Advancing air quality prediction models in urban India: a deep learning approach integrating DCNN and LSTM architectures for AQI time-series classification

Modeling Earth Systems and Environment, Год журнала: 2024, Номер 10(2), С. 2935 - 2955

Опубликована: Фев. 2, 2024

Язык: Английский

---

An Improved Chaotic Game Optimization Algorithm and Its Application in Air Quality Prediction

Axioms, Год журнала: 2025, Номер 14(4), С. 235 - 235

Опубликована: Март 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.

Язык: Английский

---

Ensemble Learning-Based Approach for Forecasting Inventory Data in Prefabricated Component Warehousing

Processes, Год журнала: 2025, Номер 13(5), С. 1443 - 1443

Опубликована: Май 8, 2025

Accurately predicting the storage area of prefabricated components facilitates transshipment scheduling and prevents waste space. Due to influence numerous factors, precise prediction remains challenging. Currently, limited research has addressed areas for components, effective solutions are lacking. To address this issue, a GRU model with an attention mechanism based on ensemble learning was proposed. The employed Bo-Bi-ATT-GRU approach time series areas. A Bayesian optimization algorithm utilized enhance parameter tuning training efficiency, while framework improved stability. In study, port container dataset used experimentation, root mean square error (RMSE) absolute percentage (MAPE) as evaluation metrics. Compared GM model, R2 proposed by 3.38%. Experimental results demonstrated that learning-based offered superior performance in forecasting components.

Язык: Английский

---

Feasibility Study for Construction Projects in Uncertainty Environment with Optimization Approach

SSRN Electronic Journal, Год журнала: 2024, Номер unknown

Опубликована: Янв. 1, 2024

Язык: Английский

---

Applications of Machine Learning in Financial Accounting for Industrial Engineering: A Case Study on Cost Estimation and Forecasting

Опубликована: Янв. 1, 2024

Язык: Английский

---

A Novel Six-Dimensional Chimp Optimization Algorithm—Deep Reinforcement Learning-Based Optimization Scheme for Reconfigurable Intelligent Surface-Assisted Energy Harvesting in Batteryless IoT Networks

Future Internet, Год журнала: 2024, Номер 16(12), С. 460 - 460

Опубликована: Дек. 6, 2024

The rapid advancement of Internet Things (IoT) networks has revolutionized modern connectivity by integrating many low-power devices into various applications. As IoT expand, the demand for energy-efficient, batteryless becomes increasingly critical sustainable future networks. These play a pivotal role in next-generation applications reducing dependence on conventional batteries and enabling continuous operation through energy harvesting capabilities. However, several challenges hinder widespread adoption devices, including limited transmission range, constrained resources, low spectral efficiency receivers. To address these limitations, reconfigurable intelligent surfaces (RISs) offer promising solution dynamically manipulating wireless propagation environment to enhance signal strength improve In this paper, we propose novel deep reinforcement learning (DRL) algorithm that optimizes phase shifts RISs maximize network’s achievable rate while satisfying devices’ constraints. Our DRL framework leverages six-dimensional chimp optimization (6DChOA) fine-tune hyper-parameters, ensuring efficient adaptive learning. proposed 6DChOA-DRL RIS received power mitigating interference from direct RIS-cascaded links. simulation results demonstrate our optimized design significantly improves data rates under system configurations. Compared benchmark algorithms, approach achieves higher gains harvested power, an improvement at transmit 20 dBm, lower root mean square error (RMSE) 0.13 compared 3.34 standard RL 6.91 DNN, indicating more precise shifts.

Язык: Английский

---

Leveraging AI-Driven Predictive Analytics for Enhancing Resource Optimization and Efficiency in Agile Construction Project Management

SSRN Electronic Journal, Год журнала: 2024, Номер unknown

Опубликована: Янв. 1, 2024

Язык: Английский

---

Integrating Artificial Intelligence and Predictive Analytics for Feasibility Studies in Construction Projects: An Optimization Approach in Uncertainty Environments

SSRN Electronic Journal, Год журнала: 2024, Номер unknown

Опубликована: Янв. 1, 2024

Язык: Английский

---

Enhancing Air Pollution Forecasting with LSTM and a Binary Chimp Optimization Algorithm

SSRN Electronic Journal, Год журнала: 2024, Номер unknown

Опубликована: Янв. 1, 2024

Язык: Английский

---