發(fā)布時(shí)間：2019-05-24 21:46

【摘要】：中醫(yī)量表中根據(jù)各癥狀對(duì)相應(yīng)的證型作出預(yù)測(cè)本身是個(gè)典型的多標(biāo)簽分類技術(shù)。故本文研究思路是將中醫(yī)量表中各癥狀作為特征屬性,每個(gè)量表對(duì)應(yīng)的證型作為標(biāo)簽,癥狀到證型的推斷將通過(guò)多標(biāo)簽分類算法得到。我們應(yīng)用修正前的帕金森數(shù)據(jù),主要工作如下:1)為了解決提出了 Classifier Chains(CC)算法中標(biāo)簽順序鏈中存在的隨機(jī)性對(duì)分類準(zhǔn)確率的影響,我們提出一個(gè)基于CC思想的多標(biāo)簽分類優(yōu)化算法Entropy based Classifier Chains(ECC),該算法計(jì)算出一個(gè)優(yōu)良標(biāo)簽預(yù)測(cè)鏈,以此討論帕金森證型之間的相關(guān)性。ECC認(rèn)為標(biāo)簽的信息熵值越小,不確定性越小,則標(biāo)簽被正確預(yù)測(cè)的概率就越大,因此首先計(jì)算出各標(biāo)簽的信息熵值并選擇具有最小值的標(biāo)簽作為鏈?zhǔn)讟?biāo)簽。然后從該標(biāo)簽開(kāi)始構(gòu)建最小權(quán)重標(biāo)簽樹(shù),最后遍歷該樹(shù)結(jié)點(diǎn)形成最終標(biāo)簽預(yù)測(cè)鏈并應(yīng)用于CC模型。2)在ECC的基礎(chǔ)上加上約瑟夫環(huán)機(jī)制,提出了一個(gè)新的算法Josephus based Classifier Chains(JCC)。JCC認(rèn)為ECC形成的標(biāo)簽預(yù)測(cè)鏈并非全局有序,標(biāo)簽之間基于相關(guān)性的排序仍然存在一定的隨機(jī)性,需要借助約瑟夫環(huán)機(jī)制最大程度地降低該隨機(jī)性。3)在JCC的基礎(chǔ)上加上了一個(gè)基于懲罰機(jī)制的動(dòng)態(tài)報(bào)數(shù)方法,提出一種新的多標(biāo)簽分類算法PeNalty based Classifier Chains(PNCC)。該算法考慮到JCC對(duì)ECC產(chǎn)生的標(biāo)簽預(yù)測(cè)鏈中隨機(jī)性的降低程度有限,通過(guò)一種懲罰機(jī)制進(jìn)一步降低隨機(jī)性,并產(chǎn)生最終的標(biāo)簽預(yù)測(cè)鏈應(yīng)用到CC模型中。實(shí)驗(yàn)證明,以上三種算法均可以挖掘出一些帕金森數(shù)據(jù)集的有用信息,對(duì)于其他數(shù)據(jù)集亦有優(yōu)良的準(zhǔn)確率表現(xiàn)。
[Abstract]:It is a typical multi-label classification technique to predict the corresponding syndrome types according to each symptom in the scale of traditional Chinese medicine (TCM). Therefore, the idea of this paper is to take each symptom in the TCM scale as the characteristic attribute, and the syndrome type corresponding to each scale as the label, and the inference from the symptom to the syndrome type will be obtained by the multi-label classification algorithm. Using the modified Parkinson's data, the main work is as follows: 1) in order to solve the influence of randomness in the label sequence chain in the Classifier Chains (CC) algorithm on the classification accuracy, We propose a multi-label classification optimization algorithm based on CC, which calculates an excellent label prediction chain and discusses the correlation between Parkinson's syndrome types. The smaller the uncertainty is, the greater the probability that the label will be predicted correctly. Therefore, the information entropy value of each label is calculated and the label with the minimum value is selected as the chain head label. Then the minimum weight label tree is constructed from the tag, and finally the node of the tree is traversed to form the final label prediction chain and applied to the CC model. 2) on the basis of ECC, the Joseph ring mechanism is added. In this paper, a new algorithm, Josephus based Classifier Chains (JCC). JCC, is proposed, which holds that the label prediction chain formed by ECC is not globally ordered, and there is still a certain randomness in the ranking based on correlation between tags. It is necessary to minimize the randomness with the help of Joseph ring mechanism. 3) on the basis of JCC, a dynamic report method based on penalty mechanism is added, and a new multi-label classification algorithm PeNalty based Classifier Chains (PNCC). Is proposed. The algorithm takes into account the limited degree of reduction of randomness in the label prediction chain generated by JCC to ECC, further reduces the randomness through a punishment mechanism, and produces the final label prediction chain to be applied to the CC model. The experimental results show that the above three algorithms can mine some useful information of Parkinson's dataset, and also have excellent accuracy performance for other datasets.
【學(xué)位授予單位】：南京大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：R742.5;TP311.13

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 劉各巧;郭濤;;基于雙層結(jié)構(gòu)的多標(biāo)簽優(yōu)序選擇分類算法[J];計(jì)算機(jī)工程與設(shè)計(jì);2016年04期

2 劉卓然;胡楊;劉驪;馮旭鵬;劉利軍;黃青松;;基于標(biāo)簽相似度的不良信息多標(biāo)簽分類方法[J];計(jì)算機(jī)應(yīng)用研究;2016年04期

3 王洋;曹迎槐;;約瑟夫環(huán)在加密算法中應(yīng)用[J];電子制作;2015年11期

4 張?chǎng)?陳波;徐濤;沈國(guó)理;俞鉆;;基于貝葉斯網(wǎng)絡(luò)的肺癌證候研究[J];中國(guó)中醫(yī)藥科技;2014年06期

5 何穎婧;王志海;李哲;;基于標(biāo)記集合劃分的多標(biāo)記分類算法[J];昆明理工大學(xué)學(xué)報(bào)(自然科學(xué)版);2014年03期

6 王霄;周李威;陳耿;朱玉全;;一種基于標(biāo)簽相關(guān)性的多標(biāo)簽分類算法[J];計(jì)算機(jī)應(yīng)用研究;2014年09期

7 李思男;李寧;李戰(zhàn)懷;;多標(biāo)簽數(shù)據(jù)挖掘技術(shù):研究綜述[J];計(jì)算機(jī)科學(xué);2013年04期

8 白宇;;約瑟夫環(huán)次序解的鏈表模算法[J];山西大同大學(xué)學(xué)報(bào)(自然科學(xué)版);2013年01期

9 方媛;車啟鳳;;數(shù)據(jù)挖掘之聚類算法綜述[J];河西學(xué)院學(xué)報(bào);2012年05期

10 付彬;王志海;;基于樹(shù)型依賴結(jié)構(gòu)的多標(biāo)記分類算法[J];模式識(shí)別與人工智能;2012年04期

，

本文編號(hào)：2485207