Breast Cancer Prediction: A Fusion of Genetic Algorithm, Chemical Reaction Optimization, and Machine Learning Techniques

Applied Computational Intelligence and Soft Computing, Journal Year: 2024, Volume and Issue: 2024(1)

Published: Jan. 1, 2024

Breast cancer is currently one of the most prevalent cancers affecting women globally. Uncontrolled growth and division breast cells lead to formation tumors, marking onset cancer. Predicting essential for early detection, making treatment plans, implementing preventive measures, ultimately improving patient outcomes reducing mortality rates. In recent years, numerous studies have been published predict where researchers use a variety methods. Most investigations conducted using narrow specific datasets, often resulting in lack accuracy. Such methods may not be suitable clinical use. The study aims address limitations existing models terms robustness generalization across diverse datasets. our study, we employed two metaheuristic algorithms, namely, genetic algorithm (GA) chemical reaction optimization (CRO) with machine learning techniques, including support vector (SVM), decision tree, random forest, XGBoost. GA CRO are used optimize feature selection process. It enables algorithms more accurately. Experiments were on three Wisconsin Cancer (WBC), Cancer‐the University California, Irvine (BC‐UCI), Coimbra (BCC) datasets contain 569, 286, 116 instances, respectively. classifiers optimized features consistently outperformed without accuracy, precision, recall, specificity, F 1 score. Among compared recently, method attained highest accuracies 99.64% WBC dataset 98% BCC dataset, as well second accuracy 99.12% BC‐UCI dataset. Comparative analysis demonstrated superiority approach over

Language: Английский

---

Differential epitope prediction across diverse circulating variants of SARS-COV-2 in Brazil

Computational Biology and Chemistry, Journal Year: 2024, Volume and Issue: 112, P. 108139 - 108139

Published: June 29, 2024

Language: Английский

---

Improving the Machine Learning Stock Trading System: An N‐Period Volatility Labeling and Instance Selection Technique

Complexity, Journal Year: 2024, Volume and Issue: 2024(1)

Published: Jan. 1, 2024

Financial technology is crucial for the sustainable development of financial systems. Algorithmic trading, a key area in technology, involves automated trading based on predefined rules. However, investors cannot manually analyze all market patterns and establish rules, necessitating supervised learning systems that can discover using machine or deep techniques. Many studies rely up–down labeling price differences, which overlooks issues nonstationarity, complexity, noise stock data. Therefore, this study proposes an N‐period volatility system addresses limitations The measures to address uncertainty enables construction stable, long‐term system. Additionally, instance‐selection technique utilized data, including noise, nonlinearity, while effectively reducing data size. effectiveness proposed model evaluated through simulations stocks comprising NASDAQ 100 index compared with experimental results demonstrate exhibits higher stability profitability than other

Language: Английский

---

DRSegNet: A cutting-edge approach to Diabetic Retinopathy segmentation and classification using parameter-aware Nature-Inspired optimization

PLoS ONE, Journal Year: 2024, Volume and Issue: 19(12), P. e0312016 - e0312016

Published: Dec. 5, 2024

Diabetic retinopathy (DR) is a prominent reason of blindness globally, which diagnostically challenging disease owing to the intricate process its development and human eye’s complexity, consists nearly forty connected components like retina, iris, optic nerve, so on. This study proposes novel approach identification DR employing methods such as synthetic data generation, K- Means Clustering-Based Binary Grey Wolf Optimizer (KCBGWO), Fully Convolutional Encoder-Decoder Networks (FCEDN). achieved using Generative Adversarial (GANs) generate high-quality transfer learning for accurate feature extraction classification, integrating these with Extreme Learning Machines (ELM). The substantial evaluation plan we have provided on IDRiD dataset gives exceptional outcomes, where our proposed model 99.87% accuracy 99.33% sensitivity, while specificity 99. 78%. why outcomes presented can be viewed promising in terms further diagnosis, well creating new reference point within framework medical image analysis providing more effective timely treatments.

Language: Английский

---