White shark optimizer with optimal deep learning based effective unmanned aerial vehicles communication and scene classification DOI Creative Commons
T. Nadana Ravishankar,

M. Ramprasath,

A. Daniel

et al.

Scientific Reports, Journal Year: 2023, Volume and Issue: 13(1)

Published: Dec. 27, 2023

Abstract Unmanned aerial vehicles (UAVs) become a promising enabler for the next generation of wireless networks with tremendous growth in electronics and communications. The application UAV communications comprises messages relying on coverage extension transmission after disasters, Internet Things (IoT) devices, dispatching distress from device positioned within hole to emergency centre. But there are some problems enhancing clustering scene classification using deep learning approaches performance. This article presents new White Shark Optimizer Optimal Deep Learning based Effective Aerial Vehicles Communication Scene Classification (WSOODL-UAVCSC) technique. categorization present many challenges disaster management: understanding complexity, data variability abundance, visual feature extraction, nonlinear high-dimensional data, adaptability generalization, real-time decision making, optimization, sparse incomplete data. need handle complex, adapt changing environments, make quick, correct decisions critical situations drives categorization. purpose WSOODL-UAVCSC technique is cluster UAVs effective communication classification. WSO algorithm utilized optimization process enables accomplish interaction network. With dynamic adjustment clustering, improves performance robustness system. For process, involves capsule network (CapsNet) marine predators (MPA) hyperparameter tuning, echo state (ESN) A wide-ranging simulation analysis was conducted validate enriched approach. Extensive result pointed out enhanced method over other existing techniques. achieved an accuracy 99.12%, precision 97.45%, recall 98.90%, F1-score 98.10% when compared

Language: Английский

Development of an unsupervised pseudo-deep approach for brain tumor detection in magnetic resonance images DOI
Rahman Farnoosh, Hamidreza Noushkaran

Knowledge-Based Systems, Journal Year: 2024, Volume and Issue: 300, P. 112171 - 112171

Published: June 26, 2024

Language: Английский

Citations

4
A review of case study on different metaheuristic optimization techniques for disease detection and classification DOI
Priyanka More, Baljit Singh Saini, Rakesh K. Sharma

et al.

Computer Methods in Biomechanics & Biomedical Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 19

Published: May 4, 2025

This framework explores the use of metaheuristic optimization techniques for disease detection, specifically in image segmentation and feature selection to enhance classification performance. The study evaluates five swarm intelligence methods: Artificial Bee Colony (ABC) segmentation, Krill Herd Optimization (KHO) both selection, Particle Swarm (PSO) Grey Wolf (GWO) Moth-Flame (MFO) selection. Results demonstrate significant performance improvements, with accuracy increases 0.9%, 2%, 2.3%, 2.1%, 4.2%. These gains are attributed optimized exploration/exploitation, enhanced diversity, convergence, showing effectiveness detection.

Language: Английский

Citations

0
An Efficient Approach of Brain Tumor Detection & Extraction using BWT with Auto Enhance Technique DOI Open Access
Nilesh Bhaskarrao Bahadure, Sudhanshu Gonge, Jagdish Chandra Patni

et al.

Procedia Computer Science, Journal Year: 2025, Volume and Issue: 258, P. 4105 - 4116

Published: Jan. 1, 2025

Language: Английский

Citations

0
Brain tumor diagnosis from MR images using boosted multi-gradient support vector machine classifier DOI Creative Commons

S. Kalaiselvi,

G. Thailambal

Measurement Sensors, Journal Year: 2024, Volume and Issue: 32, P. 101071 - 101071

Published: Feb. 28, 2024

A brain tumor develops as a result of uncontrolled and rapid cell proliferation. If not treated in its early stages, it might death. Despite several significant efforts positive outcomes, accurate segmentation classification remain challenging jobs. The variations size, shape, location provide substantial challenge for diagnosis. Therefore, identifying tumors manually is challenging, time-consuming, prone to mistakes. Consequently, there now need high-accuracy automated computer-assisted diagnostics. This paper proposes novel detection method based on machine learning classifier. Initially, the images are collected from "Magnetic Resonance Imaging (MRI)" database. In preprocessing stage, anisotropic filtering "Adaptive Histogram Equalization (AHE)" performed remove noise enhance image contrast respectively. Then segmented using "Enhanced Fruitfly Optimization-based Otsu (EFO-OTSU)". feature extraction done "Principal Component Analysis (PCA)" "Discrete Wavelet Transform (DWT)". We propose Boosted "Multi-Gradient Support Vector Machine (BMG-SVM)"to use retrieved characteristics divide picture into non-tumor sections. Further performance, we employ "Black Monkey Optimization (BMO)" algorithmalgorithm. few currently used approaches contrasted with simulation results suggested technique. final findings show that technique outperforms other methods terms effectiveness.

Language: Английский

Citations

3
Processing 2D Barcode Data with Metaheuristic Based CNN Models and Detection of Malicious PDF Files DOI
Mesut Toğaçar, Burhan Ergen

Applied Soft Computing, Journal Year: 2024, Volume and Issue: 161, P. 111722 - 111722

Published: May 9, 2024

Language: Английский

Citations

3
Knowledge distillation in transformers with tripartite attention: Multiclass brain tumor detection in highly augmented MRIs DOI Creative Commons
Salha M. Alzahrani,

Abdulrahman M. Qahtani

Journal of King Saud University - Computer and Information Sciences, Journal Year: 2023, Volume and Issue: 36(1), P. 101907 - 101907

Published: Dec. 28, 2023

The advent of attention-based architectures in medical imaging has ushered an era precision diagnostics, particularly the detection and classification brain tumors. This study introduced innovative knowledge distillation framework employing a tripartite attention mechanism within transformer encoder models, specifically tailored for identification multiple tumor classes through magnetic resonance (MRI). proposed methodology synergistically harnesses capabilities large, highly parameterized teacher models to train more compact, efficient student suitable deployment resource-constrained environments such as internet things smart healthcare devices. Utilizing diverse array MRI sequences—including T1, contrast-enhanced T2—this accounts nuanced variations across derived from three extensive datasets. addresses limitation traditional by innovatively integrating temperature-softening neighborhood attention, global cross-attention layers. sophisticated approach allows richer feature representation, capturing both local contextual information intricate features scans. is supplemented unique augmentation pipeline shifted patch tokenization technique, which enrich model's input especially underrepresented classes. Through meticulous experimentation ablation studies, demonstrates that model not only retains robustness its larger counterparts but also delivers enhanced performance metrics. When juxtaposed with benchmarking models—including deep CNNs various transformer-based architectures—the consistently showcases superior results. Its effectiveness reflected lower losses, commendable Brier scores, noteworthy top-1 top-5 accuracies, well AUC metrics all paper validates efficacy complex image analysis tasks provides promising pathway integration cutting-edge AI techniques real-world clinical applications, potentially revolutionizing early treatment

Language: Английский

Citations

8
DeepMaizeNet: A novel hybrid approach based on CBAM for implementing the doubled haploid technique DOI
İbrahim Ayaz, Fatih Kutlu, Zafer Cömert

et al.

Agronomy Journal, Journal Year: 2023, Volume and Issue: 116(3), P. 861 - 870

Published: June 7, 2023

Abstract Maize ( Zea mays L.) is an important cereal plant in the family of wheatgrass cultivated all over world. With increase human population and environmental factors, need for maize plants increasing day by day. One efficient methods production breeding. The most effective rapid method breeding doubled haploid (DH) technique. This technique reduces time increases productivity. There are different selection to select seeds process. Among these methods, common successful visual checking R1‐Navajo marker. seed separation hand a time‐consuming error‐prone operation. It labor‐intensive very tiring; therefore, it essential develop fast highly accurate intelligent system that separates diploid from each other. study presents pioneering approach, introducing DeepMaizeNet, hybrid deep learning model showcases its prowess accurately classifying seeds. classification holds significant value DH technique, proposed model's success promising step toward enhanced efficiency. exploits some new techniques such as convolution block attention module, hypercolumn, 2D upsampling, residual block. For assessment model, five‐fold cross‐validation employed. result shows DeepMaizeNet provides performance achieving 94.13% accuracy, 94.91% F1‐score, 97.27% sensitivity.

Language: Английский

Citations

7
Consecutive knowledge meta-adaptation learning for unsupervised medical diagnosis DOI
Yumin Zhang, Hongliu Li, Yawen Hou

et al.

Knowledge-Based Systems, Journal Year: 2024, Volume and Issue: 291, P. 111573 - 111573

Published: March 7, 2024

Language: Английский

Citations

2
Bat algorithm based on kinetic adaptation and elite communication for engineering problems DOI Creative Commons

Yuan Chong,

Dong Zhao, Ali Asghar Heidari

et al.

CAAI Transactions on Intelligence Technology, Journal Year: 2024, Volume and Issue: unknown

Published: June 17, 2024

Abstract The Bat algorithm, a metaheuristic optimization technique inspired by the foraging behaviour of bats, has been employed to tackle problems. Known for its ease implementation, parameter tunability, and strong global search capabilities, this algorithm finds application across diverse problem domains. However, in face increasingly complex challenges, encounters certain limitations, such as slow convergence sensitivity initial solutions. In order these present study incorporates range components into thereby proposing variant called PKEBA. A projection screening strategy is implemented mitigate solutions, enhancing quality solution set. kinetic adaptation reforms exploration patterns, while an elite communication enhances group interaction, avoid from local optima. Subsequently, effectiveness proposed PKEBA rigorously evaluated. Testing encompasses 30 benchmark functions IEEE CEC2014, featuring ablation experiments comparative assessments against classical algorithms their variants. Moreover, real‐world engineering problems are further validation. results conclusively demonstrate that exhibits superior precision compared existing algorithms.

Language: Английский

Citations

2
Recent advancements and theranostics strategies in glioblastoma therapy DOI
Sudhakar Reddy Baddam, Sudhakar Kalagara, K. KUNA

et al.

Biomedical Materials, Journal Year: 2023, Volume and Issue: 18(5), P. 052007 - 052007

Published: Aug. 15, 2023

Abstract Glioblastoma (GBM) is the most aggressive and lethal malignant brain tumor, it challenging to cure with surgery treatment. The prevention of permanent damage tumor invasion, which ultimate cause recurrence, are major obstacles in GBM Besides, emerging treatment modalities newer genetic findings helping understand manage patients. Accordingly, researchers focusing on advanced nanomaterials-based strategies for tackling various problems associated GBM. In this context, explored novel alternative approaches such as early detection techniques theranostics approaches. review, we have emphasized recent advancement cellular models their roles designing therapeutics. We added a special emphasis drug target well detection. discussed theranostic hyperthermia therapy, phototherapy image-guided therapy. Approaches utilized targeted delivery were also discussed. This article describes vivo, vitro ex vivo advances using innovative

Language: Английский

Citations

6