Grid-based many-objective optimiser for aircraft conceptual design with multiple aircraft configurations

Engineering Applications of Artificial Intelligence, Journal Year: 2023, Volume and Issue: 126, P. 106951 - 106951

Published: Aug. 12, 2023

Language: Английский

---

An effective multiclass skin cancer classification approach based on deep convolutional neural network

Cluster Computing, Journal Year: 2024, Volume and Issue: unknown

Published: June 17, 2024

Abstract Skin cancer is one of the most dangerous types due to its immediate appearance and possibility rapid spread. It arises from uncontrollably growing cells, rapidly dividing cells in area body, invading other bodily tissues, spreading throughout body. Early detection helps prevent progress reaching critical levels, reducing risk complications need for more aggressive treatment options. Convolutional neural networks (CNNs) revolutionize skin diagnosis by extracting intricate features images, enabling an accurate classification lesions. Their role extends early detection, providing a powerful tool dermatologists identify abnormalities their nascent stages, ultimately improving patient outcomes. This study proposes novel deep convolutional network (DCNN) approach classifying The proposed DCNN model evaluated using two unbalanced datasets, namely HAM10000 ISIC-2019. compared with transfer learning models, including VGG16, VGG19, DenseNet121, DenseNet201, MobileNetV2. Its performance assessed four widely used evaluation metrics: accuracy, recall, precision, F1-score, specificity, AUC. experimental results demonstrate that outperforms (DL) models utilized these datasets. achieved highest accuracy ISIC-2019 $$98.5\%$$ 98.5 % $$97.1\%$$ 97.1 , respectively. These show how competitive successful overcoming problems caused class imbalance raising accuracy. Furthermore, demonstrates superior performance, particularly excelling terms recent studies utilize same which highlights robustness effectiveness DCNN.

Language: Английский

---

Skin lesion recognition via global-local attention and dual-branch input network

Engineering Applications of Artificial Intelligence, Journal Year: 2023, Volume and Issue: 127, P. 107385 - 107385

Published: Oct. 31, 2023

Language: Английский

---

Differential evolution with migration mechanism and information reutilization for global optimization

Expert Systems with Applications, Journal Year: 2023, Volume and Issue: 238, P. 122076 - 122076

Published: Oct. 16, 2023

Language: Английский

---

Robust prediction of Coke Reactivity Index via machine learning methods

Canadian Metallurgical Quarterly, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 20

Published: May 21, 2025

Language: Английский

---

Enhanced Crested Ibis Algorithm: Performance Validation in Benchmark Functions, Engineering Problem, and Application in Brain Tumor Detection

Expert Systems with Applications, Journal Year: 2025, Volume and Issue: unknown, P. 128231 - 128231

Published: May 1, 2025

Language: Английский

---

Handling Imbalance and Limited Data in Thyroid Ultrasound and Diabetic Retinopathy Datasets Using Discrete Levy Flights Grey Wolf Optimizer Based Random Forest for Robust Medical Data Classification

ACM Transactions on Asian and Low-Resource Language Information Processing, Journal Year: 2024, Volume and Issue: unknown

Published: Feb. 16, 2024

In the field of disease diagnosis, medical image classification faces an inherent challenge due to various factors involving data imbalance, quality variability, annotation and limited availability representativeness. Such challenges affect algorithm's ability on images in adverse way, which leads biased model outcomes inaccurate interpretations. this paper, a novel Discrete Levy Flight Grey Wolf Optimizer (DLFGWO) is combined with Random Forest (RF) classifier address above limitations biomedical datasets achieve better rate. The DLFGWO-RF resolves variability ultrasound limits inaccuracies using RF by handling incomplete noisy data. sheer focus majority class may lead unequal distribution classes thus imbalance. DLFGWO balances such leveraging grey wolves its exploration exploitation capabilities are improved (DLF). It further optimizes classifier's performance balanced designed perform even datasets, thereby requirement numerous expert annotations can be reduced. diabetic retinopathy grading, reduces disagreements subjective However, representativeness dataset fails capture entire population diversity, generalization proposed DLFGWO-RF. Thus, fine-tuning robustly adapt subgroups dataset, enhancing overall performance. experiments conducted two widely used test efficacy model. experimental results show that achieves accuracy between 90-95%, outperforms existing techniques for imbalanced datasets.

Language: Английский

---

Graph-based rank aggregation: a deep-learning approach

International Journal of Web Information Systems, Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 20, 2024

Purpose This study aims to introduce a novel rank aggregation algorithm that leverages graph theory and deep-learning improve the accuracy relevance of aggregated rankings in metasearch scenarios, particularly when faced with inconsistent low-quality lists. By strategically selecting subset base rankers, enhances quality ranking while using only rankers. Design/methodology/approach The proposed graph-based model represent interrelationships between applying Spectral clustering, identifies top-performing rankers based on their retrieval effectiveness. These selected are then integrated into sequential estimate labels for query-document pairs. Findings Empirical evaluation MQ2007-agg MQ2008-agg data sets demonstrates substantial performance gains achieved by compared baseline methods, an average improvement 8.7% MAP 11.9% NDCG@1. algorithm’s effectiveness can be attributed its ability effectively integrate diverse perspectives from capture complex relationships within data. Originality/value research presents approach integrates deep-learning. author proposes select most effective applications constructing similarity innovative method addresses challenges posed lists, offering unique solution problem.

Language: Английский

---

Which opinion is more trustworthy: An analysts’ earnings forecast quality assessment framework based on machine learning

The North American Journal of Economics and Finance, Journal Year: 2024, Volume and Issue: unknown, P. 102318 - 102318

Published: Nov. 1, 2024

Language: Английский

---

Autoencoder- Based Multistage Strategy for Class Imbalance in Medical Imaging Analysis - Chest X-rays

SN Computer Science, Journal Year: 2024, Volume and Issue: 5(8)

Published: Dec. 14, 2024

Language: Английский

---