Faculty of Computers and Information, Minia University, Minia, Egypt.
School of Computing, Skyline University College, Sharjah, P.O. Box 1797, United Arab Emirates.
Comput Biol Med. 2024 Oct;181:109080. doi: 10.1016/j.compbiomed.2024.109080. Epub 2024 Aug 30.
Bladder Cancer (BC) is a common disease that comes with a high risk of morbidity, death, and expense. Primary risk factors for BC include exposure to carcinogens in the workplace or the environment, particularly tobacco. There are several difficulties, such as the requirement for a qualified expert in BC classification. The Parrot Optimizer (PO), is an optimization method inspired by key behaviors observed in trained Pyrrhura Molinae parrots, but the PO algorithm becomes stuck in sub-regions, has less accuracy, and a high error rate. So, an Improved variant of the PO (IPO) algorithm was developed using a combination of two strategies: (1) Mirror Reflection Learning (MRL) and (2) Bernoulli Maps (BMs). Both strategies improve optimization performance by avoiding local optimums and striking a compromise between convergence speed and solution diversity. The performance of the proposed IPO is evaluated against eight other competitor algorithms in terms of statistical convergence and other metrics according to Friedman's test and Bonferroni-Dunn test on the IEEE Congress on Evolutionary Computation conducted in 2022 (CEC 2022) test suite functions and nine BC datasets from official repositories. The IPO algorithm ranked number one in best fitness and is more optimal than the other eight MH algorithms for CEC 2022 functions. The proposed IPO algorithm was integrated with the Support Vector Machine (SVM) classifier termed (IPO-SVM) approach for bladder cancer classification purposes. Nine BC datasets were then used to confirm the effectiveness of the proposed IPO algorithm. The experiments show that the IPO-SVM approach outperforms eight recently proposed MH algorithms. Using the nine BC datasets, IPO-SVM achieved an Accuracy (ACC) of 84.11%, Sensitivity (SE) of 98.10%, Precision (PPV) of 95.59%, Specificity (SP) of 95.98%, and F-score (F) of 94.15%. This demonstrates how the proposed IPO approach can help to classify BCs effectively. The open-source codes are available at https://www.mathworks.com/matlabcentral/fileexchange/169846-an-efficient-improved-parrot-optimizer.
膀胱癌（BC）是一种常见疾病，具有较高的发病率、死亡率和医疗费用。BC 的主要危险因素包括接触工作场所或环境中的致癌物，特别是烟草。BC 分类需要合格的专家，这是一个难题。Parrot Optimizer（PO）是一种受训练过的 Pyrrhura Molinae 鹦鹉关键行为启发的优化方法，但 PO 算法会陷入子区域，准确性较低，错误率较高。因此，开发了一种 Parrot Optimizer 的改进变体（IPO）算法，该算法结合了两种策略：（1）镜像反射学习（MRL）和（2）伯努利图（BMs）。这两种策略通过避免局部最优和在收敛速度和解决方案多样性之间取得平衡来提高优化性能。根据 2022 年 IEEE 进化计算大会（CEC 2022）测试套件函数和来自官方存储库的九个膀胱癌数据集，通过 Friedman 检验和 Bonferroni-Dunn 检验，对所提出的 IPO 算法与其他八种竞争算法的统计收敛性和其他指标进行了评估。IPO 算法在最佳适应性方面排名第一，在 CEC 2022 函数方面比其他八种 MH 算法更优。所提出的 IPO 算法与支持向量机（SVM）分类器集成，称为（IPO-SVM）方法，用于膀胱癌分类目的。然后使用九个膀胱癌数据集来验证所提出的 IPO 算法的有效性。实验表明，IPO-SVM 方法优于最近提出的八种 MH 算法。使用九个膀胱癌数据集，IPO-SVM 达到了 84.11%的准确率（ACC）、98.10%的灵敏度（SE）、95.59%的精确度（PPV）、95.98%的特异性（SP）和 94.15%的 F 值（F）。这表明了所提出的 IPO 方法如何帮助有效地分类膀胱癌。开源代码可在 https://www.mathworks.com/matlabcentral/fileexchange/169846-an-efficient-improved-parrot-optimizer 获得。
