DR-Z2AN: dual-recurrent neural network with a tri-channel attention mechanism for financial management prediction DOI Creative Commons

Salem Knifo,

Ahmad Alzubi

Complex & Intelligent Systems, Journal Year: 2024, Volume and Issue: 11(1)

Published: Nov. 26, 2024

Financial management prediction, often known as financial forecasting, is the act of estimating future outcomes using past data and present trends. It an essential component analysis planning that aids businesses in making well-informed decisions preparing for potential events. In healthcare domain, prediction a crucial task helps patients track predict expenses required their medical services. The established methods have some flaws, such requirement labeled data, quality, time complexity, under fitting problems, longer execution times. Therefore, order to resolve these limitations; deep learning-based model developed this study efficient prediction. Specifically, research proposes dual-recurrent neural network with tri-channel attention mechanism (DR-Z2AN) accurate proposed DR-Z2AN combines dual-RNN multi-head attention, which enhances robustness interpretability systems. learns complex relationships between develops generalization capability tasks. combined efficiently processes sequence improves model's capacity extract meaningful characteristics from input. integration incentive learning approach improve parameters get better results minimum error. experimental demonstrate attains minimal error terms MAE, MAPE, MSE, RMSE 1.46, 3.83, 4.32, 2.08, respectively; thus, gives than other traditional methods. Overall, offers predictions reduced computational improved interpretability.

Language: Английский

Novel ensemble learning approach with SVM-imputed ADASYN features for enhanced cervical cancer prediction DOI Creative Commons
Raafat M. Munshi

PLoS ONE, Journal Year: 2024, Volume and Issue: 19(1), P. e0296107 - e0296107

Published: Jan. 10, 2024

Cervical cancer remains a leading cause of female mortality, particularly in developing regions, underscoring the critical need for early detection and intervention guided by skilled medical professionals. While Pap smear images serve as valuable diagnostic tools, many available datasets automated cervical contain missing data, posing challenges machine learning models’ efficacy. To address these hurdles, this study presents an system adept at managing information using ADASYN characteristics, resulting exceptional accuracy. The proposed methodology integrates voting classifier model harnessing predictive capacity three distinct models. It further incorporates SVM Imputer up-sampled features to mitigate value concerns, while leveraging CNN-generated augment model’s capabilities. Notably, achieves remarkable performance metrics, boasting 99.99% accuracy, precision, recall, F1 score. A comprehensive comparative analysis evaluates against various algorithms across four scenarios: original dataset usage, imputation, feature utilization, features. Results indicate superior efficacy over existing state-of-the-art techniques. This research not only introduces novel approach but also offers actionable suggestions refining systems. Its impact extends benefiting practitioners enabling earlier improved patient care. Furthermore, study’s findings have substantial societal implications, potentially reducing burden through enhanced accuracy timely intervention.

Language: Английский

Citations

12
An ensemble classification approach for cervical cancer prediction using behavioral risk factors DOI Creative Commons
Md Shahin Ali, Md. Maruf Hossain,

Moutushi Akter Kona

et al.

Healthcare Analytics, Journal Year: 2024, Volume and Issue: 5, P. 100324 - 100324

Published: March 28, 2024

Cervical cancer is a significant public health concern among females worldwide. Despite being preventable, it remains leading cause of mortality. Early detection crucial for successful treatment and improved survival rates. This study proposes an ensemble Machine Learning (ML) classifier efficient accurate identification cervical using medical data. The proposed methodology involves preparing two datasets effective preprocessing techniques, extracting essential features the scikit-learn package, developing based on Random Forest, Support Vector Machine, Gaussian Naïve Bayes, Decision Tree traits. Comparison with other state-of-the-art algorithms several ML including support vector machine, decision tree, random forest, logistic regression, CatBoost, AdaBoost, demonstrates that outperforms them significantly, achieving accuracies 98.06% 95.45% Dataset 1 2, respectively. current by 1.50% 6.67% respectively, highlighting its superior performance compared to existing methods. also utilizes five-fold cross-validation technique analyze benefits drawbacks predicting Receiver Operating Characteristic (ROC) curves corresponding Area Under Curve (AUC) values are 0.95 0.97 indicating overall classifiers in distinguishing between classes. Additionally, we employed SHapley Additive exPlanations (SHAP) as Explainable Artificial Intelligence (XAI) visualize classifier's performance, providing insights into important contributing identification. results demonstrate can efficiently accurately identify potentially improve diagnosis treatment.

Language: Английский

Citations

12
SkinMarkNet: an automated approach for prediction of monkeyPox using image data augmentation with deep ensemble learning models DOI
Arifa Akram, Arwa A. Jamjoom, Nisreen Innab

et al.

Multimedia Tools and Applications, Journal Year: 2024, Volume and Issue: unknown

Published: July 20, 2024

Language: Английский

Citations

5
Impact of k-Nearest Neighbors Parameter Tuning on Healthcare Prediction Accuracy Across Diverse Datasets DOI

Zsuzsa Simó,

Zsuzsa Simó, László Barna Iantovics

et al.

Lecture notes in networks and systems, Journal Year: 2025, Volume and Issue: unknown, P. 12 - 22

Published: Jan. 1, 2025

Language: Английский

Citations

0
A High-Precision Machine Learning-Based Prediction Model for Delayed Graft functon(DGF) in Chinese Kidney Transplant Patients: A Multicenter Study DOI Creative Commons
Ying Cheng,

he sun,

Ping Sun

et al.

Research Square (Research Square), Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 6, 2025

Abstract Delayed graft function (DGF) is a severe complication following kidney transplantation, and currently, there lack of accurate prediction tools tailored for the Chinese population. This study integrates data from 1,093 transplant cases across four medical centers in China (2016–2024) to develop validate machine learning-based model DGF prediction. By comparing nine learning algorithms, we found that LightGBM performed best external validation (AUC = 0.80, accuracy 0.73). SHAP analysis identified donor GFR, hemoglobin, recipient plasma BNP levels as primary predictive factors, while also highlighting novel predictors such microscopic hematuria APTT. Cox regression showed preoperative dialysis duration recipients (HR 1.006, 95% CI: 1.001–1.012) was an independent predictor recovery. In follow-up study, observed mortality group exhibited most significant impairment (serum creatinine β 200.57, eGFR -39.91), prognosis survival comparable non-DGF group. Additionally, (16.66 ± 13.73 vs. 15.44 14.62 days) number treatments (8.13 7.39 7.78 7.22 sessions) were not significantly associated with prognosis. Based on these findings, developed online platform (www.kidney-dgf-match.cn) support clinical decision-making. only establishes first high-precision population but reveals potential favorable outcomes patients proper management, offering new insights optimizing post-transplant management strategies.

Language: Английский

Citations

0
Negative Prognostic Factors and Clinical Improvement Prediction Modeling for ESWT in Calcific Shoulder Tendinitis Using Artificial Intelligence Techniques DOI
Wen‐Yi Chou, Tian-Hsiang Huang, Jai‐Hong Cheng

et al.

Journal of Shoulder and Elbow Surgery, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 1, 2025

Language: Английский

Citations

0
From Coverage to Costs: Multi-Model Analysis of Factors Shaping Cervical Cancer Prevention DOI

Xinyang Qian

Highlights in Science Engineering and Technology, Journal Year: 2025, Volume and Issue: 128, P. 279 - 286

Published: Feb. 25, 2025

World Health Organization (WHO) is developing a global strategy for cervical cancer prevention to scale the human papillomavirus vaccination coverage 90%. To measure weight of predictors affecting effect, this paper analyzes contribution factors in both statistical and machine learning methods, including logistics regression, multinominal logit random forest, extremely randomized GBDT, XGBoost. Data processing model effectiveness analysis comparison are done, varying coverage, cost, region, assumptions. The finds that current mortality prevention, projected cost HPV leading influencing future prevention. In contrast, CC rate major factor indicating coverage. Predictions consistent across six models. conclusion, although high can reduce infection rates, still affects vaccine thus

Language: Английский

Citations

0
Improved CervicalNet: integrating attention mechanisms and graph convolutions for cervical cancer segmentation DOI

K. Abinaya,

B. Sivakumar

International Journal of Machine Learning and Cybernetics, Journal Year: 2025, Volume and Issue: unknown

Published: March 17, 2025

Language: Английский

Citations

0
Detection of cotton crops diseases using customized deep learning model DOI Creative Commons
Hafiz Muhammad Faisal, Muhammad Aqib, Saif Ur Rehman

et al.

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: March 28, 2025

The agricultural industry is experiencing revolutionary changes through the latest advances in artificial intelligence and deep learning-based technologies. These powerful tools are being used for a variety of tasks including crop yield estimation, maturity assessment, disease detection. cotton an essential source revenue many countries highlighting need to protect it from deadly diseases that can drastically reduce yields. Early accurate detection quite crucial preventing economic losses sector. Thanks learning algorithms, researchers have developed innovative approaches help safeguard promote growth. This study presents dissimilar state-of-the-art models recognition VGG16, DenseNet, EfficientNet, InceptionV3, MobileNet, NasNet, ResNet models. For this purpose, real data collected fields preprocessed using different well-known techniques before as input Experimental analysis reveals ResNet152 model outperforms all other models, making practical efficient approach recognition. By harnessing power intelligence, we ensure prosperous future

Language: Английский

Citations

0
Risk warning model for predicting sleep disorders in healthcare workers on long-term shifts DOI
Xin Li, Long Xiao, Bingyi Shi

et al.

Sleep and Biological Rhythms, Journal Year: 2025, Volume and Issue: unknown

Published: April 10, 2025

Language: Английский

Citations

0