The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
O índice de qualidade do ar (AQI) é um índice adimensional para a descrição da qualidade do ar e é amplamente utilizado em esquemas de gestão da qualidade do ar. Um novo método para previsão do índice de qualidade do ar baseado em Deep Dictionary Learning (AQIF-DDL) e visão de máquina é proposto neste artigo. Uma imagem do céu é usada como entrada do método e a saída é o valor AQI previsto. O aprendizado profundo do dicionário é empregado para extrair automaticamente os recursos da imagem do céu e obter a previsão do AQI. A ideia de aprender níveis de dicionário mais profundos decorrentes do aprendizado profundo também está incluída para aumentar a precisão e estabilidade da previsão. O AQIF-DDL proposto é comparado com outros métodos baseados em aprendizagem profunda, como rede de crenças profundas, autoencoder empilhado e rede neural convolucional. Os resultados experimentais indicam que o método proposto leva a um bom desempenho na previsão do AQI.
Bin CHEN
Jiaxing University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Bin CHEN, "Air Quality Index Forecasting via Deep Dictionary Learning" in IEICE TRANSACTIONS on Information,
vol. E103-D, no. 5, pp. 1118-1125, May 2020, doi: 10.1587/transinf.2019EDP7296.
Abstract: Air quality index (AQI) is a non-dimensional index for the description of air quality, and is widely used in air quality management schemes. A novel method for Air Quality Index Forecasting based on Deep Dictionary Learning (AQIF-DDL) and machine vision is proposed in this paper. A sky image is used as the input of the method, and the output is the forecasted AQI value. The deep dictionary learning is employed to automatically extract the sky image features and achieve the AQI forecasting. The idea of learning deeper dictionary levels stemmed from the deep learning is also included to increase the forecasting accuracy and stability. The proposed AQIF-DDL is compared with other deep learning based methods, such as deep belief network, stacked autoencoder and convolutional neural network. The experimental results indicate that the proposed method leads to good performance on AQI forecasting.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2019EDP7296/_p
Copiar
@ARTICLE{e103-d_5_1118,
author={Bin CHEN, },
journal={IEICE TRANSACTIONS on Information},
title={Air Quality Index Forecasting via Deep Dictionary Learning},
year={2020},
volume={E103-D},
number={5},
pages={1118-1125},
abstract={Air quality index (AQI) is a non-dimensional index for the description of air quality, and is widely used in air quality management schemes. A novel method for Air Quality Index Forecasting based on Deep Dictionary Learning (AQIF-DDL) and machine vision is proposed in this paper. A sky image is used as the input of the method, and the output is the forecasted AQI value. The deep dictionary learning is employed to automatically extract the sky image features and achieve the AQI forecasting. The idea of learning deeper dictionary levels stemmed from the deep learning is also included to increase the forecasting accuracy and stability. The proposed AQIF-DDL is compared with other deep learning based methods, such as deep belief network, stacked autoencoder and convolutional neural network. The experimental results indicate that the proposed method leads to good performance on AQI forecasting.},
keywords={},
doi={10.1587/transinf.2019EDP7296},
ISSN={1745-1361},
month={May},}
Copiar
TY - JOUR
TI - Air Quality Index Forecasting via Deep Dictionary Learning
T2 - IEICE TRANSACTIONS on Information
SP - 1118
EP - 1125
AU - Bin CHEN
PY - 2020
DO - 10.1587/transinf.2019EDP7296
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E103-D
IS - 5
JA - IEICE TRANSACTIONS on Information
Y1 - May 2020
AB - Air quality index (AQI) is a non-dimensional index for the description of air quality, and is widely used in air quality management schemes. A novel method for Air Quality Index Forecasting based on Deep Dictionary Learning (AQIF-DDL) and machine vision is proposed in this paper. A sky image is used as the input of the method, and the output is the forecasted AQI value. The deep dictionary learning is employed to automatically extract the sky image features and achieve the AQI forecasting. The idea of learning deeper dictionary levels stemmed from the deep learning is also included to increase the forecasting accuracy and stability. The proposed AQIF-DDL is compared with other deep learning based methods, such as deep belief network, stacked autoencoder and convolutional neural network. The experimental results indicate that the proposed method leads to good performance on AQI forecasting.
ER -