MNPDenseNet: Automated Monkeypox Detection Using Multiple Nested Patch Division and Pretrained DenseNet201

Multimedia Tools and Applications, Journal Year: 2024, Volume and Issue: 83(30), P. 75061 - 75083

Published: Feb. 15, 2024

Abstract Background Monkeypox is a viral disease caused by the monkeypox virus (MPV). A surge in infection has been reported since early May 2022, and outbreak classified as global health emergency situation continues to worsen. Early accurate detection of required control its spread. Machine learning methods offer fast COVID-19 from chest X-rays, computed tomography (CT) images. Likewise, computer vision techniques can automatically detect monkeypoxes digital images, videos, other inputs. Objectives In this paper, we propose an automated model first step toward controlling Materials method new dataset comprising 910 open-source images into five categories (healthy, monkeypox, chickenpox, smallpox, zoster zona) was created. deep feature engineering architecture proposed, which contained following components: (i) multiple nested patch division, (ii) extraction, (iii) selection deploying neighborhood component analysis (NCA), Chi2, ReliefF selectors, (iv) classification using SVM with 10-fold cross-validation, (v) voted results generation iterative hard majority voting (IHMV) (vi) best vector greedy algorithm. Results Our proposal attained 91.87% accuracy on collected dataset. This result our presented framework, selected 70 generated results. Conclusions The findings demonstrated that could be successfully detected proposed model.

Language: Английский

---

Classification of monkeypox images using Al-Biruni earth radius optimization with deep convolutional neural network

AIP Advances, Journal Year: 2024, Volume and Issue: 14(6)

Published: June 1, 2024

There is a connection that has been established between the virus responsible for monkeypox and formation of skin lesions. This detected in Africa many years. Our research centered around detection lesions as potential indicators during pandemic. primary objective to utilize metaheuristic optimization techniques improve performance feature selection classification algorithms. In order accomplish this goal, we make use deep learning transfer technique extract attributes. The GoogleNet network, framework, used carry out extraction. Furthermore, process conducted using binary version dynamic Al-Biruni earth radius (DBER). After that, convolutional neural network assign labels selected features from collection. To accuracy, adjustments are made by utilizing continuous DBER algorithm. We range metrics analyze different assessment methods, including sensitivity, specificity, positive predictive value (P-value), negative (N-value), F1-score. They were compared each other. All metrics, F1-score, P-value, N-value, achieved high values 0.992, 0.991, 0.993, respectively. outcomes combining with network. optimizing parameters proposed method an impressive overall accuracy rate 0.992.

Language: Английский

---

A Hybridization of Spatial Modeling and Deep Learning for People’s Visual Perception of Urban Landscapes

Sustainability, Journal Year: 2023, Volume and Issue: 15(13), P. 10403 - 10403

Published: July 1, 2023

The visual qualities of the urban environment influence people’s perception and reaction to their surroundings; hence quality affects mental states can have detrimental societal effects. Therefore, understanding are necessary. This study used a deep learning-based approach address relationship between effective spatial criteria perception, as well modeling preparing potential map in environments. Dependent data on Tehran, Iran, was gathered through questionnaire that contained information about 663 people, 517 pleasant places, 146 unpleasant places. independent consisted distances industrial areas, public transport stations, recreational attractions, primary streets, secondary local passages, billboards, restaurants, shopping malls, dilapidated cemeteries, religious traffic volume, population density, night light, air index (AQI), normalized difference vegetation (NDVI). convolutional neural network (CNN) algorithm created map. evaluated using receiver operating characteristic (ROC) curve area under (AUC), with estimates AUC 0.877 0.823 for visuals, respectively. maps obtained CNN showed northern, northwest, central, eastern, some southern areas city potent sight, southeast, regions had sight potential. OneR method results demonstrated distance volume is most important sights.

Language: Английский

---

Enhancing stroke disease classification through machine learning models via a novel voting system by feature selection techniques

PLoS ONE, Journal Year: 2025, Volume and Issue: 20(1), P. e0312914 - e0312914

Published: Jan. 9, 2025

Heart disease remains a leading cause of mortality and morbidity worldwide, necessitating the development accurate reliable predictive models to facilitate early detection intervention. While state art work has focused on various machine learning approaches for predicting heart disease, but they could not able achieve remarkable accuracy. In response this need, we applied nine algorithms XGBoost, logistic regression, decision tree, random forest, k-nearest neighbors (KNN), support vector (SVM), gaussian naïve bayes (NB gaussian), adaptive boosting, linear regression predict based range physiological indicators. Our approach involved feature selection techniques identify most relevant predictors, aimed at refining enhance both performance interpretability. The were trained, incorporating processes such as grid search hyperparameter tuning, cross-validation minimize overfitting. Additionally, have developed novel voting system with advance classification. Furthermore, evaluated using key metrics including accuracy, precision, recall, F1-score, area under receiver operating characteristic curve (ROC AUC). Among models, XGBoost demonstrated exceptional performance, achieving 99% F1-Score, 98% 100% ROC AUC. This study offers promising diagnosis preventive healthcare.

Language: Английский

---

Robustly detecting mpox and non-mpox using a deep learning framework based on image inpainting

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Jan. 10, 2025

Language: Английский

---

Next-generation healthcare: Digital twin technology and Monkeypox Skin Lesion Detector network enhancing monkeypox detection - Comparison with pre-trained models

Engineering Applications of Artificial Intelligence, Journal Year: 2025, Volume and Issue: 145, P. 110257 - 110257

Published: Feb. 14, 2025

Language: Английский

---

A hybrid long short-term memory-convolutional neural network multi-stream deep learning model with Convolutional Block Attention Module incorporated for monkeypox detection

Science Progress, Journal Year: 2025, Volume and Issue: 108(1)

Published: Jan. 1, 2025

Background Monkeypox (mpox) is a zoonotic infectious disease caused by the mpox virus and characterized painful body lesions, fever, headaches, exhaustion. Since report of first human case in Africa, there have been multiple outbreaks, even nonendemic regions world. The emergence re-emergence highlight critical need for early detection, which has spurred research into applying deep learning to improve diagnostic capabilities. Objective This aims develop robust hybrid long short-term memory (LSTM)-convolutional neural network (CNN) model with Convolutional Block Attention Module (CBAM) provide potential tool detection mpox. Methods A LSTM-CNN multi-stream CBAM was developed trained using Mpox Skin Lesion Dataset Version 2.0 (MSLD v2.0). We employed LSTM layers preliminary feature extraction, CNN further conditioning. evaluated standard metrics, gradient-weighted class activation maps (Grad-CAM) local interpretable model-agnostic explanations (LIME) were used interpretability. Results achieved an F1-score, recall, precision 94%, area under curve 95.04%, accuracy demonstrating competitive performance compared state-of-the-art models. highlights reliability our model. LIME Grad-CAM offered insights model's decision-making process. Conclusion successfully detects mpox, providing promising that can be integrated web mobile platforms convenient widespread use.

Language: Английский

---

A stacked ensemble approach for symptom-based monkeypox diagnosis

Computers in Biology and Medicine, Journal Year: 2025, Volume and Issue: 191, P. 110140 - 110140

Published: April 8, 2025

The recent monkeypox outbreak has raised global health concerns. Caused by a virus, it is characterized symptoms such as skin lesions. Early detection critical for treatment and controlling its spread. This study uses advanced machine learning deep techniques, including Tab Transformer, Long Short-Term Memory, XGBoost, LightGBM, Stacking Classifier, to predict the presence of virus based on patient symptoms. performance these models evaluated using accuracy, precision, recall, F1-score metrics. experiments reveal that Classifier significantly outperforms other models, achieving an accuracy 87.29 %, precision 86.12 recall 87.47 F1 score 87.89 %. Additionally, applying Conditional Tabular GAN generate synthetic data helps address imbalance issues, further improving model robustness. These results highlight proposed approach's potential timely, accurate detection, aiding in effective disease management control.

Language: Английский

---

Revolutionizing Healthcare Delivery Through Wireless Wearable Antenna Frameworks: Current Trends and Future Prospects

IEEE Access, Journal Year: 2023, Volume and Issue: 11, P. 80327 - 80347

Published: Jan. 1, 2023

The arrival of various mechanism applications to healthcare is gaining more attention with novel breakthroughs in digitalizing healthcare. use technology improving the delivery comprises such as electronic health systems, telemedicine, mobile health, remote patient monitoring, and wearable devices. Wearables implants are making a significant impact on revolutionizing globally, next generation advanced providing adequate tackling challenges digital advancement techniques gives future direction Antennas play key part because their characteristics adaptation wireless communication transmission reception different human body parts. Although there lot studies done published healthcare, wearable, many mechanisms that enhance delivery, however, systematic comprehensively review antenna framework remain scarce. This paper attempts close gap investigating for care, devices applications. comprehensive covers application Furthermore, it provides state-of-the-art update recent developments focus design, monitoring devices, diagnostic implants, early detection mechanisms, control. We also examine analysis performance, fabrication experimental approaches, major types wearables. assists existing chronic disease management epidemics provided tools. finding will give blueprint how zero spread be achieved by implementing bio-electromagnetic sector.

Language: Английский

---

Mpox-AISM: AI-mediated super monitoring for mpox and like-mpox

iScience, Journal Year: 2024, Volume and Issue: 27(5), P. 109766 - 109766

Published: April 17, 2024

Swift and accurate diagnosis for earlier-stage monkeypox (mpox) patients is crucial to avoiding its spread.However, the similarities between common skin disorders mpox need professional unavoidably impaired of contributed outbreak.To address challenge, we proposed "Super Monitoring", a real-time visualization technique employing artificial intelligence (AI) Internet technology diagnose cheaply, conveniently, quickly.Concretely, AI-mediated Monitoring" (mpox-AISM) integrates deep learning models, data augmentation, self-supervised learning, cloud services.According publicly accessible datasets, mpox-AISM's Precision, Recall, Specificity, F1-score in diagnosing reach 99.3%, 94.1%, 99.9%, 96.6%, respectively, it achieves 94.51% accuracy mpox, six like-mpox disorders, normal skin.With communication terminal, mpox-AISM has potential perform real-world scenarios, thereby preventing outbreak.

Language: Английский

---