本文選題：大數(shù)據(jù) + 基于基準(zhǔn)點(diǎn)特征　； 參考：《華中科技大學(xué)》2016年碩士論文

【摘要】：在過去十幾年中,生物識(shí)別技術(shù)已經(jīng)相當(dāng)成熟了,它是一門利用統(tǒng)計(jì)學(xué)方法和人體生理活動(dòng)數(shù)據(jù)來驗(yàn)證個(gè)人身份的技術(shù)。心電信號(hào)ECG(Electrocardiograph)本身因人而異的,并且在每個(gè)人當(dāng)中不可復(fù)制,目前大量的ECG信號(hào)用于生物識(shí)別技術(shù),最新研究指出了ECG生物識(shí)別技術(shù)的一個(gè)待解決問題:在應(yīng)用場(chǎng)景多樣化和人群數(shù)量龐大的情況下,如何充分的利用ECG各類特征來保持識(shí)別魯棒性的問題。針對(duì)上述問題,本研究首先利用傳統(tǒng)的特征提取方法,將基于特征點(diǎn)特征(Fiducial based features)和基于非特征點(diǎn)特征(Non-Fiducial based features)進(jìn)行結(jié)合,提取一種結(jié)合Fiducial和Non-fidicuial的混合特征提取方法,以完成ECG信號(hào)多維特征的建模。其中,Fiducial特征包括ECG信號(hào)的波幅特征、ECG信號(hào)的時(shí)序特征和ECG信號(hào)的頻譜特征;Non-Fiducial特征包括ECG心電圖的波形形狀。進(jìn)而將兩類特征混合并進(jìn)行統(tǒng)一建模,經(jīng)驗(yàn)證,在多樣化場(chǎng)景中本研究提出的ECG混合特征比傳統(tǒng)的ECG單維度特征擁有更高的識(shí)別率。第二步,針對(duì)人群數(shù)據(jù)龐大時(shí),數(shù)據(jù)訓(xùn)練的時(shí)間開銷大的問題,本研究基于上述ECG混合特征,提出新的LDA的算法(LDA Based On Multiple Features,LOMF),LOMF算法包含了ECG信號(hào)的預(yù)處理、子塊劃分和分塊訓(xùn)練。并利用MapReduce分布式計(jì)算框架進(jìn)行算法并行化,提出一種基于多維特征空間的二級(jí)檢索方式,在保證計(jì)算效率提高的同時(shí),將識(shí)別率提升到一個(gè)更高的等級(jí)。文中實(shí)驗(yàn)部分將ECG混合特征分別與Fiducial,Non-Fiducial兩種單維特征方法進(jìn)行對(duì)比,發(fā)現(xiàn)在同一種識(shí)別算法中,ECG混合特征有更高的識(shí)別率。并且本文提出的基于多維特征空間二次檢索的LOMF算法比傳統(tǒng)的LDA,SVM等算法精度有7%-8%的提升,且LOMF最大的優(yōu)勢(shì)在于很好的契合于MapReduce并行框架,更適于互聯(lián)網(wǎng)這種數(shù)據(jù)集增長(zhǎng)速度快的應(yīng)用場(chǎng)景。
[Abstract]:In the past decade, biometric technology has been developed, it is a use of statistical methods and human physiological activity data to verify the identity of individuals. ECG electrocardiography (ECG) itself varies from person to person and cannot be duplicated in everyone. A large number of ECG signals are currently used in biometrics. The latest research has pointed out an unsolved problem of ECG biometrics: how to make full use of the ECG features to maintain the robustness of recognition under the circumstances of diverse application scenarios and large number of people. In order to solve the above problems, this paper firstly uses the traditional feature extraction method to combine the feature point based feature based (feature) and non-Fiducial based feature (Non-Fiducial based feature) to extract a hybrid feature extraction method which combines Fiducial and Non-fidicuial. In order to complete the modeling of multidimensional features of ECG signal. Fiducial features include the amplitude characteristics of ECG signals and the frequency spectrum features of ECG signals, including the waveform shapes of ECG electrocardiograms. Then the two kinds of features are mixed and unified modeling. It is proved that the ECG hybrid feature proposed in this paper has a higher recognition rate than the traditional ECG one-dimensional feature in the diverse scenarios. The second step is to solve the problem that the time cost of data training is large when the crowd data is large. Based on the mixed characteristics of ECG mentioned above, a new LDA algorithm named LDA Based On Multiple Features-LOMF algorithm is proposed, which includes the preprocessing of ECG signal, subblock partition and block training. The algorithm is parallelized by using MapReduce distributed computing framework, and a two-level retrieval method based on multidimensional feature space is proposed, which can improve the efficiency of computation and raise the recognition rate to a higher level. In the experiment part, we compare the mixed features of ECG with those of Fiducial Non-Fiducial and find that the mixed feature of ECG has higher recognition rate in the same recognition algorithm. Moreover, the proposed LOMF algorithm based on multidimensional feature space quadratic retrieval has 7- 8% higher accuracy than the traditional LDA-SVM algorithm, and the biggest advantage of LOMF is that it fits well with the MapReduce parallel framework. More suitable for the Internet, such as the rapid growth of data sets application scenarios.
【學(xué)位授予單位】：華中科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2016
【分類號(hào)】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前2條

1 李玉榕;項(xiàng)國(guó)波;;一種基于馬氏距離的線性判別分析分類算法[J];計(jì)算機(jī)仿真;2006年08期

2 陳伏兵;陳秀宏;張生亮;楊靜宇;;基于模塊2DPCA的人臉識(shí)別方法[J];中國(guó)圖象圖形學(xué)報(bào);2006年04期

，

本文編號(hào)：1807988