Bio-Inspired Feature Selection Algorithms With Their Applications: A Systematic Literature Review

IEEE Access, Journal Year: 2023, Volume and Issue: 11, P. 43733 - 43758

Published: Jan. 1, 2023

Based on the principles of biological evolution nature, bio-inspired algorithms are gaining popularity in developing robust techniques for optimization. Unlike gradient descent optimization methods, these metaheuristic computationally less expensive, and can also considerably perform well with nonlinear high-dimensional data. Objectives: To understand algorithms, application domains, effectiveness, challenges feature selection techniques. Method: A systematic literature review is conducted five major digital databases science engineering. Results: The primary search included 695 articles. After removing 263 duplicated articles, 432 studies remained to be screened. Among those, 317 irrelevant papers were removed. We then excluded 77 according exclusion criteria. Finally, 38 articles selected this study. Conclusion: Out studies, 28 discussed Swarm-based 2 studied Genetic Algorithms, 8 covered both categories. Considering 21 focused problems healthcare sector, while rest mainly investigated issues cybersecurity, text classification, image processing. Hybridization other BIAs was employed by approximately 18.5% papers, 13 out used S-shaped transfer functions. majority supervised classification methods such as k-NN SVM building fitness Accordingly, we conclude that future research should focus applying a diverse area applications finance social networks. And further exploration into enhancement quantum representation, rough set theory, chaotic maps, Lévy flight necessary. Additionally, suggest investigating functions besides S-shaped, V-shaped X-shaped. Moreover, clustering deep learning models constructing need further.

Language: Английский

---

A machine learning and deep learning-based integrated multi-omics technique for leukemia prediction

Heliyon, Journal Year: 2024, Volume and Issue: 10(3), P. e25369 - e25369

Published: Feb. 1, 2024

In recent years, scientific data on cancer has expanded, providing potential for a better understanding of malignancies and improved tailored care. Advances in Artificial Intelligence (AI) processing power algorithmic development position Machine Learning (ML) Deep (DL) as crucial players predicting Leukemia, blood cancer, using integrated multi-omics technology. However, realizing these goals demands novel approaches to harness this deluge. This study introduces Leukemia diagnosis approach, analyzing accuracy ML DL algorithms. techniques, including Random Forest (RF), Naive Bayes (NB), Decision Tree (DT), Logistic Regression (LR), Gradient Boosting (GB), methods such Recurrent Neural Networks (RNN) Feedforward (FNN) are compared. GB achieved 97 % ML, while RNN outperformed by achieving 98 DL. approach filters unclassified effectively, demonstrating the significance leukemia prediction. The testing validation was based 17 different features patient age, sex, mutation type, treatment methods, chromosomes, others. Our compares techniques chooses best technique that gives optimum results. emphasizes implications high-throughput technology healthcare, offering

Language: Английский

---

Integrating Data Envelopment Analysis and Machine Learning for Resource Allocation in Efficient Multitumor Analyzer for Brain Tumors

IGI Global eBooks, Journal Year: 2025, Volume and Issue: unknown, P. 425 - 454

Published: May 2, 2025

The Efficient Multitumor Analyzer for segmentation and classification of brain tumors, while promising, faces several drawbacks that limit its effectiveness in clinical settings. A framework combines Data Envelopment Analysis (DEA) with Machine Learning (ML) approaches is presented the proposed research to enhance decision-making healthcare resource allocation, specifically within context deploying an tumor classification. DEA assesses efficiency providers based on inputs such as staffing, equipment, budget, outputs like treatment outcomes patient satisfaction. After this evaluation, ensemble techniques machine learning algorithms Random Forests Gradient Boosting, analyze factors influencing predict needs implementing Analyzer. model achieved a prediction accuracy 98.87% identifying potential shortages, enabling proactive management care services.

Language: Английский

---

PRFE-driven gene selection with multi-classifier ensemble for cancer classification

Egyptian Informatics Journal, Journal Year: 2025, Volume and Issue: 30, P. 100637 - 100637

Published: March 17, 2025

Language: Английский

---

Omics data classification using constitutive artificial neural network optimized with single candidate optimizer

Network Computation in Neural Systems, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 25

Published: May 12, 2024

Recent technical advancements enable omics-based biological study of molecules with very high throughput and low cost, such as genomic, proteomic, microbionics'. To overcome this drawback, Omics Data Classification using Constitutive Artificial Neural Network Optimized Single Candidate Optimizer (ODC-ZOA-CANN-SCO) is proposed in manuscript. The input data pre-processing by Adaptive variational Bayesian filtering (AVBF) to replace missing values. fed Zebra Optimization Algorithm (ZOA) for dimensionality reduction. Then, the (CANN) employed classify omics data. weight parameter optimized (SCO). ODC-ZOA-CANN-SCO method attains 25.36%, 21.04%, 22.18%, 26.90%, 28.12% higher accuracy when analysed existing methods like multi-omics integration utilizing adaptive graph learning attention mode patient categorization biomarker identification (MOD-AGL-AM-PABI), deep depending upon create risk stratification prediction skin cutaneous melanoma (DL-MODI-RSP-SCM), Deep belief network-base model identifying Alzheimer's disease (DDN-DAD-MOD), hybrid cancer reinforcement state action reward (HCP-MOD-RL-SARSA), machine basis under including knowledge database clinical endpoint (ML-ODBKD-CCEP) methods, respectively.

Language: Английский

---

Enhancing IoT Security Through Deep learning and Evolutionary Bio-Inspired Intrusion Detection in IoT systems

Published: April 24, 2024

Advancements in systems based on the Internet of Things (IoT) have led to a significant transformation across various sectors. However, security IoT networks remains major concern due diversity and ubiquity connected devices. This paper introduces an innovative intrusion detection method for systems, combining bioinspired features selection algorithms with artificial neural network, emphasing special focuse Grey wolf optimisation algorithm (GWOA). Bio-inspired select most relevant from dataset used evaluation, while machine learning/deep learning (ML/DL) techniques ensure accurate classification attacks. approach provides effective solution enhancing network by identifying responding threats precision speed, thereby contributing protection critical infrastructures against cyberattacks. The obtained results showed promising performances optimal set features. In which GWO achived performance above 90% approximately 20% global set.

Language: Английский

---

Predicting Lung Cancer Disease Using Optimized Weighting-Based Enhanced Neural Network Classification

Published: May 3, 2024

Language: Английский

---

Intelligent mutation based evolutionary optimization algorithm for genomics and precision medicine

Functional & Integrative Genomics, Journal Year: 2024, Volume and Issue: 24(4)

Published: July 22, 2024

Language: Английский

---

An adaptive binary classifier for highly imbalanced datasets on the Edge

Microprocessors and Microsystems, Journal Year: 2024, Volume and Issue: unknown, P. 105120 - 105120

Published: Oct. 1, 2024

Language: Английский

---

Comparing Models and Performance Metrics for Lung Cancer Prediction using Machine Learning Approaches.

Sir Syed University Research Journal of Engineering & Technology, Journal Year: 2024, Volume and Issue: 14(2), P. 29 - 33

Published: Dec. 27, 2024

Lung cancer is both common and lethal, leading to a significant rise in death rates worldwide. This research focuses on utilizing Machine-Learning (ML) detect early-stage lung cancer, aiming address these major public health concerns by using ML help develop more efficient early detection techniques. It will lower improve global healthcare. To achieve goals, we explored many algorithms compared them dataset with lifestyle data. The models included Logistic Regression (LR), Random Forest (RF), Naive Bayes (NB), Support Vector Classifier (SVC). We evaluated i.e., based the evaluation key performance metrics. These metrics highlight benefits drawbacks of each model. When them, found that SVC LR achieved 84% accuracy. In contrast, NB RF got 81% performed hyperparameter tuning, which improved accuracy 85%. enhancement shows tuning hyperparameters effective. optimizes for predicting cancer.

Language: Английский

---