本文選題：時(shí)間序列預(yù)測(cè) + 回聲狀態(tài)網(wǎng)絡(luò)　； 參考：《中國(guó)科學(xué)技術(shù)大學(xué)》2017年碩士論文

【摘要】：時(shí)間序列數(shù)據(jù)廣泛存在于電子商務(wù),金融,視頻活動(dòng)分析等任務(wù)中,針對(duì)時(shí)序數(shù)據(jù)的分析和預(yù)測(cè)是一項(xiàng)十分重要且有挑戰(zhàn)性的工作。對(duì)時(shí)間序列分析的難點(diǎn)有二,其一是:時(shí)間序列數(shù)據(jù)具有時(shí)序性。其二是:時(shí)間序列數(shù)據(jù)通常包含較多的噪聲�；芈暊顟B(tài)網(wǎng)絡(luò)(Echo State Network,ESN)是目前一種流行的時(shí)間序列分析模型,它的儲(chǔ)蓄池(相當(dāng)于傳統(tǒng)神經(jīng)網(wǎng)絡(luò)的隱藏層)的循環(huán)連接使其具有一定的"記憶"能力,可以很好地?cái)M合出時(shí)間序列數(shù)據(jù)的時(shí)序關(guān)系。由于回聲狀態(tài)網(wǎng)絡(luò)儲(chǔ)蓄池中的節(jié)點(diǎn)個(gè)數(shù)較多,當(dāng)它被用來擬合噪聲較多的數(shù)據(jù)時(shí),容易造成過擬合,影響模型的預(yù)測(cè)能力。傳統(tǒng)ESN模型中,ESN輸入層到儲(chǔ)蓄池、儲(chǔ)蓄池內(nèi)部節(jié)點(diǎn)之間連接權(quán)重隨機(jī)生成,ESN的性能依賴于這種隨機(jī)性,導(dǎo)致它具有不穩(wěn)定性。為了得到合適的ESN,通常需要不斷地隨機(jī)生成ESN,直到產(chǎn)生合適模型為止,傳統(tǒng)方法無法保證新生成的ESN優(yōu)于之前的ESN�；诨芈暊顟B(tài)網(wǎng)絡(luò)的上述缺點(diǎn),本文提出了多目標(biāo)多樣性回聲狀態(tài)網(wǎng)絡(luò)(Multi-objective Diversified Echo State Network,MODESN),MODESN 定義了 ESN 多樣性。ESN 多樣性通過考慮儲(chǔ)蓄池中節(jié)點(diǎn)之間的冗余度,從而盡可能地避免過擬合情況發(fā)生。MODESN利用多目標(biāo)遺傳算法同時(shí)對(duì)ESN多樣性和預(yù)測(cè)準(zhǔn)確率進(jìn)行優(yōu)化,使得新生成的ESN模型向期望的方向演化,從而避免了傳統(tǒng)生成ESN方法的隨機(jī)性。本文的主要工作可以總結(jié)如下:(1)本文定義了 ESN多樣性,通過優(yōu)化ESN多樣來優(yōu)化ESN結(jié)構(gòu),從而盡可能避免過擬合。(2)本文改進(jìn)了一種多目標(biāo)遺傳算法,并用其對(duì)ESN多樣性和預(yù)測(cè)準(zhǔn)確率同時(shí)進(jìn)行優(yōu)化,規(guī)范了 ESN演化方向。(3)本文將日本蠟燭圖技術(shù)與MODESN模型結(jié)合,降低了特征數(shù)量,避免引入不必要的噪聲。
[Abstract]:Time series data are widely used in e-commerce, finance, video activity analysis and other tasks. The analysis and prediction of time series data is a very important and challenging task. There are two difficulties in time series analysis. One is that the time series data are temporal. The second is that time series data usually contain more noise. Echo State Network (ESN) is a popular time series analysis model. Its storage pool (equivalent to the hidden layer of the traditional neural network) is cyclically connected to enable it to have a certain "memory" capability. The temporal relationship of time series data can be fitted well. Because of the large number of nodes in the echo state network savings pool, when it is used to fit the noisy data, it is easy to cause over-fitting, which affects the prediction ability of the model. In the traditional ESN model, the performance of randomly generating the ESN input layer from the input layer to the savings pool is dependent on this randomness, which leads to its instability. In order to obtain a suitable ESNs, it is usually necessary to generate them at random until the appropriate models are generated. The traditional method can not guarantee that the newly generated ESN is superior to the previous ones. Based on the above disadvantages of echo state network, this paper proposes a multi-objective Diversified Echo State network named Multi-objective Diversified Echo State Network / MODESN which defines ESN diversity by considering the redundancy between nodes in the storage pool. In order to avoid overfitting as far as possible. MODESN optimizes the diversity and prediction accuracy of ESN using multi-objective genetic algorithm at the same time, so that the newly generated ESN model evolves in the desired direction. Thus, the randomness of the traditional ESN generation method is avoided. The main work of this paper can be summarized as follows: 1) this paper defines the diversity of ESN, optimizes the structure of ESN by optimizing the diversity of ESN, and avoids overfitting. 2) this paper improves a multi-objective genetic algorithm. In this paper, we combine the Japanese candle chart technology with the MODESN model to reduce the number of features and avoid the introduction of unnecessary noise by optimizing the diversity and prediction accuracy of ESN at the same time, and standardizing the evolution direction of ESN.
【學(xué)位授予單位】：中國(guó)科學(xué)技術(shù)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：O211.61

【參考文獻(xiàn)】

相關(guān)期刊論文 前3條

1 張屹;盧超;張虎;方子帆;;基于差分元胞多目標(biāo)遺傳算法的車間布局優(yōu)化[J];計(jì)算機(jī)集成制造系統(tǒng);2013年04期

2 尹安東;趙韓;楊亞娟;馮瑞;;多目標(biāo)遺傳算法的混合動(dòng)力傳動(dòng)系參數(shù)優(yōu)化[J];中國(guó)機(jī)械工程;2013年04期

3 李楠;王明輝;馬書根;李斌;王越超;;基于多目標(biāo)遺傳算法的水陸兩棲可變形機(jī)器人結(jié)構(gòu)參數(shù)設(shè)計(jì)方法[J];機(jī)械工程學(xué)報(bào);2012年17期

，

本文編號(hào)：1851691