The explainable potential of coupling hybridized metaheuristics, XGBoost, and SHAP in revealing toluene behavior in the atmosphere

The Science of The Total Environment, Journal Year: 2024, Volume and Issue: 929, P. 172195 - 172195

Published: April 15, 2024

Language: Английский

---

Enhancing stock index prediction: A hybrid LSTM-PSO model for improved forecasting accuracy

PLoS ONE, Journal Year: 2025, Volume and Issue: 20(1), P. e0310296 - e0310296

Published: Jan. 14, 2025

Stock price prediction is a challenging research domain. The long short-term memory neural network (LSTM) widely employed in stock due to its ability address long-term dependence and transmission of historical time signals series data. However, manual tuning LSTM parameters significantly impacts model performance. PSO-LSTM leveraging PSO’s efficient swarm intelligence strong optimization capabilities proposed this article. experimental results on six global indices demonstrate that effectively fits real data, achieving high accuracy. Moreover, increasing PSO iterations lead gradual loss reduction, which indicates PSO-LSTM’s good convergence. Comparative analysis with seven other machine learning algorithms confirms the superior performance PSO-LSTM. Furthermore, impact different retrospective periods accuracy finding consistent across varying spans are. Conducted experiments.

Language: Английский

---

Intrusion detection using metaheuristic optimization within IoT/IIoT systems and software of autonomous vehicles

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Oct. 2, 2024

Language: Английский

---

Respiratory Condition Detection Using Audio Analysis and Convolutional Neural Networks Optimized by Modified Metaheuristics

Axioms, Journal Year: 2024, Volume and Issue: 13(5), P. 335 - 335

Published: May 18, 2024

Respiratory conditions have been a focal point in recent medical studies. Early detection and timely treatment are crucial factors improving patient outcomes for any condition. Traditionally, doctors diagnose respiratory through an investigation process that involves listening to the patient’s lungs. This study explores potential of combining audio analysis with convolutional neural networks detect patients. Given significant impact proper hyperparameter selection on network performance, contemporary optimizers employed enhance efficiency. Moreover, modified algorithm is introduced tailored specific demands this study. The proposed approach validated using real-world dataset has demonstrated promising results. Two experiments conducted: first tasked models condition when observing mel spectrograms patients’ breathing patterns, while second experiment considered same data format multiclass classification. Contemporary optimize architecture training parameters both cases. Under identical test conditions, best optimized by metaheuristic, accuracy 0.93 detection, slightly reduced 0.75 identification.

Language: Английский

---

Evaluating the performance of metaheuristic-tuned weight agnostic neural networks for crop yield prediction

Neural Computing and Applications, Journal Year: 2024, Volume and Issue: 36(24), P. 14727 - 14756

Published: May 10, 2024

Abstract This study explores crop yield forecasting through weight agnostic neural networks (WANN) optimized by a modified metaheuristic. WANNs offer the potential for lighter with shared weights, utilizing two-layer cooperative framework to optimize network architecture and weights. The proposed metaheuristic is tested on real-world datasets benchmarked against state-of-the-art algorithms using standard regression metrics. While not claiming WANN as definitive solution, model demonstrates significant in lightweight architectures. models achieve mean absolute error (MAE) of 0.017698 an R -squared ( $$R^2$$ R 2 ) score 0.886555, indicating promising performance. Statistical analysis Simulator Autonomy Generality Evaluation (SAGE) validate improvement significance feature importance approach.

Language: Английский

---

Computer-Vision Unmanned Aerial Vehicle Detection System Using YOLOv8 Architectures

International Journal of Robotics and Automation Technology, Journal Year: 2024, Volume and Issue: 11, P. 1 - 12

Published: May 22, 2024

Abstract: This work aims to test the performance of you only look once version 8 (YOLOv8) model for problem drone detection. Drones are very slightly regulated and standards need be established. With a robust system detecting drones possibilities regulating their usage becoming realistic. Five different sizes were tested determine best architecture size this problem. The results indicate high across all models that each is used specific case. Smaller suited lightweight approaches where some false identification tolerable, while largest with stationary systems require precision.

Language: Английский

---

Enhanced Forecasting and Assessment of Urban Air Quality by an Automated Machine Learning System: The AI‐Air

Earth and Space Science, Journal Year: 2025, Volume and Issue: 12(1)

Published: Jan. 1, 2025

Abstract An automated air quality forecasting system (AI‐Air) was developed to optimize and improve for different typical cities, combined with the China Meteorological Administration Unified Atmospheric Chemistry Environmental Model (CUACE), used in a inland city of Zhengzhou coastal Haikou China. The performance evaluation results show that PM 2.5 forecasts, correlation coefficient (R) is increased by 0.07–0.13, mean error (ME) root square (RMSE) decreased 3.2–3.5 3.8–4.7 μg/m³. Similarly, O 3 R value improved 0.09–0.44, ME RMSE values are reduced 7.1–22.8 9.0–25.9 μg/m³, respectively. Case analyses operational also indicate AI‐Air can significantly pollutant concentrations effectively correct underestimation, or overestimation phenomena compared CUACE model. Additionally, explanatory were performed assess key meteorological factors affecting cities topographic climatic conditions. highlights potential AI techniques forecast accuracy efficiency, promising applications field forecasting.

Language: Английский

---

A novel feature extraction method based on dynamic handwriting for Parkinson’s disease detection

PLoS ONE, Journal Year: 2025, Volume and Issue: 20(1), P. e0318021 - e0318021

Published: Jan. 24, 2025

Parkinson’s disease (PD) is a common of the elderly. Given easy accessibility handwriting samples, many researchers have proposed handwriting-based detection methods for disease. Extracting more discriminative features from an important step. Although been in previous researches, insight analysis combination handwriting’s kinematic, pressure, and angle dynamic lacking. Moreover, most existing feature incompletely represented, with information lost. Therefore, to solve above problems, new extraction approach PD using handwriting. First, built on features, we propose moment by composed these three types overall representation information. Then, method extract time-frequency-based statistical (TF-ST) terms their temporal frequency characteristics. Finally, escape Coati Optimization Algorithm (eCOA) global optimization enhance classification performance. Self-constructed public datasets are used verify method’s effectiveness respectively. The experimental results showed accuracy 97.95% 98.67%, sensitivity 98.15% (average) 97.78%, specificity 99.17% 100%, AUC 98.66% 98.89%. code available at https://github.com/dreamhcy/MLforPD .

Language: Английский

---

Adaptive feature selection with flexible mapping for diagnosis and prediction of Parkinson's disease

Engineering Applications of Artificial Intelligence, Journal Year: 2025, Volume and Issue: 146, P. 110342 - 110342

Published: Feb. 21, 2025

Language: Английский

---

Racism Detecting in Twitter Comments Using Metaheuristics Optimized Text Mining and Classification

Communications in computer and information science, Journal Year: 2025, Volume and Issue: unknown, P. 217 - 231

Published: Jan. 1, 2025

Language: Английский

---