高可信度加权的多分类器融合行为识别模型

为了提高基于智能移动设备的人体日常行为识别准确率,提出一种高可信度加权的多分类器融合行为识别模型（MCFM）。针对不同智能设备内置加速度传感器获取的三轴加速度信息,优选出与人体行为相关度高的特征集作为该模型的输入,将决策树、支持向量机以及反向传播（BP）神经网络三个基分类器通过高可信度加权投票算（HRWV）法训练出一个新的融合分类器。实验结果表明,所提出的分类器融合模型能有效提高行为识别的准确率,对静止、散步、跑步、上楼及下楼五种日常行为的平均识别准确率达到94.88%。     

一种自适应子融合集成多分类器方法

融合集成方法已经广泛应用在模式识别领域,然而一些基分类器实时性能稳定性较差,导致多分类器融合性能差,针对上述问题本文提出了一种新的基于多分类器的子融合集成分类器系统。该方法考虑在度量层融合层次之上通过对各类基多分类器进行动态选择,票数最多的类别作为融合系统中对特征向量识别的类别,构成一种新的自适应子融合集成分类器方法。实验表明,该方法比传统的分类器以及分类融合方法识别准确率明显更高,具有更好的鲁棒性。     

基于性格的微博情感分析模型PLSTM

不同性格用户所具有的语言表达方式不尽相同,现有情感分析工作很少考虑到用户性格,针对此问题,提出一种基于性格的微博情感分析模型PLSTM。该模型首先采用性格识别规则将微博文本分为五个性格集合和一个通用集合,其次针对每种性格文本集合分别训练出一个情感分类器,最后对六个基本情感分类器进行融合,得出最终的情感极性。实验结果显示PLSTM方法的◢F1◣值可以达到96.95%,表明PLSTM比起基准情感分析模型在准确率、召回率、◢F1◣值上都有较大提高。     

基于差异性聚类的选择性集成人体行为识别模型

为了提高基于智能手机的人体行为识别率,优化多分类器集成系统的泛化性能及个体分类器的差异性,提出了基于差异性增量聚类(Diversity Measure Increment-Affinity Propagation clustering,DMI-AP)的选择性集成人体行为识别模型。首先对训练集的所有样本进行bootstrap抽样并训练基分类器,选出大于平均识别率的基分类器构成分类器集合;然后将集合的基分类器作为聚类对象进行分组,通过计算基分类器间的双误差异性值求出表征个体分类器特征的双误差异性增量值,输入近邻传播聚类算法得到k个类簇,选取每簇的中心分类器构成多分类器集成系统;最后使用等概率均值法融合k个分类器的输出结果。实验表明,该模型算法使个体分类器的差异性增大、分类器搜索空间缩小;与传统的Bagging,Adaboost以及RF方法相比,该模型的识别准确率平均提高了8.11%。     

多分类器选择集成方法

针对目前人们对分类性能的高要求和多分类器集成实现的复杂性,从基分类器准确率和基分类器间差异性两方面出发,提出了一种新的多分类器选择集成算法。该算法首先从生成的基分类器中选择出分类准确率较高的,然后利用分类器差异性度量来选择差异性大的高性能基分类器,在分类器集成之前先对分类器集进行选择获得新的分类器集。在UCI数据库上的实验结果证明,该方法优于bagging方法,取得了很好的分类识别效果。     

基于支持向量机多分类器的室内外场景感知算法

针对普适室内外场景持续感知面临的低功耗、复杂动态环境、异构使用模式带来的挑战,提出了一种轻量级的基于支持向量机多分类器的高精度、低功耗室内外场景检测算法.该算法使用智能手机集成的各种传感器(可见光传感器、磁传感器、加速度传感器、陀螺仪传感器和气压传感器),在挖掘分析各种传感器在室内外场景的不同特征,以及人们在室内外场景的行为差异基础上,根据时间和气象条件设计多个支持向量机分类器,对复杂室内外场景进行识别.实验结果表明,基于支持向量机多分类器的室内外场景检测算法具有较好的普适性,可获得95%以上的室内外判定准确率,平均功耗小于5 mW.     

基于多分类器融合的步态识别方法

为了提高现有基于智能手机加速度传感器步态身份识别的性能,提出了一种基于多分类器融合（MCF）的识别方法。首先,针对现有方法所提取的步态特征较为单一的问题,对单个步态周期提取相对匀变加速度的速度变化量,以及单位时间内加速度变化量作为两类新特征（共16个）;其次,将新特征结合常用的时域、频域特征组成新的特征集,用于训练识别效果与训练时间俱佳的多个分类器;最后,采用多尺度投票法（MSV）对多分类器的输出进行融合处理,得到最终的分类结果。为了检测该方法的性能,采集了32个志愿者的步态数据。实验结果表明,新特征对于单个分类器的识别率平均提升5.95个百分点,最终通过MSV融合算法的识别率为97.78%。     

基于智能手机传感器的基础行为识别方法研究

为提高人类行为识别准确性的同时降低实现过程的复杂程度,提出基于智能手机加速度传感器与陀螺仪数据对六种日常基础行为进行识别的方法。在分析传感器框架的基础上,对加速度传感器进行数据采集并对原始数据进行数据预处理,然后采用主成分分析方法结合已有知识对数据统计特征进行降低维数处理,再利用机器学习算法实现对行为特征的分类与识别,目的是简化基础行为的识别过程并提高数据的利用率。实验测试结果验证了决策树与支持向量机分类器结合使用的有效性,识别准确率可接近97%。     

基于三维骨骼节点的人体行为识别方法

针对传统行为识别方法存在的数据存储空间不足、识别效率不高以及扩展性不强等问题,本文在利用空间中人体关节点数据进行人体行为表示的基础上,通过自建行为数据集结合Spark MLlib算法库的随机森林算法对行为识别进行建模。为了提升识别模型的泛化能力,本文利用Spark平台下算法的并行且快速迭代的特性,提出了一种多重随机森林的加权大数投票算法。实验结果表明,随着基分类器个数的增加,行为分类准确率显著增高,基分类器个数在5个以后行为识别准确率趋于稳定且高达95%以上。在MSR Daily 3D与MSRC-12数据集上也验证本文行为识别方法的有效性。     

多维数据特征融合的用户情绪识别

针对目前基于智能手机的情绪识别研究中所用数据较为单一,不能全面反应用户行为模式,进而不能真实反应用户情绪这一问题展开研究,基于智能手机从多个维度全面收集反应用户日常行为的细粒度感知数据,采用多维数据特征融合方法,利用支持向量机(support vector machine,SVM)、随机森林(random forest)等6种分类方法,基于离散情绪模型和环状情绪模型两种情绪分类模型,对12名志愿者的混合数据和个人数据分别进行情绪识别,并进行了对比实验。实验结果表明,该全面反应用户行为的多维数据特征融合方法能够很好地对用户的情绪进行识别,其中使用个人数据进行情绪识别的准确率最高可达到79.78%,而且环状情感模型分类结果明显优于离散分类模型。     

一种基于卷积神经网络深度学习的人体行为识别方法

为提高基于智能终端的人体行为识别的准确率,提出一种基于卷积神经网络深度学习人体行为识别方法。该方法将原始数据进行简单处理,直接作为输入数据输入到卷积神经网络中,由卷积神经网络进行局部特征分析,得到特征输出项,直接输入到Softmax分类器中,可识别走路、跑步、上下楼梯、站立等5种动作。 对比实验结果表明,其对不同的实验者的识别率达到84.8%,证明了该方法的有效性。     

Fusion of multiple diverse predictors in stock market

Forecasting stock returns and their risk represents one of the most important concerns of market decision makers. Although many studies have examined single classifiers of stock returns and risk methods, fusion methods, which have only recently emerged, require further study in this area. The main aim of this paper is to propose a fusion model based on the use of multiple diverse base classifiers that operate on a common input and a Meta classifier that learns from base classifiers’ outputs to obtain more precise stock return and risk predictions. A set of diversity methods, including Bagging, Boosting and AdaBoost, is applied to create diversity in classifier combinations. Moreover, the number and procedure for selecting base classifiers for fusion schemes is determined using a methodology based on dataset clustering and candidate classifiers’ accuracy. The results demonstrate that Bagging exhibited superior performance within the fusion scheme and could achieve a maximum of 83.6% accuracy with Decision Tree, LAD Tree and Rep Tree for return prediction and 88.2% accuracy with BF Tree, DTNB and LAD Tree in risk prediction. For feature selection part, a wrapper-GA algorithm is developed and compared with the fusion model. This paper seeks to help researcher select the best individual classifiers and fuse the proper scheme in stock market prediction. To illustrate the approach, we apply it to Tehran Stock Exchange (TSE) data for the period from 2002 to 2012.     

Hand gesture recognition using two-level speed normalization,feature selection and classifier fusion

Hand gesture recognition provides an alternative way to many devices for human computer interaction. In this work, we have developed a classifier fusion based dynamic free-air hand gesture recognition system to identify the isolated gestures. Different users gesticulate at different speed for the same gesture. Hence, when comparing different samples of the same gesture, variations due to difference in gesturing speed should not contribute to the dissimilarity score. Thus, we have introduced a two-level speed normalization procedure using DTW and Euclidean distance-based techniques. Three features such as ‘orientation between consecutive points’, ‘speed’ and ‘orientation between first and every trajectory points’ were used for the speed normalization. Moreover, in feature extraction stage, 44 features were selected from the existing literatures. Use of total feature set could lead to overfitting, information redundancy and may increase the computational complexity due to higher dimension. Thus, we have tried to overcome this difficulty by selecting optimal set of features using analysis of variance and incremental feature selection techniques. The performance of the system was evaluated using this optimal set of features for different individual classifiers such as ANN, SVM, k-NN and Naïve Bayes. Finally, the decisions of the individual classifiers were combined using classifier fusion model. Based on the experimental results it may be concluded that classifier fusion provides satisfactory results compared to other individual classifiers. An accuracy of 94.78 % was achieved using the classifier fusion technique as compared to baseline CRF (85.07 %) and HCRF (89.91 %) models.     

Data fusion and multiple classifier systems for human activity detection and health monitoring: Review and open research directions

Activity detection and classification using different sensor modalities have emerged as revolutionary technology for real-time and autonomous monitoring in behaviour analysis, ambient assisted living, activity of daily living (ADL), elderly care, rehabilitations, entertainments and surveillance in smart home environments. Wearable devices, smart-phones and ambient environments devices are equipped with variety of sensors such as accelerometers, gyroscopes, magnetometer, heart rate, pressure and wearable camera for activity detection and monitoring. These sensors are pre-processed and different feature sets such as time domain, frequency domain, wavelet transform are extracted and transform using machine learning algorithm for human activity classification and monitoring. Recently, deep learning algorithms for automatic feature representation have also been proposed to lessen the burden of reliance on handcrafted features and to increase performance accuracy. Initially, one set of sensor data, features or classifiers were used for activity recognition applications. However, there are new trends on the implementation of fusion strategies to combine sensors data, features and classifiers to provide diversity, offer higher generalization, and tackle challenging issues. For instances, combination of inertial sensors provide mechanism to differentiate activity of similar patterns and accurate posture identification while other multimodal sensor data are used for energy expenditure estimations, object localizations in smart homes and health status monitoring. Hence, the focus of this review is to provide in-depth and comprehensive analysis of data fusion and multiple classifier systems techniques for human activity recognition with emphasis on mobile and wearable devices. First, data fusion methods and modalities were presented and also feature fusion, including deep learning fusion for human activity recognition were critically analysed, and their applications, strengths and issues were identified. Furthermore, the review presents different multiple classifier system design and fusion methods that were recently proposed in literature. Finally, open research problems that require further research and improvements are identified and discussed.     

The effects of combining classifiers with the same training statistics using Bayesian decision rules

Multiple classifier systems (MCS) are attracting increasing interest in the field of pattern recognition and machine learning. Recently, MCS are also being introduced in the remote sensing field where the importance of classifier diversity for image classification problems has not been examined. In this article, Satellite Pour l'Observation de la Terre (SPOT) IV panchromatic and multispectral satellite images are classified into six land cover classes using five base classifiers: contextual classifier, k-nearest neighbour classifier, Mahalanobis classifier, maximum likelihood classifier and minimum distance classifier. The five base classifiers are trained with the same feature sets throughout the experiments and a posteriori probability, derived from the confusion matrix of these base classifiers, is applied to five Bayesian decision rules (product rule, sum rule, maximum rule, minimum rule and median rule) for constructing different combinations of classifier ensembles. The performance of these classifier ensembles is evaluated for overall accuracy and kappa statistics. Three statistical tests, the McNemar's test, the Cochran's Q test and the Looney's F-test, are used to examine the diversity of the classification results of the base classifiers compared to the results of the classifier ensembles. The experimental comparison reveals that (a) significant diversity amongst the base classifiers cannot enhance the performance of classifier ensembles; (b) accuracy improvement of classifier ensembles can only be found by using base classifiers with similar and low accuracy; (c) increasing the number of base classifiers cannot improve the overall accuracy of the MCS and (d) none of the Bayesian decision rules outperforms the others.     

多层分类器模型的相似人体活动识别

针对基于单传感器活动识别中相似活动易混淆的问题,本文提出了一种基于广义判别分析的多层分类器融合的相似人体活动识别算法.首先提取基于单加速度计的多类活动数据的时域特征、频域特征以及时频特征,对不同特征进行特征分析与重要性评估以确定有效的特征维度.使用随机森林(RF,Random forest)算法对活动特征进行第1层分类,然后根据分类混淆矩阵分析相似活动,由广义判别分析算法提取相似人体活动的映射特征,使用支持向量机(SVM,Support vector machine)算法对相似活动进行第2层分类,最后将相似活动的双层分类器识别概率加权融合得到最终识别结果.为了验证该识别算法,在公开的数据集SCUT-NAA上执行,识别算法对相似活动识别的正确率达到97.2%,提高了基于该数据集研究的正确率.     

利用D-S证据理论进行特征融合的同义实体识别*

针对现实中同一实体存在不同表象的问题,提出一种基于D-S证据理论特征融合的同义实体识别方法。以搜索引擎为外部知识库获取实体特征信息,利用相似函数计算特征值,由D-S证据理论融合n个特征值,经阈值判断完成同义实体的识别。特征融合识别算法在医疗机构数据集上的识别精度、召回率和F值分别达到了85.80%、81.18%、83.43%,比单纯利用实体名的算法分别提高了4.09%、4.30%和4.21%。实验表明D-S证据理论将多特征融合,对同义实体识别具有更好的识别效果。     

在线生物文献磁共振图像识别方法

为实现在线生物文献磁共振成像(MRI)图像库的构建,利用图像特征的塔式梯度方向直方图(PHOG)和塔式关键词直方图(PHOW)进行互补特征表示,使用支持向量机对MRI图像与非MRI图像以及脑部MRI与非脑部MRI图像进行自动分类。实验结果表明,空间形状信息与局部分布信息融合的特征能提高图像分类的准确率,为构建在线文献中MRI图像库的知识系统提供技术支持。