. .. Choix-des-paramètres,

. .. , Réduction de dimension de l'ensemble de paramètres, p.119

.. .. Impact,

.. .. Impact,

. .. , 121 6.6.1 Performance des algorithmes de classification

.. .. Conclusion,

. .. Algorithme-d'identification, 129 7.3.1 Principe de l'algorithme

. .. Exemple-numérique,

.. .. Conclusion,

, On propose ici d'utiliser une séquence d'entrée spécifique pour faciliter l'estimation de l'ensemble B. On propose d'utiliser la séquence d

E. K. Antonsson and R. W. Mann, « The frequency content of gait, Journal Biomechanics, vol.18, pp.39-47, 1985.

L. Atallah, « Sensor Placement for Activity Detection Using Wearable Accelerometers, IEEE Transactions on Biomedical Circuits and Systems, vol.5, 2011.

F. Attal, « Physical Human Activity Recognition Using Wearable Sensors, pp.31314-31338, 2015.

R. Auber, « Activity Recognition from Binary Data, UKACC International Conference on Control, 2018.

R. Auber, « Estimation of Auto-Regressive models for time series using Binary or Quantized Data, 2018.

R. Auber, « Identification for Switched FIR Linear Systems using Binary Measurements, 58th Conference on Decision and Control, 2019.

R. Auber, « Identification of AR Time-series based on binary data, IET Research Journals, 2019.

A. J. Bagnall and G. J. Janacek, « Clustering time series from ARMA models with clipped data, 10th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, vol.58, pp.151-178, 2004.

O. Banos, « Window Size Impact in Human Activity Recognition, Sensors 14, pp.6474-6499, 2014.

A. Bayat, M. Pomplun, and D. A. Tran, « A Study on Human Activity Recognition Using Accelerometer Data from Smartphones, vol.34, pp.450-457, 2014.

T. Blackwell, « Comparison of Sleep Parameters from Actigraphy and Polysomnography in Older Women : The SOF Study, Sleep 31, pp.283-291, 2008.

G. Bottegal, H. Hjalmarsson, and G. Pillonetto, A new kernel-based approach to system identification with quantized output data" », Automatica, vol.85, pp.145-152, 2017.

L. Bourgois and J. Juillard, « "Convergence Analysis of an Online Approach to Parameter Estimation Problems Based on Binary Noisy Observations" », IEEE Conference on Decision and Control, 2012.

C. V. Bouten, « A triaxial accelerometer and portable data processing unit for the assessment of daily physical activity, IEEE Transactions on Biomedical Engineering, vol.44, pp.136-147, 1997.

L. Breiman, « Bagging predictors, Machine Learning, vol.24, pp.5-32, 1996.

L. Breiman, « Classification and regression trees, 1984.

V. Breschi, D. Piga, and A. Bemporad, Piecewise affine regression via recursive multiple least squares and multicategory discrimination" », Automatica, vol.73, pp.155-162, 2016.

L. M. Bruce, C. H. Koger, and J. Li, « Dimensionality reduction of hyperspectral data using discrete wavelet transform feature extraction, IEEE Transactions on Geoscience and Remote Sensing, vol.40, pp.2331-2338, 2002.

C. J. Burges, « A Tutorial on Support Vector Machines for Pattern Recognition, Data Mining and Knowledge Discovery, vol.2, pp.121-167, 1998.

C. Burrus, R. A. Gopinath, and H. T. Guo, Introduction to Wavelets and Wavelet Transforms : a Primer, 1998.

P. Casale, O. Pujol, and P. Radeva, « Human Activity Recognition from Accelerometer Data Using a Wearable Device, Iberian Conference on Pattern Recognition and Image Analysis, 2011.

D. Castro, « Wearable-Based Human Activity Recognition Using an IoT Approach, Journal of Sensor and Actuator Networks, vol.6, 2017.

J. D. Ceron, D. M. Lopez, and B. M. Eskofier, « Human Activity Recognition Using Binary Sensors, BLE Beacons, an Intelligent Floor and Acceleration Data : A Machine Learning Approach, International Conference on Ubiquitous Computing and Ambient Intelligence, 2018.

K. Chapron, « A More Efficient Transportable and Scalable System for Real-Time Activities and Exercises Recognition, Sensors 18, 2018.

Y. Chen and C. Shen, « Performance Analysis of Smartphone-Sensor Behavior for Human Activity Recognition, IEEE Access, vol.5, pp.3095-3110, 2017.

I. Cleland, « Optimal Placement of Accelerometers for the Detection of Everyday Activities, Sensors 13, pp.9183-9200, 2013.

B. Companjen, « Classification methods for activity recognition, Twente Student Conference on IT, 2009.

T. Daghistani and R. Alshammari, « Improving Accelerometer-Based Activity Recognition by Using Ensemble of Classifiers, International Journal of Advanced Computer Science and Applications, vol.7, pp.128-133, 2016.

A. V. Dandawate and G. B. Giannakis, « Asymptotic properties and covariance expressions of kth-order sample moments and cumulants, Proceedings of 27th, 1993.

, Asilomar Conference on Signals, Systems and Computers, pp.1186-1190

M. Dash and H. Liu, « Feature selection for classification, Intelligent Data Analysis, vol.1, pp.131-156, 1997.

I. Daubechies, « Ten Lectures on Wavelets, 1992.

F. N. David, « A note on the evaluation of the multivariate normal integral, Biometrika, vol.40, pp.458-459, 1953.

J. C. Davila, A. Cretu, and M. Zaremba, « Wearable Sensor Data Classification for Human Activity Recognition Based on an Iterative Learning Framework, Sensors 17, 2017.

R. O. Duda, P. E. Hart, and D. G. Stork, Pattern Classification, 2001.

A. Dutta, « Identifying Free-Living Physical Activities Using Lab-Based Models with Wearable Accelerometers, Sensors, vol.18, pp.190-202, 2018.

A. P. Engelbrecht, « Computational Intelligence : An Introduction, 2007.

M. Ermes, J. Parkka, and L. Cluitmans, « Advancing from offline to online activity recognition with wearable sensors, IEEE International Conference of Engineering in Medicine and Biology Society, 2008.

M. Espinilla, « Human Activity Recognition from the Acceleration Data of a Wearable Device, In : International Conference on Ubiquitous Computing and Ambient Intelligence, 2018.

O. S. Eyobu and D. Han, « Feature Representation and Data Augmentation for Human Activity Classification Based on Wearable IMU Sensor Data Using a Deep LSTM Neural Network, Sensors 18, 2018.

T. Fawcett, « ROC Graphs : Notes and Practical Considerations for Researchers, Pattern Recognition Letters, vol.31, pp.1-38, 2004.

G. Ferrari-trecate, « "A clustering technique for the identification of piecewise affine systems, ». In : Automatica, vol.39, pp.250-217, 2003.

D. Figo, « Preprocessing Techniques for Context Recognition from Accelerometer Data, Personal Ubiquitous Computing, vol.14, pp.645-662, 2010.

E. Fullerton, B. Heller, and M. Munoz-organero, « Recognizing Human Activity in Free-Living Using Multiple Body-Worn Accelerometers, IEEE Sensors Journal, vol.17, pp.5290-5297, 2017.

N. F. Ghazali, « Common sport activity recognition using inertial sensor, IEEE International Colloquium on Signal Processing Its Applications, 2018.

A. Goudjil, « "A real-time identification algorithm for switched linear systems with bounded noise" », European Control Conference, 2016.

, « "Convergence analysis of a real-time identification algorithm for switched linear systems with bounded noise" », IEEE Conference on Decision and Control, 2016.

F. Gu, « User-Independent Motion State Recognition Using Smartphone Sensors, Sensors 15, pp.30636-30652, 2015.

J. Guo and Y. Zhao, « Recursive projection algorithm on FIR system identification with binary-valued observations, Automatica 49, vol.11, pp.3396-3401, 2013.

J. Guo, « Recursive identification of FIR systems with binary-valued outputs and communication channels, Automatica, pp.165-172, 2015.

P. Gupta and T. Dallas, « Feature Selection and Activity Recognition System Using a Single Triaxial Accelerometer, IEEE Transactions on Biomedical Engineering, vol.61, pp.1780-1786, 2014.

Y. Hashambhoy and R. Vidal, « "Recursive identification of switched ARX models with unknown number of models and unknown orders" », IEEE Conference on Decision and Control, 2005.

Z. He and L. Jin, « Activity Recognition from acceleration data Based on Discrete Consine Transform and SVM, IEEE International Conference on Machine Learning and Cybernetics, 2008.

T. Ho, « The random subspace method for constructing decision forests, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.20, pp.832-844, 1998.

K. Jafari, J. Juillard, and M. Roger, « "Convergence analysis of an online approach to parameter estimation problems based on binary observations, ». In : Automatica, vol.48, pp.2837-2842, 2012.

A. Jain and V. Kanhangad, « Human Activity Classification in Smartphones Using Accelerometer and Gyroscope Sensor, IEEE Sensors Journal, vol.18, pp.1169-1177, 2018.

M. Janidarmian, A Comprehensive Analysis on Wearable Acceleration Sensors in Human Activity Recognition, 2017.

J. M. Jasiewicz, « Gait event detection using linear accelerometers or angular velocity transducers in able-bodied and spinal-cord injured individuals, Gait Posture, vol.24, pp.502-509, 2006.

I. T. Jolliffe, « Principal Component Analysis, 2002.

A. Juloski, S. Weiland, and W. P. Heemels, A Bayesian approach to identification of hybrid systems" », IEEE Transactions on Automatic Control, vol.50, pp.1520-1533, 2005.

B. Kedem, Estimation of the Parameters in Stationary Autoregressive Processes after Hard Limiting, vol.75, pp.146-153, 1980.

B. E. Kedem and . Slud, « On Goodness of Fit of Time Series Models : An Application of Higher Order Crossings, Biometrika, vol.68, pp.551-556, 1981.

A. M. Khan, Y. K. Lee, and T. Kim, Accelerometer Signal-based Human Activity Recognition Using Augmented Autoregressive Model Coefficients and Artificial Neural Nets, 2008.

A. M. Khan, « A Triaxial Accelerometer-Based Physical-Activity Recognition via Augmented-Signal Features and a Hierarchical Recognizer, IEEE Transactions on Information Technology in Biomedicine, vol.14, pp.1166-1172, 2010.

T. Kim, J. Cho, and J. T. Kim, « Mobile Motion Sensor-Based Human Activity Recognition and Energy Expenditure Estimation in Building Environments, International Conference in Sustainability in Energy and Buildings, 2012.

K. Kira and L. A. Rendell, « A Practical Approach to Feature Selection, International Workshop on Machine Learning, 1992.

I. Kononenko, « Estimating attributes : Analysis and extensions of RELIF, European Conference on Machine Learning, 1994.

O. D. Lara and M. A. Labrador, « A Survey on Human Activity Recognition using Wearable Sensors, vol.15, pp.1192-1209, 2013.

F. Lauer, Estimating the probability of success of a simple algorithm for switched linear regression" », Nonlinear Analysis : Hybrid Systems, vol.8, pp.31-47, 2013.
URL : https://hal.archives-ouvertes.fr/hal-00743954

V. L. Le, F. Lauer, and G. Bloch, Identification of linear hybrid systems : A geometric Approach" », IEEE American Control Conference, pp.830-835, 2013.
URL : https://hal.archives-ouvertes.fr/hal-00799147

M. Lee, « A single tri-axial accelerometer-based real-time personal life log system capable of activity classification and exercise information generation, Personal and Ubiquitous Computing, vol.15, pp.887-898, 2011.

F. Li, Comparison of Feature Learning Methods for Human Activity Recognition Using Wearable Sensors, 2018.

H. Liu and R. Setiono, « A Probabilistic Approach to Feature Selection -A Filter Solution, International Conference on International Conference on Machine Learning, pp.319-327, 1996.

Y. Ma and R. Vidal, « "Identification of deterministic switched ARX systems via identification of algebraic varieties" », International Conference on Hybrid Systems : Computation and Control, 2005.

S. Mehrang, J. Pietila, and I. Korhonen, « An Activity Recognition Framework Deploying the Random Forest Classifier and A Single Optical Heart Rate Monitoring and Triaxial Accelerometer Wrist-Band, Sensors 18, 2018.

E. Mitchell, D. Monaghan, and N. E. O'connor, « Classification of Sporting Activities Using Smartphone Accelerometers, Sensors 13, pp.5317-5337, 2013.

T. M. Mitchell, Machine Learning, 1997.

H. Nakada, K. Takaba, and T. Katayama, Identification of piecewise affine systems based on statistical clustering technique" », Automatica 41, vol.5, pp.905-913, 2005.

A. Nguyen, D. Moore, and I. Mccowan, « Unsupervised Clustering of Free-Living Human Activities using Ambulatory Accelerometry, IEEE International Conference of Engineering in Medicine and Biology Society, 2007.

Q. Ni, L. Zhang, and L. Li, « A Heterogeneous Ensemble Approach for Activity Recognition with Integration of Change Point-Based Data Segmentation, Applied Sciences, vol.8, 2018.

N. Ozay, C. Lagoa, and M. Sznaier, Set membership identification of switched linear systems with known number of subsystems" », Automatica 51, vol.1, pp.180-191, 2015.

N. Pannurat, « Analysis of Optimal Sensor Positions for Activity Classification and Application on a Different Data Collection Scenarios, Sensors 17, 2017.

S. S. Pittner and . Kamarthi, « Feature Extraction From Wavelet Coefficients for Pattern Recognition Tasks, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.21, pp.83-88, 1999.

P. Prasertsung and T. Horanont, « A classification of accelerometer data to differentiate pedestrian state, 2016.

S. J. Preece, « A Comparison of Feature Extraction Methods for the Classification of Dynamic Activities From Accelerometer Data, IEEE Transactions on Biomedical Engineering, vol.56, pp.871-879, 2009.

S. J. Preece, « Activity identification using body-mounted sensors-a review of classification techniques, Physiological Measurement, vol.30, 2009.

P. Pudil, J. Novovicova, and J. Kittler, « Floating search methods in feature selection, Pattern Recognition Letters, vol.15, pp.1119-1125, 1994.

J. R. Quinlan, « Induction of Decision Trees, Machine Learning, vol.1, pp.81-106, 1986.

«. C4, 5 : Programs for Machine Learning

K. Rahim and . Ku-abd, « Classification of Human Daily Activities Using Ensemble Methods Based on Smartphone Inertial Sensors, Sensors 18, 2018.

L. E. Raileanu and K. Stoffel, Theoretical Comparison between the Gini Index and Information Gain Criteria, vol.41, 2004.

A. Reiss and D. Stricker, « Introducing a New Benchmarked Dataset for Activity Monitoring, 2012.

A. Reiss and S. Didier, « Creating and Benchmarking a New Dataset for Physical Activity Monitoring, The 5th Workshop on Affect and Behaviour, 2012.

M. Robnik-sikonja and I. Kononenko, « Theoretical and Empirical Analysis of ReliefF and RReliefF, Machine Learning, pp.23-69, 2003.

L. Rokach and O. Maimon, « Data Mining With Decision Trees : Theory and Applications, 2014.

S. Rosati, G. Balestra, and M. Knaflitz, Comparison of Different Sets of Features for Human Activity Recognition by Wearable Sensors, 2018.

F. M. Rueda, Convolutional Neural Networks for Human Activity Recognition Using Body-Worn Sensors, 2018.

S. Saeedi and N. El-sheimy, « Activity Recognition Using Fusion of Low-Cost Sensors on a Smartphone for Mobile Navigation Application, Micromachines 6, pp.1100-1134, 2015.

Y. Saez, A. Baldominos, and P. Isasi, « A Comparison Study of Classifier Algorithms for Cross-Person Physical Activity Recognition, Sensors 17, 2017.

O. Sagi and L. Rokach, « Ensemble learning : A survey, Wiley Data Mining and knowledge discovery 8, 2018.

S. Saif, S. Tehseen, and S. Kausar, « A Survey of the Techniques for The Identification and Classification of Human Actions from Visual Data, Sensors 18, 2018.

R. San-segundo, « Robust Human Activity Recognition using smartwatches and smartphones, Engineering Applications of Artificial Intelligence, vol.72, pp.190-202, 2018.

M. Sekine, « Classification of acceleration waveform in a continuous walking record, IEEE International Conference of Engineering in Medicine and Biology Society, 1998.

W. F. Sheppard, « On the application of the theory of error to cases of normal distribution and normal correlation, Philosophical Transactions of the Royal Society A, vol.192, pp.101-167, 1899.

M. Shoaib, « A Survey of Online Activity Recognition Using Mobile Phones, Sensors 15, pp.2059-2085, 2015.

M. Skurichina and R. Duin, « Limited Bagging, Boosting and the Random Subspace Method for Linear Classifiers, Formal Pattern Analysis & Application, vol.5, pp.121-135, 2002.

I. Steinwart and A. Christmann, « Support Vector Machines, 2008.

A. Tharwat, « Linear discriminant analysis : A detailed tutorial, AI Communications, vol.30, pp.169-190, 2017.

N. Twomey, « A Comprehensive Study of Activity Recognition Using Accelerometers, Informatics 5, 2018.

R. Urbanowicz, « Relief-Based Feature Selection : Introduction and Review, Journal of Biomedical Informatics, 2017.

P. H. Veltink, « Detection of static and dynamic activities using uniaxial accelerometers, IEEE Transactions on Rehabilitation Engineering, vol.4, pp.375-385, 1996.

R. Vidal, « "Recursive identification of switched ARX systems, ». In : Automatica, vol.44, pp.2274-2287, 2008.

V. V. Vyas, K. H. Walse, and R. V. Dharaskar, « A Survey on Human Activity Recognition using Smartphone, International Journal of Advance Research in Computer Science and Management Studies, vol.5, pp.118-125, 2017.

G. Wang, « Impact of Sliding Window Length in Indoor Human Motion Modes and Pose Pattern Recognition Based on Smartphone Sensors, Sensors 18, 2018.

J. Wang, « Recognizing Human Daily Activities From Accelerometer Signal, Procedia Engineering, vol.15, pp.1780-1786, 2011.

W. Wang, « Analysis of filtering methods for 3D acceleration signals in body sensor network, International Symposium on Bioelectronics and Bioinformations, 2011.

A. W. Whitney, « A Direct Method of Nonparametric Measurement Selection, IEEE Transactions on Computers, 1971.

J. Yang, J. Wang, and Y. Chen, « Using acceleration measurements for activity recognition : An effective learning algorithm for constructing neural classifiers », Pattern Recognition Letters, vol.29, pp.2213-2220, 2008.

A. Yurtman, B. Barshan, and B. Fidan, « Activity Recognition Invariant to Wearable Sensor Unit Orientation Using Differential Rotational Transformations Represented by Quaternions, Sensors 18, 2018.

M. Zhang and A. A. Sawchuk, « A feature selection-based framework for human activity recognition using wearable multimodal sensors, 2011.

M. Zhang and A. A. Sawchuk, « A Feature Selection-Based Framework for Human Activity Recognition Using Wearable Multimodal Sensors, International Conference on Body Area Networks, 2011.

X. Zhen and I. V. Basawa, « Estimation for binary models generated by Gaussian autoregressive processes, Journal of Statistical Computation and Simulation, vol.80, pp.1041-1051, 2010.

, dispositif développé par la société Bodycap. Plusieurs solutions sont proposées afin d'optimiser l'autonomie de l'objet connecté. Ces solutions sont mises en oeuvre et comparées sur différentes séries de données. L'originalité d'une de ces solutions consiste à binariser les données de l'accéléromètre avant de les transférer vers une plateforme externe où elles sont analysées. L'utilisation de données binaires entraîne la perte de nombreuses informations, cependant il est montré dans ce manuscrit qu'il est possible d'estimer, entres autres, les paramètres d'un modèle Auto Régressif d'une série temporelle à partir de l'information binaire sur cette série. A ce titre, un algorithme d'identification est proposé et analysé. Mots clés : données binaires, Résumé Ce manuscrit porte sur la reconnaissance d'activités à partir de données accéléromètriques. Le dispositif utilisé pour collecter les données de l'accéléromètre est eTact