Air Quality Index Prediction Based on an Adaptive Dynamic Particle Swarm Optimized Bidirectional Gated Recurrent Neural Network–China Region

Li, Ping; Wang, Shengwei; Ji, Hao; Zhan, Yi; Li, Honghong

doi:10.1002/adts.202100220

Cited by 4 publications

(3 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Neural networks (NNs) and deep learning (DL) techniques have found their way into the field, with the application of ANNs to assess the concentration of various air pollutants and classify air quality grades [41]- [43]. Recursive Neural Networks (RNNs) have facilitated the connection and training of multiple layers of neurons with pre-established weights, effectively processing time-series data and predicting future changes in air quality based on past pollutant concentrations [44], [45].…”

Section: Related Workmentioning

confidence: 99%

Toward Cleaner Industries: Smart Cities’ Impact on Predictive Air Quality Management

Chatterjee,

Raju,

Navya Thara

et al. 2024

IEEE Access

View full text Add to dashboard Cite

The Smart City (SC) framework has garnered global recognition for its transformative influence on society through innovative solutions. However, the extensive use of Internet of Things (IoT) devices in SCs raises concerns regarding electronic waste and resource consumption. Addressing this challenge necessitates integrating smart grid systems to safeguard SC residents' environment and wellbeing. Accurate air quality prediction is essential for informed societal decisions, safe transportation, and disaster preparedness. This study introduces a novel approach: Towards Cleaner Industries: Smart Cities' Impact on Predictive Air Quality Management (SPAM). The SPAM model utilizes a bidirectional stacking mechanism of long short-term memory neural networks, considering spatiotemporal correlations to forecast future air pollutant concentrations. Surpassing conventional methods, SPAM enhances accuracy while reducing computational complexity. Experimental findings demonstrate enhanced efficiency and accuracy, underscoring its practicality in industrial contexts. The SPAM model represents a significant advancement in promoting environmental sustainability within the SC framework.

show abstract

Section: Related Workmentioning

confidence: 99%

Toward Cleaner Industries: Smart Cities’ Impact on Predictive Air Quality Management

Chatterjee,

Raju,

Navya Thara

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…[ 11,12 ] In recent years, scholars have made many valuable achievements in evacuation modeling. [ 13,14 ] Evacuation simulation models can be divided into macro‐models and micro‐models. [ 15 ]…”

Section: Introductionmentioning

confidence: 99%

“…[11,12] In recent years, scholars have made many valuable achievements in evacuation modeling. [13,14] Evacuation simulation models can be divided into macro-models and micro-models. [15] In terms of the macroscopic model, the internal environment of the passenger ship is extracted into an undirected graph with weights by graph theory, and then the evacuation route is planned by using the Dijkstra algorithm, network flow algorithm, and Floyd algorithm.…”

Section: Introductionmentioning

confidence: 99%

Evacuation Simulation of a Passenger Ship Fire Based on a Modified Cellular Automaton

Liu

Zhang

Shi³

et al. 2023

Advcd Theory and Sims

View full text Add to dashboard Cite

This study proposes a modified cellular automaton to simulate passenger ship fire evacuation. A fire dynamics simulator (FDS) is used to simulate the firing process for the passenger ship. The generated carbon monoxide (CO) concentration, temperature, and visibility are converted into equivalent lengths and input to the equivalent field of the modified cellular automaton. The fire field is applied to keep the evacuees away from the fire. And game theory is adopted to solve the conflict in the choice of route for evacuees. With or without fire on the passenger ship, three different evacuees' densities are used to study the influence of different proportions of evacuees who are familiar with exits during the evacuation time. The positions of exits are also studied. The results show that when the fire release rate increases from 3000 to 8000 kW s −2 for the same evacuation scenario, the earliest time that evacuees are in danger is 50% earlier. The impact of fire on evacuees is greater than that of evacuees' density. In the case of two close exits or exits close to the bulkheads, the congestion near exits is obvious and has the greatest effect on the evacuation time of the high evacuees' density.

show abstract

Application of Meta-Heuristic Algorithms for Training Neural Networks and Deep Learning Architectures: A Comprehensive Review

Kaveh

Mesgari

2022

Neural Process Lett

View full text Add to dashboard Cite

The learning process and hyper-parameter optimization of artificial neural networks (ANNs) and deep learning (DL) architectures is considered one of the most challenging machine learning problems. Several past studies have used gradient-based back propagation methods to train DL architectures. However, gradient-based methods have major drawbacks such as stucking at local minimums in multi-objective cost functions, expensive execution time due to calculating gradient information with thousands of iterations and needing the cost functions to be continuous. Since training the ANNs and DLs is an NP-hard optimization problem, their structure and parameters optimization using the meta-heuristic (MH) algorithms has been considerably raised. MH algorithms can accurately formulate the optimal estimation of DL components (such as hyper-parameter, weights, number of layers, number of neurons, learning rate, etc.). This paper provides a comprehensive review of the optimization of ANNs and DLs using MH algorithms. In this paper, we have reviewed the latest developments in the use of MH algorithms in the DL and ANN methods, presented their disadvantages and advantages, and pointed out some research directions to fill the gaps between MHs and DL methods. Moreover, it has been explained that the evolutionary hybrid architecture still has limited applicability in the literature. Also, this paper classifies the latest MH algorithms in the literature to demonstrate their effectiveness in DL and ANN training for various applications. Most researchers tend to extend novel hybrid algorithms by combining MHs to optimize the hyper-parameters of DLs and ANNs. The development of hybrid MHs helps improving algorithms performance and capable of solving complex optimization problems. In general, the optimal performance of the MHs should be able to achieve a suitable trade-off between exploration and exploitation features. Hence, this paper tries to summarize various MH algorithms in terms of the convergence trend, exploration, exploitation, and the ability to avoid local minima. The integration of MH with DLs is expected to accelerate the training process in the coming few years. However, relevant publications in this way are still rare.

show abstract

Air Quality Index Prediction Based on an Adaptive Dynamic Particle Swarm Optimized Bidirectional Gated Recurrent Neural Network–China Region

Cited by 4 publications

References 45 publications

Toward Cleaner Industries: Smart Cities’ Impact on Predictive Air Quality Management

Toward Cleaner Industries: Smart Cities’ Impact on Predictive Air Quality Management

Evacuation Simulation of a Passenger Ship Fire Based on a Modified Cellular Automaton

Application of Meta-Heuristic Algorithms for Training Neural Networks and Deep Learning Architectures: A Comprehensive Review

Contact Info

Product

Resources

About