Results 71 to 80 of about 266,019 (309)

Research on Cavitation Fault Diagnosis of Axial Piston Pumps Based on Rough Set Attribute Weighted Convolutional Neural Networks

open access: yesSensors
Cavitation phenomenon in piston pumps not only causes vibration and noise but also leads to component damage. Conventional diagnostic methods suffer from low accuracy, while deep learning approaches lack interpretability.
Min Liu   +6 more
doaj   +1 more source

Toward Interpretable Machine Learning Models for Materials Discovery

open access: yesAdvanced Intelligent Systems, 2019
Machine learning (ML) and artificial intelligence (AI) methods for modeling useful materials properties are now important technologies for rational design and optimization of bespoke functional materials.
Paulius Mikulskis   +2 more
doaj   +1 more source

Feeding, Fear, and Acceptance: Caregivers’ Experiences of Nutritional Support During Childhood Cancer Treatment

open access: yesPediatric Blood &Cancer, EarlyView.
ABSTRACT Purpose To explore caregivers' experiences and perceptions of the nutritional challenges faced by children and adolescents undergoing cancer treatment, including oral intake and the use of nutritional support. Methods This was a qualitative study based on focus groups with parents and caregivers at a Brazilian pediatric oncology hospital ...
Danyelle Apparecida Balsamão Marques   +5 more
wiley   +1 more source

Approach for Microseismic Monitoring Data-Driven Rockburst Short-Term Prediction Using Deep Feature Extraction and Interpretable Coupling Neural Networks

open access: yesApplied Sciences
Rockburst disasters have become increasingly prevalent as distinct forms of subsurface geotechnical engineering advanced to the deep earth. Confronted with such a threatening subsurface geopressure disaster that poses a risk to personnel and equipment ...
Shirui Wang   +8 more
doaj   +1 more source

Representation of Sickle Cell Disease Patients in Pediatric and Adult Care: What We Discovered Using Informatics for Integrating Biology and the Bedside (i2b2) Data

open access: yesPediatric Blood &Cancer, EarlyView.
ABSTRACT Transitioning from pediatric to adult care is a high‐risk period for individuals with sickle cell disease (SCD). An initial observation at one academic medical center suggested a sex‐based disparity in clinic populations, prompting a national investigation.
Laurie J. Duckworth   +5 more
wiley   +1 more source

Being confident in confidence scores: calibration in deep learning models for camera trap image sequences

open access: yesRemote Sensing in Ecology and Conservation
In ecological studies, machine learning models are increasingly being used for the automatic processing of camera trap images. Although this automation facilitates and accelerates the identification step, the results of these models may lack ...
Gaspard Dussert   +3 more
doaj   +1 more source

CDPNet: a deformable ProtoPNet for interpretable wheat leaf disease identification

open access: yesFrontiers in Plant Science
IntroductionAccurate identification of wheat leaf diseases is crucial for food security, but existing prototype-based computer vision models struggle with the scattered nature of lesions in field conditions and lack interpretability.
Jinyu Zeng   +5 more
doaj   +1 more source

Uncovering Inequities: The Role of Social Determinants of Health in Hospitalized Adolescents and Young Adults With Heavy Menstrual Bleeding

open access: yesPediatric Blood &Cancer, EarlyView.
ABSTRACT Background Heavy menstrual bleeding (HMB) is a common condition among adolescents and young adults (AYAs) and is the leading cause of iron deficiency anemia (IDA) in this population. Growing evidence suggests that social determinants of health (SDOH) influence menstrual bleeding patterns, access to care, and treatment. However, no studies have
Maria Carter‐Febres   +6 more
wiley   +1 more source

The many faces of interpretability [PDF]

open access: yes, 2005
In this paper we discus work in progress on interpretability logics. We show how semantical considerations have allowed us to formulate non-trivial principles about formalized interpretability.
Joosten, Joost J., Goris, Evan
core  

Deep Learning for Time-Series Forecasting With Exogenous Variables in Energy Consumption: A Performance and Interpretability Analysis

open access: yesIEEE Access
The rise of decentralized energy sources and renewables demands advanced grid planning, with short-term load forecasting (STLF) playing a crucial role.
Ava Mohammadi   +2 more
doaj   +1 more source

Home - About - Disclaimer - Privacy