Results 21 to 30 of about 14,024,113 (261)

Short-Term Urban Water Demand Forecasting Using an Improved NeuralProphet Model

Engineering Proceedings
The use of machine learning models for short-term network flow prediction has become increasingly widespread in recent years. Existing data-driven models are usually able to achieve good accuracy, but machine learning models are usually weakly ...
Yao Yao, Haixing Liu, Fengrui Gao, Hongcai Guo, Jiaxuan Zou   +4 more
doaj   +1 more source

Social Functioning Within the First Years After Pediatric Brain Tumor Diagnosis and the Relationship With Family Psychosocial Risk

Pediatric Blood &Cancer, EarlyView.
ABSTRACT Background Survivors of pediatric brain tumors (PBTs) can experience long‐term social difficulties, impacting quality of life. Beyond medical and environmental factors, family psychosocial risk may play a role in social outcomes by shaping the caregiving environment and may provide intervention options.
Renske H. Houben, Marisa H. Huisman, Martha A. Grootenhuis, Femke K. Aarsen, Marita Partanen   +4 more
wiley   +1 more source

Improve Adversarial Robustness of AI Models in Remote Sensing via Data-Augmentation and Explainable-AI Methods

Remote Sensing
Artificial intelligence (AI) has made remarkable progress in recent years in remote sensing applications, including environmental monitoring, crisis management, city planning, and agriculture.
Sumaiya Tasneem, Kazi Aminul Islam
doaj   +1 more source

Retrospective Analysis of Donor Lymphocyte Infusions in Pediatric Patients With Mixed Chimerism After Hematopoietic Stem Cell Transplantation

Pediatric Blood &Cancer, EarlyView.
ABSTRACT Background Allogeneic hematopoietic stem cell transplantation (alloHSCT) is an essential therapy for several malignant and nonmalignant diseases, but relapse and graft loss remain the principal threats to its success. Routine monitoring of chimerism and minimal residual disease (MRD) enables early detection of imminent recurrence and guides ...
Carmen Junk, Sebastian Michaelis, Michaela Döring, Thomas Eichholz, Ursula Holzer, Martin Ebinger, Tim Flaadt, Rupert Handgretinger, Peter Lang, Jan Frederic Weller, Markus Mezger   +10 more
wiley   +1 more source

The Impact of the COVID‐19 Pandemic on Childhood Cancer Survival: A Population‐Based Assessment of Survival Patterns Between 2015 and 2023 in Germany

Pediatric Blood &Cancer, EarlyView.
ABSTRACT Background Numerous international studies have reported declines in new cancer diagnoses, delayed diagnoses and disruptions in cancer treatment following the implementation of COVID‐19 pandemic public health measures, raising concerns that these effects may ultimately contribute to increased cancer mortality.
Friederike Erdmann, Maike Wellbrock, Javier Louro, Arndt Borkhardt, Martin Schrappe, Claudia Trübenbach, Desiree Grabow, Cécile M. Ronckers, Joachim Schüz   +8 more
wiley   +1 more source

An Explainable AI-Based Fault Diagnosis Model for Bearings

Sensors, 2021
In this paper, an explainable AI-based fault diagnosis model for bearings is proposed with five stages, i.e., (1) a data preprocessing method based on the Stockwell Transformation Coefficient (STC) is proposed to analyze the vibration signals for ...
Md Junayed Hasan, Muhammad Sohaib, Jong-Myon Kim   +2 more
doaj   +1 more source

Referral Patterns and Diagnostic Timeliness in Pediatric Cancer: A Hospital‐Based Study in Indonesia

Pediatric Blood &Cancer, EarlyView.
ABSTRACT Background Timely diagnosis and treatment are critical for improving survival among children with cancer. In low‐ and middle‐income countries (LMICs), delays are common and may be influenced by fragmented referral pathways and diagnostic limitations.
Nur Melani Sari, Regina Hadi Putri, Fatimah Assyifa, Judith Spijkerman, Gertjan Johannes Kaspers, Susi Susanah   +5 more
wiley   +1 more source

Explainable machine learning for stroke risk prediction: a comparative study with SHAP-based interpretation

Frontiers in Neurology
BackgroundStroke is one of the leading causes of death and disability worldwide, making early screening and risk prediction crucial. Traditional methods have limitations in handling nonlinear relationships between variables, class imbalance, and model ...
Xiaoyu Tang, Xiaoyu Tang, Xiaoyu Tang, Min Tang, Wu Liu, Shaoyang Cui, Shaoyang Cui, Shaoyang Cui   +7 more
doaj   +1 more source

Um modelo de rede neuro-fuzzy baseada em funções de base radial capaz de inferir regras do tipo Mamdani [PDF]

, 2015
Dissertação (mestrado) - Universidade Federal de Santa Catarina, Centro Tecnológico, Programa de Pós-Graduação em Ciência da Computação, Florianópolis, 2015.Este trabalho tem como objetivo apresentar um novo sistema de inferência neuro-fuzzy, chamado ...
Rodrigues, Diego Garcia
core  

Model agnostic interpretability [PDF]

This thesis explores the development and application of model-agnostic interpretability methods for deep neural networks. I introduce novel techniques for interpreting trained models irrespective of their architecture, including Centroid Maximisation, an
Rumbelow, Jessica
core   +1 more source