人体运动信息获取及物理活动识别研究
|
摘要
人的物理活动具有可感知性、非侵犯性以及受环境影响小等特点，在上下文环境中能体现人的意图，是生物特征研究的一个新兴领域，在普适计算、虚拟现实、运动训练和医疗保健等众多领域有广阔的应用前景。人体运动信息可通过加速度等惯性传感器采集，经过特征提取和活动建模后，运用统计和机器学习算法进行物理活动识别。其中，将大量的低层传感器数据转换为高层的物理活动信息是物理活动识别的关键问题。本文重点研究了人体运动信息的获取方法、基于步态加速度的步态识别、物理活动特征的自动选择、短时物理活动识别和基于多传感器的物理活动识别等内容。
运动环境的多样性及物理活动的复杂性影响人体运动信息的准确获取。为有效提取人体运动信息，设计了基于加速度传感器的可穿戴人体运动信息采集系统。通过对人体运动信号的检测与分析，研究了运动数据的位置校正与加速度信号去噪等数据预处理方法，保证了人体运动信息获取的准确度。
通过分析步态加速度的无偏自相关特性，研究了步态参数计算和步态对称性评估方法，给出了行走速度与步频、步长和步幅之间的关系。提出了一种混合时频域特征的最近邻步态识别算法，该方法对单步态切分得到步态代码，采用混合时频域特征匹配实现身份的识别。实验结果显示，最近邻步态识别方法能消除人体行走的步态周期不确定性问题，提高了身份识别的准确率。
从运动数据中提取有效特征是物理活动识别的关键。针对短时物理活动中加速度信号的相似性和不稳定性等问题，提出了基于聚类特征选择的DHMM姿势识别方法。该方法运用k-means聚类算法自动提取物理活动特征，并将多维特征输入离散隐马尔可夫模型，通过模型训练和似然度计算，识别出不同的姿势动作。实验结果表明，聚类特征选择降低了隐马尔可夫模型的复杂度，提高了短时物理活动的识别性能。
在多个传感器节点的物理活动识别中，需要融合多特征参数以减少节点传送的信息量。本文采用机器学习算法得到各节点的分类混淆概率，然后采用贝叶斯规则融合多节点上的分类信息，将物理活动分类为具有最大后验概率的类别，提高了物理活动的识别率。为了减少各传感器节点的训练样本数量，研究了在多个未标识活动中选择特定实例的主动学习方法，从而提高了系统的分类效率。
最后对全文进行总结，并指出今后需要进一步研究的工作。
Human activity owns features of perceptibility, noninvasive and stability; it can reflect people's intention. Human activity recognition is currently one of the most active research topics in the field of biometrics research; it has potential application prospects in pervasive computing, virtual reality, sport training and health care. In recent years, although human activity recognition with wearable sensors received increasing attention, it only relies at the stage of theoretical exploration; many theoretical and technical problems remain open. Human activity information can be captured by inertial sensors such as accelerometer, after feature extraction and modeling, human activities can be recognized through statistics and machine learning algorithm. How to map low-level sensor data to higher level abstractions is the key to activity recognition. This paper focuses mainly on the method of acquisition rich data about human activities, gait recognition based on gait acceleration, automatic feature extraction, short-term activity recognition and high-level human activity recognition.
The diversity of environment and the complexity of human activity affect the information extraction. A portable accelerometer-based system which used to accurately record human activities is designed, and the method of motion detection from sensor node, sensor data calibration and denoising are also analyzed.
Aiming at the means of gait parameters extracting based on the portable gait data acquisition system, the method of measuring cadence, step and stride lengths by an autocorrelation procedure is presented, and gait symmetry could be estimated by analysis the ratio of correlation coefficient between signal step and gait cycle. The relation between walking speed and cadence, step and stride lengths is also given. This thesis proposes a kind of nearest neighbor algorithm which used to identify human individual through features of gait acceleration data in time domain and frequency domain. Experiments demonstrate the effectiveness of our algorithm.
For the similarity and instability of short-term human activity signal, Discrete Hidden Markov Models used for gesture recognition are established with the combination of feature extraction by k-means clustering. The k-means clustering algorithm selects a small number of critical features from a large set by ranking different features according to the quality of the resulting clustering, and the small feature subset are taken as the input of DHMM, so as to identify different gestures. Experiments show that the feature selection algorithm can not only reduce the complexity of Discrete Hidden Markov Models, but also improve the recognition performance, and the method proposed in this thesis can be used for different kinds of sensor data, and extended to other kinds of short-term human activity identification.
Usually the recognition of daily human activity need to collect multi-sensor data, this thesis explores an information fusion algorithm based Na(?)ve Bayes so as to obtain higher-level contexts from a small number of sensor. The sensor data from single node are firstly classified by C4.5 Decision Tree or AdaBoost algorithm, once the confusion matrix of every sensor node have be gotten, the sensor fusion can be performed at the classifier level by calculating the corresponding posterior probability. In order to reduce the level of supervision, this thesis also analyzes the feasibility of active learning for searching most informative samples to be labeled by users in activity recognition. The Experimental results of daily human activity recognition indicate that our algorithm can extract low-level context information from few sensor nodes and then be processed to obtain high-level context information; and the active learning algorithm can detect the most informative unlabeled activity data to ask people to label, so as to learn from large amount of readily available unlabeled data. The research in this thesis owns important practical values in natural human-computer interaction.
Finally, it concludes the dissertation briefly, and the future research work is indicated.
运动环境的多样性及物理活动的复杂性影响人体运动信息的准确获取。为有效提取人体运动信息，设计了基于加速度传感器的可穿戴人体运动信息采集系统。通过对人体运动信号的检测与分析，研究了运动数据的位置校正与加速度信号去噪等数据预处理方法，保证了人体运动信息获取的准确度。
通过分析步态加速度的无偏自相关特性，研究了步态参数计算和步态对称性评估方法，给出了行走速度与步频、步长和步幅之间的关系。提出了一种混合时频域特征的最近邻步态识别算法，该方法对单步态切分得到步态代码，采用混合时频域特征匹配实现身份的识别。实验结果显示，最近邻步态识别方法能消除人体行走的步态周期不确定性问题，提高了身份识别的准确率。
从运动数据中提取有效特征是物理活动识别的关键。针对短时物理活动中加速度信号的相似性和不稳定性等问题，提出了基于聚类特征选择的DHMM姿势识别方法。该方法运用k-means聚类算法自动提取物理活动特征，并将多维特征输入离散隐马尔可夫模型，通过模型训练和似然度计算，识别出不同的姿势动作。实验结果表明，聚类特征选择降低了隐马尔可夫模型的复杂度，提高了短时物理活动的识别性能。
在多个传感器节点的物理活动识别中，需要融合多特征参数以减少节点传送的信息量。本文采用机器学习算法得到各节点的分类混淆概率，然后采用贝叶斯规则融合多节点上的分类信息，将物理活动分类为具有最大后验概率的类别，提高了物理活动的识别率。为了减少各传感器节点的训练样本数量，研究了在多个未标识活动中选择特定实例的主动学习方法，从而提高了系统的分类效率。
最后对全文进行总结，并指出今后需要进一步研究的工作。
Human activity owns features of perceptibility, noninvasive and stability; it can reflect people's intention. Human activity recognition is currently one of the most active research topics in the field of biometrics research; it has potential application prospects in pervasive computing, virtual reality, sport training and health care. In recent years, although human activity recognition with wearable sensors received increasing attention, it only relies at the stage of theoretical exploration; many theoretical and technical problems remain open. Human activity information can be captured by inertial sensors such as accelerometer, after feature extraction and modeling, human activities can be recognized through statistics and machine learning algorithm. How to map low-level sensor data to higher level abstractions is the key to activity recognition. This paper focuses mainly on the method of acquisition rich data about human activities, gait recognition based on gait acceleration, automatic feature extraction, short-term activity recognition and high-level human activity recognition.
The diversity of environment and the complexity of human activity affect the information extraction. A portable accelerometer-based system which used to accurately record human activities is designed, and the method of motion detection from sensor node, sensor data calibration and denoising are also analyzed.
Aiming at the means of gait parameters extracting based on the portable gait data acquisition system, the method of measuring cadence, step and stride lengths by an autocorrelation procedure is presented, and gait symmetry could be estimated by analysis the ratio of correlation coefficient between signal step and gait cycle. The relation between walking speed and cadence, step and stride lengths is also given. This thesis proposes a kind of nearest neighbor algorithm which used to identify human individual through features of gait acceleration data in time domain and frequency domain. Experiments demonstrate the effectiveness of our algorithm.
For the similarity and instability of short-term human activity signal, Discrete Hidden Markov Models used for gesture recognition are established with the combination of feature extraction by k-means clustering. The k-means clustering algorithm selects a small number of critical features from a large set by ranking different features according to the quality of the resulting clustering, and the small feature subset are taken as the input of DHMM, so as to identify different gestures. Experiments show that the feature selection algorithm can not only reduce the complexity of Discrete Hidden Markov Models, but also improve the recognition performance, and the method proposed in this thesis can be used for different kinds of sensor data, and extended to other kinds of short-term human activity identification.
Usually the recognition of daily human activity need to collect multi-sensor data, this thesis explores an information fusion algorithm based Na(?)ve Bayes so as to obtain higher-level contexts from a small number of sensor. The sensor data from single node are firstly classified by C4.5 Decision Tree or AdaBoost algorithm, once the confusion matrix of every sensor node have be gotten, the sensor fusion can be performed at the classifier level by calculating the corresponding posterior probability. In order to reduce the level of supervision, this thesis also analyzes the feasibility of active learning for searching most informative samples to be labeled by users in activity recognition. The Experimental results of daily human activity recognition indicate that our algorithm can extract low-level context information from few sensor nodes and then be processed to obtain high-level context information; and the active learning algorithm can detect the most informative unlabeled activity data to ask people to label, so as to learn from large amount of readily available unlabeled data. The research in this thesis owns important practical values in natural human-computer interaction.
Finally, it concludes the dissertation briefly, and the future research work is indicated.
引文
[1] Weiser M. The computer for the twenty-first century[R]. Scientific American, September, 1991: 10-94
[2] Harper R, Rodden T, Rogers Y and Sellen A. Being human: human-computer interaction in the year 2020[R]. Microsoft Research Ltd, England, 2008, ISBN: 978-0-9554761-1-2
[3] Dey A K. Understanding and using context[J]. Personal Ubiquitous Comput., 2001,5(1): 4-7
[4] Backman A, Bodin K, Bucht G, Janlert L E, Maxhall M, Pederson T, et.al. Easyadl - wearable support system for independent life despite dementia[C]. In CHI 2006 Workshop on Designing Technology for People with Cognitive Impairments, Montreal, Canada, April 2006
[5] Jafari R, Li W, Bajcsy R, Glaser S and Sastry S. Physical activity monitoring for assisted living at home[C]. 4th International Workshop on Wearable and Implantable Body Sensor Networks (Bsn 2007): March 26-28, 2007 RWTH Aachen University, Germany, 2007
[6] Bourke A K, O'Brien J V and Lyons G M. Evaluation of a thresholdbased tri-axial accelerometer fall detection algorithm[J]. Gait & Posture, 2007, 26(2): 194-199
[7] Pan C W. Rehabilitation exercises recognition based on acceleration signals. Master Thesis, Department of Computer Science and Information Engineering, Taiwan University, 2007
[8] Ermes M, Parkka J, Mantyjarvi J and Korhonen I. Detection of daily activities and sports with wearable sensors in controlled and uncontrolled conditions[C]. In Proceedings of the IEEE Transactions on Information Technology in Biomedicine 2008,12: 20-26
[9] Blum M L. Real-time context recognition. Master Thesis, Department of Information Technology and Electrical Engineering, Swiss Federal Institute of Technology Zurich (ETH), 2005
[10] Zhang H and Hartmann B. Building upon everyday play[C]. In Conference on Human Factors in Computing Systems (CHI). ACM Press New York,NY, USA, 2007
[11] Nintendo. Wii entertainment system. http://www.nintendo.com/wii
[12] Ward J A, Lukowicz P, Troster G and Starner T E. Activity recognition of assembly tasks using body-worn microphones and accelerometers[J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 28:10:1553-1567, October 2006.
[13] Bardram J E, Christensen H B. Pervasive computing support for hospitals: an overview of the activity-based computing project[J]. IEEE Pervasive Computing, 2007,6(1):44-51
[14] Tentori M, Favela J. Activity-aware computing for healthcare[J]. IEEE Pervasive Computing, 2008: 51-57
[15] Stiefmeier T, Roggen D, Ogris G, Lukowicz P and Troster G Wearable activity tracking in car manufacturing[J]. IEEE Pervasive Computing, 2008, 7(2)
[16] Dunne L E, Walsh P, Smyth B and Caulfield B. Design and evaluation of a wearable optical sensor for monitoring seated spinal posture[C]. In Proceedings of the 10th IEEE International Symposium on Wearable Computing(ISWC), 2006
[17] Intille S S, Larson K, Beaudin J S, Nawyn J, Tapia E M and Kaushik P. A living laboratory for the design and evaluation of ubiquitous computing technologies[C]. In Extended Abstracts of the 2005 Conference on Human Factors in Computing Systems. New York, NY: ACM Press, 2004
[18] Tapia E M, Intille S S and Larson K. Activity recognition in the home setting using simple and ubiquitous sensors[C]. Proceedings of PERVASIVE 2004, vol. LNCS 3001, A. Ferscha and F. Mattern, Eds. Berlin Heidelberg: Springer-Verlag, 2004: 158-175
[19] Lester J, Choudhury T, Kern N, Borriello G, Hannaford B. A hybrid discriminative-generative approach for modeling human activities[C]. Proceedings of International Joint Conference on Artificial Intelligence (IJCAI 2005), Edinburgh, United Kingdom, 2005: 766-772
[20] Gavrila D. The visual analysis of human movement: a survey[J]. Computer Vision and Image Understanding. 1999: 73(1): 82-98
[21] Pentland A. Looking at people: sensing for ubiquitous and wearable computing[J]. IEEE Trans Pattern Analysis and Machine Intelligence, 2000, 22 (1): 107-119
[22] Lee L. Gait analysis for classification[R]. AI Technical Report 2003-014, Massachusetts Institute of Technology-artificial Intelligence Laboratory, 2003
[23] Cunado D, Nixon M, Carter J. Using gait as a biometric, via phase-weighted magnitude spectra[C]. In:Proc International Conference on Audio- and Video-based Biometric Person Authentication, Crans-Montana, Switzerland, 1997: 95-102.
[24] Yoo J H, Nixon M S, Harris C J. Extracting gait signatures based on anatomical knowledge[C]. Proceedings of BMVA Symposium on Advancing Biometric Technologies, 2002
[25] Little J, Boyd J. Recognizing people by their gait: the shape of motion[J]. Videre: Journal of Computer Vision Research, The MIT Press, 1998,1(2)
[26] Kale A, Rajagopalan A N, et al. Identification of Humans Using Gait[J]. IEEE Transactons on Image Processing. Vol.13, No 9, September 2004.
[27] 王亮,胡卫明,谭铁牛.基于步态的身份识别[J]. 计算机学报, 2003, 26(3)
[28] Tapia E M. Using machine learning for real-time activity recognition and estimation of energy expenditure. PhD Thesis, MIT, June, 2008
[29] Subramanya A, Raj A, Bilmes J, Fox D. Recognizing activity and spatial context using wearable sensors. In: Uncertainly in Artificiallntelligence, 2006
[30] Kern N J. Multi-sensor context-awareness for wearable computing. Phd Thesis, DARMSTADT University of Technology Fachbereich 20, July, 2005
[31] Sawada H, Hashimoto S. Gesture recognition using an accelerometer sensor and its application to musical performance control. Electronics and Communications in Japan, Part 3, 80(5):9-17, 1997
[32] Paradiso J et al. Design and implementation of expressive footwear. IBM Systems Journal, 2000, 39:511-529
[33] Hoffman F, Heyer P arid Hommel G Velocity profile based recognition of dynamic gestures with discrete hidden Markov models[C]. In Proceedings of Gesture Workshop '97, page unknown. Springer Verlag, 1997
[34] Kern N, Troster G, Schiele B, Junker H and Lukowicz P. Wearable sensing to an-notate meeting recordings[C]. In Proceedings of the 6th IEEE International Symposium on Wearable Computers ( ISWC 2002), 2002: 186-196
[35] Kunze K, Barry M, Heinz E A, Lukowicz P, Majoe D and Gutknecht J. Towards recognizing tai chi - an initial experiment[C]. In Proceedings of the 3rd International Forum on Applied Wearable Computing, 2006
[36] Heinz E A, Kunze K S, Gruber M, Bannach D and Lukowicz P. Using wearable sensors for real-time recognition tasks in games of martial arts- an initial experiment[C]. In Proceedings of the 2nd IEEE symposium on Computational Intelligence and Games (CIG 2006), 2006: 98-102
[37] Chambers G S, Venkatesh S, West G and Bui H. Hierarchical recognition of intentional human gestures for sports video annotation[C]. In Proceedings of the 16th International Conference on Pattern Recognition (ICPR 2002), 2002: 1082-1085
[38] Chambers G S, Venkatesh S, West G and Bui H. Segmentation of intentional human gestures for sports video annotation[C]. In Proceedings of the 10th International Multimedia Modeling Conference (MMM 2004), 2004: 124-129
[39] Mantyjarvi J, Juha K, Panu K and Sanna K. Enabling fast and effortless customisation in accelerometer based gesture interaction. MUM, College Park, Maryland, 2004: 25-31
[40] Raj A, Subramanya A,, Bilmes J and Fox D. Rao-blackwellized particlefilters for recognizing activities and spatial context from wearable sensors[C]. In Experimental Robotics: The 10th International Symposium, Springer Tracts in Advanced Robotics (STAR), Springer-Verlag, 2006
[41] Bao L, Intille S S. Activity recognition from user-annotated acceleration data[C]. In Proceedings of the Second International Conference in Pervasive Computing (PERVASIVE '04). Vienna, Austria, 2004: 1-17
[42] Si H, Kim S J, Kawanishi N and Morikawa H. A context-aware reminding system for daily activities of dementia patients. In ISWAWC, 2007: 50
[43] Maitland J, Sherwood S, Barkhuus L, Anderson I, Hall M, Brown B, et.al. Increasing the awareness of daily activity levels with pervasive computing[C].In 1st International Conference on Pervasive Computing Technologies for Healthcare 2006,2006
[44] Andrew A, Anokwa Y, Koscher K, Lester J, Bordello G Context to make you more aware[C]. The 7th International Workshop on Smart Appliances and Wearable Computing, 2007
[45] Choudhury T, Borriello G, Consolvo S, Haehnel D, et al. The mobile sensing platform: an embedded activity recognition system[J]. IEEE Pervasive Computing, 2008, 7(2): 32-41
[46] news.sinopart.com/fstatic/upload/new/10090481.htm, “未来的汽车”.
[47] http://www.media.mit.edu/resenv/index.html.
[48] M(?)ntyj(?)rvi J, Lindholm M, et al. Identifying users of portable devices from gait pattern with accelerometers[C]. IEEE International Conference on Acoustics, Speech, and Signal Processing. 2005,2: 973-976
[49] Gafurov D, Helkala K, Soendrol T. Gait recognition using acceleration from MEMs. In: Availability, Reliability and Security, The First International Conference, 2006
[50] Bouten C V, Koekkoek K T, Verduin M, Kodde R and Janssen J D. A triaxial accelerometer and portable data processing unit for the assessment of daily physical activity[J]. IEEE Transactions on Bio-Medical Engineering, 1997,44(3): 136-147
[51] Randell C, Muller H. Context awareness by analysing accelerometer data[C]. In Proc. ISWC, Atlanta, GA, USA, 2000:175-176
[52] Laerhoven K, Cakmakci O. What shall we teach our pants?[C] In Proc. ISWC, Atlanta, GA, USA, 2000: 77-86
[53] Laerhoven K, Aido K, Lowette S. Real-time analysis of data from many sensors with neural networks[C]. In Proc. ISWC, Zurich, Switzerland, 2001: 115-123
[54] Mantyjarvi J, Himberg J, Seppanen T. Recognizing human motion with multiple acceleration sensors[C]. In Proc. Systems, Man and Cybernetics, 2001: 747-752
[55] Kern N, Schiele B. Context-aware notfication for wearable computing[C]. In Proc. ISWC, White Plains, NY, USA, October 2003: 223-230
[56] Schmidt A, Aidoo K A, Takaluoma A, Tuomela U, Laerhoven K V and Velde W V. Advanced interaction in context[C]. In HUC, 1999: 89-101
[57] Peltonen V, Tuomi J, Klapuri A, Huopaniemi J and Sorsa T. Computational auditory scene recognition[C]. In Proc. ICASSP, 2002: 1941-1944
[58] Huynh T, Schiele B. Analyzing features for activity recognition[C]. In J. Conf. on Smart Objects and Ambient Intelligence, 2005
[59] Najafi B, Aminian K, Parschiv-Ionescu A, Loew F, B(?)la C and Robert P. Ambulatory system for human motion analysis using a kinematic sensor: monitoring of daily physical activity in the elderly[J]. IEEE Transactions on Biomedical Engineering, 2003, 50(6):711-723
[60] Lukowicz P, Ward J A, Junker H, Stager M, Troster G, Atrash A and Starner T. Recognizing workshop activity using body worn microphones and accelerometers[C]. In Proc. of the 2nd Int'1 Conf. on Pervasive Computing, 2004:18-22
[61] Pirttikangas S, Fujinami K and Nakajima T. Feature selection and activity recognition from wearable sensors[C]. In Int.Symp. on Ubi. Comp. Sys., 2006
[62] Benbasat A, Paradiso J. Groggy wakeup-automated generation of power-efficient detection hierarchies for wearable sensors[C]. In Int. Work, on Wearable and Implantable Body Sensor Networks, 2007
[63] Huynh T. Human activity recognition with wearable sensors. Phd Thesis, TECHNISCHE UNIVERSITAT DARMSTADT Fachbereich Informatik, German, 2008
[64] Ravi N, Dandekar N, Mysore P and Littman M L. Activity recognition from accelerometer data[C]. In Proceedings of the Seventeenth Innovative Applications of Artificial Intelligence Conference. Pittsburgh, Pennsylvania, 2005
[65] Maurer U, Smailagic A, Siewiorek D P and Deisher M. Activity recognition and monitoring using multiple sensors on different body positions[C]. In Proceedings of the International Workshop on Wearable and Implantable Body Sensor Networks (BSN'06): IEEE Computer Society 2006:113-116
[66] Chieu H L, Lee W S and Kaelbling L P. Activity recognition from physiological data using conditional random fields[C]. In Proceedings of the Singapore-MIT Alliance (SMA) Computer Science Program. Cambridge, MA, 2006
[67] Mithchell T M著，曾华军，张银奎等译．机器学习．机械工业出版社，2004
[68] Rabiner L R. A tutorial on hidden markov models and selected applications in speech recognition[C]. Proceedings of the IEEE, 1989, 77(2): 257-286
[69] 谷秋隆嗣编著，朱虹译．语音与图像的数字信号处理．科学出版社，2003年
[70] Lee S W, Mase K. Recognition of walking behaviors for pedestrian navigation[C]. In Proceedings of 2001 IEEE Conference on Control Applications (CCA01), 2001
[71] Aminian K, Robert P, Buchser E E, Rutschmann B, Hayoz D and Depairon M. Physical activity monitoring based on accelerometry: validation and comparison with video Observation. Medical & Biological Engineering & Computing, 1999, 37(3):304308
[72] Parkka J, Ermes M, Korpipaa P, Mantyjarvi J, Peltola J and Korhonen I. Activity classification using realistic data from wearable sensors[J]. IEEE Transactions on Information Technology in Biomedicine, 2006: 10(1): 119-128
[73] Benbasat A Y, Paradiso J A. A framework for the automated generation of power-efficient classifiers for embedded sensor nodes[C]. In Proceedings of the 5th ACM Conference on Embedded Networked Sensor Systems. 2007:219-232
[74] Yang J Y, Wang J S and Chen Y P. Using acceleration measurements for activity recognition: an effective learning algorithm for constructing neural classifiers[J]. Pattern Recognition Letters, 2008, 29: 2213-2220
[75] Hastie T，Tibshirani R，Friedman J著，范明，柴玉梅等译．统计学习基础-数据挖掘、推理与预测．电子工业出版社，2005
[76] 彭军．传感器与检测技术．西安：西安电子科技大学出版社，2003．11
[77] http://www.new-lifestyles.com/DIGIWALKER/sw200.html
[78] Krause A, Ihmig M, Rankin E, Leong D, Gupta S, Siewiorek D, et.al. Trading off prediction accuracy and power consumption for context-aware wearable computing[C]. In Proceedings of the 9th IEEE International Symposium on Wearable Computers, 2005: 20-26
[79] Farella E, O'Modhrain M, Benini L and Ricco B. Gesture signature for ambient intelligence applications: a feasibility study[C]. In Proceedings of the 4th International Conference on Pervasive Computing, 2006: 288-304
[80] Morris S J. A shoe-integrated sensor system for wireless gait analysis and real-time therapeutic feedback. Phd Thesis, MIT, June, 2004
[81] DeVaul R W, Dunn S. Real-time motion classification for wearable computing applications[R]. Technical report, MIT Media Laboratory, 2001
[82] Freescale Devices. MMA7260Q data sheet. http://www.freescale. com/webapp/sps/prod-summary.jsp?code=MMA7260Q&srch=l, Last visit: 03. 02.2006
[83] Analog Devices. ADUC841 data sheet, http://www.analog.com/ UploadedFiles/Data_Sheets/ADUC84l_842_843ANOMALY.pdf, Last visit: 14.05, 2006
[84] http://www.appcon.com.cn
[85] Benbasat A Y, Paradiso J A. An inertial measurement framework for gesture recognition and applications [C]. Revised Papers from the International Gesture Workshop on Gesture and Sign Languages in Human-Computer Interaction, April,2001:9-20
[86] Davy J L, Dunn I P. The statistical bandwidth of Butterworth filters[J]. Journal of Sound and Vibration, 1987, 115(3): 539-549
[87] Arbieri R, Farella E, et.al. A low-power motion capture system with integrated accelerometers[C]. Proceedings of 2004 First Consumer Communications And Networking Conference, 2004: 418-423
[88] Averbuch A Z, Pevnyi A B, Zheludev V A. Butterworth wavelet transforms derived from discrete interpolatory splines:recursive implementation[J]. Signal Processing,2001, 81(11): 2363-2382
[89] 程佩青著。数字信号处理教程(第二版)。清华大学出版社,2001
[90] Sequeira M M, Rickenbach M, Wietlisbach V, Tullen B and Schutz Y. Physical activity assessment using a pedometer and its comparison with a questionnaire in a large population survey[J]. Am J Epidemiol 1995, 142(9): 989-99
[91] Cutting J T, Proffitt D R and Kozlowski L T. A biomechanical invariant for gait perception[C]. J. Exp. Psych. Human Perception and Performance, 1978:357-372
[92] Tabb K, Davey N, Adams R and George S. Analysis of human motion using snakes and neural networks[C]. Proc.IWAMDO, Palma de Mallorca, Balaeric Islands, 2000: 48-57
[93] Murray M P, Drought A B and Kory R C. Walking patterns of normal men. J. Bone and Joint Surgery, 1964,46-a(2): 335-360
[94] Hosein R, Lord M. A study of in-shoe plantar shear in normals[J]. Clinical Biomechanics, 2000, (15): 46-53
[95] Perna A. Tapping into MIDI[J]. Keyboard Magazine, 1988:27
[96] 戴克戎．步态分析及其应用．中国骨科杂志，1991，11：207
[97] Moe-Nilssen R, Helbostad J L. Estimation of gait cycle characteristics of trunk accelerometry[J]. Journal of Biomechanics, 2004, 37:121-126
[98] Murray M P. Gait as a total pattern of movement[J]. American Journal of Physical Medicine, 1967, 46(1): 290-332
[99] Cutting J, Barclay C and Kozlowski L. Temporal and spatial factors in gait perception that influence gender recognition[J]. Perception and Psychophysics, 1978, 23(2): 145-152
[100] Cutting J, Kozlowski L. Recognition friends by their walk: gait perception without familiarity cues[J]. Bulletin of the Psychonomic Society, 1977. 9(5): 353-356
[101] Ralston H J, Inman V, Todd F. Human Walking[M]. Baltimore: Williams and Wilkins, 1981.
[102] http://www.darpa.mil/ito/research/hid/index.html
[103] Ailisto H, Lindholm M, M(a|¨)ntyj(a|¨)rvi J, Vildjiounaite E and M(a|¨)kel(a|¨) S M. Identifying people from gait pattern with accelerometers[C]. In Proceedings of SPIE Volume: 5779; Biometric Technology for Human Identification Ⅱ, 2005: 7-14
[104] Ailisto H, Haataja, et al. Wearable context aware terminal for maintenance personnel[C]. First European Symposium on Ambient Intelligence, 2003:149-159
[105] Pirttikangas S, Suutala J, et al. Footstep identification from pressure signals using hidden Markov models[C]. Finnish Signal Processing Symposium, 2003:124-128
[106] Duda R O，Hart P E，Stork D G著，李宏东，姚天翔等译．模式分类．机械工业出版社，2006
[107] Kale A, Cuntoor N, Yegnanarayana B, Rajagopalan A N and Chellappa R. Gait analysis for human identification[C]. In Audio- and Video-Based Biometric Person Authentication, AVBPA. Guildford, UK: Springer, 2003:706-714
[108] Chen S, Chen W. Generalized minimal distortion segmentation for ANN-based speech recognition[J]. IEEE Trans on Speech and Audio Processing, 1995, 3(2): 141-145
[109] Zhu S, Chen D, Huang T. Feature parameter curve method for high performance NN-based speech recognition[C]. Proc. ICASSP, 1996:1-4
[110] 史笑兴，顾明亮，王太君等．一种时间规整算法在神经网络语音识别中的应用[J]．东南大学学报，1999，29(5)：47-51
[111] 边肇祺等．模式识别．第二版．北京：清华大学出版社，2000
[112] Witten U H，Frank E著，董琳，邱泉等译．数据挖掘-实用机器学习技术．机械工业出版社，2006
[113] Wang L, Tan T, Hu W, Ning H. Automatic gait recognition based on statistical shape analysis[J]. IEEE Transactions on Image Processing, 2003, 12(9): 1120-1131
[114] Yam C Y, Nixon M S, Carter JN. Automated person recognition by walking and running via model-based approaches. Pattern Recognition, 2004, 37(5): 1057-1072
[115] Cho I, Sunwoo J, Son Y, Oh M, Lee C. Development of a Single 3-axis Accelerometer Sensor Based Wearable Gesture Recognition Band[C]. In Proceedings of Ubiquitous Intelligence and Computing, Hong Kong, 2007: 43-52
[116] Kela J, Korpipaa P, M(a|¨)ntyj(a|¨)rvi J, et. al, Accelerometer-based gesture control for a design environment[C], In Pers Ubiquit Comput 10, 2006: 285-299
[117] Speeter T H. Transformation human hand motion for telemanipulation[J]. Presence, 1992, 1(1): 63-79
[118] Vardy A, Robinson J, Cheng LT. The wristCam as input device[C]. In Proc. ISWC, San Francisco, 1999:199-202
[119] Starner T, Weaver J, Pentland A. Real-time american sign language recognition using desk and wearable computer based video[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(12): 1371-1375
[120] Brashear H, Starner T, Lukowicz P, Junker H. Using multiple sensors for mobile sign language recognition[C]. In Proc.ISWC, White Plains, NY, USA, 2003:45-52
[121] Hinckley K, Pierce J, Sinclair M, Horvitz E. Sensing techniques for mobile interaction[C]. In User Interface Software and Technology, 2000: 91-100
[122] Perng J K, Fisher B, Hollar S and Pister K. Acceleration sensing glove[C]. In Proc. ISWC, San Francisco, 1999: 178-181
[123] Li C, Zheng S Q and Prabhakaran B. Segmentation and recognition of motion streams by similarity search[J]. ACM Trans. Multimedia Computing,Communications and Applications, 2007
[124] http://www.seas.upenn.edu/-cis505/proj/dasapich/project.htm
[125] Pylvanainen T. Accelerometer based gesture recognition using continuous HMMs[C]. Proceedings of the Second Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA) 2005: 639-646
[126] Mantyla V M. Discrete hidden Markov models with application to isolated user-dependent hand gesture recognition. Espoo: VTT Publications 2001,449, 104p.http://www.vtt.fi/inf/pdf/publications/2001/P449.pdf
[127] Huynh T, Schiele B. Analyzing features for activity recognition[C]. In Proceedings of the 2005 joint conference on Smart objects and ambient intelligence: innovative context-aware services: usages and technologies (soc-EUSAI), Grenoble, France,2005: 159-163
[128] Schmidt A. Implicit human computer interaction through context[J]. Journal of Personal Technologies, Vol. 4,2000: 191-199
[129] Lee S, Mase K. Activity and location recognition using wearable sensors[J].Pervasive Computing, 2002,1(3): 24-32
[130] Kern N, Schiele B, Schmidt A. Recognizing context for annotating a live life recording[C]. Personal and Ubiquituous Computing, 2005
[131] Kern N, Schiele B, Junker H, Lukowicz P and Trster G Wearable sensing to annotate meeting recordings[C]. In The International Symposiumon Wearable Computers, 20037(5): 263-274
[132] BodyMedia Inc. The BodyBugg Armband, http://www.bodybugg.com/
[133] MiniSun. The Intelligent Device for Energy Expenditure and Activity (IDEEA).http://www.minisun.com/
[134] Andre D, Pelletier R, Farringdon J, et al. The development of the sensewear armband, a revolutionary energy assessment device to assess physical activity and lifestyle[R]. Technical Report, BodyMedia Inc, 2006
[135] Karantonis D M, Narayanan M R, Mathie M, Lovell N H and Celler BG. Implementation of a real-time human movement classifier using a triaxial accelerometer for ambulatory monitoring[J]. IEEE Trans. Inform. Technol. Biomed,2006, 10(1): 156-167
[136] Mathie M J, Celler BG, Lovell N H, Coster A C F. Classification of basic daily
锘??movements using a triaxial accelerometer[J]. Med. Biol. Eng. Comput. 2004, 42(5):679-687
[137] Sola J, Celka P, Dasen S and Chetelat 0. Very low complexity algorithm for ambulatory activity classification[C]. In: 3rd European Med. Biol. Conf. EMBEC 2005
[138] Keogh E, Chu S, Hart D, Pazzani M. An online algorithm for segmenting time series[C]. In Proceedings of the IEEE International Conference on Data Mining,2001:289-296
[139] Brown P J. Triggering information by context[J]. Personal Technologies, 1998, 2(1):18-27
[140] Kearns M, Valiant L G Cryptographic limitations on learning boolean formulae and finite automata[J]. Journal of the ACM, 1994,41(1): 67-95
[141] Foerster F, Smeja M and Fahrenberg J. Detection of posture and motion by accelerometry: a validation in ambulatory monitoring[J]. Computers in Human Behavior, 1999, 15: 571-583
[142] Blum A L, Langley P. Selection of relevant features and examples in machine learning [J]. Artificial Intelligence, 1997, 97(12): 245-271
[143] Maron O. Learning from ambiguity. PhD dissertation, Department of Electrical and Computer Science, MIT, Cambridge, MA, 1998
[144] 周志华,王珏主编。机器学习及应用。北京：清华大学出版社,2007: 259-275
[145] Conn D A, Chah ramani Z, Jordan M I. Active learning with statistical models [J].Journal of Artificial Intelligence Research, 1996,4: 129-145
[146] Freund Y, Seung H S, Shamir E, Tishby N. Selective sampling using the query by committee algorithm[J]. Machine Learning, 1997: 133-168
[147] Dagon I, Engelson S. Committee-based sampling for training probabilistic classifiers[C]. In Process of the 12th International Confonerence Machine Learning,SanFrancisco, CA: Morgan Kaufrnann, 1995: 150-157
[148] Engelson S, Dagon I Committee-based sample selection for probabilistic classifiers[J]. Journal of Artificial Intelligence research, 1999, 11:335-360
[149] Lewis D D, Gail W A. A sequential algorithm for training text classifiers[C]. In Process of the 17th ACM International Confonerence Research and Development in Information Retrieval, Berlin:Springer, 1994: 3-12
[150] Mccallum A, Nigam K. Employing EM and pool-based active learning for text classification[C]. In Proc of the 15th nternational Confonerence MachineLearning, SanFrancisco, CA: Morgan Kaufmann, 1998:350-358
[151] Muslea I, Minton S, Knoblock C A. Active learning with multiple view[J]. Journal of Artificial Intelligence Research, 2006, 27: 203-233
[152] Seung H, Opper M and Sompolinsky H. Query by Committee[C]. In Computational Learning Theory, 1992: 287-294
[153] Friedman J H On Bias, Variance, 0/1-Loss, and the Curse-of-Dimensionality. Data Mining and Knowledge Discovery, 1997, 1(1): 55-277
[154] 张旭东．离散随机信号处理．北京：清华大学出版社，2006
[2] Harper R, Rodden T, Rogers Y and Sellen A. Being human: human-computer interaction in the year 2020[R]. Microsoft Research Ltd, England, 2008, ISBN: 978-0-9554761-1-2
[3] Dey A K. Understanding and using context[J]. Personal Ubiquitous Comput., 2001,5(1): 4-7
[4] Backman A, Bodin K, Bucht G, Janlert L E, Maxhall M, Pederson T, et.al. Easyadl - wearable support system for independent life despite dementia[C]. In CHI 2006 Workshop on Designing Technology for People with Cognitive Impairments, Montreal, Canada, April 2006
[5] Jafari R, Li W, Bajcsy R, Glaser S and Sastry S. Physical activity monitoring for assisted living at home[C]. 4th International Workshop on Wearable and Implantable Body Sensor Networks (Bsn 2007): March 26-28, 2007 RWTH Aachen University, Germany, 2007
[6] Bourke A K, O'Brien J V and Lyons G M. Evaluation of a thresholdbased tri-axial accelerometer fall detection algorithm[J]. Gait & Posture, 2007, 26(2): 194-199
[7] Pan C W. Rehabilitation exercises recognition based on acceleration signals. Master Thesis, Department of Computer Science and Information Engineering, Taiwan University, 2007
[8] Ermes M, Parkka J, Mantyjarvi J and Korhonen I. Detection of daily activities and sports with wearable sensors in controlled and uncontrolled conditions[C]. In Proceedings of the IEEE Transactions on Information Technology in Biomedicine 2008,12: 20-26
[9] Blum M L. Real-time context recognition. Master Thesis, Department of Information Technology and Electrical Engineering, Swiss Federal Institute of Technology Zurich (ETH), 2005
[10] Zhang H and Hartmann B. Building upon everyday play[C]. In Conference on Human Factors in Computing Systems (CHI). ACM Press New York,NY, USA, 2007
[11] Nintendo. Wii entertainment system. http://www.nintendo.com/wii
[12] Ward J A, Lukowicz P, Troster G and Starner T E. Activity recognition of assembly tasks using body-worn microphones and accelerometers[J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 28:10:1553-1567, October 2006.
[13] Bardram J E, Christensen H B. Pervasive computing support for hospitals: an overview of the activity-based computing project[J]. IEEE Pervasive Computing, 2007,6(1):44-51
[14] Tentori M, Favela J. Activity-aware computing for healthcare[J]. IEEE Pervasive Computing, 2008: 51-57
[15] Stiefmeier T, Roggen D, Ogris G, Lukowicz P and Troster G Wearable activity tracking in car manufacturing[J]. IEEE Pervasive Computing, 2008, 7(2)
[16] Dunne L E, Walsh P, Smyth B and Caulfield B. Design and evaluation of a wearable optical sensor for monitoring seated spinal posture[C]. In Proceedings of the 10th IEEE International Symposium on Wearable Computing(ISWC), 2006
[17] Intille S S, Larson K, Beaudin J S, Nawyn J, Tapia E M and Kaushik P. A living laboratory for the design and evaluation of ubiquitous computing technologies[C]. In Extended Abstracts of the 2005 Conference on Human Factors in Computing Systems. New York, NY: ACM Press, 2004
[18] Tapia E M, Intille S S and Larson K. Activity recognition in the home setting using simple and ubiquitous sensors[C]. Proceedings of PERVASIVE 2004, vol. LNCS 3001, A. Ferscha and F. Mattern, Eds. Berlin Heidelberg: Springer-Verlag, 2004: 158-175
[19] Lester J, Choudhury T, Kern N, Borriello G, Hannaford B. A hybrid discriminative-generative approach for modeling human activities[C]. Proceedings of International Joint Conference on Artificial Intelligence (IJCAI 2005), Edinburgh, United Kingdom, 2005: 766-772
[20] Gavrila D. The visual analysis of human movement: a survey[J]. Computer Vision and Image Understanding. 1999: 73(1): 82-98
[21] Pentland A. Looking at people: sensing for ubiquitous and wearable computing[J]. IEEE Trans Pattern Analysis and Machine Intelligence, 2000, 22 (1): 107-119
[22] Lee L. Gait analysis for classification[R]. AI Technical Report 2003-014, Massachusetts Institute of Technology-artificial Intelligence Laboratory, 2003
[23] Cunado D, Nixon M, Carter J. Using gait as a biometric, via phase-weighted magnitude spectra[C]. In:Proc International Conference on Audio- and Video-based Biometric Person Authentication, Crans-Montana, Switzerland, 1997: 95-102.
[24] Yoo J H, Nixon M S, Harris C J. Extracting gait signatures based on anatomical knowledge[C]. Proceedings of BMVA Symposium on Advancing Biometric Technologies, 2002
[25] Little J, Boyd J. Recognizing people by their gait: the shape of motion[J]. Videre: Journal of Computer Vision Research, The MIT Press, 1998,1(2)
[26] Kale A, Rajagopalan A N, et al. Identification of Humans Using Gait[J]. IEEE Transactons on Image Processing. Vol.13, No 9, September 2004.
[27] 王亮,胡卫明,谭铁牛.基于步态的身份识别[J]. 计算机学报, 2003, 26(3)
[28] Tapia E M. Using machine learning for real-time activity recognition and estimation of energy expenditure. PhD Thesis, MIT, June, 2008
[29] Subramanya A, Raj A, Bilmes J, Fox D. Recognizing activity and spatial context using wearable sensors. In: Uncertainly in Artificiallntelligence, 2006
[30] Kern N J. Multi-sensor context-awareness for wearable computing. Phd Thesis, DARMSTADT University of Technology Fachbereich 20, July, 2005
[31] Sawada H, Hashimoto S. Gesture recognition using an accelerometer sensor and its application to musical performance control. Electronics and Communications in Japan, Part 3, 80(5):9-17, 1997
[32] Paradiso J et al. Design and implementation of expressive footwear. IBM Systems Journal, 2000, 39:511-529
[33] Hoffman F, Heyer P arid Hommel G Velocity profile based recognition of dynamic gestures with discrete hidden Markov models[C]. In Proceedings of Gesture Workshop '97, page unknown. Springer Verlag, 1997
[34] Kern N, Troster G, Schiele B, Junker H and Lukowicz P. Wearable sensing to an-notate meeting recordings[C]. In Proceedings of the 6th IEEE International Symposium on Wearable Computers ( ISWC 2002), 2002: 186-196
[35] Kunze K, Barry M, Heinz E A, Lukowicz P, Majoe D and Gutknecht J. Towards recognizing tai chi - an initial experiment[C]. In Proceedings of the 3rd International Forum on Applied Wearable Computing, 2006
[36] Heinz E A, Kunze K S, Gruber M, Bannach D and Lukowicz P. Using wearable sensors for real-time recognition tasks in games of martial arts- an initial experiment[C]. In Proceedings of the 2nd IEEE symposium on Computational Intelligence and Games (CIG 2006), 2006: 98-102
[37] Chambers G S, Venkatesh S, West G and Bui H. Hierarchical recognition of intentional human gestures for sports video annotation[C]. In Proceedings of the 16th International Conference on Pattern Recognition (ICPR 2002), 2002: 1082-1085
[38] Chambers G S, Venkatesh S, West G and Bui H. Segmentation of intentional human gestures for sports video annotation[C]. In Proceedings of the 10th International Multimedia Modeling Conference (MMM 2004), 2004: 124-129
[39] Mantyjarvi J, Juha K, Panu K and Sanna K. Enabling fast and effortless customisation in accelerometer based gesture interaction. MUM, College Park, Maryland, 2004: 25-31
[40] Raj A, Subramanya A,, Bilmes J and Fox D. Rao-blackwellized particlefilters for recognizing activities and spatial context from wearable sensors[C]. In Experimental Robotics: The 10th International Symposium, Springer Tracts in Advanced Robotics (STAR), Springer-Verlag, 2006
[41] Bao L, Intille S S. Activity recognition from user-annotated acceleration data[C]. In Proceedings of the Second International Conference in Pervasive Computing (PERVASIVE '04). Vienna, Austria, 2004: 1-17
[42] Si H, Kim S J, Kawanishi N and Morikawa H. A context-aware reminding system for daily activities of dementia patients. In ISWAWC, 2007: 50
[43] Maitland J, Sherwood S, Barkhuus L, Anderson I, Hall M, Brown B, et.al. Increasing the awareness of daily activity levels with pervasive computing[C].In 1st International Conference on Pervasive Computing Technologies for Healthcare 2006,2006
[44] Andrew A, Anokwa Y, Koscher K, Lester J, Bordello G Context to make you more aware[C]. The 7th International Workshop on Smart Appliances and Wearable Computing, 2007
[45] Choudhury T, Borriello G, Consolvo S, Haehnel D, et al. The mobile sensing platform: an embedded activity recognition system[J]. IEEE Pervasive Computing, 2008, 7(2): 32-41
[46] news.sinopart.com/fstatic/upload/new/10090481.htm, “未来的汽车”.
[47] http://www.media.mit.edu/resenv/index.html.
[48] M(?)ntyj(?)rvi J, Lindholm M, et al. Identifying users of portable devices from gait pattern with accelerometers[C]. IEEE International Conference on Acoustics, Speech, and Signal Processing. 2005,2: 973-976
[49] Gafurov D, Helkala K, Soendrol T. Gait recognition using acceleration from MEMs. In: Availability, Reliability and Security, The First International Conference, 2006
[50] Bouten C V, Koekkoek K T, Verduin M, Kodde R and Janssen J D. A triaxial accelerometer and portable data processing unit for the assessment of daily physical activity[J]. IEEE Transactions on Bio-Medical Engineering, 1997,44(3): 136-147
[51] Randell C, Muller H. Context awareness by analysing accelerometer data[C]. In Proc. ISWC, Atlanta, GA, USA, 2000:175-176
[52] Laerhoven K, Cakmakci O. What shall we teach our pants?[C] In Proc. ISWC, Atlanta, GA, USA, 2000: 77-86
[53] Laerhoven K, Aido K, Lowette S. Real-time analysis of data from many sensors with neural networks[C]. In Proc. ISWC, Zurich, Switzerland, 2001: 115-123
[54] Mantyjarvi J, Himberg J, Seppanen T. Recognizing human motion with multiple acceleration sensors[C]. In Proc. Systems, Man and Cybernetics, 2001: 747-752
[55] Kern N, Schiele B. Context-aware notfication for wearable computing[C]. In Proc. ISWC, White Plains, NY, USA, October 2003: 223-230
[56] Schmidt A, Aidoo K A, Takaluoma A, Tuomela U, Laerhoven K V and Velde W V. Advanced interaction in context[C]. In HUC, 1999: 89-101
[57] Peltonen V, Tuomi J, Klapuri A, Huopaniemi J and Sorsa T. Computational auditory scene recognition[C]. In Proc. ICASSP, 2002: 1941-1944
[58] Huynh T, Schiele B. Analyzing features for activity recognition[C]. In J. Conf. on Smart Objects and Ambient Intelligence, 2005
[59] Najafi B, Aminian K, Parschiv-Ionescu A, Loew F, B(?)la C and Robert P. Ambulatory system for human motion analysis using a kinematic sensor: monitoring of daily physical activity in the elderly[J]. IEEE Transactions on Biomedical Engineering, 2003, 50(6):711-723
[60] Lukowicz P, Ward J A, Junker H, Stager M, Troster G, Atrash A and Starner T. Recognizing workshop activity using body worn microphones and accelerometers[C]. In Proc. of the 2nd Int'1 Conf. on Pervasive Computing, 2004:18-22
[61] Pirttikangas S, Fujinami K and Nakajima T. Feature selection and activity recognition from wearable sensors[C]. In Int.Symp. on Ubi. Comp. Sys., 2006
[62] Benbasat A, Paradiso J. Groggy wakeup-automated generation of power-efficient detection hierarchies for wearable sensors[C]. In Int. Work, on Wearable and Implantable Body Sensor Networks, 2007
[63] Huynh T. Human activity recognition with wearable sensors. Phd Thesis, TECHNISCHE UNIVERSITAT DARMSTADT Fachbereich Informatik, German, 2008
[64] Ravi N, Dandekar N, Mysore P and Littman M L. Activity recognition from accelerometer data[C]. In Proceedings of the Seventeenth Innovative Applications of Artificial Intelligence Conference. Pittsburgh, Pennsylvania, 2005
[65] Maurer U, Smailagic A, Siewiorek D P and Deisher M. Activity recognition and monitoring using multiple sensors on different body positions[C]. In Proceedings of the International Workshop on Wearable and Implantable Body Sensor Networks (BSN'06): IEEE Computer Society 2006:113-116
[66] Chieu H L, Lee W S and Kaelbling L P. Activity recognition from physiological data using conditional random fields[C]. In Proceedings of the Singapore-MIT Alliance (SMA) Computer Science Program. Cambridge, MA, 2006
[67] Mithchell T M著，曾华军，张银奎等译．机器学习．机械工业出版社，2004
[68] Rabiner L R. A tutorial on hidden markov models and selected applications in speech recognition[C]. Proceedings of the IEEE, 1989, 77(2): 257-286
[69] 谷秋隆嗣编著，朱虹译．语音与图像的数字信号处理．科学出版社，2003年
[70] Lee S W, Mase K. Recognition of walking behaviors for pedestrian navigation[C]. In Proceedings of 2001 IEEE Conference on Control Applications (CCA01), 2001
[71] Aminian K, Robert P, Buchser E E, Rutschmann B, Hayoz D and Depairon M. Physical activity monitoring based on accelerometry: validation and comparison with video Observation. Medical & Biological Engineering & Computing, 1999, 37(3):304308
[72] Parkka J, Ermes M, Korpipaa P, Mantyjarvi J, Peltola J and Korhonen I. Activity classification using realistic data from wearable sensors[J]. IEEE Transactions on Information Technology in Biomedicine, 2006: 10(1): 119-128
[73] Benbasat A Y, Paradiso J A. A framework for the automated generation of power-efficient classifiers for embedded sensor nodes[C]. In Proceedings of the 5th ACM Conference on Embedded Networked Sensor Systems. 2007:219-232
[74] Yang J Y, Wang J S and Chen Y P. Using acceleration measurements for activity recognition: an effective learning algorithm for constructing neural classifiers[J]. Pattern Recognition Letters, 2008, 29: 2213-2220
[75] Hastie T，Tibshirani R，Friedman J著，范明，柴玉梅等译．统计学习基础-数据挖掘、推理与预测．电子工业出版社，2005
[76] 彭军．传感器与检测技术．西安：西安电子科技大学出版社，2003．11
[77] http://www.new-lifestyles.com/DIGIWALKER/sw200.html
[78] Krause A, Ihmig M, Rankin E, Leong D, Gupta S, Siewiorek D, et.al. Trading off prediction accuracy and power consumption for context-aware wearable computing[C]. In Proceedings of the 9th IEEE International Symposium on Wearable Computers, 2005: 20-26
[79] Farella E, O'Modhrain M, Benini L and Ricco B. Gesture signature for ambient intelligence applications: a feasibility study[C]. In Proceedings of the 4th International Conference on Pervasive Computing, 2006: 288-304
[80] Morris S J. A shoe-integrated sensor system for wireless gait analysis and real-time therapeutic feedback. Phd Thesis, MIT, June, 2004
[81] DeVaul R W, Dunn S. Real-time motion classification for wearable computing applications[R]. Technical report, MIT Media Laboratory, 2001
[82] Freescale Devices. MMA7260Q data sheet. http://www.freescale. com/webapp/sps/prod-summary.jsp?code=MMA7260Q&srch=l, Last visit: 03. 02.2006
[83] Analog Devices. ADUC841 data sheet, http://www.analog.com/ UploadedFiles/Data_Sheets/ADUC84l_842_843ANOMALY.pdf, Last visit: 14.05, 2006
[84] http://www.appcon.com.cn
[85] Benbasat A Y, Paradiso J A. An inertial measurement framework for gesture recognition and applications [C]. Revised Papers from the International Gesture Workshop on Gesture and Sign Languages in Human-Computer Interaction, April,2001:9-20
[86] Davy J L, Dunn I P. The statistical bandwidth of Butterworth filters[J]. Journal of Sound and Vibration, 1987, 115(3): 539-549
[87] Arbieri R, Farella E, et.al. A low-power motion capture system with integrated accelerometers[C]. Proceedings of 2004 First Consumer Communications And Networking Conference, 2004: 418-423
[88] Averbuch A Z, Pevnyi A B, Zheludev V A. Butterworth wavelet transforms derived from discrete interpolatory splines:recursive implementation[J]. Signal Processing,2001, 81(11): 2363-2382
[89] 程佩青著。数字信号处理教程(第二版)。清华大学出版社,2001
[90] Sequeira M M, Rickenbach M, Wietlisbach V, Tullen B and Schutz Y. Physical activity assessment using a pedometer and its comparison with a questionnaire in a large population survey[J]. Am J Epidemiol 1995, 142(9): 989-99
[91] Cutting J T, Proffitt D R and Kozlowski L T. A biomechanical invariant for gait perception[C]. J. Exp. Psych. Human Perception and Performance, 1978:357-372
[92] Tabb K, Davey N, Adams R and George S. Analysis of human motion using snakes and neural networks[C]. Proc.IWAMDO, Palma de Mallorca, Balaeric Islands, 2000: 48-57
[93] Murray M P, Drought A B and Kory R C. Walking patterns of normal men. J. Bone and Joint Surgery, 1964,46-a(2): 335-360
[94] Hosein R, Lord M. A study of in-shoe plantar shear in normals[J]. Clinical Biomechanics, 2000, (15): 46-53
[95] Perna A. Tapping into MIDI[J]. Keyboard Magazine, 1988:27
[96] 戴克戎．步态分析及其应用．中国骨科杂志，1991，11：207
[97] Moe-Nilssen R, Helbostad J L. Estimation of gait cycle characteristics of trunk accelerometry[J]. Journal of Biomechanics, 2004, 37:121-126
[98] Murray M P. Gait as a total pattern of movement[J]. American Journal of Physical Medicine, 1967, 46(1): 290-332
[99] Cutting J, Barclay C and Kozlowski L. Temporal and spatial factors in gait perception that influence gender recognition[J]. Perception and Psychophysics, 1978, 23(2): 145-152
[100] Cutting J, Kozlowski L. Recognition friends by their walk: gait perception without familiarity cues[J]. Bulletin of the Psychonomic Society, 1977. 9(5): 353-356
[101] Ralston H J, Inman V, Todd F. Human Walking[M]. Baltimore: Williams and Wilkins, 1981.
[102] http://www.darpa.mil/ito/research/hid/index.html
[103] Ailisto H, Lindholm M, M(a|¨)ntyj(a|¨)rvi J, Vildjiounaite E and M(a|¨)kel(a|¨) S M. Identifying people from gait pattern with accelerometers[C]. In Proceedings of SPIE Volume: 5779; Biometric Technology for Human Identification Ⅱ, 2005: 7-14
[104] Ailisto H, Haataja, et al. Wearable context aware terminal for maintenance personnel[C]. First European Symposium on Ambient Intelligence, 2003:149-159
[105] Pirttikangas S, Suutala J, et al. Footstep identification from pressure signals using hidden Markov models[C]. Finnish Signal Processing Symposium, 2003:124-128
[106] Duda R O，Hart P E，Stork D G著，李宏东，姚天翔等译．模式分类．机械工业出版社，2006
[107] Kale A, Cuntoor N, Yegnanarayana B, Rajagopalan A N and Chellappa R. Gait analysis for human identification[C]. In Audio- and Video-Based Biometric Person Authentication, AVBPA. Guildford, UK: Springer, 2003:706-714
[108] Chen S, Chen W. Generalized minimal distortion segmentation for ANN-based speech recognition[J]. IEEE Trans on Speech and Audio Processing, 1995, 3(2): 141-145
[109] Zhu S, Chen D, Huang T. Feature parameter curve method for high performance NN-based speech recognition[C]. Proc. ICASSP, 1996:1-4
[110] 史笑兴，顾明亮，王太君等．一种时间规整算法在神经网络语音识别中的应用[J]．东南大学学报，1999，29(5)：47-51
[111] 边肇祺等．模式识别．第二版．北京：清华大学出版社，2000
[112] Witten U H，Frank E著，董琳，邱泉等译．数据挖掘-实用机器学习技术．机械工业出版社，2006
[113] Wang L, Tan T, Hu W, Ning H. Automatic gait recognition based on statistical shape analysis[J]. IEEE Transactions on Image Processing, 2003, 12(9): 1120-1131
[114] Yam C Y, Nixon M S, Carter JN. Automated person recognition by walking and running via model-based approaches. Pattern Recognition, 2004, 37(5): 1057-1072
[115] Cho I, Sunwoo J, Son Y, Oh M, Lee C. Development of a Single 3-axis Accelerometer Sensor Based Wearable Gesture Recognition Band[C]. In Proceedings of Ubiquitous Intelligence and Computing, Hong Kong, 2007: 43-52
[116] Kela J, Korpipaa P, M(a|¨)ntyj(a|¨)rvi J, et. al, Accelerometer-based gesture control for a design environment[C], In Pers Ubiquit Comput 10, 2006: 285-299
[117] Speeter T H. Transformation human hand motion for telemanipulation[J]. Presence, 1992, 1(1): 63-79
[118] Vardy A, Robinson J, Cheng LT. The wristCam as input device[C]. In Proc. ISWC, San Francisco, 1999:199-202
[119] Starner T, Weaver J, Pentland A. Real-time american sign language recognition using desk and wearable computer based video[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(12): 1371-1375
[120] Brashear H, Starner T, Lukowicz P, Junker H. Using multiple sensors for mobile sign language recognition[C]. In Proc.ISWC, White Plains, NY, USA, 2003:45-52
[121] Hinckley K, Pierce J, Sinclair M, Horvitz E. Sensing techniques for mobile interaction[C]. In User Interface Software and Technology, 2000: 91-100
[122] Perng J K, Fisher B, Hollar S and Pister K. Acceleration sensing glove[C]. In Proc. ISWC, San Francisco, 1999: 178-181
[123] Li C, Zheng S Q and Prabhakaran B. Segmentation and recognition of motion streams by similarity search[J]. ACM Trans. Multimedia Computing,Communications and Applications, 2007
[124] http://www.seas.upenn.edu/-cis505/proj/dasapich/project.htm
[125] Pylvanainen T. Accelerometer based gesture recognition using continuous HMMs[C]. Proceedings of the Second Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA) 2005: 639-646
[126] Mantyla V M. Discrete hidden Markov models with application to isolated user-dependent hand gesture recognition. Espoo: VTT Publications 2001,449, 104p.http://www.vtt.fi/inf/pdf/publications/2001/P449.pdf
[127] Huynh T, Schiele B. Analyzing features for activity recognition[C]. In Proceedings of the 2005 joint conference on Smart objects and ambient intelligence: innovative context-aware services: usages and technologies (soc-EUSAI), Grenoble, France,2005: 159-163
[128] Schmidt A. Implicit human computer interaction through context[J]. Journal of Personal Technologies, Vol. 4,2000: 191-199
[129] Lee S, Mase K. Activity and location recognition using wearable sensors[J].Pervasive Computing, 2002,1(3): 24-32
[130] Kern N, Schiele B, Schmidt A. Recognizing context for annotating a live life recording[C]. Personal and Ubiquituous Computing, 2005
[131] Kern N, Schiele B, Junker H, Lukowicz P and Trster G Wearable sensing to annotate meeting recordings[C]. In The International Symposiumon Wearable Computers, 20037(5): 263-274
[132] BodyMedia Inc. The BodyBugg Armband, http://www.bodybugg.com/
[133] MiniSun. The Intelligent Device for Energy Expenditure and Activity (IDEEA).http://www.minisun.com/
[134] Andre D, Pelletier R, Farringdon J, et al. The development of the sensewear armband, a revolutionary energy assessment device to assess physical activity and lifestyle[R]. Technical Report, BodyMedia Inc, 2006
[135] Karantonis D M, Narayanan M R, Mathie M, Lovell N H and Celler BG. Implementation of a real-time human movement classifier using a triaxial accelerometer for ambulatory monitoring[J]. IEEE Trans. Inform. Technol. Biomed,2006, 10(1): 156-167
[136] Mathie M J, Celler BG, Lovell N H, Coster A C F. Classification of basic daily
锘??movements using a triaxial accelerometer[J]. Med. Biol. Eng. Comput. 2004, 42(5):679-687
[137] Sola J, Celka P, Dasen S and Chetelat 0. Very low complexity algorithm for ambulatory activity classification[C]. In: 3rd European Med. Biol. Conf. EMBEC 2005
[138] Keogh E, Chu S, Hart D, Pazzani M. An online algorithm for segmenting time series[C]. In Proceedings of the IEEE International Conference on Data Mining,2001:289-296
[139] Brown P J. Triggering information by context[J]. Personal Technologies, 1998, 2(1):18-27
[140] Kearns M, Valiant L G Cryptographic limitations on learning boolean formulae and finite automata[J]. Journal of the ACM, 1994,41(1): 67-95
[141] Foerster F, Smeja M and Fahrenberg J. Detection of posture and motion by accelerometry: a validation in ambulatory monitoring[J]. Computers in Human Behavior, 1999, 15: 571-583
[142] Blum A L, Langley P. Selection of relevant features and examples in machine learning [J]. Artificial Intelligence, 1997, 97(12): 245-271
[143] Maron O. Learning from ambiguity. PhD dissertation, Department of Electrical and Computer Science, MIT, Cambridge, MA, 1998
[144] 周志华,王珏主编。机器学习及应用。北京：清华大学出版社,2007: 259-275
[145] Conn D A, Chah ramani Z, Jordan M I. Active learning with statistical models [J].Journal of Artificial Intelligence Research, 1996,4: 129-145
[146] Freund Y, Seung H S, Shamir E, Tishby N. Selective sampling using the query by committee algorithm[J]. Machine Learning, 1997: 133-168
[147] Dagon I, Engelson S. Committee-based sampling for training probabilistic classifiers[C]. In Process of the 12th International Confonerence Machine Learning,SanFrancisco, CA: Morgan Kaufrnann, 1995: 150-157
[148] Engelson S, Dagon I Committee-based sample selection for probabilistic classifiers[J]. Journal of Artificial Intelligence research, 1999, 11:335-360
[149] Lewis D D, Gail W A. A sequential algorithm for training text classifiers[C]. In Process of the 17th ACM International Confonerence Research and Development in Information Retrieval, Berlin:Springer, 1994: 3-12
[150] Mccallum A, Nigam K. Employing EM and pool-based active learning for text classification[C]. In Proc of the 15th nternational Confonerence MachineLearning, SanFrancisco, CA: Morgan Kaufmann, 1998:350-358
[151] Muslea I, Minton S, Knoblock C A. Active learning with multiple view[J]. Journal of Artificial Intelligence Research, 2006, 27: 203-233
[152] Seung H, Opper M and Sompolinsky H. Query by Committee[C]. In Computational Learning Theory, 1992: 287-294
[153] Friedman J H On Bias, Variance, 0/1-Loss, and the Curse-of-Dimensionality. Data Mining and Knowledge Discovery, 1997, 1(1): 55-277
[154] 张旭东．离散随机信号处理．北京：清华大学出版社，2006