MonDiaL-CAD: Monkeypox diagnosis via selected hybrid CNNs unified with feature selection and ensemble learning

Digital Health, Journal Year: 2023, Volume and Issue: 9

Published: Jan. 1, 2023

Recently, monkeypox virus is slowly evolving and there are fears it will spread as COVID-19. Computer-aided diagnosis (CAD) based on deep learning approaches especially convolutional neural network (CNN) can assist in the rapid determination of reported incidents. The current CADs were mostly an individual CNN. Few employed multiple CNNs but did not investigate which combination has a greater impact performance. Furthermore, they relied only spatial information features to train their models. This study aims construct CAD tool named "Monkey-CAD" that address previous limitations automatically diagnose rapidly accurately.Monkey-CAD extracts from eight then examines best possible influence classification. It employs discrete wavelet transform (DWT) merge diminishes fused features' size provides time-frequency demonstration. These sizes further reduced via entropy-based feature selection approach. finally used deliver better representation input feed three ensemble classifiers.Two freely accessible datasets called Monkeypox skin image (MSID) lesion (MSLD) this study. Monkey-CAD could discriminate among cases with without achieving accuracy 97.1% for MSID 98.7% MSLD respectively.Such promising results demonstrate be health practitioners. They also verify fusing selected boost

Language: Английский

---

Optimizing IoT-driven smart grid stability prediction with dipper throated optimization algorithm for gradient boosting hyperparameters

Energy Reports, Journal Year: 2024, Volume and Issue: 12, P. 305 - 320

Published: June 19, 2024

With the surge in global population and economic expansion, there's been a marked increase electricity demand. This necessitates efficient distribution of to both residential industrial sectors minimize energy loss. Smart Grids (SG) emerge as promising solution reduce power dissipation networks. The application machine learning artificial intelligence SGs has significantly improved precision predicting consumer needs. paper presents novel approach improving stability prediction Internet Things (IOT)-driven using different advanced models. study explores multiple machine-learning techniques, including Gradient Boosting (GB), K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Neural Networks, Decision Tree classifier, focusing on SGs. efficiency hyperparameter-optimized GB models SG dynamic that encompasses ability system return stable operating point following disturbance. Focusing various models, it identifies Dipper Throated Optimization Algorithm DTO+GB model standout, exhibiting unparalleled accuracy reliability across critical performance metrics such (99.32 %), sensitivity (99.16 specificity (99.54 %). Diagnostic regression analyses further emphasize its better predictive need for hyperparameter optimization improve model. highlights capabilities algorithms conjunction with tactical enhancing prediction, introducing new baseline future technological methodological developments this application.

Language: Английский

---

Efficient Technique for Monkeypox Skin Disease Classification with Clinical Data using Pre-Trained Models

Journal of Innovative Image Processing, Journal Year: 2023, Volume and Issue: 5(2), P. 192 - 213

Published: June 1, 2023

Monkeypox is an infectious zoonotic disease with clinical features similar to those actually observed in victims smallpox, however being medically less severe. With the control of smallpox diseases 1980 as well termination by immunization, monkeypox has become most significant orthopoxvirus affecting global health. It very important prevent and diagnose this immediately efficiently before its spread worldwide. Currently, traditional system used for diagnosis disease, which a medical practitioner identifies swabs fluid from skin rash. This approach lot limitations such it requires expertise, costly slow, result not satisfactory. AI-based technologies may assist identify disorder. Because limitations, proposed work suggests can detect virus immediately. Five transfer learning models are applied on image -based dataset some pre-processing optimization techniques detection. The Inception-Resnet outperformed achieving 97% accuracy, VGG16 achieved 94% Inception 96% VGG19 91% Resnet50 71% accuracy. positive results investigation suggest that strategy outperforms current approaches. obtained Kaggle online repository new patients’ data added various sources. suggested be health professionals screening.

Language: Английский

---

A Novel Artificial-Intelligence-Based Approach for Classification of Parkinson’s Disease Using Complex and Large Vocal Features

Biomimetics, Journal Year: 2023, Volume and Issue: 8(4), P. 351 - 351

Published: Aug. 7, 2023

Parkinson’s disease (PD) affects a large proportion of elderly people. Symptoms include tremors, slow movement, rigid muscles, and trouble speaking. With the aging developed world’s population, this number is expected to rise. The early detection PD avoiding its severe consequences require precise efficient system. Our goal create an accurate AI model that can identify using human voices. We transformer-based method for detecting by retrieving dysphonia measures from subject’s voice recording. It uncommon use neural network (NN)-based solution tabular vocal characteristics, but it has several advantages over tree-based approach, including compatibility with continuous learning network’s potential be linked image/voice encoder more multi modal solution, shifting SOTA approach (NN) crucial advancing research in multimodal solutions. outperforms state art (SOTA), namely Gradient-Boosted Decision Trees (GBDTs), at least 1% AUC, precision recall scores are also improved. additionally offered XgBoost-based feature-selection fully connected NN layer technique measures, addition network. discussed numerous important discoveries relating our suggested deep (DL) application such as how resilient increased depth compared simple MLP performance proposed conventional machine techniques MLP, SVM, Random Forest (RF) have been compared. A detailed comparison matrix added article, along solution’s space time complexity.

Language: Английский

---

An Optimized Model Based on Deep Learning and Gated Recurrent Unit for COVID-19 Death Prediction

Biomimetics, Journal Year: 2023, Volume and Issue: 8(7), P. 552 - 552

Published: Nov. 17, 2023

The COVID-19 epidemic poses a worldwide threat that transcends provincial, philosophical, spiritual, radical, social, and educational borders. By using connected network, healthcare system with the Internet of Things (IoT) functionality can effectively monitor cases. IoT helps patient recognize symptoms receive better therapy more quickly. A critical component in measuring, evaluating, diagnosing risk infection is artificial intelligence (AI). It be used to anticipate cases forecast alternate incidences number, retrieved instances, injuries. In context COVID-19, technologies are employed specific monitoring processes reduce exposure others. This work uses an Indian dataset create enhanced convolutional neural network gated recurrent unit (CNN-GRU) model for death prediction via IoT. data were also subjected normalization imputation. 4692 eight characteristics utilized this research. performance CNN-GRU was assessed five evaluation metrics, including median absolute error (MedAE), mean (MAE), root squared (RMSE), square (MSE), coefficient determination (R2). ANOVA Wilcoxon signed-rank tests determine statistical significance presented model. experimental findings showed outperformed other models regarding prediction.

Language: Английский

---

A Recommendation System for Electric Vehicles Users Based on Restricted Boltzmann Machine and WaterWheel Plant Algorithms

IEEE Access, Journal Year: 2023, Volume and Issue: 11, P. 145111 - 145136

Published: Jan. 1, 2023

Ensuring reliable and easily accessible charging infrastructure becomes crucial as more people adopt electric vehicles. This study introduces a recommendation system designed to assist vehicle users in finding convenient stations, enhancing the experience, reducing range anxiety. The employs advanced data analysis techniques offer personalized suggestions based on users' preferences. Real-time factors like station availability, individual preferences, past usage patterns are collected processed using restricted Boltzmann machine-learning algorithm. waterwheel plant algorithm, known for its effectiveness solving complex optimization problems, is utilized optimize parameters of machine. considers various user including speed, cost, network compatibility, amenities, proximity user's current location. aims minimize frustration, improve performance, enhance customer satisfaction by addressing these aspects. Results indicate system's efficiency suggesting locations. explores statistical significance optimized algorithm machine model through Wilcoxon rank-sum Analysis Variance tests.

Language: Английский

---

Numerical thermodynamic-economic study and machine learning-based optimization of an innovative biogas-driven integrated power plant combined with sustainable liquid CO2 and liquid H2 production-storage processes

Case Studies in Thermal Engineering, Journal Year: 2025, Volume and Issue: 69, P. 106043 - 106043

Published: March 30, 2025

Language: Английский

---

AI-Driven Risk Assessment in Food Safety Using EU RASFF Database

Food and Bioprocess Technology, Journal Year: 2025, Volume and Issue: unknown

Published: April 2, 2025

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

---

Improving air quality prediction using hybrid BPSO with BWAO for feature selection and hyperparameters optimization

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

Published: April 16, 2025

Air pollution poses a significant threat to public health and environmental sustainability, necessitating accurate predictive models for effective air quality management. This study uses machine learning techniques forecast through utilizing the annual AQI dataset obtained from U.S. Environmental Protection Agency (EPA). Feature selection (FS) was conducted using Binary version of Grey Wolf Optimizer (BGWO), Particle Swarm Optimization (BPSO), Whale Algorithm (BWAO), novel hybrid BPSO-BWAO approach identify most relevant features prediction. Among feature methods, BPSO achieved best Mean Squared Error (MSE) score 53.56, but with high variance, while BWAO demonstrated lower variance consistent results. The method emerged as optimal solution, achieving an MSE 53.93 improved stability set balance, selecting key such 'Days AQI,' 'Median CO,' NO2,' PM2.5,' 'Good_Days_Percent,' 'Unhealthy_Days_Percent.' Machine models, including Random Forest (RF), Gradient Boosting (GB), K-Nearest Neighbors (KNN), Multi-Layer Perceptron (MLP), Support Vector (SVM), Linear Regression (LR), were evaluated before after selection. model performance 53.93, R² 0.9710, reduced fitted time. Further optimization PSO-WAO enhanced RF performance, 51.82 0.9821, demonstrating efficacy hyperparameter tuning. concludes that significantly improve accuracy computational efficiency, offering robust framework forecasting.

Language: Английский

---