Recent Advances in Grey Wolf Optimizer, its Versions and Applications: Review

IEEE Access, Journal Year: 2023, Volume and Issue: 12, P. 22991 - 23028

Published: Aug. 14, 2023

The Grey Wolf Optimizer (GWO) has emerged as one of the most captivating swarm intelligence methods, drawing inspiration from hunting behavior wolf packs. GWO's appeal lies in its remarkable characteristics: it is parameter-free, derivative-free, conceptually simple, user-friendly, adaptable, flexible, and robust. Its efficacy been demonstrated across a wide range optimization problems diverse domains, including engineering, bioinformatics, biomedical, scheduling planning, business. Given substantial growth effectiveness GWO, essential to conduct recent review provide updated insights. This delves into GWO-related research conducted between 2019 2022, encompassing over 200 articles. It explores GWO terms publications, citations, domains that leverage potential. thoroughly examines latest versions categorizing them based on their contributions. Additionally, highlights primary applications with computer science engineering emerging dominant domains. A critical analysis accomplishments limitations presented, offering valuable Finally, concludes brief summary outlines potential future developments theory applications. Researchers seeking employ problem-solving tool will find this comprehensive immensely beneficial advancing endeavors.

Language: Английский

---

Review of the grey wolf optimization algorithm: variants and applications

Neural Computing and Applications, Journal Year: 2023, Volume and Issue: 36(6), P. 2713 - 2735

Published: Nov. 22, 2023

Language: Английский

---

A Decision Support System for Diagnosis of COVID-19 from Non-COVID-19 Influenza-like Illness Using Explainable Artificial Intelligence

Bioengineering, Journal Year: 2023, Volume and Issue: 10(4), P. 439 - 439

Published: March 31, 2023

The coronavirus pandemic emerged in early 2020 and turned out to be deadly, killing a vast number of people all around the world. Fortunately, vaccines have been discovered, they seem effectual controlling severe prognosis induced by virus. reverse transcription-polymerase chain reaction (RT-PCR) test is current golden standard for diagnosing different infectious diseases, including COVID-19; however, it not always accurate. Therefore, extremely crucial find an alternative diagnosis method which can support results RT-PCR test. Hence, decision system has proposed this study that uses machine learning deep techniques predict COVID-19 patient using clinical, demographic blood markers. data used research were collected from two Manipal hospitals India custom-made, stacked, multi-level ensemble classifier diagnosis. Deep such as neural networks (DNN) one-dimensional convolutional (1D-CNN) also utilized. Further, explainable artificial (XAI) Shapley additive values (SHAP), ELI5, local interpretable model explainer (LIME), QLattice make models more precise understandable. Among algorithms, stacked obtained excellent accuracy 96%. precision, recall, f1-score AUC 94%, 95%, 94% 98% respectively. initial screening patients help ease existing burden on medical infrastructure.

Language: Английский

---

MCSC-Net: COVID-19 detection using deep-Q-neural network classification with RFNN-based hybrid whale optimization

Journal of X-Ray Science and Technology, Journal Year: 2023, Volume and Issue: 31(3), P. 483 - 509

Published: Feb. 28, 2023

COVID-19 is the most dangerous virus, and its accurate diagnosis saves lives slows spread. However, takes time requires trained professionals. Therefore, developing a deep learning (DL) model on low-radiated imaging modalities like chest X-rays (CXRs) needed.The existing DL models failed to diagnose other lung diseases accurately. This study implements multi-class CXR segmentation classification network (MCSC-Net) detect using images.Initially, hybrid median bilateral filter (HMBF) applied images reduce image noise enhance infected regions. Then, skip connection-based residual network-50 (SC-ResNet50) used segment (localize) The features from CXRs are further extracted robust feature neural (RFNN). Since initial contain joint COVID-19, normal, pneumonia bacterial, viral properties, conventional methods fail separate class of each disease-based feature. To extract distinct class, RFNN includes disease-specific attention mechanism (DSFSAM). Furthermore, hunting nature Hybrid whale optimization algorithm (HWOA) select best in class. Finally, deep-Q-neural (DQNN) classifies into multiple disease classes.The proposed MCSC-Net shows enhanced accuracy 99.09% for 2-class, 99.16% 3-class, 99.25% 4-class compared state-of-art approaches.The enables conduct tasks applying with high accuracy. Thus, together gold-standard clinical laboratory tests, this new method promising be future practice evaluate patients.

Language: Английский

---

Chest X-ray Images for Lung Disease Detection Using Deep Learning Techniques: A Comprehensive Survey

Archives of Computational Methods in Engineering, Journal Year: 2024, Volume and Issue: 31(6), P. 3267 - 3301

Published: Feb. 19, 2024

Language: Английский

---

An ensemble method for the detection and classification of lung cancer using Computed Tomography images utilizing a capsule network with Visual Geometry Group

Biomedical Signal Processing and Control, Journal Year: 2023, Volume and Issue: 85, P. 104930 - 104930

Published: April 17, 2023

Language: Английский

---

Swarm intelligence empowered three-stage ensemble deep learning for arm volume measurement in patients with lymphedema

Biomedical Signal Processing and Control, Journal Year: 2023, Volume and Issue: 85, P. 105027 - 105027

Published: May 17, 2023

Language: Английский

---

The effectiveness of deep learning vs. traditional methods for lung disease diagnosis using chest X-ray images: A systematic review

Applied Soft Computing, Journal Year: 2023, Volume and Issue: 147, P. 110817 - 110817

Published: Sept. 9, 2023

Language: Английский

---

A novel ensemble CNN model for COVID-19 classification in computerized tomography scans

Results in Control and Optimization, Journal Year: 2023, Volume and Issue: 11, P. 100215 - 100215

Published: Feb. 17, 2023

COVID-19 is a rapidly spread infectious disease caused by severe acute respiratory syndrome that can lead to death in just few days. Thus, early detection provide more time for successful treatment or action, even though an efficient unknown so far. In this context, work proposes and investigates four ensemble CNNs using transfer learning compares them with state-of-art CNN architectures. To select which models use we tested 11 architectures: DenseNet121, DenseNet169, DenseNet201, VGG16, VGG19, Xception, ResNet50, ResNet50v2, InceptionV3, MobileNet, MobileNetv2. We used public dataset comprised of 2477 computerized tomography images divided into two classes: patients diagnosed negative diagnosis. Then three architectures were selected: Xception. Finally, the all possible combinations. The results showed tend present best results. Moreover, CNN, called EnsenbleDVX, comprising CNNs, provides achieving average accuracy 97.7%, precision recall 97.8%, F1 score 97.7%

Language: Английский

---

High-Performance Convolutional Neural Network Model to Identify COVID-19 in Medical Images

Journal of Computing Theories and Applications, Journal Year: 2023, Volume and Issue: 1(1), P. 19 - 30

Published: Aug. 30, 2023

Convolutional neural network (CNN) is a deep learning (DL) model that has significantly contributed to medical systems because it very useful in digital image processing. However, CNN several limitations, such as being prone overfitting, not properly trained if there data duplication, and can cause unwanted results an imbalance the amount of each class. Data augmentation techniques are used overcome eliminate random under sampling methods balance class, these problems. In addition, designed properly, computation less efficient. Research proved prevent or eliminating duplicate make more stable, balancing makes unbiased easy learn new evidenced through evaluation testing. The also show custom convolutional best compared ResNet50 VGG19 terms accuracy, precision, recall, F1-score, loss performance, time efficiency

Language: Английский

---