本文選題：JM雙層模型 + 醫(yī)療主訴文本��； 參考：《北京郵電大學(xué)》2015年碩士論文

【摘要】：在醫(yī)療數(shù)據(jù)中挖掘有價值信息是一個亟待解決的問題。隨著醫(yī)療領(lǐng)域文本數(shù)據(jù)的累積,其中蘊含價值不可估量,對知識發(fā)現(xiàn)工具需求日益強(qiáng)烈。此外,就患者而言,有遠(yuǎn)程自助導(dǎo)診的需求。為解決以上問題,本文將Bayes分類技術(shù)應(yīng)用于醫(yī)療導(dǎo)診中,并針對醫(yī)療文本特征提出優(yōu)化模型。 本文提出基于Jelinek-Mercer (JM)的雙層Bayes分類模型。醫(yī)療文本具有類別區(qū)分不明顯、缺乏大規(guī)模訓(xùn)練集、某些低頻詞具有高判別性、多層級等特征,JM雙層模型利用JM平滑技術(shù)解決訓(xùn)練集不完備的問題,并針對文本多層級特征,構(gòu)建雙層模型,提高分類精度。 基于JM雙層模型的理論分析,本文完成實驗平臺搭建,用JAVA語言實現(xiàn)了伯努利和多項式兩種Bayes分類器,并分別完成雙層模型構(gòu)建,最后在雙層模型基礎(chǔ)上引入JM平滑模塊。 實驗結(jié)果表明,雙層伯努利和多項式模型的分類準(zhǔn)確率分別為0.894和0.903,較單層模型分別提高7.84%和6.61%。在雙層模型基礎(chǔ)上引入JM平滑模塊后,精度有進(jìn)一步提升,伯努利和多項式準(zhǔn)確率分別為0.905和0.912。實驗中精度最高的是基于JM的雙層多項式Bayes模型。 最后,將分類精度達(dá)0.912的分類器應(yīng)用于導(dǎo)診系統(tǒng)中,完成導(dǎo)診應(yīng)用系統(tǒng)的設(shè)計和實現(xiàn)�；颊呖梢酝ㄟ^遠(yuǎn)程輸入主訴癥狀,進(jìn)行自助導(dǎo)診。利用JM雙層多項式Bayes分類器進(jìn)行疾病類別判定,完成改進(jìn)的貝葉斯分類模型在醫(yī)療導(dǎo)診領(lǐng)域的應(yīng)用研究。
[Abstract]:Mining valuable information in medical data is an urgent problem. With the accumulation of text data in the medical field, there is an inestimable value and an increasing demand for knowledge discovery tools. In addition, for patients, there is a need for remote self-help guidance. In order to solve the problem, this paper applies Bayes classification technology to medical treatment. In the guidance, we propose an optimization model for medical texts.
In this paper, a two-layer Bayes classification model based on Jelinek-Mercer (JM) is proposed. The medical text has no obvious classification, a lack of large-scale training set, some low-frequency words have high discriminability, multilayer and so on. The JM double layer model uses JM smoothing technology to solve the problem of incomplete training set, and constructs a double layer model for the multi-layer features of the text. To improve the classification accuracy.
Based on the theoretical analysis of the JM double layer model, this paper completes the experiment platform and implements the two Bayes classifiers of Bernoulli and polynomial in JAVA language, and constructs the double layer model respectively. Finally, the JM smooth module is introduced on the basis of the double layer model.
The experimental results show that the classification accuracy of the double Bernoulli and the polynomial model is 0.894 and 0.903 respectively. The accuracy is further improved after the JM smoothing module is introduced on the basis of the double layer model by 7.84% and 6.61%. respectively. The accuracy of the Bernoulli and polynomial accuracy is the highest in the JM experiment. Bilevel polynomial Bayes model.
Finally, the classifier with the classification accuracy of 0.912 is applied to the guidance system to complete the design and implementation of the guidance application system. The patient can carry on the self-guidance through the remote input of the main complaint symptoms. The JM double decker polynomial Bayes classifier is used to determine the disease category, and the improved Bias classification model in the medical guidance field should be completed. Use research.

【學(xué)位授予單位】：北京郵電大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2015
【分類號】：R44;TP391.1

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 羅森林;劉盈盈;馮揚;韓磊;陳功;王倩;;BFS-CTC漢語句義結(jié)構(gòu)標(biāo)注語料庫構(gòu)建方法[J];北京理工大學(xué)學(xué)報;2012年03期

2 孫健,王偉,鐘義信;基于K-最近距離的自動文本分類的研究[J];北京郵電大學(xué)學(xué)報;2001年01期

3 胡佳妮,徐蔚然,郭軍,鄧偉洪;中文文本分類中的特征選擇算法研究[J];光通信研究;2005年03期

4 李雪蕾,張冬茉;一種基于向量空間模型的文本分類方法[J];計算機(jī)工程;2003年17期

5 胡碧松;馮丹;曹務(wù)春;方立群;龔建華;;基于貝葉斯算法的移動式疾病智能診斷系統(tǒng)[J];計算機(jī)應(yīng)用;2008年S1期

6 代雪蓮;陳正偉;;基于粗糙集和遺傳算法的醫(yī)療診斷方法研究[J];計算機(jī)與數(shù)字工程;2009年10期

7 林關(guān)成;;基于最大匹配算法的中文分詞模型改進(jìn)[J];科技信息(學(xué)術(shù)研究);2008年36期

8 毛偉;徐蔚然;郭軍;;基于n-gram語言模型和鏈狀樸素貝葉斯分類器的中文文本分類系統(tǒng)[J];中文信息學(xué)報;2006年03期

9 鄭霖;徐德華;;基于改進(jìn)TFIDF算法的文本分類研究[J];計算機(jī)與現(xiàn)代化;2014年09期

10 林士敏,王雙成,陸玉昌;Bayesian方法的計算學(xué)習(xí)機(jī)制和問題求解[J];清華大學(xué)學(xué)報(自然科學(xué)版);2000年09期

，

本文編號：1842951