Enhancing Diabetes Prediction Accuracy through Hybrid Machine Learning Models: A Comparative Study DOI Creative Commons
Gregorius Airlangga

Jurnal Teknologi Terapan G-Tech, Journal Year: 2024, Volume and Issue: 8(2), P. 1297 - 1306

Published: April 25, 2024

This study investigates the effectiveness of various machine learning (ML) models in predicting onset diabetes, emphasizing superior performance hybrid over single learner models. Employing a dataset comprising 10,000 individuals with features like Glucose level, BMI, Insulin, and more, we meticulously processed engineered data to optimize it for ML applications. We developed several models, including Decision Trees, Random Forest, KNN, XGBoost, then advanced using ensemble techniques stacking soft voting classifiers. Our findings indicate that significantly outperform These achieved remarkable accuracy (98.11%), precision (97.31%), ROC AUC (99.82%), highlighting their potential clinical settings. The underscores value enhancing predictive reliability diabetes diagnostics.

Language: Английский

Microneedle wearables in advanced microsystems: unlocking next-generation biosensing with AI DOI
Ghazala Ashraf, Khalil Ahmed, Ayesha Aziz

et al.

TrAC Trends in Analytical Chemistry, Journal Year: 2025, Volume and Issue: 187, P. 118208 - 118208

Published: Feb. 27, 2025

Language: Английский

Citations

2
A multi-functional phosphor Ba5La3MgAl3O15:Pr3+ with diverse thermal responses for high sensitive temperature sensing, photothermochromism indicator and patterned anti-counterfeiting DOI

Mengzhu Long,

Chao Li, Bing Li

et al.

Ceramics International, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 1, 2025

Language: Английский

Citations

1
Biobased Self-healable Photoluminescent Polyacylhydrazones Imparted by Supramolecular Interactions DOI

Mingze Xia,

Yi Cheng,

Jingzhao Shang

et al.

Macromolecules, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 13, 2025

With the rise of circular economy, self-healing polymers have attracted significant attention for their longer lifespan and greater recyclability compared with traditional thermoplastics thermosetting polymers. However, addressing instability units to develop high-performance materials remains a challenge. Herein, we report series superior polyimine derivatives, biobased polyacylhydrazones (bio-PHys), via aldehyde-hydrazide condensation. The coexistence amide bonds imine bonds, which provide hydrogen bonding dynamics, imparts remarkable mechanical properties (tensile strength 103 MPa, elongation at break 180%) bio-PHys, along notable capabilities under glass transition temperature (Tg). Bio-PHys also exhibits potential scalable production, excellent processability, photoluminescence characteristics. We explored its application in adhesive-free laminated substrates thoroughly investigated aggregation-induced emission acylhydrazone group. Furthermore, utilized bio-PHys create recyclable smart paper anticounterfeiting dynamic information storage. This work presents novel approach developing

Language: Английский

Citations

0
Nanoparticles: a promising tool against environmental stress in plants DOI Creative Commons
Xu Zhou, Ahmed H. El‐Sappah, Amani Khaskhoussi

et al.

Frontiers in Plant Science, Journal Year: 2025, Volume and Issue: 15

Published: Jan. 27, 2025

With a focus on plant tolerance to environmental challenges, nanotechnology has emerged as potent instrument for assisting crops and boosting agricultural production in the face of growing worldwide population. Nanoparticles (NPs) systems may interact molecularly change stress response, growth, development. NPs feed nutrients plants, prevent diseases pathogens, detect monitor trace components soil by absorbing their signals. More excellent knowledge processes that help plants survive various stressors would aid creating more long-term strategies combat these challenges. Despite many studies NPs’ use agriculture, we reviewed types anticipated molecular metabolic effects upon entering cells. In addition, discussed different applications against all stresses. Lastly, introduced risks, difficulties, prospects.

Language: Английский

Citations

0
Synthesis, Photoluminescence, Antimicrobial Evaluation, Molecular Docking, and Pharmacokinetic Prediction of New Pyrimidoselenolo[2,3-d]pyrimidine Derivatives DOI
Mahmoud S. Tolba, Mostafa Ahmed,

Ahmed A. K. Mohammed

et al.

Journal of Molecular Structure, Journal Year: 2025, Volume and Issue: unknown, P. 142097 - 142097

Published: March 1, 2025

Language: Английский

Citations

0
Tailored Organic Light-Emitting Diodes (OLEDs) for Next-Generation Biomedicine DOI

Maida Mobeen,

Akim Oladokoun,

Maryam Hussain

et al.

Engineering materials, Journal Year: 2025, Volume and Issue: unknown, P. 211 - 230

Published: Jan. 1, 2025

Language: Английский

Citations

0
Enhancing Diabetes Prediction Accuracy through Hybrid Machine Learning Models: A Comparative Study DOI Creative Commons
Gregorius Airlangga

Jurnal Teknologi Terapan G-Tech, Journal Year: 2024, Volume and Issue: 8(2), P. 1297 - 1306

Published: April 25, 2024

This study investigates the effectiveness of various machine learning (ML) models in predicting onset diabetes, emphasizing superior performance hybrid over single learner models. Employing a dataset comprising 10,000 individuals with features like Glucose level, BMI, Insulin, and more, we meticulously processed engineered data to optimize it for ML applications. We developed several models, including Decision Trees, Random Forest, KNN, XGBoost, then advanced using ensemble techniques stacking soft voting classifiers. Our findings indicate that significantly outperform These achieved remarkable accuracy (98.11%), precision (97.31%), ROC AUC (99.82%), highlighting their potential clinical settings. The underscores value enhancing predictive reliability diabetes diagnostics.

Language: Английский

Citations

0