Browse Articles
Discover research articles across all indexed journals
Biogeographic barriers and environmental gradients reveal distribution limits in Hynobius salamanders
New deep sea terebellid polychaete with sucker like ventral pads adapted to a sediment free environment
Enhanced skin cancer classification using modified efficientNetV2L with adaptive early stopping mechanism
Abstract The accurate classification of skin cancer types is a critical task in medical diagnostics, requiring robust and reliable models to distinguish between various skin lesions. Despite advancements in deep learning, developing models that generalize well to unseen data remains a challenge. Current methodologies primarily utilize convolutional neural networks (CNNs) for image classification tasks, leveraging architectures such as ResNet, VGG, and Inception. These models have shown promise in improving classification accuracy for skin cancer detection. However, existing models often face limitations, including overfitting to the training data and difficulty in handling imbalanced datasets. This results in decreased performance on validation and test datasets, reducing their practical applicability in clinical settings. Additionally, these models may lack the fine-grained discrimination required to accurately classify a diverse range of skin lesion types. To address the limitations of traditional CNN-based approaches, we propose a novel model based on the EfficientNetV2L architecture, optimized for skin lesion classification. Our approach introduces adaptive early stopping and learning rate callbacks to enhance generalization and prevent overfitting. Trained on the ISIC dataset, the model achieved a high classification accuracy of 99.22%, demonstrating robustness across various lesion types. This work contributes a powerful, efficient, and clinically relevant solution to the field of automated skin cancer diagnosis.
Daily briefing: Custom-made gene-editing therapy for children to enter clinical trial
Graph-augmented multi-modal learning framework for robust android malware detection
Fraudulent account detection in social media using hybrid deep transformer model and hyperparameter optimization
OSU-ERβ-12: a promising pre-clinical candidate selective estrogen receptor beta agonist
Investigation of floor blasting for rock burst prevention in high-stress roadway under dynamic loading
Increased autoantibodies against incretin indicate poor prognosis in patients with diabetes
HyFusion-X: hybrid deep and traditional feature fusion with ensemble classifiers for breast cancer detection using mammogram and ultrasound images
Differential effects of KRAS G-domain and hypervariable region mutants on cancer phenotypes
Ensemble machine learning models for predicting strength of concrete with foundry sand and coal bottom ash as fine aggregate replacements
Depression in mice causes decreased neuronal excitability and enhanced frequency adaptation in medial prefrontal cortex pyramidal neurons
Exploring the relationship between boredom proneness and short-form videos addiction among Chinese college students through a moderated mediation model
Abstract Previous studies have shown positive associations between boredom proneness and mobile phone addiction. However, the association between boredom proneness and short-form video addiction (SFVA), as well as the intermediate psychological mechanisms, remain unclear. This study aimed to investigate the correlation between boredom proneness and subsequent SFVA among Chinese college students and to examine the mediating role of fear of missing out and the moderating role of intolerance of uncertainty. A total of 458 college students (62.2% male; M age = 19.17) from a university in central China participated in a two-wave time-lagged study with six months intervals. Results showed that boredom proneness was positively associated with SFVA six months later. Fear of missing out mediated this association, and intolerance of uncertainty moderated the association between boredom proneness and fear of missing out. The results further showed that the indirect effect of boredom proneness on SFVA via fear of missing out was more salient when there was a higher levels of intolerance of uncertainty. Interventions targeting boredom proneness and intolerance of uncertainty may be important in addressing SFVA in college populations.