本文選題：粒子群算法 + 數(shù)據(jù)分析　； 參考：《廣東工業(yè)大學(xué)》2017年碩士論文

【摘要】：最優(yōu)化方法是研究給定約束條件下如何使某一(或某些)指標(biāo)達(dá)到最優(yōu)的一門學(xué)科,而優(yōu)化算法研究一直是該領(lǐng)域研究的關(guān)鍵問題.粒子群算法是優(yōu)化算法中一個(gè)參數(shù)簡單且效果出眾的算法,它結(jié)合個(gè)體學(xué)習(xí)經(jīng)驗(yàn)和社會經(jīng)驗(yàn)調(diào)整粒子的進(jìn)化方向,從而獲得最優(yōu)解.在互聯(lián)網(wǎng)快速發(fā)展的今天,每天產(chǎn)生的數(shù)據(jù)量急速增加,數(shù)據(jù)規(guī)模從TB躍升到PB甚至EB;數(shù)據(jù)類型多且數(shù)據(jù)結(jié)構(gòu)復(fù)雜,處理難度增加.目前大數(shù)據(jù)的處理和分析技術(shù)越來越受到政府和企業(yè)的關(guān)注.而大多數(shù)數(shù)據(jù)挖掘算法的本質(zhì)基本上都是建立優(yōu)化模型,并用最優(yōu)化方法對目標(biāo)函數(shù)(或損失函數(shù))進(jìn)行優(yōu)化,以確定最優(yōu)解.本文對優(yōu)化算法進(jìn)行研究,針對粒子群算法容易早熟收斂和陷入局部最優(yōu)解的問題,提出一種改進(jìn)的粒子群算法.并將改進(jìn)后的粒子群算法應(yīng)用到K-means聚類算法與大數(shù)據(jù)處理平臺應(yīng)用中.本文的主要工作如下:首先針對粒子群算法容易早熟收斂和陷入局部最優(yōu)解的缺點(diǎn),利用遠(yuǎn)離個(gè)體最差經(jīng)驗(yàn)和最差群體經(jīng)驗(yàn),提出一種遠(yuǎn)離最差解的粒子群算法,并進(jìn)行了仿真實(shí)驗(yàn),驗(yàn)證算法具有良好的全局收斂性.其次將改進(jìn)后的粒子群算法并行化在Spark集群上編程實(shí)現(xiàn).Spark平臺是目前應(yīng)用最廣的大數(shù)據(jù)分析平臺,支持Java、Scala、Python和R等多種語言,能夠無縫結(jié)合Hadoop平臺等.最后將改進(jìn)后的粒子群算法應(yīng)用到K-means聚類算法中,對Iris和Wine數(shù)據(jù)集進(jìn)行了仿真實(shí)驗(yàn),實(shí)驗(yàn)結(jié)果較好,并將其應(yīng)用到電信定位樓群中,對所得到的所屬樓群用戶MR信息進(jìn)行聚類,聚類后提取簇間無線基站接入特征作為學(xué)習(xí)特征,以期后來無線接入特征相同或相似的MR定位到所屬樓宇.
[Abstract]:Optimization method is a discipline to study how to achieve the optimal performance of one or some indexes under a given constraint condition, and the research of optimization algorithm has always been the key problem in this field. Particle swarm optimization (PSO) is an algorithm with simple parameters and excellent effect. It adjusts the evolutionary direction of particles by combining individual learning experience and social experience to obtain the optimal solution. With the rapid development of Internet, the amount of data generated every day increases rapidly, the scale of data leaps from TB to PB or even EB.There are many types of data and complicated data structure, which makes processing more difficult. At present, the processing and analysis technology of big data is paid more and more attention by the government and enterprises. The essence of most data mining algorithms is to establish the optimization model and optimize the objective function (or loss function) with the optimization method to determine the optimal solution. In this paper, the optimization algorithm is studied, and an improved particle swarm optimization algorithm is proposed to solve the problem that particle swarm optimization is easy to converge prematurely and fall into local optimal solution. The improved particle swarm optimization algorithm is applied to K-means clustering algorithm and big data processing platform. The main work of this paper is as follows: firstly, aiming at the shortcomings of particle swarm optimization (PSO), which is easy to converge prematurely and fall into local optimal solution, a particle swarm optimization algorithm is proposed, which is far from the worst individual experience and the worst group experience. The simulation results show that the algorithm has good global convergence. Secondly, the improved particle swarm optimization algorithm is parallelized on Spark cluster to realize the Spark platform, which is the most widely used big data analysis platform at present. It supports Java Scala Python, R and other languages, and can seamlessly combine Hadoop platform and so on. Finally, the improved particle swarm optimization algorithm is applied to the K-means clustering algorithm, and the simulation experiments on the Iris and Wine data sets are carried out. The experimental results are good, and the improved PSO algorithm is applied to the telecom location-oriented buildings. After clustering, the access feature of wireless base station between clusters is extracted as the learning feature, so that the Mr with the same or similar wireless access features can be located to the building later.
【學(xué)位授予單位】：廣東工業(yè)大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP18;TP311.13

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 馬勝藍(lán);葉東毅;楊玲玲;;一種新的粒子群拓?fù)湓O(shè)計(jì)準(zhǔn)則[J];計(jì)算機(jī)工程;2015年01期

2 趙志剛;黃樹運(yùn);王偉倩;;基于隨機(jī)慣性權(quán)重的簡化粒子群優(yōu)化算法[J];計(jì)算機(jī)應(yīng)用研究;2014年02期

3 石松;陳云;;層次環(huán)形拓?fù)浣Y(jié)構(gòu)的動態(tài)粒子群算法[J];計(jì)算機(jī)工程與應(yīng)用;2013年08期

4 王千;王成;馮振元;葉金鳳;;K-means聚類算法研究綜述[J];電子設(shè)計(jì)工程;2012年07期

5 吳正娟;職為梅;楊勇;范明;;并行化的粒子群技術(shù)[J];微計(jì)算機(jī)信息;2009年36期

6 任鳳鳴;李麗娟;;改進(jìn)的PSO算法中學(xué)習(xí)因子(c_1,c_2)取值的實(shí)驗(yàn)與分析[J];廣東工業(yè)大學(xué)學(xué)報(bào);2008年01期

7 孫吉貴;劉杰;趙連宇;;聚類算法研究[J];軟件學(xué)報(bào);2008年01期

8 方峻;唐普英;任誠;;一種基于加權(quán)有向拓?fù)涞母倪M(jìn)粒子群算法[J];計(jì)算機(jī)技術(shù)與發(fā)展;2006年08期

9 張選平,杜玉平,秦國強(qiáng),覃征;一種動態(tài)改變慣性權(quán)的自適應(yīng)粒子群算法[J];西安交通大學(xué)學(xué)報(bào);2005年10期

10 王華秋,曹長修;基于模擬退火的并行粒子群優(yōu)化研究[J];控制與決策;2005年05期

相關(guān)博士學(xué)位論文 前1條

1 李曉磊;一種新型的智能優(yōu)化方法-人工魚群算法[D];浙江大學(xué);2003年

相關(guān)碩士學(xué)位論文 前3條

1 馬紅偉;粒子群算法改進(jìn)及其在數(shù)據(jù)挖掘中的應(yīng)用研究[D];山東師范大學(xué);2014年

2 馮琳;集群計(jì)算引擎Spark中的內(nèi)存優(yōu)化研究與實(shí)現(xiàn)[D];清華大學(xué);2013年

3 楊康;基于DNS訪問記錄挖掘的用戶群劃分[D];南京郵電大學(xué);2013年

，

本文編號：1924848