Greylag goose optimization and multilayer perceptron for enhancing lung cancer classification

Scientific Reports, Год журнала: 2024, Номер 14(1)

Опубликована: Окт. 10, 2024

Lung cancer is an important global health problem, and it defined by abnormal growth of the cells in tissues lung, mostly leading to significant morbidity mortality. Its timely identification correct staging are very for proper therapy prognosis. Different computational methods have been used enhance precision lung classification, among which optimization algorithms such as Greylag Goose Optimization (GGO) employed. These purpose improving performance machine learning models that presented with a large amount complex data, selecting most features. As per data preparation one steps, contains operations scaling, normalization, handling gap factor ensure reasonable reliable input data. In this domain, use GGO includes refining feature selection, mainly focuses on enhancing classification accuracy compared other binary format algorithms, like bSC, bMVO, bPSO, bWOA, bGWO, bFOA. The efficiency bGGO algorithm choosing optimal features improved indicator possible application method field diagnosis. achieved highest MLP model at 98.4%. selection results were assessed using statistical analysis, utilized Wilcoxon signed-rank test ANOVA. also accompanied set graphical illustrations ensured adequacy adopted hybrid (GGO + MLP).

Язык: Английский

---

Orthopedic disease classification based on breadth-first search algorithm

Scientific Reports, Год журнала: 2024, Номер 14(1)

Опубликована: Окт. 8, 2024

Orthopedic diseases are widespread worldwide, impacting the body's musculoskeletal system, particularly those involving bones or hips. They have potential to cause discomfort and impair functionality. This paper aims address lack of supplementary diagnostics in orthopedics improve method diagnosing orthopedic diseases. The study uses binary breadth-first search (BBFS), particle swarm optimization (BPSO), grey wolf optimizer (BGWO), whale algorithm (BWAO) for feature selections, BBFS makes an average error 47.29% less than others. Then we apply six machine learning models, i.e., RF, SGD, NBC, DC, QDA, ET. dataset used contains 310 instances distinct features. Through experimentation, RF model led optimal outcomes during comparison remaining with accuracy 91.4%. parameters were optimized using four algorithms: BFS, PSO, WAO, GWO. To check how well works on dataset, this prediction evaluation metrics such as accuracy, sensitivity, specificity, F-score, AUC curve. results showed that BFS-RF can performance original classifier compared others 99.41% accuracy.

Язык: Английский

---

An Improved Expeditious Meta-Heuristic Clustering Method for Classifying Student Psychological Issues with Homogeneous Characteristics

Mathematics, Год журнала: 2024, Номер 12(11), С. 1620 - 1620

Опубликована: Май 22, 2024

Nowadays, cluster analyses are widely used in mental health research to categorize student stress levels. However, conventional clustering methods experience challenges with large datasets and complex issues, such as converging local optima sensitivity initial random states. To address these limitations, this work introduces an Improved Grey Wolf Clustering Algorithm (iGWCA). This improved approach aims adjust the convergence rate mitigate risk of being trapped optima. The iGWCA algorithm provides a balanced technique for exploration exploitation phases, alongside search mechanism around optimal solution. assess its efficiency, proposed is verified on two different datasets. dataset-I comprises 1100 individuals obtained from Kaggle database, while dataset-II based 824 Mendeley database. results demonstrate competence classifying outperforms other terms lower intra-cluster distances, obtaining reduction 1.48% compared Optimization (GWO), 8.69% Mayfly (MOA), 8.45% Firefly (FFO), 2.45% Particle Swarm (PSO), 3.65%, Hybrid Sine Cosine Cuckoo (HSCCS), 8.20%, Genetic (FAGA) 8.68% Gravitational Search (GSA). demonstrates effectiveness minimizing making it better choice classification. contributes advancement understanding managing well-being within academic communities by providing robust tool level

Язык: Английский

---

Skin cancer classification based on an optimized convolutional neural network and multicriteria decision-making

Scientific Reports, Год журнала: 2024, Номер 14(1)

Опубликована: Июль 27, 2024

Abstract Skin cancer is a type of disease in which abnormal alterations skin characteristics can be detected. It treated if it detected early. Many artificial intelligence-based models have been developed for detection and classification. Considering the development numerous according to various scenarios selecting optimum model was rarely considered previous works. This study aimed develop classification select model. Convolutional neural networks (CNNs) form AlexNet, Inception V3, MobileNet V2, ResNet 50 were used feature extraction. Feature reduction carried out using two algorithms grey wolf optimizer (GWO) addition original features. images classified into four classes based on six machine learning (ML) classifiers. As result, 51 with different combinations CNN algorithms, without GWO ML To best results, multicriteria decision-making approach utilized rank alternatives by perimeter similarity (RAPS). Model training testing conducted International Imaging Collaboration (ISIC) 2017 dataset. Based nine evaluation metrics RAPS method, AlexNet algorithm classical yielded model, achieving accuracy 94.5%. work presents first benchmarking many models. not only reduces time spent but also improves accuracy. The method has proven its robustness problem

Язык: Английский

---

A hybrid bat and grey wolf optimizer for gene selection in cancer classification

Knowledge and Information Systems, Год журнала: 2024, Номер unknown

Опубликована: Сен. 25, 2024

Язык: Английский

---

Feature Selection of Gene Expression Data Using a Modified Artificial Fish Swarm Algorithm With Population Variation

IEEE Access, Год журнала: 2024, Номер 12, С. 72688 - 72706

Опубликована: Янв. 1, 2024

Microarray data is of great significance for cancer identification at the gene level. In microarray dataset, only a small number characteristic genomes have significant classification and rates cancer. How to extract genes from large classic NP-hard problem. This paper proposes practical hybrid approach implement feature selection expression by combining F-score algorithm an improved artificial fish swarm with population variation (FSA-PV). Firstly, eliminates useless redundant features in set. Then, FSA-PV discussed obtain ability jump out local optimum while retaining excellent subset as much possible, adaptive step visual are used adjust search space move range different environments improve optimization global abilities. addition, naive Bayesian classifier test accuracy subsets. Eight classical datasets verify performance proposed mechanism experiment part. The results reveal that using superior other algorithms Breast more than 90% 8 cases. It further indicates robustness feasibility process.

Язык: Английский

---

Precise feature selection using suffix array algorithm of bioinformatics

International Journal of Machine Learning and Cybernetics, Год журнала: 2025, Номер unknown

Опубликована: Янв. 21, 2025

Язык: Английский

---

Dynamic time-varying transfer function for cancer gene expression data feature selection problem

Journal Of Big Data, Год журнала: 2025, Номер 12(1)

Опубликована: Март 1, 2025

Язык: Английский

---

Security-aware user authentication based on multimodal biometric data using dilated adaptive RNN with optimal weighted feature fusion

Network Computation in Neural Systems, Год журнала: 2025, Номер unknown, С. 1 - 41

Опубликована: Апрель 1, 2025

This work plans to develop a biometric authentication model by the combination of multi-modal inputs like voice, fingerprint, and iris provide high security. At first, spectrogram images, collected input were given Multi-scale Residual Attention Network (RAN) with Atrous Spatial Pyramid Pooling (ASPP) extract best values. These three features are then fed optimal weighted feature fusion, where weight optimization from is done via Enhanced Lichtenberg Algorithm (ELA). into decision-making stage, Dilated Adaptive Recurrent Neural utilized identify individuals, parameters optimized RNN using ELA improve recognition performance. The simulation findings achieved developed multimodal systems validated diverse algorithms over several efficacy metrics accuracy, precision, sensitivity, F1-score, etc. From result analysis, ELA-DARNN-based user system showed higher accuracy 96.01, other models such as 90% than SVM, CNN, CNN-AlexNet, Dil-ARNN be 87.94, 89.88, 93.25, 91.94. Therefore, outcomes explored that offered approach has attained elevated results also effectively supports reduction data theft.

Язык: Английский

---

Identifying candidate biomarkers for detecting bronchogenic carcinoma stages using metaheuristic algorithms based on information fusion theory

Discover Oncology, Год журнала: 2025, Номер 16(1)

Опубликована: Апрель 29, 2025

Язык: Английский

---