本文選題：BP神經(jīng)網(wǎng)絡(luò)　切入點(diǎn)：因子分析　出處：《云南大學(xué)》2015年碩士論文　論文類型：學(xué)位論文

【摘要】：綜合評(píng)價(jià)在社會(huì)經(jīng)濟(jì)各個(gè)領(lǐng)域有著廣泛應(yīng)用,經(jīng)過多年的研究,逐漸形成了多種評(píng)價(jià)方法,每種方法有各自的優(yōu)點(diǎn)和缺陷,因此,一直處于不斷改進(jìn)和完善的過程中。近些年來,隨著網(wǎng)絡(luò)的廣泛應(yīng)用和發(fā)展,數(shù)據(jù)信息量日益增大,對(duì)綜合評(píng)價(jià)方法的發(fā)展提出了新的要求,因此對(duì)多指標(biāo)綜合評(píng)價(jià)方法的研究更加有實(shí)際意義。 近年來比較流行的人工神經(jīng)網(wǎng)絡(luò)法,以其獨(dú)特的分布式處理能力、非線性處理能力、自學(xué)功能和容錯(cuò)性等成為了解決復(fù)雜且難以建模問題的強(qiáng)有力工具。通過對(duì)數(shù)據(jù)的多次訓(xùn)練,在輸出結(jié)果中直接對(duì)變量進(jìn)行等級(jí)(類別)判定。在一定程度上彌補(bǔ)了以前許多方法過于依賴主觀判斷或客觀特定數(shù)據(jù)的不足,成為目前被廣泛應(yīng)用的一種綜合評(píng)價(jià)方法。當(dāng)指標(biāo)過多時(shí),為了提高網(wǎng)絡(luò)的學(xué)習(xí)能力,加快處理問題的速度以及增加評(píng)價(jià)結(jié)果的可靠性,需要對(duì)網(wǎng)絡(luò)模型進(jìn)行簡化,可以配合統(tǒng)計(jì)方法對(duì)多指標(biāo)進(jìn)行有效降維,這樣可以縮小神經(jīng)網(wǎng)絡(luò)模型在處理較多指標(biāo)時(shí)的結(jié)果偏差,使評(píng)價(jià)結(jié)果更加可靠。 將因子分析引入BP神經(jīng)網(wǎng)絡(luò)模型進(jìn)行BP神經(jīng)網(wǎng)絡(luò)綜合評(píng)價(jià)方法的改進(jìn)研究是本論文的主旨,具體的思路是先采用因子分析法將多指標(biāo)進(jìn)行降維,再運(yùn)用BP神經(jīng)網(wǎng)絡(luò)模型進(jìn)行綜合評(píng)價(jià),將該模型應(yīng)用到環(huán)境空氣質(zhì)量的實(shí)證評(píng)價(jià)中,以國家2012年環(huán)境空氣質(zhì)量新標(biāo)準(zhǔn)中提出的AQI法為評(píng)價(jià)參考,經(jīng)過試驗(yàn),驗(yàn)證了因子分析-BP神經(jīng)網(wǎng)絡(luò)相融合的多指標(biāo)綜合評(píng)價(jià)模型在環(huán)境空氣質(zhì)量評(píng)價(jià)中具有實(shí)用性和可行性。同時(shí),通過與單純使用神經(jīng)網(wǎng)絡(luò)模型作對(duì)比,進(jìn)一步驗(yàn)證了該方法的有效性。并且,該模型還可以進(jìn)一步拓展應(yīng)用到其他領(lǐng)域的類似多指標(biāo)綜合評(píng)價(jià)研究中。
[Abstract]:Comprehensive evaluation has been widely used in various fields of social economy. After many years of research, various evaluation methods have been gradually formed, each method has its own advantages and disadvantages, therefore, In recent years, with the extensive application and development of the network, the amount of data information is increasing day by day, which puts forward new requirements for the development of comprehensive evaluation method. Therefore, the study of multi-index comprehensive evaluation method has more practical significance. In recent years, artificial neural network (Ann), which is popular in recent years, has its unique distributed processing ability and nonlinear processing ability. Self-learning and fault tolerance have become powerful tools for solving complex and difficult modeling problems. To a certain extent, it makes up for the deficiency of many previous methods that rely too much on subjective judgment or objective and specific data. In order to improve the learning ability of network, accelerate the speed of processing problems and increase the reliability of evaluation results, the network model should be simplified. It is possible to reduce the dimension of multiple indexes effectively with statistical methods, which can reduce the deviation of the results of the neural network model in dealing with more than one index, and make the evaluation results more reliable. It is the main idea of this paper to introduce factor analysis into BP neural network model to improve the comprehensive evaluation method of BP neural network. Then the BP neural network model is used for comprehensive evaluation, and the model is applied to the empirical evaluation of ambient air quality. The AQI method proposed in the new national standards for ambient air quality in 2012 is used as a reference for the evaluation. The feasibility and practicability of the multi-index comprehensive evaluation model based on factor analysis and BP neural network fusion in the assessment of ambient air quality are verified. At the same time, the model is compared with the neural network model. The validity of the proposed method is further verified. Furthermore, the model can be further extended to other fields of similar multi-index comprehensive evaluation research.
【學(xué)位授予單位】：云南大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2015
【分類號(hào)】：X823

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 張虹冕;孫世群;;基于BP神經(jīng)網(wǎng)絡(luò)的大氣環(huán)境質(zhì)量評(píng)價(jià)模型[J];安徽農(nóng)業(yè)科學(xué);2010年31期

2 邱東;多指標(biāo)綜合評(píng)價(jià)方法的系統(tǒng)分析[J];財(cái)經(jīng)問題研究;1988年09期

3 陳其坤,林元慶;基于粗糙集和模糊聚類的評(píng)價(jià)方法研究[J];福建行政學(xué)院福建經(jīng)濟(jì)管理干部學(xué)院學(xué)報(bào);2005年04期

4 徐濟(jì)超;劉玉敏;南斌;;多指標(biāo)綜合評(píng)價(jià)的統(tǒng)計(jì)理論及其方法(Ⅰ)[J];管理工程學(xué)報(bào);1993年03期

5 亢永;;室內(nèi)空氣品質(zhì)評(píng)價(jià)的集對(duì)分析方法[J];工業(yè)安全與環(huán)保;2009年10期

6 王淑琴;王立志;單春榮;;多指標(biāo)綜合評(píng)價(jià)方法研究[J];河北機(jī)電學(xué)院學(xué)報(bào);1994年04期

7 鄭成德;大氣環(huán)境質(zhì)量的人工神經(jīng)網(wǎng)絡(luò)決策模型[J];環(huán)境科學(xué)進(jìn)展;1999年01期

8 楊立民,許有鵬;改進(jìn)遺傳神經(jīng)網(wǎng)絡(luò)方法在大氣環(huán)境質(zhì)量評(píng)價(jià)中的應(yīng)用[J];環(huán)境科學(xué)研究;1999年02期

9 孫修東,李宗斌,陳富民;基于改進(jìn)BP神經(jīng)網(wǎng)絡(luò)算法的多指標(biāo)綜合評(píng)價(jià)方法的應(yīng)用研究[J];河南機(jī)電高等專科學(xué)校學(xué)報(bào);2003年01期

10 方瑩;;基于粗糙集和BP神經(jīng)網(wǎng)絡(luò)的空氣質(zhì)量評(píng)價(jià)方法[J];河南科學(xué);2010年04期

，

本文編號(hào)：1626550