Results 101 to 110 of about 13,846 (260)

Explainable Ensemble Learning Framework with SMOTE, SHAP and LIME for Predicting 30-Day Readmission in Diabetic Patients

Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
Hospital readmission among diabetic patients poses a significant burden on healthcare systems due to its frequency and associated costs. This study presents a machine learning framework for predicting 30-day readmission in diabetic patients using the ...
Joshua Pinem, Widi Astuti, Adiwijaya
doaj   +1 more source

A comparative study on SMOTE, CTGAN, and hybrid SMOTE-CTGAN for medical data augmentation

Science in Information Technology Letters
The imbalance of clinical datasets remains a challenge in medical data mining, often resulting in models biased toward majority outcomes and reduced sensitivity to rare but clinically critical cases. This study presents a comparative evaluation of three augmentation strategies—Synthetic Minority Oversampling Technique (SMOTE), Conditional Tabular GAN ...
Ninda Khoirunnisa, Miftahurrahma Rosyda
openaire   +1 more source

Three Spirometry‐Based At‐Risk Phenotypes Predict Incident Airflow Limitation: A Population‐Based Study

Respirology, EarlyView.
Analysing the population‐based KORA and SHIP studies, three spirometric at‐risk subtypes (early airflow limitation, PRISm, and small airway dysfunction) were consistently associated with incident airflow limitation. Their combination in a conceptual framework identified most future cases with high negative predictive value, suggesting potential for ...
Hendrik Pott, Roman Martin, Wilhelm Bertrams, Mustafa Abdo, Margit Heier, Annette Peters, Beate Stubbe, Max Kutzinski, Anne Obst, Ralf Ewert, Dominik Heider, Henry Völzke, Gernot Rohde, Claus F. Vogelmeier, Bernd Schmeck, Stefan Karrasch, on behalf of the KORA‐study group   +16 more
wiley   +1 more source

Optimizing Decision Tree and Random Forest with Grid Search and SMOTE for Malware Classification on IoT Network Traffic

Journal of Applied Informatics and Computing
The rapid growth of the Internet of Things (IoT) has increased the risk of malware attacks, posing serious threats especially to micro, small, and medium enterprises (MSMEs) that often lack sufficient cybersecurity resources.
Muhammad Nurus Siroj, Akhmad Khanif Zyen, Gentur Wahyu Nyipto Wibowo   +2 more
doaj   +1 more source

Rhyming in the cold: first evidence of soniferous fishes in the Southern Ocean

Remote Sensing in Ecology and Conservation, EarlyView.
The acoustic ecology of Southern Ocean fishes remains unknown due to a lack of dedicated acoustic research on the fishes of this ocean. Passive acoustic monitoring data were collected at the South African sub‐Antarctic Prince Edward Islands using an underwater acoustic recorder, and towed underwater Ski‐Monkey cameras were deployed to identify fish ...
Fannie W. Shabangu, Grant van der Heever, Charles von der Meden, Hannah Truter, Stephen J. Lamberth, Ofer Gon   +5 more
wiley   +1 more source

Performance Comparison of Machine Learning Algorithms Using EfficientNetB0 Feature Extraction on Dental Disease Classification

Journal of Applied Informatics and Computing
Oral health conditions such as dental caries, calculus, gingivitis, and ulcers are prevalent globally and require accurate early detection to prevent further complications.
Mohammad Faiq Ruliff Mustafa, Ajie Kusuma Wardhana   +1 more
doaj   +1 more source

Science for All? A Systematic Literature Review on Effective Teaching Approaches in Inclusive and Separate Settings

Science Education, EarlyView.
ABSTRACT This systematic literature review examines intervention studies focused on teaching science to a diverse range of learners. It adopts a broad definition of inclusion and makes use of the PRISMA statement. The review aims to provide an overview of evidence‐based teaching approaches in the current literature, identify the science skills targeted,
Silvia Fränkel, Nadine Großmann, Melanie Basten   +2 more
wiley   +1 more source

SMOTE-D, Una versión determinista de SMOTE

, 2017
En diferentes aplicaciones prácticas es común que se presente desbalance entre clases. Este problema aparece cuando la cantidad de objetos en una clase es mucho menor que en la otra. Esta diferencia en el tamaño de las clases causa que los métodos de clasificación favorezcan a la clase con mayor cantidad de objetos (mayoritaria), produciendo un mal ...
openaire   +1 more source

Transparency, Sustainable Governance and Digital Accessibility in Municipalities: A Machine Learning Approach

Sustainable Development, EarlyView.
ABSTRACT Achieving the Sustainable Development Goals (SDGs) requires transparent and accountable local governments, yet little is known about the structural drivers of municipal transparency. This study introduces a machine learning approach to predict municipal transparency using the Bidimensional Transparency Index (BTI), which measures both the ...
Ana M. Plata‐Díaz, Elisabeth Zafra‐Gómez, Juan C. Garrido‐Rodríguez, M. Carmen Pérez‐López   +3 more
wiley   +1 more source

Camels as a Climate‐Resilient Linchpin for Sustainable Development in Global Drylands

Sustainable Development, EarlyView.
ABSTRACT Camels represent a significant, yet underutilized, asset for advancing integrated sustainable development in the world's expanding drylands. Previous reviews have examined camels' physiology, milk composition, or pastoral systems in isolation; this review examines their potential as a climate‐resilient linchpin for food systems by synthesizing
Ayana Angassa, Minyahel Tilahun, Solomon G. Tesfamichael   +2 more
wiley   +1 more source