【摘要】：本文的選題來自遼寧省教育廳人文社會(huì)科學(xué)“移動(dòng)云計(jì)算環(huán)境下基于認(rèn)知模型的高校教學(xué)評(píng)價(jià)與優(yōu)化模型”的項(xiàng)目。研究的出發(fā)點(diǎn)是為了在云計(jì)算環(huán)境下建立行之有效的輔助教學(xué)效果的評(píng)價(jià)模型。本文主要對(duì)其中的學(xué)習(xí)質(zhì)量評(píng)價(jià)方面的問題進(jìn)行深入研究。評(píng)價(jià)系統(tǒng)平臺(tái)的結(jié)構(gòu)設(shè)計(jì)從評(píng)價(jià)系統(tǒng)的工作流程出發(fā),將平臺(tái)分為四個(gè)模塊分別為:數(shù)據(jù)采集模塊、數(shù)據(jù)存儲(chǔ)模塊、數(shù)據(jù)分析模塊和數(shù)據(jù)查詢模塊。通過數(shù)據(jù)采集模塊進(jìn)行數(shù)據(jù)的收集,經(jīng)過數(shù)據(jù)存儲(chǔ)模塊進(jìn)行數(shù)據(jù)存儲(chǔ),為之后的數(shù)據(jù)分析模塊做數(shù)據(jù)準(zhǔn)備,數(shù)據(jù)分析之后,用戶可以通過數(shù)據(jù)查詢模塊查詢?cè)撚脩舻念A(yù)測(cè)結(jié)果。其中最為重要的是數(shù)據(jù)分析模塊,在該模塊中通過改進(jìn)算法的方式使預(yù)測(cè)效果達(dá)到更佳。本研究主要分為兩方面:一方面是調(diào)查問卷題項(xiàng)的選取,另一方面是回歸預(yù)測(cè)的算法優(yōu)化。在進(jìn)行《基于認(rèn)知的學(xué)習(xí)質(zhì)量評(píng)價(jià)調(diào)查問卷》的編制時(shí),從認(rèn)知學(xué)習(xí)理論出發(fā),采用經(jīng)過國際公認(rèn)的《學(xué)習(xí)動(dòng)機(jī)策略問卷》(MSLQ)為基礎(chǔ),并結(jié)合《學(xué)習(xí)質(zhì)量評(píng)價(jià):SOLO分類理論(可觀察的學(xué)習(xí)成果結(jié)構(gòu))》一書修改得來。將首輪獲得的調(diào)查數(shù)據(jù)使用SPSS進(jìn)行效度和信度的檢驗(yàn),剔除掉不適用的題項(xiàng),保留對(duì)學(xué)習(xí)質(zhì)量影響較大的題項(xiàng)。經(jīng)過內(nèi)部一致性的檢驗(yàn)由之前的0.926提升到0.930。說明問卷的可靠性較高,能夠作為基于認(rèn)知的學(xué)習(xí)質(zhì)量評(píng)價(jià)的依據(jù)。用于回歸預(yù)測(cè)的數(shù)據(jù)是通過調(diào)查問卷的再次發(fā)放回收得來。在云計(jì)算平臺(tái)上使用Python語言編寫相應(yīng)的算法,對(duì)數(shù)值型數(shù)據(jù)進(jìn)行回歸預(yù)測(cè)�；貧w預(yù)測(cè)時(shí)將會(huì)面臨兩個(gè)問題,一是欠擬合、二是擴(kuò)展瓶頸。本研究要通過多個(gè)自變量預(yù)測(cè)因變量,所以首先采用多元線性回歸算法預(yù)測(cè)。進(jìn)行回歸預(yù)測(cè)的目的是想得到更佳的預(yù)測(cè)效果,由于多元線性回歸算法確定的回歸模型是要滿足所有樣本的規(guī)律,往往會(huì)把異常點(diǎn)也考慮到模型中,最終得到的模型將會(huì)出現(xiàn)欠擬合的現(xiàn)象。為了能夠提高預(yù)測(cè)效果,改進(jìn)基本算法給局部的點(diǎn)加權(quán),采用局部加權(quán)線性回歸算法提高預(yù)測(cè)的準(zhǔn)確度。隨著研究的深入,數(shù)據(jù)量將會(huì)不斷的激增,在進(jìn)行數(shù)據(jù)分析時(shí)將會(huì)出現(xiàn)擴(kuò)展瓶頸的問題,為了能夠讓改進(jìn)的算法在運(yùn)算速率上有所提升,將局部加權(quán)線性回歸算法進(jìn)行并行化的處理,使其符合MapReduce編程模型的運(yùn)算要求。最后通過數(shù)據(jù)分析得到的復(fù)相關(guān)系數(shù)R和殘差的平方和的大小來確定模型的精度。用戶通過本評(píng)價(jià)系統(tǒng)預(yù)測(cè)學(xué)習(xí)質(zhì)量,便于用戶及時(shí)對(duì)之后的學(xué)習(xí)做合理規(guī)劃。
[Abstract]:The topic of this paper comes from the project of Humanities and Social Sciences of Liaoning Provincial Education Department, "Evaluation and Optimization Model of College Teaching based on Cognitive Model in Mobile Cloud Computing Environment". The starting point of the research is to establish an effective evaluation model of assistant teaching effect in cloud computing environment. This paper mainly studies the problems of learning quality evaluation. Based on the workflow of the evaluation system, the platform is divided into four modules: data acquisition module, data storage module, data analysis module and data query module. Data collection module through the data storage module for the subsequent data analysis module to do data preparation after the data analysis the user can query the user's prediction results through the data query module. The most important one is the data analysis module, in which the prediction effect is better by improving the algorithm. This research is mainly divided into two aspects: on the one hand, the selection of questionnaire items, on the other hand, the optimization of regression prediction algorithm. On the basis of cognitive learning theory and the internationally recognized Learning motivation Strategy questionnaire (MSLQ), a cognitive learning quality evaluation questionnaire was compiled. It is revised by the book Evaluation of Learning quality: SOLO Classification Theory (observable structure of Learning results). SPSS was used to test the validity and reliability of the data obtained in the first round of the survey. The inapplicable items were eliminated and the items that had a great impact on the learning quality were retained. After the internal consistency test from the previous 0.926 to 0. 930. It shows that the reliability of the questionnaire is high and can be used as the basis of cognitive learning quality evaluation. The data used for regression forecasting are recovered through the re-distribution of questionnaires. In the cloud computing platform, Python language is used to program the corresponding algorithm to predict the numerical data. Regression prediction will be faced with two problems, one is under-fitting, the other is expansion bottleneck. In this study, multiple independent variables are used to predict dependent variables, so multivariate linear regression algorithm is first used to predict dependent variables. The purpose of regression prediction is to get better prediction effect. Because the regression model determined by multivariate linear regression algorithm is to satisfy the laws of all samples, the outliers are often taken into account in the model. The resulting model will be underfitted. In order to improve the prediction effect, the local weighted linear regression algorithm is used to improve the accuracy of prediction. With the deepening of the research, the amount of data will continue to surge, and the problem of expansion bottleneck will occur in the analysis of the data, in order to improve the speed of the improved algorithm. The local weighted linear regression algorithm is parallelized to meet the operational requirements of the MapReduce programming model. Finally, the precision of the model is determined by analyzing the complex correlation coefficient R and the squared sum of the residuals. Users predict the learning quality through this evaluation system, which is convenient for users to make reasonable planning for the later learning in time.
【學(xué)位授予單位】：沈陽師范大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：G642.0;O213

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 解峰;;運(yùn)用元認(rèn)知策略提高高職英語專業(yè)學(xué)生學(xué)業(yè)水平——基于語言學(xué)科平臺(tái)的研究[J];山西青年職業(yè)學(xué)院學(xué)報(bào);2016年02期

2 孫麗娜;楊殊;;學(xué)習(xí)質(zhì)量評(píng)價(jià)中數(shù)據(jù)采集系統(tǒng)的設(shè)計(jì)與實(shí)現(xiàn)[J];軟件導(dǎo)刊(教育技術(shù));2016年02期

3 王新剛;孔云峰;;城市住房?jī)r(jià)格局部線性地理加權(quán)回歸分析——以湖北省黃石市為例[J];中國土地科學(xué);2015年03期

4 顏春寧;;局部?jī)?yōu)化加權(quán)回歸算法在電力設(shè)備失效預(yù)測(cè)中的應(yīng)用[J];計(jì)算機(jī)測(cè)量與控制;2014年01期

5 陳學(xué)軍;黃利華;;基于云計(jì)算的義務(wù)教育學(xué)科課程資源共建共享模式[J];中國電化教育;2013年01期

6 張懷南;楊成;;我國云計(jì)算教育應(yīng)用的研究綜述[J];中國遠(yuǎn)程教育;2013年01期

7 趙子云;左明章;鄧果;;基于云計(jì)算的教育信息公共服務(wù)平臺(tái)的構(gòu)建[J];現(xiàn)代教育技術(shù);2012年12期

8 王麗娜;楊亭亭;劉仁坤;;國內(nèi)外高等教育學(xué)習(xí)評(píng)價(jià)現(xiàn)狀研究綜述——兼論對(duì)國家開放大學(xué)學(xué)習(xí)評(píng)價(jià)體系建設(shè)的啟示[J];現(xiàn)代遠(yuǎn)距離教育;2012年02期

9 包文婷;李三福;丁麗;;農(nóng)村小學(xué)生學(xué)習(xí)動(dòng)機(jī)、學(xué)習(xí)態(tài)度及其學(xué)習(xí)質(zhì)量的實(shí)證研究[J];當(dāng)代教育論壇(管理研究);2011年11期

10 張芝萍;曹燕華;鄭棟;俞揚(yáng);;基于AHP應(yīng)用的多元化、開放式高職學(xué)生學(xué)習(xí)質(zhì)量評(píng)價(jià)體系研究[J];浙江師范大學(xué)學(xué)報(bào)(社會(huì)科學(xué)版);2011年06期

相關(guān)博士學(xué)位論文 前1條

1 王文婧;移動(dòng)云計(jì)算的QoE評(píng)價(jià)與優(yōu)化研究[D];北京郵電大學(xué);2013年

相關(guān)碩士學(xué)位論文 前7條

1 萬偉權(quán);放療中腫瘤運(yùn)動(dòng)基于實(shí)時(shí)跟蹤呼吸預(yù)測(cè)的算法研究[D];南方醫(yī)科大學(xué);2015年

2 周章海;基于云計(jì)算理念的職業(yè)教育園區(qū)資源共享研究[D];大連海事大學(xué);2014年

3 李志強(qiáng);云計(jì)算教育服務(wù)平臺(tái)模型分析和應(yīng)用研究[D];廣東技術(shù)師范學(xué)院;2013年

4 鄧麗博;高中學(xué)生立體幾何學(xué)習(xí)質(zhì)量評(píng)價(jià)研究[D];湖南師范大學(xué);2013年

5 杜玲玲;基于MapReduce的數(shù)據(jù)挖掘算法研究與應(yīng)用[D];桂林電子科技大學(xué);2012年

6 黃靜;初中生數(shù)學(xué)學(xué)習(xí)興趣、自我效能感、學(xué)業(yè)情緒與數(shù)學(xué)學(xué)業(yè)成績(jī)的關(guān)系研究[D];四川師范大學(xué);2012年

7 姜文;基于Hadoop平臺(tái)的數(shù)據(jù)分析和應(yīng)用[D];北京郵電大學(xué);2011年

，

本文編號(hào)：2269694