An Improved Chaotic Game Optimization Algorithm and Its Application in Air Quality Prediction DOI Creative Commons
Yanping Liu,

Ruili Zheng,

Bohao Yu

et al.

Axioms, Journal Year: 2025, Volume and Issue: 14(4), P. 235 - 235

Published: March 21, 2025

Air pollution poses significant threats to public health and ecological sustainability, necessitating precise air quality prediction facilitate timely preventive measures policymaking. Although Long Short-Term Memory (LSTM) networks demonstrate effectiveness in prediction, their performance critically depends on appropriate hyperparameter configuration. Traditional manual parameter tuning methods prove inefficient prone suboptimal solutions. While conventional swarm intelligence algorithms have been proved be effective optimizing the hyperparameters of LSTM models, they still face challenges accuracy model generalizability. To address these limitations, this study proposes an improved chaotic game optimization (ICGO) algorithm incorporating multiple improvement strategies, subsequently developing ICGO-LSTM hybrid for Chengdu’s prediction. The experimental validation comprises two phases: First, comprehensive benchmarking 23 mathematical functions reveals that proposed ICGO achieves superior mean values across all test optimal variance metrics 22 functions, demonstrating enhanced global convergence capability algorithmic robustness. Second, comparative analysis with seven swarm-optimized models six machine learning benchmarks dataset shows model’s performance. Extensive evaluations show minimal error metrics, MAE = 3.2865, MAPE 0.720%, RMSE 4.8089, along exceptional coefficient determination (R2 0.98512). These results indicate significantly outperforms predictive reliability, suggesting substantial practical implications urban environmental management.

Language: Английский

Multi-level lag scheme significantly improves training efficiency in deep learning: a case study in air quality alert service over sub-tropical area DOI Creative Commons
Benedito Chi Man Tam, Su-Kit Tang, Alberto Cardoso

et al.

Journal Of Big Data, Journal Year: 2025, Volume and Issue: 12(1)

Published: Jan. 5, 2025

Abstract In environmental monitoring, deep learning models are used where we can either use past observations or extrapolated values with high uncertainty as input. The lag scheme is commonly applied during the modeling and construction process, in application of multivariate time series prediction. For an adaptive feature engineering, automated essential for improving training efficiency. (MTS) models, predictive accuracy artificial neural network ANN-type be improved by including more features. It assumed that when processing a certain number features, timeliness inter-influencing between any pair elements different. This research aims to adopt approach solve it, namely, multi-level scheme. methods include literature review, searching relevant technology frontiers, feasibility studies, selection design solutions, modeling, data collection pre-processing, experiments, evaluation, comprehensive analysis conclusions. proof concept, demonstrated practical case seasonal ANN type MTS model public service on air quality. terms were attempted ARIMA comparing baseline. We set than two base stations pollution varying from low southern northern district small city. Conclusions drawn multiple experimental results, proving proposed solution effectively improve efficiency model. great significance, so most such implemented adaptively lagged measured input, instead synchronously inputting future prediction values, which greatly ability.

Language: Английский

Citations

1
AIoT-based Indoor Air Quality Prediction for Building Using Enhanced Metaheuristic Algorithm and Hybrid Deep Learning DOI
Phuong Nguyen Thanh

Journal of Building Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 112448 - 112448

Published: March 1, 2025

Language: Английский

Citations

1
Revolutionizing air quality forecasting: Fusion of state-of-the-art deep learning models for precise classification DOI
Umesh Kumar Lilhore, Sarita Simaiya, Surjeet Dalal

et al.

Urban Climate, Journal Year: 2025, Volume and Issue: 59, P. 102308 - 102308

Published: Jan. 28, 2025

Language: Английский

Citations

0
An Improved Chaotic Game Optimization Algorithm and Its Application in Air Quality Prediction DOI Creative Commons
Yanping Liu,

Ruili Zheng,

Bohao Yu

et al.

Axioms, Journal Year: 2025, Volume and Issue: 14(4), P. 235 - 235

Published: March 21, 2025

Air pollution poses significant threats to public health and ecological sustainability, necessitating precise air quality prediction facilitate timely preventive measures policymaking. Although Long Short-Term Memory (LSTM) networks demonstrate effectiveness in prediction, their performance critically depends on appropriate hyperparameter configuration. Traditional manual parameter tuning methods prove inefficient prone suboptimal solutions. While conventional swarm intelligence algorithms have been proved be effective optimizing the hyperparameters of LSTM models, they still face challenges accuracy model generalizability. To address these limitations, this study proposes an improved chaotic game optimization (ICGO) algorithm incorporating multiple improvement strategies, subsequently developing ICGO-LSTM hybrid for Chengdu’s prediction. The experimental validation comprises two phases: First, comprehensive benchmarking 23 mathematical functions reveals that proposed ICGO achieves superior mean values across all test optimal variance metrics 22 functions, demonstrating enhanced global convergence capability algorithmic robustness. Second, comparative analysis with seven swarm-optimized models six machine learning benchmarks dataset shows model’s performance. Extensive evaluations show minimal error metrics, MAE = 3.2865, MAPE 0.720%, RMSE 4.8089, along exceptional coefficient determination (R2 0.98512). These results indicate significantly outperforms predictive reliability, suggesting substantial practical implications urban environmental management.

Language: Английский

Citations

0