An enhanced soft-computing based strategy for efficient feature selection for timely breast cancer prediction: Wisconsin Diagnostic Breast Cancer dataset case

Multimedia Tools and Applications, Journal Year: 2024, Volume and Issue: 83(31), P. 76607 - 76672

Published: Feb. 19, 2024

Language: Английский

---

VELM: a voting based ensemble learning model for breast cancer prediction

Physica Scripta, Journal Year: 2025, Volume and Issue: 100(2), P. 026002 - 026002

Published: Jan. 3, 2025

Abstract Today breast cancer (BC) is the most common and dangerous type of in women. The increasing numbers cases have been realized recent past all over world. Based on World Cancer Survey Report, 2022; global incidence 2.3 million new 670,000 deaths Breast screening timely diagnosis greatly affect life expectancy since current interventions cannot adequately treat individuals later stages. Nonetheless, development various expert systems has initiated for early cancer, wherein a major concern that many these often fail to localize potential causes such as class imbalance, appropriate methods data pre-processing, systematic feature selection appropriately. Therefore, this work develops model named ‘Voting-based Ensemble Learning Model Prediction’ (VELM) improve BC prediction based machine learning. In present work, imbalance problem solved using ‘SMOTE’ method, while ‘SelectKBest’ used determine features set. order compare proposed VELM analyse its performance, results models including individual classifiers, ensemble literature computed accuracy, precision, recall, F1-score AUC ROC. outcome shows our highest, accuracy 0. 9912 other metrices comparison with discussed literature.

Language: Английский

---

A comparative study of machine learning models with LASSO and SHAP feature selection for breast cancer prediction

Healthcare Analytics, Journal Year: 2024, Volume and Issue: 6, P. 100353 - 100353

Published: June 25, 2024

In recent decades, breast cancer has become the most prevalent type of that impacts women in world, which shows a significant risk to death rates women. Early identification might drastically decrease patient mortality and greatly improve chance an effective treatment. modern times, machine learning models have crucial for classifying strengthening both accuracy efficiency diagnostic medical treatment strategies. Therefore, this study is focused on early detection using variety algorithms desires identify feature selection process with amalgamated dataset. Initially, we evaluated five traditional two meta-models separate datasets. To find valuable features, used Least Absolute Shrinkage Selection Operator (LASSO) as well SHapley Additive exPlanations (SHAP) methods analyzed them through wide range performance regulations. Additionally, applied these combined dataset observed mergeddataset was significantly beneficial diagnosis. After analyzing strategies, it demonstrated majority performed more accurately when utilizing SHAP methodologies. Notably, three meta-classifiers obtained 99.82%, demonstrating superior compared state-of-the-art methods. This advancement holds role lays foundation refining tools enhancing progression science field.

Language: Английский

---

An Emperical Way to Diagnose the Cancer Stages Using Algorithm in AI System

Published: Feb. 9, 2024

This paper gives a unique technique for automated cancer detection the use of AI-based totally prediction algorithms. Cancer often as complicated and heterogeneous set traits, making prognosis hard. In this novel method, an AI-primarily based rules is used to come across most cancers from visible scientific information. The utilizes supervised studying categorize information photograph features, after which practice type version be expecting presence cancers. optimized accuracy can discover multiple types with excessive accuracy. results demonstrate that approach stumble on up ninety%, it effective device automatic prognosis. Additionally, might similarly applied other diagnosis tasks, in treasured device.

Language: Английский

---

A three-stage novel framework for efficient and automatic glaucoma classification from retinal fundus images

Multimedia Tools and Applications, Journal Year: 2024, Volume and Issue: unknown

Published: June 14, 2024

Language: Английский

---

Cross vision transformer with enhanced Growth Optimizer for breast cancer detection in IoMT environment

Computational Biology and Chemistry, Journal Year: 2024, Volume and Issue: 111, P. 108110 - 108110

Published: May 22, 2024

Language: Английский

---

SUPER-COUGH: A Super Learner-based ensemble machine learning method for detecting disease on cough acoustic signals

Biomedical Signal Processing and Control, Journal Year: 2024, Volume and Issue: 93, P. 106165 - 106165

Published: Feb. 28, 2024

Language: Английский

---

The Smart Performance Comparison of AI-based Breast Cancer Detection Models

Published: Feb. 23, 2024

The smart performance comparison of AI-based breast cancer detection models is an important research topic in the healthcare industry. It used to compare and evaluate different that are diagnose cancer. These mainly developed using machine learning, computer vision, or deep learning techniques. methods these can vary depending on purpose comparison. This include comparing accuracy, precision, recall, f-measure models. Furthermore, other criteria such as stability, reliability, explain ability, speed, cost-effectiveness may be taken into consideration when evaluating have achieved high sensitivity specificity rates, outperforming traditional methods. However, AI varies based type imaging technique dataset used. Further, also highlights need for more diverse inclusive datasets avoid potential biases results from this provide valuable insight help professionals researchers select deploy best model their particular applications.

Language: Английский

---

A new binary chaos-based metaheuristic algorithm for software defect prediction

Cluster Computing, Journal Year: 2024, Volume and Issue: 27(7), P. 10093 - 10123

Published: May 4, 2024

Abstract Software defect prediction is a critical challenge within software engineering aimed at enhancing quality by proactively identifying potential defects. This approach involves selecting defect-prone modules ahead of the testing phase, thereby reducing time and costs. Machine learning methods provide developers with valuable models for categorising faulty modules. However, arises from numerous elements present in training dataset, which frequently reduce accuracy precision classification. Addressing this, effective features classification dataset becomes an NP-hard problem, often tackled using metaheuristic algorithms. study introduces novel approach, Binary Chaos-based Olympiad Optimisation Algorithm, specifically designed to select most impactful dataset. By these influential classification, module classifiers can be notably improved. The study's primary contributions involve devising binary variant chaos-based optimisation algorithm meticulously construct efficient model Five real-world standard datasets were utilised across both phases classifier evaluate proposed method's effectiveness. findings highlight that among 21 datasets, specific metrics such as basic complexity, sum operators operands, lines code, quantity containing code comments, operands have significant influence on prediction. research underscores combined effectiveness method machine algorithms, significantly boosting (91.13%), (92.74%), recall (97.61%), F1 score (94.26%)

Language: Английский

---

A snake optimization algorithm-based feature selection framework for rapid detection of cardiovascular disease in its early stages

Biomedical Signal Processing and Control, Journal Year: 2024, Volume and Issue: 102, P. 107417 - 107417

Published: Dec. 24, 2024

Language: Английский

---