《電子技術(shù)應(yīng)用》
您所在的位置:首頁(yè) > 其他 > 設(shè)計(jì)應(yīng)用 > 基于改進(jìn)BCCSA和深層LSTM的空氣質(zhì)量預(yù)測(cè)方法
基于改進(jìn)BCCSA和深層LSTM的空氣質(zhì)量預(yù)測(cè)方法
2022年電子技術(shù)應(yīng)用第6期
韋詩(shī)玥,徐洪珍
東華理工大學(xué) 信息工程學(xué)院,,江西 南昌330013
摘要: 現(xiàn)有的空氣質(zhì)量預(yù)測(cè)方法很少考慮季節(jié)性因素,,且預(yù)測(cè)的效果不佳,因此提出一種基于改進(jìn)二元混沌烏鴉搜索算法(Binary Chaotic Crow Search Algorithm,,BCCSA)和深層長(zhǎng)短期記憶神經(jīng)網(wǎng)絡(luò)(Long Short Term Memory,,LSTM)的空氣質(zhì)量預(yù)測(cè)方法。首先提出季節(jié)調(diào)整的方法對(duì)收集的原始空氣質(zhì)量數(shù)據(jù)進(jìn)行預(yù)處理,,以消除季節(jié)對(duì)預(yù)測(cè)的影響,;然后提出改進(jìn)BCCSA,,對(duì)空氣質(zhì)量數(shù)據(jù)進(jìn)行優(yōu)化處理,;最后,將自注意力機(jī)制加入到深層LSTM中,,對(duì)空氣質(zhì)量數(shù)據(jù)進(jìn)行預(yù)測(cè),。實(shí)驗(yàn)結(jié)果表明,,該方法能有效地提高空氣質(zhì)量的預(yù)測(cè)精度。
中圖分類號(hào): TP399
文獻(xiàn)標(biāo)識(shí)碼: A
DOI:10.16157/j.issn.0258-7998.222731
中文引用格式: 韋詩(shī)玥,,徐洪珍. 基于改進(jìn)BCCSA和深層LSTM的空氣質(zhì)量預(yù)測(cè)方法[J].電子技術(shù)應(yīng)用,2022,,48(6):28-32.
英文引用格式: Wei Shiyue,,Xu Hongzhen. Air quality prediction method based on improved BCCSA and deep LSTM[J]. Application of Electronic Technique,,2022,,48(6):28-32.
Air quality prediction method based on improved BCCSA and deep LSTM
Wei Shiyue,,Xu Hongzhen
School of Information Engineering,East China University of Technology,,Nanchang 330013,China
Abstract: The existing air quality prediction methods rarely consider seasonal factors, and the prediction effect is not good. Therefore, an air quality prediction method based on improved binary chaotic crow search algorithm(BCCSA) and deep long short term memory neural network(LSTM) is proposed. Firstly, the method of seasonal adjustment is proposed to preprocess the collected original air quality data in order to eliminate the influence of season on prediction. Then, an improved BCCSA is proposed to optimize the air quality data. Finally, the self-attention mechanism is added to the deep LSTM to predict the air quality data. The experimental results show that this method can effectively improve the prediction accuracy of air quality.
Key words : air quality,;seasonal adjustment,;improved binary chaotic crow search algorithm(BCCSA);deep long short term memory(LSTM);self-attention mechanism

0 引言

    隨著社會(huì)的發(fā)展和生活質(zhì)量的提高,,人們不再是關(guān)注溫飽問題,,更多地開始關(guān)注健康問題,。被污染了的空氣會(huì)給人類健康帶來(lái)危害,,特別是在人口稠密的地區(qū)[1],。空氣質(zhì)量是一個(gè)十分復(fù)雜的現(xiàn)象,,會(huì)受到許多因素的影響[2],??諝赓|(zhì)量能夠通過計(jì)算空氣中的污染物來(lái)反映空氣污染的嚴(yán)重程度,,通常用空氣質(zhì)量指數(shù)(Air Quality Index,AQI)來(lái)進(jìn)行定量描述,。有效的空氣質(zhì)量預(yù)測(cè)能夠?yàn)槿藗兲峁┘皶r(shí)的空氣質(zhì)量警報(bào),,能夠使政府部門及時(shí)干預(yù)高污染事件,能夠提醒人們是否適宜進(jìn)行戶外活動(dòng),。嚴(yán)重的空氣污染不僅會(huì)影響人們的生活,,更會(huì)影響人們的生命健康[3],。準(zhǔn)確地進(jìn)行空氣質(zhì)量預(yù)測(cè)對(duì)國(guó)家,、政府,、民眾來(lái)說都是一件重要的事,。

    空氣質(zhì)量數(shù)據(jù)具有明顯的季節(jié)性,,如果忽視這一因素,,會(huì)導(dǎo)致對(duì)空氣質(zhì)量數(shù)據(jù)的預(yù)處理不夠充分并且預(yù)測(cè)精度不夠高,,所以本文提出季節(jié)調(diào)整的空氣質(zhì)量數(shù)據(jù)預(yù)處理方法。本文首次將二元混沌烏鴉搜索算法(Binary Chaotic Crow Search Algorithm,,BCCSA)應(yīng)用于空氣質(zhì)量數(shù)據(jù)的預(yù)測(cè),,能夠更好地優(yōu)化非線性、非平穩(wěn)的空氣質(zhì)量數(shù)據(jù),并針對(duì)BCCSA存在的不足,,提出3種改進(jìn)方法用以提高它的收斂速度,。本文還將自注意力機(jī)制與深層長(zhǎng)短期記憶神經(jīng)網(wǎng)絡(luò)(Long Short Term Memory,LSTM)相結(jié)合來(lái)預(yù)測(cè)經(jīng)過處理的空氣質(zhì)量數(shù)據(jù),,能有效挖掘空氣質(zhì)量數(shù)據(jù)中隱藏的時(shí)間序列信息,提高了方法的預(yù)測(cè)精度?,F(xiàn)有的研究大多都是對(duì)空氣質(zhì)量進(jìn)行未來(lái)幾個(gè)小時(shí)的短期預(yù)測(cè),,而本文對(duì)空氣質(zhì)量進(jìn)行了未來(lái)24小時(shí)的預(yù)測(cè),,并且具有較高的精度,。




本文詳細(xì)內(nèi)容請(qǐng)下載:http://forexkbc.com/resource/share/2000004414,。




作者信息:

韋詩(shī)玥,,徐洪珍

(東華理工大學(xué) 信息工程學(xué)院,,江西 南昌330013)




wd.jpg

此內(nèi)容為AET網(wǎng)站原創(chuàng),未經(jīng)授權(quán)禁止轉(zhuǎn)載,。