Cited by Analisis Bibliometrik Penelitian Pohon Keputusan untuk Prediksi Kanker Payudara

Prediction of flight departure delays caused by weather conditions adopting data-driven approaches DOI

Seong‐Eun Kim, Eunil Park

Journal Of Big Data, Journal Year: 2024, Volume and Issue: 11(1)

Published: Jan. 9, 2024

Abstract In this study, we utilize data-driven approaches to predict flight departure delays. The growing demand for air travel is outpacing the capacity and infrastructure available support it. addition, abnormal weather patterns caused by climate change contribute frequent occurrence of light extensive network international flights covering vast distances across continents oceans, importance forecasting delays over extended time periods becomes increasingly evident. Existing research has predominantly concentrated on short-term predictions, prompting our study specifically address aspect. We collected datasets spanning 10 years from three different airports such as ICN airport in South Korea, JFK MDW United States, capturing information at six intervals (2, 4, 8, 16, 24, 48 h) prior departure. comprise 1,569,879 instances ICN, 773,347 JFK, 404,507 MDW, respectively. employed a range machine learning deep approaches, including Decision Tree, Random Forest, Support Vector Machine, K-nearest neighbors, Logistic Regression, Extreme Gradient Boosting, Long Short-Term Memory, Our models achieved accuracy rates 0.749 airport, 0.852 0.785 2-h predictions. Furthermore, 48-h 0.748 0.846 0.772 based experimental results. Consequently, have successfully validated delay predictions longer frames. implications future directions derived these findings are also discussed.

Language: Английский

Citations

Artificial intelligence for breast cancer detection and its health technology assessment: A scoping review DOI

Anisie Uwimana,

Giorgio Gnecco, Massimo Riccaboni

et al.

Computers in Biology and Medicine, Journal Year: 2024, Volume and Issue: 184, P. 109391 - 109391

Published: Nov. 22, 2024

Language: Английский

Citations

An integrated approach of feature selection and machine learning for early detection of breast cancer DOI

Jing Zhu, Zheng Zhao, Bangzheng Yin

et al.

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

Published: April 15, 2025

Language: Английский

Citations

Explainable extreme boosting model for breast cancer diagnosis DOI

Tamilarasi Suresh, Tsehay Admassu Assegie, Sangeetha Ganesan

et al.

International Journal of Power Electronics and Drive Systems/International Journal of Electrical and Computer Engineering, Journal Year: 2023, Volume and Issue: 13(5), P. 5764 - 5764

Published: June 23, 2023

<span lang="EN-US">This study investigates the Shapley additive explanation (SHAP) of extreme boosting (XGBoost) model for breast cancer diagnosis. The employed Wisconsin’s dataset, characterized by 30 features extracted from an image a cell. SHAP module generated different explainer values representing impact feature on experiment computed 569 samples dataset. indicates perimeter and concave points have highest explains XGB diagnosis outcome showing affecting XGBoost model. developed achieves accuracy 98.42%.</span>

Language: Английский

Citations

PLA—A Privacy-Embedded Lightweight and Efficient Automated Breast Cancer Accurate Diagnosis Framework for the Internet of Medical Things DOI

Chengxiao Yan, Xiaoyang Zeng, Rui Xi

et al.

Electronics, Journal Year: 2023, Volume and Issue: 12(24), P. 4923 - 4923

Published: Dec. 7, 2023

The Internet of Medical Things (IoMT) can automate breast tumor detection and classification with the potential artificial intelligence. However, leakage sensitive data cause harm to patients. To address this issue, study proposed an intrauterine cancer diagnosis method, namely “Privacy-Embedded Lightweight Efficient Automated (PLA)”, for IoMT, which represents approach that combines privacy-preserving techniques, efficiency, automation achieve our goals. Firstly, model is designed lightweight prediction global information processing by utilizing advanced IoMT-friendly ViT backbone. Secondly, PLA protects patients’ privacy federated learning, taking task as main introducing texture analysis images auxiliary train model. For framework, accuracy 0.953, recall rate 0.998 best, F1 value 0.969, precision 0.988, time 61.9 ms. experimental results show performs better than all comparison methods in terms accuracy, improvement more 0.5%. Furthermore, demonstrates significant advantages over regarding memory.

Language: Английский

Citations

Decoding pulsatile patterns of cerebrospinal fluid dynamics through enhancing interpretability in machine learning DOI

Ayşe Keleş, Pınar Özışık, Oktay Algın

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Aug. 1, 2024

Analyses of complex behaviors Cerebrospinal Fluid (CSF) have become increasingly important in diseases diagnosis. The changes the phase-contrast magnetic resonance imaging (PC-MRI) signal formed by velocity flowing CSF are represented as a set velocity-encoded images or maps, which can be thought data context medical imaging, enabling evaluation pulsatile patterns throughout cardiac cycle. However, automatic segmentation region PC-MRI image is challenging, and implementing an explained ML method using feature remains unexplored. This paper presents lightweight machine learning (ML) algorithms to perform lumen spinal, utilizing sets maps feature. Dataset contains 57 slabs 3T MRI scanner from control idiopathic scoliosis participants involved collect data. models trained with 2176 time series images. Different periods (frame) numbers PC-MRIs interpolated preprocessing step align features equal size. fivefold cross-validation procedure used estimate success models. Additionally, study focusses on enhancing interpretability highest-accuracy eXtreme gradient boosting (XGB) model applying shapley additive explanations (SHAP) technique. XGB algorithm presented its highest accuracy, average accuracy 0.99% precision, 0.95% recall, 0.97% F1 score. We evaluated significance each feature's contribution predictions, offering more profound understanding model's behavior distinguishing pixels SHAP. Introducing novel approach field, develop offer comprehension into extraction selection Moreover, offers valuable insights domain experts, contributing enhanced scholarly dynamics.

Language: Английский

Citations

Analisis Bibliometrik Penelitian Pohon Keputusan untuk Prediksi Kanker Payudara DOI

Suhartono Suhartono, Totok Chamidy, Syahiduz Zaman

et al.

Journal of Documentation and Information Science, Journal Year: 2023, Volume and Issue: 7(2)

Published: Sept. 1, 2023

The purpose of this paper is to conduct a bibliometric analysis scientific publications that discuss the use decision tree method for breast cancer prediction. A total 322 documents from Scopus were collected using indicators such as productivity and citations. produces mapping based on keywords co-occurrence, co-authorship, co-citation reflect conceptual, social, intellectual structure research. results evolution article found an exponential increase in citations number authors study period 2005-2023, where China was dominant country conducting In thematic map analysis, three research topics produced, namely medical field, computer field bioinformatics field. Research prediction are included This suggests topic needs be continuously improved.

Language: Английский

Citations