本文選題：信任函數(shù)理論　切入點：認(rèn)知不確定性　出處：《中國科學(xué)技術(shù)大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

【摘要】：隨著科學(xué)技術(shù)的不斷發(fā)展,越來越多的信息涌入人類的生產(chǎn)生活中,與此同時夾雜在其中的不確定信息也日漸增多,如何從這些龐大而復(fù)雜的數(shù)據(jù)中獲取有效信息成為了信息技術(shù)發(fā)展中的一項巨大挑戰(zhàn)。尤其在模式識別問題中,不確定數(shù)據(jù)的增加大大提升了解決問題的難度。例如在機(jī)器學(xué)習(xí)領(lǐng)域中,手寫數(shù)字識別作為熱門話題一直受到廣泛關(guān)注。在該問題中,研究者們可以獲得大量的數(shù)據(jù)信息作為訓(xùn)練樣本,而這其中的大部分?jǐn)?shù)據(jù)都由于存在著不精確、不可靠等情況而具有或多或少的認(rèn)知不確定性。工程實踐中解決此問題的辦法多是通過對訓(xùn)練樣本進(jìn)行人工標(biāo)注的方式來獲取精確訓(xùn)練集,然而無論是類標(biāo)的手動添加亦或是待標(biāo)注樣本的選擇都需要人工參與,人力成本會隨著數(shù)據(jù)的增加而增多。如何有效處理不確定信息以及應(yīng)用不確定信息完成分類器的學(xué)習(xí)與構(gòu)建成為眾多研究者亟待解決的難題。信任函數(shù)理論憑借其可以靈活處理多種不確定性的出眾能力,近些年來受到了廣泛的關(guān)注,在工程、醫(yī)學(xué)等眾多方面得到了廣泛的應(yīng)用。與傳統(tǒng)的信息融合、證據(jù)推理方向不同,2008年信任函數(shù)在統(tǒng)計推斷方向上的應(yīng)用為信任函數(shù)理論的研究帶來了更廣闊的方向。在此基礎(chǔ)上,一部分研究者率先進(jìn)行了該理論與機(jī)器學(xué)習(xí)方法的結(jié)合,打破了該領(lǐng)域的空白,并取得了不錯的成果。本文在前人的足跡上繼續(xù)前行,將信任分類樹與Bagging集成算法相結(jié)合,通過質(zhì)量函數(shù)完成對認(rèn)知不確定的建模,并通過集成一系列結(jié)構(gòu)簡單的信任分類樹得到最終的集成分類器。其中,作為基分類器的信任分類樹是在輸出含有不確定的樣本上直接訓(xùn)練得出的。與此同時,考慮到當(dāng)下大部分不確定分類算法均未涉及實際應(yīng)用,本文分別應(yīng)用提出的BGBC4.5算法與其他常用不確定分類算法完成不確定手寫數(shù)字識別問題,并取得了滿意的識別精度。文章直接在輸出含有大量認(rèn)知不確定性的訓(xùn)練集上完成分類器訓(xùn)練,分析討論算法數(shù)據(jù)質(zhì)量及幾種不確定程度變化下的表現(xiàn)結(jié)果以及與其他常用分類算法表現(xiàn)的對比,分析了各個算法的優(yōu)劣性、驗證了算法的優(yōu)越性。
[Abstract]:With the continuous development of science and technology, more and more information flows into the production and life of human beings, and at the same time, the amount of uncertain information mixed with it is increasing day by day. How to obtain effective information from these huge and complex data has become a great challenge in the development of information technology, especially in the problem of pattern recognition. The increase in uncertain data greatly increases the difficulty of solving problems. For example, in the field of machine learning, handwritten numeral recognition has been a hot topic. Researchers can get a lot of data as training samples, and most of this data is due to inaccuracy. The methods to solve this problem in engineering practice are to obtain the accurate training set by manually marking the training sample. However, both the manual addition of the class mark and the selection of the sample to be tagged require manual participation. Human cost will increase with the increase of data. How to deal with uncertain information effectively and how to use uncertain information to complete the learning and construction of classifier has become a difficult problem to be solved by many researchers. Trust function theory depends on the theory of trust function. Its superior ability to deal with a variety of uncertainties flexibly, In recent years has received extensive attention, in engineering, medicine and many other aspects of a wide range of applications. And traditional information fusion, In 2008, the application of trust function in statistical inference direction has brought a broader direction for the research of trust function theory. On this basis, some researchers have taken the lead in combining this theory with machine learning methods. It breaks the blank in this field and has achieved good results. In this paper, the trust classification tree is combined with the Bagging ensemble algorithm to build the model of cognitive uncertainty through the quality function. The final ensemble classifier is obtained by integrating a series of simple trust classification trees, in which the trust classification tree, which is used as the base classifier, is trained directly on the output samples with uncertainty. At the same time, Considering that most of the current uncertain classification algorithms do not involve practical applications, this paper uses the proposed BGBC4.5 algorithm and other commonly used uncertain classification algorithms to complete the problem of uncertain handwritten numeral recognition. In this paper, the classifier is trained directly on the output training set with a large amount of cognitive uncertainty. The performance of algorithm data quality and some uncertain degree are analyzed and compared with other common classification algorithms. The advantages and disadvantages of each algorithm are analyzed and the superiority of the algorithm is verified.
【學(xué)位授予單位】：中國科學(xué)技術(shù)大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP391.4

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 杜元偉;劉靜;龍銀才;;基于證據(jù)理論的前景構(gòu)建方法[J];控制與決策;2015年04期

2 胡玲琳;張若男;李培年;王仁芳;;手寫數(shù)字體自動識別技術(shù)的研究現(xiàn)狀[J];浙江萬里學(xué)院學(xué)報;2015年02期

3 王璇;薛瑞;;基于BP神經(jīng)網(wǎng)絡(luò)的手寫數(shù)字識別的算法[J];自動化技術(shù)與應(yīng)用;2014年05期

4 李靖平;;基于BP神經(jīng)網(wǎng)絡(luò)的手寫數(shù)字識別系統(tǒng)[J];佛山科學(xué)技術(shù)學(xué)院學(xué)報(自然科學(xué)版);2014年03期

5 劉希亮;陳桂明;李方溪;張倩;;基于改進(jìn)證據(jù)理論的齒輪泵故障診斷方法研究[J];機(jī)械科學(xué)與技術(shù);2014年02期

6 楊藝;韓德強(qiáng);韓崇昭;;基于多準(zhǔn)則排序融合的證據(jù)組合方法[J];自動化學(xué)報;2012年05期

7 ;Some notes on betting commitment distance in evidence theory[J];Science China(Information Sciences);2012年03期

8 李鵬;劉思峰;;基于灰色關(guān)聯(lián)分析和D-S證據(jù)理論的區(qū)間直覺模糊決策方法[J];自動化學(xué)報;2011年08期

9 韓德強(qiáng);韓崇昭;鄧勇;楊藝;;基于證據(jù)方差的加權(quán)證據(jù)組合[J];電子學(xué)報;2011年S1期

10 郭曉永;王相軍;;一種基于SNMP的網(wǎng)絡(luò)拓?fù)浒l(fā)現(xiàn)算法[J];重慶工商大學(xué)學(xué)報(自然科學(xué)版);2011年01期

相關(guān)博士學(xué)位論文 前2條

1 馬荔瑤;信任函數(shù)建模的認(rèn)知不確定性數(shù)據(jù)分析與學(xué)習(xí)[D];中國科學(xué)技術(shù)大學(xué);2016年

2 梁偉光;基于證據(jù)理論的在軌航天器故障診斷方法研究[D];中國科學(xué)技術(shù)大學(xué);2011年

相關(guān)碩士學(xué)位論文 前1條

1 張學(xué)海;車牌字符分割方法研究與實現(xiàn)[D];西南交通大學(xué);2010年

，

本文編號：1638885