Ensemble feature selection and tabular data augmentation with generative adversarial networks to enhance cutaneous melanoma identification and interpretability DOI Creative Commons
Vanesa Gómez-Martínez, David Chushig-Muzo, Marit B. Veierød

и другие.

BioData Mining, Год журнала: 2024, Номер 17(1)

Опубликована: Окт. 30, 2024

Cutaneous melanoma is the most aggressive form of skin cancer, responsible for cancer-related deaths. Recent advances in artificial intelligence, jointly with availability public dermoscopy image datasets, have allowed to assist dermatologists identification. While feature extraction holds potential detection, it often leads high-dimensional data. Furthermore, datasets present class imbalance problem, where a few classes numerous samples, whereas others are under-represented.

Язык: Английский

Low-Code Automl Solutions for Predicting Bond Strength and Failure Modes of Cfrp-Steel Joints DOI
Songbo Wang, Zhen Liu, Jun Su

и другие.

Опубликована: Янв. 1, 2024

Язык: Английский

Процитировано

0
Evaluation of Stress Distributions in Trimaterial Bonded Joints with Nano-Resin Adhesive Using Machine Learning Models DOI Creative Commons
Shah Mohammad Azam Rishad, Md. Shahidul Islam, Md. Ariful Islam

и другие.

Results in Materials, Год журнала: 2024, Номер 23, С. 100618 - 100618

Опубликована: Авг. 24, 2024

Adhesive bonded joints hold significant importance across various industrial sectors in modern engineering, owing to their lightweight nature and myriad advantages. The rising demand for trimaterial underscores utility versatility. In these joints, the choice of materials both adherends greatly influences strength, structural reliability, overall characteristics. While numerous researches have extensively analyzed stress distributions, effects, behaviors, many relied on a one-factor-at-a-time approach, focusing solely individual design variables' effects. However, recognizing intricate interplay among material combinations collective impact performance, this study employs types White-box, Black-box, Grey-box machine learning algorithms identify an optimized ML model as well predict distributions any random upper lower adherend materials. Dataset total 178 were utilized training phases with 5-fold cross validation tuning. decision tree regressor emerged by comparing quantitative metrics accuracy benchmark prediction outcomes obtained through all models. maximum attained was impressive 99.97 %, while minimum recorded 89.74 %. This research aims tailored specifically where nano layer resin is adhesive.

Язык: Английский

Процитировано

0
Low-code AutoML solutions for predicting bond strength and failure modes of CFRP-steel joints DOI
Songbo Wang, Zhen Liu, Jun Su

и другие.

Construction and Building Materials, Год журнала: 2024, Номер 449, С. 138420 - 138420

Опубликована: Сен. 24, 2024

Язык: Английский

Процитировано

0
Ensemble feature selection and tabular data augmentation with generative adversarial networks to enhance cutaneous melanoma identification and interpretability DOI Creative Commons
Vanesa Gómez-Martínez, David Chushig-Muzo, Marit B. Veierød

и другие.

BioData Mining, Год журнала: 2024, Номер 17(1)

Опубликована: Окт. 30, 2024

Cutaneous melanoma is the most aggressive form of skin cancer, responsible for cancer-related deaths. Recent advances in artificial intelligence, jointly with availability public dermoscopy image datasets, have allowed to assist dermatologists identification. While feature extraction holds potential detection, it often leads high-dimensional data. Furthermore, datasets present class imbalance problem, where a few classes numerous samples, whereas others are under-represented.

Язык: Английский

Процитировано

0