations conducted across 23 categories, as defined by HIPAA, ensuring thorough security critical domains. The optimized achieves exceptional metrics, with precision 99%, recall 98%, F1-score underscoring its effectiveness balancing precision. By enabling medical records, this research strengthens patient confidentiality, promotes compliance regulations, facilitates safe data sharing analysis.

Language: Английский

Citations

1
ChainHealth: Blockchain-Based IoT-Edge Model for Secure Management of Health Data DOI Open Access
Rukiye Nur Çayan, Feyza Yıldırım Okay

Gazi University Journal of Science Part A Engineering and Innovation, Journal Year: 2025, Volume and Issue: 12(1), P. 72 - 95

Published: March 26, 2025

The Internet of Things (IoT) is rapidly expanding and seamlessly integrating into our daily lives, with an increasing number objects connecting to the Internet. It operates as a networked architecture that enables communication between connected devices. IoT applications span various domains, including smart homes, cities, transportation, healthcare. Among these, healthcare particularly important, allowing specialists monitor patients remotely, anytime, anywhere. In this system, patient data transmitted through systems, enabling remote health monitoring. However, significant challenges remain regarding privacy integrity data. This study addresses these by proposing model named ChainHealth leverages devices for collection, edge infrastructure processing, contracts on blockchain ensure integrity, store securely. Experimental results demonstrate significantly outperforms traditional models in terms transmission efficiency, scalability, overall system performance. enhances throughput, reduces latency even users increases, strengthens encryption processes. Additionally, contract mechanism evaluated shown be reliable managing integrity. As result, proposed ensures secure transfer across network critical information. By maintaining confidentiality, security, improves both quality reliability services compared approaches.

Language: Английский

Citations

0
Blockchain-Integrated Image Steganography using xDoG Edge Detection for Authentication DOI Creative Commons

Biswajit Patwari,

Utpal Nandi,

Srishti Dey

et al.

Cyber Security and Applications, Journal Year: 2025, Volume and Issue: unknown, P. 100091 - 100091

Published: April 1, 2025

Language: Английский

Citations

0
Blockchain security threats: A comprehensive classification and impact assessment DOI
Zhijun Wu, Hanwen Xu,

Meng Yue

et al.

Computer Networks, Journal Year: 2025, Volume and Issue: unknown, P. 111284 - 111284

Published: April 1, 2025

Language: Английский

Citations

0
Medical IoT Record Security and Blockchain: Systematic Review of Milieu, Milestones, and Momentum DOI Creative Commons
Simeon Okechukwu Ajakwe, Igboanusi Ikechi Saviour, Vivian Ukamaka Ihekoronye

et al.

Big Data and Cognitive Computing, Journal Year: 2024, Volume and Issue: 8(9), P. 121 - 121

Published: Sept. 12, 2024

The sensitivity and exclusivity attached to personal health records make such a prime target for cyber intruders, as unauthorized access causes unfathomable repudiation public defamation. In reality, most medical are micro-managed by different healthcare providers, exposing them various security issues, especially third-party access. Over time, substantial progress has been made in preventing this critical highly classified information. This review investigated the mainstream challenges associated with transmissibility of records, evolutionary strategies maintaining confidentiality, existential enablers trustworthy transparent authorization authentication before data transmission can be carried out. adopted PRSIMA-SPIDER methodology systematic 122 articles, comprising 9 surveys (7.37%) qualitative analysis, 109 technical papers (89.34%), 4 online reports (3.27%) quantitative studies. outcome indicates that confidentiality document, record, demand unabridged owner, unquestionable preservation host, untainted transparency transmission, unbiased traceability, ubiquitous security, which blockchain technology guarantees, although at infancy stage. Therefore, developing blockchain-assisted frameworks digital record addressing inherent technological hitches will further accelerate preservation, user authorization, they transmitted host

Language: Английский

Citations

3
Integrating Quadratic Polynomial and Symbolic Chaotic Map-Based Feistel Network to Improve Image Encryption Performance DOI Creative Commons
Edy Winarno, Wiwien Hadikurniawati,

Kristiawan Nugroho

et al.

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 106720 - 106734

Published: Jan. 1, 2024

This research introduces an innovative image encryption method that amalgamates two secure and efficient chaotic maps, namely a 2D Simplified Quadratic Polynomial Map (2D-SQPM) Symbolic Chaotic (2D-SCM), within enhanced Feistel network structure. The primary motivation for this is to address the limitations of current methods are vulnerable statistical differential attacks. A hash function also integrated elevate key's security sensitivity. Unlike standard networks, which split plaintext into parts employ only XOR operations at bit level, research's Network modification involves dividing four sections introducing diverse set operations, including substitution permutation both byte levels across different parts, thereby optimizing confusion diffusion effects. empirical evaluation demonstrates significantly reduces pixel correlation strengthens against Supported by various analytical tools like entropy analysis, NPCR, UACI, chi-square, key space sensitivity robustness testing, NIST suite evaluations, proposed enhances performance. In conclusion, effectively secures data sets new benchmark in encryption. significance lies its integration complex, dynamics advanced mechanisms, providing substantial contribution digital information security.

Language: Английский

Citations

1
Enhancing image encryption security through integration multi-chaotic systems and mixed pixel-bit level DOI

Muhammad Naufal Erza Farandi,

Aris Marjuni, Nova Rijati

et al.

The Imaging Science Journal, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 18

Published: Sept. 4, 2024

Language: Английский

Citations

1
Lightweight blockchain mechanism for secure data transmission in healthcare system DOI
Murari Kumar Singh, Sanjeev Kumar Pippal, Vishnu Sharma

et al.

Biomedical Signal Processing and Control, Journal Year: 2024, Volume and Issue: 102, P. 107411 - 107411

Published: Dec. 24, 2024

Language: Английский

Citations

1
Digital Solutions and Lean Management in African Public Hospital Medicines Supply Chain DOI
Bouchra Bouterfas, Imane Ibn El Farouk

Advances in medical technologies and clinical practice book series, Journal Year: 2024, Volume and Issue: unknown, P. 463 - 494

Published: Nov. 22, 2024

The healthcare sector has made several changes after technological devices have been introduced to different processes. In addition, in Africa, the concept of “lean” comes save medicines supply chains from waste. this context, chapter evolves intersection lean management public hospital chain and digital solutions. Therefore, it focuses on how integration can address critical challenges improve delivery. highlights side solutions Africa differently based integrated before technologies are not focused overall; however, results demonstrate importance implementing with Integrating into a lean-managed holds considerable promise for African hospitals aiming

Language: Английский

Citations

0