基于无线体域网的在线人体活动识别

基于智能手机传感器的人体活动识别是普适计算领域的研究热点.为扩展可识别的活动种类,并提高准确率和实时性,提出了由智能手环和智能手机组建无线体域网通过深度神经网络在线识别人体活动的方法.首先,设计由智能手环和智能手机组成的无线体域网的总体框架;然后,对预处理后的传感信号,构造带有Inception结构的卷积神经网络和长短时记忆递归神经网络来分别提取时空域特征,并结合两类网络结构来融合多模态传感数据,离线进行神经网络模型训练;最后,对训练好的神经网络模型进行优化,并部署到智能手机上,在线实时识别人体活动.实验结果表明,本文方法无需手工设计特征,可自动融合各类异构传感数据,更加准确、高效地识别了更多种类的活动.     

光纤光栅传感阵列的数据融合分析

针对一种结合神经网络技术对光纤光栅传感阵列信号进行分析的方案.以光纤光栅为传感元件,混凝土简支梁模板为研究对象,BP神经网络为信号处理方法,研究了光纤光栅传感阵列和BP神经网络技术在载荷应变损伤监测中的应用.通过有限元法对模板试件的应变分布进行分析,确定光纤光栅应变传感阵列的合理位置,用液压机进行加载实验.通过BP神经网络对这些离散的应变信号进行数据融合,反向分析模板试件的载荷.实验表明,在加载范围0～110 kN内,识别样本相对误差均在3%以下,均方误差小于1 kN.     

基于压力传感器与摄像头的颈椎病预防系统

本文设计并实现了一种基于压力传感器与摄像头的颈椎病预防系统.该系统将薄膜压力传感器放置于坐垫中对人体体压进行采集,并使用摄像头采集人类脸部数据.对于坐垫,我们对传感器的布置和数目进行了优化.对于摄像头,我们在多目标识别时通过五官识别减少了系统运算量.在将压力传感器与摄像头两类数据融合之后,我们实现了比单类数据更准确的坐姿识别,进而对颈椎病的危险程度进行估计.我们还使用卷积神经网络实现了对用户的动作检测,可引导用户完成一系列动作用于评估颈椎病危险程度.系统实现小巧美观,采用非侵入式的方法,非常适合于在办公室环境下的颈椎病早期预防.     

混合神经网络模型在人体活动识别中的研究

针对人体活动识别问题与其在实际情况中的应用,综合考量卷积神经网络与作为循环神经网络变体的门控循环单元,设计能自动提取传感器数据特征和记忆时序性活动数据的CNN-GRU混合神经网络模型,并予以改良.使用该模型在公开的数据集上进行实验,较其他的模型效果更加理想.在人体活动识别的处理中,CNN-GRU模型能达到预期的高准确率.在数据集时序性依赖较强的情况下,CNN-GRU模型能拥有更好的准确度和稳定性.     

混合神经网络模型在人体活动识别中的研究

针对人体活动识别问题与其在实际情况中的应用,综合考量卷积神经网络与作为循环神经网络变体的门控循环单元,设计能自动提取传感器数据特征和记忆时序性活动数据的CNN-GRU混合神经网络模型,并予以改良.使用该模型在公开的数据集上进行实验,较其他的模型效果更加理想.在人体活动识别的处理中,CNN-GRU模型能达到预期的高准确率.在数据集时序性依赖较强的情况下,CNN-GRU模型能拥有更好的准确度和稳定性.     

基于多流卷积神经网络的行为识别

人体行为识别与人体姿态有很强的相关性,由于许多公开的行为识别的数据集并未提供相关姿态数据,因此很少有将姿态数据进行训练并与其它模态进行融合的识别方法.针对当今主流基于深度学习的人体行为识别方法采用RGB与光流融合的现状,提出一种融合人体姿态特征的多流卷积神经网络人体行为识别算法.首先,用姿态估计算法从包含人的静态图片生成人体关键点数据,并对关键点连接构建姿态;其次,分别将RGB、光流、姿态数据对多流卷积神经网络进行训练,并进行分数融合;最后,在UCF101与HMDB51数据集进行了大量的消融,识别精度等方面的实验研究.实验结果表明,融合了姿态图像的多流卷积神经网络在UCF101与HMDB51数据集的实验精度分别提高了2.3％和3.1％.实验结果验证了提出算法的有效性.     

基于PNN的手势识别

为了实现人体手势姿态识别的目标,选用氯化银(AgCl)贴片电极作为信号传感端,通过采集前臂表面肌电(SEMG)信号,经信号放大、滤波等前期处理,再经活动段检测、降噪等信号处理后,提取伸食指、握拳、伸腕、屈腕4种手势的均方根值和积分EMG值作为特征向量,送入概率神经网络(PNN)中进行训练识别,实现人体手势识别.实验结果表明:PNN对前臂SEMG信号的模式识别的正确率可达到97.62％,将PNN应用于手势识别系统具有可行性.     

一种改进的GRU-InFCN人体行为识别模型

为了克服传统机器学习方法在采用传感器数据进行人体行为识别领域上识别效果对人工特征选取依赖严重、识别准确率不高等问题,提出一种改进的全卷积神经网络和多层循环神经网络并联的深度学习模型(GRU-InFCN),并对传感器数据特征进行自动提取,实现人体动作的识别。该模型通过多尺度卷积神经网络和双层GRU网络(Gated Recurrent Unit,GRU)分别对传感器数据进行特征提取,将特征矩阵在矩阵维度上进行特征拼接再通过Softmax完成特征分类。实验结果表明,在开源人体行为识别(HAR)数据集上采用该方法进行人体行为识别,准确率达到了97.76%。该模型在取得高准确率的同时,避免了复杂的信号预处理和特征工程。     

基于改进卷积神经网络的交通标志识别方法

针对传统卷积神经网络时间成本高的不足,对卷积神经网络进行了改进,减少其卷积核的数量,增加池化方式.为解决真实场景中自动驾驶系统和辅助驾驶系统中的道路交通标志识别问题,将改进的卷积神经网络运用到道路交通标志识别当中,以达到在较短时间内识别出交通标志的目的.以图形数据集GTRSB实景交通标志图像数据作为样本,用改进的卷积神经网络对实景交通标志进行识别,其识别总体准确率达到98.38%.实验结果表明,本方法可以在保持较高识别准确率的同时减少其识别的时间.     

基于神经网络的多元特征融合身份识别系统

从信息融合的角度出发，利用神经网络的方法将语音信号、人脸图像等多元特征数据信息有机地结合起来，设计并实现了一种基于神经网络的智能融合身份识别系统。系统利用改进的线性预测和轮廓检测等方法，求出3类特征参数，并将它们进行关联，最后利用RBF人工神经网络进行融合识别。实验表明，与传统的单一特征识别系统相比，该方法具有更好的识别效果。     

基于函数型数据时间序列建模的单传感器日常行为识别

在基于惯性传感器的人体行为识别中,传统算法常忽略行为的周期性与时序性,对提取特征的滑动窗口大小也有相应要求.文中基于单个腰部传感器分析人体日常行为,提出面向周期行为的函数型数据分析方法和隐马尔可夫模型结合的行为识别算法.首先,使用函数型数据分析方法,拟合周期性日常行为的动作捕捉数据,提取拟合后的单个周期数据.然后基于此周期时间序列数据建立描述各个日常行为过程的隐马尔可夫模型.最后,使用最大似然估计判别行为,得到识别结果.该算法通过单个腰部传感器即可快速有效地识别8种日常行为,在基于用户依赖策略和用户独立策略时识别率较高.     

Integrating the enriched feature with machine learning algorithms for human movement and fall detection

Movement detection is gaining more and more attention among various pattern recognition problems. Recognizing human movement activity types is extremely useful for fall detection for elderly people. Wireless sensor network technology enables human motion data from wearable wireless sensor devices be transmitted for remote processing. This paper studies methods to process the human motion data received from wearable wireless sensor devices for detecting different types of human movement activities such as sitting, standing, lying, fall, running, and walking. Machine learning methods K Nearest Neighbor algorithm (KNN) and the Back Propagation Neural Network (BPNN) algorithm are used to classify the activities from the data acquired from sensors based on sample data. As there are a large amount of real-time raw data received from sensors and there are noises associated with these data, feature construction and reduction are used to preprocess these raw sensor data obtained from accelerometers embedded in wireless sensing motes for learning and processing. The singular value decomposition (SVD) technique is used for constructing the enriched features. The enriched features are then integrated with machine learning algorithms for movement detection. The testing data are collected from five adults. Experimental results show that our methods can achieve promising performance on human movement recognition and fall detection.     

基于卷积长短时记忆网络的人体行为识别研究

人体行为识别利用深度学习网络模型自动提取数据的深层特征,但传统机器学习算法存在依赖手工特征提取、模型泛化能力差等问题。提出基于空时特征融合的深度学习模型（CLT-net）用于人体行为识别。采用卷积神经网络（CNN）自动提取人体行为数据的深层次隐含特征,利用长短时记忆（LSTM）网络构建时间序列模型,学习人体行为特征在时间序列上的长期依赖关系。在此基础上,通过softmax分类器实现对不同人体行为分类。在DaLiAc数据集的实验结果表明,相比CNN、LSTM、BP模型,CLT-net模型对13种人体行为的总体识别率达到了97.6%,具有较优的人体行为识别分类性能。     

Recognizing composite daily activities from crowd-labelled social media data

Human activity recognition is a core component of context-aware, ubiquitous computing systems. Traditionally, this task is accomplished by analysing signals of wearable motion sensors. While successful for low-level activities (e.g. walking or standing), high-level activities (e.g. watching movies or attending lectures) are difficult to distinguish from motion data alone. Furthermore, instrumentation of complex body sensor network at population scale is impractical. In this work, we take an alternative approach of leveraging rich, dynamic, and crowd-generated self-report data from social media platforms as the basis for in-situ activity recognition. By treating the user as the “sensor”, we make use of implicit signals emitted from natural use of mobile smartphones, in the form of textual content, semantic location, and time. Tackling both the task of recognizing a main activity (multi-class classification) and recognizing all applicable activity categories (multi-label tagging) from one instance, we are able to obtain mean accuracies of more than 75%. We conduct a thorough analysis and interpret of our model to illustrate a promising first step towards comprehensive, high-level activity recognition using instrumentation-free, crowdsourced, social media data.     

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.     

Times-series data augmentation and deep learning for construction equipment activity recognition

Automated, real-time, and reliable equipment activity recognition on construction sites can help to minimize idle time, improve operational efficiency, and reduce emissions. Previous efforts in activity recognition of construction equipment have explored different classification algorithms anm accelerometers and gyroscopes. These studies utilized pattern recognition approaches such as statistical models (e.g., hidden-Markov models); shallow neural networks (e.g., Artificial Neural Networks); and distance algorithms (e.g., K-nearest neighbor) to classify the time-series data collected from sensors mounted on the equipment. Such methods necessitate the segmentation of continuous operational data with fixed or dynamic windows to extract statistical features. This heuristic and manual feature extraction process is limited by human knowledge and can only extract human-specified shallow features. However, recent developments in deep neural networks, specifically recurrent neural network (RNN), presents new opportunities to classify sequential time-series data with recurrent lateral connections. RNN can automatically learn high-level representative features through the network instead of being manually designed, making it more suitable for complex activity recognition. However, the application of RNN requires a large training dataset which poses a practical challenge to obtain from real construction sites. Thus, this study presents a data-augmentation framework for generating synthetic time-series training data for an RNN-based deep learning network to accurately and reliably recognize equipment activities. The proposed methodology is validated by generating synthetic data from sample datasets, that were collected from two earthmoving operations in the real world. The synthetic data along with the collected data were used to train a long short-term memory (LSTM)-based RNN. The trained model was evaluated by comparing its performance with traditionally used classification algorithms for construction equipment activity recognition. The deep learning framework presented in this study outperformed the traditionally used machine learning classification algorithms for activity recognition regarding model accuracy and generalization.     

基于CNN-LSTM的活动识别方法

在识别活动时,传统的循环神经网络RNN识别方法不考虑传感器活动数据之间依赖性强的问题,导致识别准确率降低。为了提高识别准确率,解决活动数据依赖性强的问题,用长短期记忆网络LSTM进行活动识别,LSTM在考虑当前点输入的同时考虑先前点的输出,能够保持数据之间的强依赖性。但是,LSTM在处理传感器活动数据的特征提取方面时间效率不高,而卷积神经网络CNN能共享卷积核,且可以从杂乱无章的数据中提取出明显特征向量。提出一种基于CNN-LSTM的活动识别方法CLAR,利用CNN能够很好地提取出活动序列数据中的特征向量,并将提取出的特征向量作为LSTM的输入,利用LSTM门限之间的相互作用进行活动识别,使得依赖性很强的活动数据成为活动识别的优势,进而提高活动识别的准确率和时间效率。实验表明,CLAR方法的识别准确率比单一神经网络活动识别方法的准确率提高了9%,时间平均缩短了10%。     

Enhancing activity recognition using CPD-based activity segmentation

Segmenting behavior-based sensor data and recognizing the activity that the data represents are vital steps in all applications of human activity learning such as health monitoring, security, and intervention. In this paper, we enhance activity recognition by identifying activity transitions. To accomplish this goal, we introduce a change point detection-based activity segmentation model which partitions behavior-driven sensor data into non-overlapping activities in real time. In addition to providing valuable activity information, activity segmentation also can be used to improve the performance of activity recognition. We evaluate our proposed segmentation-enhanced activity recognition method on data collected from 29 smart homes. Results of this analysis indicate that the method not only provides useful information about activity boundaries and transitions between activities but also increases recognition accuracy by 7.59% and f measure by 6.69% in comparison with the traditional window-based methods.     

一种基于特征增强和决策融合的人体行为识别方法

利用三轴加速度传感器进行人体行为识别一直是传感器数据处理、模式识别领域的研究热点。加速度数据往往存在着多种动作数据难以区分的情况,特别是走、上楼、下楼这3个动作数据非常相似,这给正确识别这3种人体动作带来了较大的难度。提出一种基于特征增强与决策融合的行为识别方法,通过对部分特征值进行增强处理和对多个分类结果进行决策融合来识别走、上楼、下楼这些难以区分的相似动作。实验验证,所提方法可克服由于加速度数据的相似性而导致的动作识别正确率低、识别误差大的情况,有效提高人体行为识别率,且可在实际应用中实时识别人体行为动作。