PM2.5 forecasting using SVR with PSOGSA algorithm based on CEEMD, GRNN and GCA considering meteorological factors

Zhu, Suling; Lian, Xiuyuan; Lin, Wey Jinq; Che, Jinxing; Shen, Xiping; Yang, Ling; Qiu, Xuanlin; Liu, Xiaoning; Gao, Wenlong; Ren, Xiaowei; Li, Juansheng

doi:10.1016/j.atmosenv.2018.04.004

Cited by 141 publications

(51 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…An additional extension can be to achieve medium-and long-term forecasts in terms of the time factor. PM 2.5 forecasting using SVR with PSOGSA algorithm based on CEEMD, GRNN and GCA considering meteorological factors [64]: is focused on forecasting of next 30 days' PM 2.5 . The proposed model, CEEMD-PSOGSA-SVR-GRNN, is based on Complementary Ensemble Empirical Mode Decomposition (CEEMD), Particle Swarm Optimization and Gravitational Search Algorithm (PSOGSA), SVR, Generalized Regression Neural Network (GRNN) and Grey Correlation Analysis (GCA).…”

Section: Group 4: Hybrid Modelmentioning

confidence: 99%

Air Quality Prediction in Smart Cities Using Machine Learning Technologies Based on Sensor Data: A Review

2020

View full text Add to dashboard Cite

The influence of machine learning technologies is rapidly increasing and penetrating almost in every field, and air pollution prediction is not being excluded from those fields. This paper covers the revision of the studies related to air pollution prediction using machine learning algorithms based on sensor data in the context of smart cities. Using the most popular databases and executing the corresponding filtration, the most relevant papers were selected. After thorough reviewing those papers, the main features were extracted, which served as a base to link and compare them to each other. As a result, we can conclude that: (1) instead of using simple machine learning techniques, currently, the authors apply advanced and sophisticated techniques, (2) China was the leading country in terms of a case study, (3) Particulate matter with diameter equal to 2.5 micrometers was the main prediction target, (4) in 41% of the publications the authors carried out the prediction for the next day, (5) 66% of the studies used data had an hourly rate, (6) 49% of the papers used open data and since 2016 it had a tendency to increase, and (7) for efficient air quality prediction it is important to consider the external factors such as weather conditions, spatial characteristics, and temporal features.

show abstract

Section: Group 4: Hybrid Modelmentioning

confidence: 99%

Air Quality Prediction in Smart Cities Using Machine Learning Technologies Based on Sensor Data: A Review

2020

View full text Add to dashboard Cite

show abstract

“…Assessing the air pollution by measuring all the compounds introduced into the air is impossible, for this reason to evaluate the extent, it is preferred to detect only some compounds considered indicative to describe the phenomenon [6,7].…”

Section: Methodsmentioning

confidence: 99%

Air pollution effects on the intensity of received signal in 3G/4G mobile terminal

Sciuto

2019

Int J Energy Environ Eng

View full text Add to dashboard Cite

In this paper, the existence of the interaction between the atmospheric particulate and the electromagnetic waves attenuation in the frequency band used by the 3G/4G mobile network was investigated. A few papers present in literature indicate, in presence of air pollution, the possibility of a significant cross polarization of the electromagnetic waves, while none of the papers indicated the possibility of a significant attenuation. This paper has tried to partially fill this gap of knowledge in this field with some new contributions. In all the experiments performed at the department of electrical, electronics and informatics engineering in the University of Catania (87 experiments each one lasting about 36 min), significant variations have not been found in the received signal level (RSL), while a polynomial dependency of the RSL local variance from the particulate concentration has been found. To demonstrate that the results obtained in the laboratory have general validity, a campaign test was conducted in an outdoors environment in the frequency band used by the 3G/4G mobile network. The site of the considered measurement station is selected to represent a typical residential area with high traffic influences in the city of Catania. Also, in this measures campaign conducted in the outdoors environment in the 3G/4G frequency band, significant variations have not been found in the RSL. While a marked dependence of the RSL local variance from the PM 10 concentration has been found. This is a noteworthy result, because certain non-negligible RSL local variance variations indicate the possibility of a pronounced cross polarization. The impact of the cross polarization becomes significant for systems reusing frequency, because the cross polarization counteracts the optimum frequency spectrum utilization.Publisher's Note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

show abstract

“…For example, Zhang et al [9] combined CEEMD -Lempel-Ziv complexity and extreme learning machine (ELM) to improve the precision and stability of wind power prediction. Zhu et al [10] put forward a hybrid algorithm of CEEMD and particle swarm optimization and gravitational search algorithm (PSOGSA) to realize the prediction and early warning of air quality. Qiao et al [11] realized the classification and detection of wheat pests by using the spectral analysis and feature extraction method based on CEEMD.…”

Section: Introductionmentioning

confidence: 99%

CEEMD: A New Method to Identify Mine Water Inrush Based on the Signal Processing and Laser-Induced Fluorescence

Bian

Zhou

et al. 2020

IEEE Access

View full text Add to dashboard Cite

The rapid and accurate identification of water source types in mine water inrush has been achieved by combining laser-induced fluorescence technology (LIF) with artificial intelligence algorithms. However, these algorithms solely rely on data and image processing analysis to identify different kinds of water samples. To address this issue, the fluorescence spectrum and identified the types of mine water inrush sources from the signal point of view. Firstly, a LIF water inrush spectral analysis system was built to collect spectral data and exhibit fluorescence spectra. Different methods of spectral signal decomposition and reconstruction were compared. The complementary ensemble empirical mode decomposition (CEEMD) algorithm with a better signal evaluation index was selected to preprocess raw spectral signals. Then, the multi-class support vector machine of the cuckoo search optimization (CS-MSVM) model was implemented to the reconstructed spectral signals in different stages. The classification accuracy of the reconstructed signals in the fifth stage was 100%. Compared with raw spectra, other signal processing methods, and other different classifiers, the proposed method has the highest classification accuracy. Finally, the reliability of the algorithm was validated by using the LIF spectral signals of different edible oils and the classification accuracy was 100%. The experimental results show that the CEEMD signal processing method combined with LIF spectroscopy is effective for the accurate identification of mine water inrush source, and it also provides a theoretical basis for the spectral analysis technology that can be used for the identification of other substances.

show abstract

PM2.5 forecasting using SVR with PSOGSA algorithm based on CEEMD, GRNN and GCA considering meteorological factors

Cited by 141 publications

References 35 publications

Air Quality Prediction in Smart Cities Using Machine Learning Technologies Based on Sensor Data: A Review

Air Quality Prediction in Smart Cities Using Machine Learning Technologies Based on Sensor Data: A Review

Air pollution effects on the intensity of received signal in 3G/4G mobile terminal

CEEMD: A New Method to Identify Mine Water Inrush Based on the Signal Processing and Laser-Induced Fluorescence

Contact Info

Product

Resources

About