基于智能手機傳感器數(shù)據(jù)的人類行為識別研究
發(fā)布時間：2019-02-24 15:02
【摘要】：人類行為識別是模式識別領(lǐng)域的研究熱點,目前有基于視頻數(shù)據(jù)和基于智能手機傳感器數(shù)據(jù)兩種研究方向。隨著時代的快速發(fā)展,智能手機的普及化以及嵌入在智能手機中的傳感器的多樣化,使得運用智能手機傳感器數(shù)據(jù)進行人類行為識別研究更加有實際意義。本文主要針對人類行為識別中出現(xiàn)的分類結(jié)果精度不準確,實驗特征數(shù)據(jù)量大,分類效果不佳等問題,在真實數(shù)據(jù)的基礎(chǔ)上,提出了基于多階層連續(xù)隱馬爾科夫模型的人類行為識別和基于稀疏局部保持投影結(jié)合隨機森林集成分類器(Sparse Locality Preserving Projections and Random Forest,SpLPP-RF)的人類行為識別兩種創(chuàng)新性算法,有效的解決了目前行為識別研究中遇到的困難。本文主要研究成果如下所示:(1)傳統(tǒng)的連續(xù)隱馬爾科夫模型在進行行為識別時,最終的行為識別準確率相對較低。基于人類活動的層次特點與傳感器數(shù)據(jù)的時序性、多元性與連續(xù)性,本文提出了三階層連續(xù)隱馬爾科夫模型(Three-Stage Continuous Hidden Markov Model,TSCHMM)的人類行為識別新算法。實驗結(jié)果表明所提出的算法不僅可以明顯判別出活動的誤分類別,而且解決了識別率低的問題,尤其是提高了易混淆活動的分類準確率。(2)首次將稀疏局部保持投影算法應(yīng)用于連續(xù)隱馬爾科夫模型的人類行為識別中。稀疏局部保持投影(Sparse Locality Preserving Projections,SpLPP)優(yōu)化保留了鄰域結(jié)構(gòu)的數(shù)據(jù)集,并且相比于局部保持投影算法,可以從傳感器數(shù)據(jù)中提取出更多有代表性的活動行為特征變量。以SpLPP作為降維方法的實驗結(jié)果表明新算法效果明顯。(3)由于集成分類器一般情況下分類效果優(yōu)于單一分類器,所以已有一些研究采用隨機森林(RandomForest,RF)分類器應(yīng)用于智能手機傳感器數(shù)據(jù)的人類行為識別上。但他們的方法沒有充分利用較前沿的降維技術(shù)。因此,本文提出了用SpLPP進行降維,有效的解決了人類行為識別研究中的特征數(shù)量多的問題,降低了實驗的時間復(fù)雜度,行為識別的總體識別率得到了顯著的提高。同時,也比較了 SpLPP-RF和TSCHMM這兩種算法,闡述了兩種算法在性能上的差異與適用情況。
[Abstract]:Human behavior recognition is a hot topic in the field of pattern recognition. There are two research directions: video data and smart phone sensor data. With the rapid development of the times, the popularization of smart phones and the diversity of sensors embedded in smart phones, it is more meaningful to study human behavior recognition using smart phone sensor data. Based on the real data, this paper mainly aims at the problems of inaccurate classification results, large experimental data volume and poor classification effect, which appear in human behavior recognition. Two innovative algorithms for human behavior recognition based on multilevel continuous hidden Markov model and sparse local preserving projection combined with stochastic forest ensemble classifier (Sparse Locality Preserving Projections and Random Forest,SpLPP-RF) are proposed. Effectively solve the current behavior recognition research encountered difficulties. The main results of this paper are as follows: (1) the accuracy of behavior recognition in the traditional continuous hidden Markov model is relatively low. Based on the hierarchical characteristics of human activities and the timing, plurality and continuity of sensor data, a new human behavior recognition algorithm based on three-level continuous Hidden Markov Model (Three-Stage Continuous Hidden Markov Model,TSCHMM) is proposed in this paper. The experimental results show that the proposed algorithm can not only clearly distinguish the wrong classification of activities, but also solve the problem of low recognition rate. In particular, the classification accuracy of confusing activities is improved. (2) the sparse local preserving projection algorithm is applied to human behavior recognition of continuous Hidden Markov models for the first time. Sparse local preserving projection (Sparse Locality Preserving Projections,SpLPP) optimizes the neighborhood structure of the data set, and can extract more representative activity characteristic variables from the sensor data than the local preserving projection algorithm. The experimental results using SpLPP as a dimensionality reduction method show that the new algorithm is effective. (3) because the ensemble classifier is better than a single classifier in general, some researches have adopted random forest (RandomForest,). RF) classifier is applied to human behavior recognition of smart phone sensor data. However, their methods do not make full use of the more advanced dimensionality reduction techniques. Therefore, this paper proposes to reduce the dimension by using SpLPP, which effectively solves the problem of the large number of features in the research of human behavior recognition, reduces the time complexity of the experiment, and improves the overall recognition rate of behavior recognition significantly. At the same time, two algorithms, SpLPP-RF and TSCHMM, are compared, and their performance and applicability are discussed.
【學(xué)位授予單位】：浙江師范大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP391.4;TP212.9
本文編號：2429654
[Abstract]:Human behavior recognition is a hot topic in the field of pattern recognition. There are two research directions: video data and smart phone sensor data. With the rapid development of the times, the popularization of smart phones and the diversity of sensors embedded in smart phones, it is more meaningful to study human behavior recognition using smart phone sensor data. Based on the real data, this paper mainly aims at the problems of inaccurate classification results, large experimental data volume and poor classification effect, which appear in human behavior recognition. Two innovative algorithms for human behavior recognition based on multilevel continuous hidden Markov model and sparse local preserving projection combined with stochastic forest ensemble classifier (Sparse Locality Preserving Projections and Random Forest,SpLPP-RF) are proposed. Effectively solve the current behavior recognition research encountered difficulties. The main results of this paper are as follows: (1) the accuracy of behavior recognition in the traditional continuous hidden Markov model is relatively low. Based on the hierarchical characteristics of human activities and the timing, plurality and continuity of sensor data, a new human behavior recognition algorithm based on three-level continuous Hidden Markov Model (Three-Stage Continuous Hidden Markov Model,TSCHMM) is proposed in this paper. The experimental results show that the proposed algorithm can not only clearly distinguish the wrong classification of activities, but also solve the problem of low recognition rate. In particular, the classification accuracy of confusing activities is improved. (2) the sparse local preserving projection algorithm is applied to human behavior recognition of continuous Hidden Markov models for the first time. Sparse local preserving projection (Sparse Locality Preserving Projections,SpLPP) optimizes the neighborhood structure of the data set, and can extract more representative activity characteristic variables from the sensor data than the local preserving projection algorithm. The experimental results using SpLPP as a dimensionality reduction method show that the new algorithm is effective. (3) because the ensemble classifier is better than a single classifier in general, some researches have adopted random forest (RandomForest,). RF) classifier is applied to human behavior recognition of smart phone sensor data. However, their methods do not make full use of the more advanced dimensionality reduction techniques. Therefore, this paper proposes to reduce the dimension by using SpLPP, which effectively solves the problem of the large number of features in the research of human behavior recognition, reduces the time complexity of the experiment, and improves the overall recognition rate of behavior recognition significantly. At the same time, two algorithms, SpLPP-RF and TSCHMM, are compared, and their performance and applicability are discussed.
【學(xué)位授予單位】：浙江師范大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP391.4;TP212.9
【參考文獻】
相關(guān)期刊論文 前6條
1 張云強;張培林;;基于半監(jiān)督局部保持投影的磨粒圖像特征降維[J];中南大學(xué)學(xué)報(自然科學(xué)版);2015年08期
2 宋欠欠;李軼群;侯艷;李康;;隨機森林的變量捕獲方法在高維數(shù)據(jù)變量篩選中的應(yīng)用[J];中國衛(wèi)生統(tǒng)計;2015年01期
3 孫冰怡;呂巍;李文洋;;基于智能手機傳感器和SC-HMM算法的行為識別[J];吉林大學(xué)學(xué)報(理學(xué)版);2013年06期
4 方匡南;吳見彬;朱建平;謝邦昌;;隨機森林方法研究綜述[J];統(tǒng)計與信息論壇;2011年03期
5 吳寶元;余永;許德章;吳仲城;陳峰;;可穿戴式下肢助力機器人運動學(xué)分析與仿真[J];機械科學(xué)與技術(shù);2007年02期
6 張振躍,查宏遠;Principal Manifolds and Nonlinear Dimensionality Reduction via Tangent Space Alignment[J];Journal of Shanghai University;2004年04期
相關(guān)博士學(xué)位論文 前2條
1 劉韜;基于隱馬爾可夫模型與信息融合的設(shè)備故障診斷與性能退化評估研究[D];上海交通大學(xué);2014年
2 何衛(wèi)華;人體行為識別關(guān)鍵技術(shù)研究[D];重慶大學(xué);2012年
相關(guān)碩士學(xué)位論文 前1條
1 李曉曼;局部保持投影中的若干問題研究[D];華僑大學(xué);2012年
，本文編號：2429654
本文鏈接：http://sikaile.net/kejilunwen/zidonghuakongzhilunwen/2429654.html
最近更新
教材專著
