Human Activity Recognition Based on Symbolic Representation Algorithms for Inertial Sensors

Mobile sensing has allowed the emergence of a variety of solutions related to the monitoring and recognition of human activities (HAR). Such solutions have been implemented in smartphones for the purpose of better understanding human behavior. However, such solutions still suffer from the limitations of the computing resources found on smartphones. In this sense, the HAR area has focused on the development of solutions of low computational cost. In general, the strategies used in the solutions are based on shallow and deep learning algorithms. The problem is that not all of these strategies are feasible for implementation in smartphones due to the high computational cost required, mainly, by the steps of data preparation and the training of classification models. In this context, this article evaluates a new set of alternative strategies based on Symbolic Aggregate Approximation (SAX) and Symbolic Fourier Approximation (SFA) algorithms with the purpose of developing solutions with low computational cost in terms of memory and processing. In addition, this article also evaluates some classification algorithms adapted to manipulate symbolic data, such as SAX-VSM, BOSS, BOSS-VS and WEASEL. Experiments were performed on the UCI-HAR, SHOAIB and WISDM databases commonly used in the literature to validate HAR solutions based on smartphones. The results show that the symbolic representation algorithms are faster in the feature extraction phase, on average, by 84.81%, and reduce the consumption of memory space, on average, by 94.48%, and they have accuracy rates equivalent to conventional algorithms.

[1]  Patrick Schäfer,et al.  Scalable time series similarity search for data analytics , 2015 .

[2]  Paul J. M. Havinga,et al.  Complex Human Activity Recognition Using Smartphone and Wrist-Worn Motion Sensors , 2016, Sensors.

[3]  Gary M. Weiss,et al.  Activity recognition using cell phone accelerometers , 2011, SKDD.

[4]  Yunhao Liu,et al.  Indexable PLA for Efficient Similarity Search , 2007, VLDB.

[5]  Li Wei,et al.  Experiencing SAX: a novel symbolic representation of time series , 2007, Data Mining and Knowledge Discovery.

[6]  Héctor Pomares,et al.  Window Size Impact in Human Activity Recognition , 2014, Sensors.

[7]  Teh Ying Wah,et al.  Data fusion and multiple classifier systems for human activity detection and health monitoring: Review and open research directions , 2019, Inf. Fusion.

[8]  Khalil El-Khatib,et al.  A Comparative Analysis of the Impact of Features on Human Activity Recognition with Smartphone Sensors , 2017, WebMedia.

[9]  Jessica Lin,et al.  HOT SAX: Finding the Most Unusual Time Series Subsequence: Algorithms and Applications , 2004 .

[10]  Matteo Terzi,et al.  A multivariate symbolic approach to activity recognition for wearable applications , 2017 .

[11]  George C. Runger,et al.  Learning a symbolic representation for multivariate time series classification , 2015, Data Mining and Knowledge Discovery.

[12]  Donald J. Berndt,et al.  Using Dynamic Time Warping to Find Patterns in Time Series , 1994, KDD Workshop.

[13]  Tim Oates,et al.  Time series anomaly discovery with grammar-based compression , 2015, EDBT.

[14]  Diogo R. Ferreira,et al.  Preprocessing techniques for context recognition from accelerometer data , 2010, Personal and Ubiquitous Computing.

[15]  Adil Mehmood Khan,et al.  Activity Recognition on Smartphones via Sensor-Fusion and KDA-Based SVMs , 2014, Int. J. Distributed Sens. Networks.

[16]  Raymond T. Ng,et al.  Indexing spatio-temporal trajectories with Chebyshev polynomials , 2004, SIGMOD '04.

[17]  Milos Hauskrecht,et al.  Multivariate Time Series Classification with Temporal Abstractions , 2009, FLAIRS.

[18]  Davide Anguita,et al.  A Public Domain Dataset for Human Activity Recognition using Smartphones , 2013, ESANN.

[19]  Paul J. M. Havinga,et al.  Fusion of Smartphone Motion Sensors for Physical Activity Recognition , 2014, Sensors.

[20]  Patrick Schäfer,et al.  SFA: a symbolic fourier approximation and index for similarity search in high dimensional datasets , 2012, EDBT '12.

[21]  Audra E. Kosh,et al.  Linear Algebra and its Applications , 1992 .

[22]  Jun Yang,et al.  Toward physical activity diary: motion recognition using simple acceleration features with mobile phones , 2009, IMCE '09.

[23]  S. Mallat.  A wavelet tour of signal processing , 1998 .

[24]  Wael Hassan Gomaa,et al.  A Survey of Text Similarity Approaches , 2013 .

[25]  Kalaiarasi Sonai Muthu,et al.  Classification Algorithms in Human Activity Recognition using Smartphones , 2012 .

[26]  Paul J. M. Havinga,et al.  A Survey of Online Activity Recognition Using Mobile Phones , 2015, Sensors.

[27]  P. C. Wong,et al.  Generalized vector spaces model in information retrieval , 1985, SIGIR '85.

[28]  Kent Larson,et al.  Activity Recognition in the Home Using Simple and Ubiquitous Sensors , 2004, Pervasive.

[29]  Christos Faloutsos,et al.  Fast Time Sequence Indexing for Arbitrary Lp Norms , 2000, VLDB.

[30]  Ifeyinwa E. Achumba,et al.  Monitoring: Taxonomy of Issues, Techniques, Applications, Challenges and Limitations , 2013 .

[31]  Kimiaki Shirahama,et al.  Comparison of Feature Learning Methods for Human Activity Recognition Using Wearable Sensors , 2018, Sensors.

[32]  Cem Ersoy,et al.  A Review and Taxonomy of Activity Recognition on Mobile Phones , 2013 .

[33]  Juha Röning,et al.  Improving the classification accuracy of streaming data using SAX similarity features , 2011, Pattern Recognit. Lett..

[34]  Xiaohui Peng,et al.  Deep Learning for Sensor-based Activity Recognition: A Survey , 2017, Pattern Recognit. Lett..

[35]  Jesús Fontecha,et al.  Elderly frailty detection by using accelerometer-enabled smartphones and clinical information records , 2012, Personal and Ubiquitous Computing.

[36]  Eamonn J. Keogh,et al.  iSAX 2.0: Indexing and Mining One Billion Time Series , 2010, 2010 IEEE International Conference on Data Mining.

[37]  Patrick Schäfer.  The BOSS is concerned with time series classification in the presence of noise , 2014, Data Mining and Knowledge Discovery.

[38]  Ana M. Bernardos,et al.  Activity logging using lightweight classification techniques in mobile devices , 2012, Personal and Ubiquitous Computing.

[39]  Patrick Schäfer,et al.  Bag-Of-SFA-Symbols in Vector Space (BOSS VS) , 2015 .

[40]  Surapa Thiemjarus,et al.  A study on instance-based learning with reduced training prototypes for device-context-independent activity recognition on a mobile phone , 2013, 2013 IEEE International Conference on Body Sensor Networks.

[41]  Juha Röning,et al.  Ready-to-use activity recognition for smartphones , 2013, 2013 IEEE Symposium on Computational Intelligence and Data Mining (CIDM).

[42]  Yufei Chen,et al.  Performance evaluation of implicit smartphones authentication via sensor-behavior analysis , 2018, Inf. Sci..

[43]  Michael Mock,et al.  A step counter service for Java-enabled devices using a built-in accelerometer , 2009, CAMS '09.

[44]  Eamonn J. Keogh,et al.  iSAX: indexing and mining terabyte sized time series , 2008, KDD.

[45]  Ulf Leser,et al.  Fast and Accurate Time Series Classification with WEASEL , 2017, CIKM.

[46]  Eamonn J. Keogh,et al.  A Simple Dimensionality Reduction Technique for Fast Similarity Search in Large Time Series Databases , 2000, PAKDD.

[47]  Eduardo Souto,et al.  User activity recognition for energy saving in smart home environment , 2015, 2015 IEEE Symposium on Computers and Communication (ISCC).

[48]  Jonathan Loo,et al.  Authentication of Smartphone Users Based on Activity Recognition and Mobile Sensing , 2017, Sensors.

[49]  R. Lowry,et al.  Concepts and Applications of Inferential Statistics , 2014 .

[50]  Sergey Malinchik,et al.  SAX-VSM: Interpretable Time Series Classification Using SAX and Vector Space Model , 2013, 2013 IEEE 13th International Conference on Data Mining.

[51]  Seok-Won Lee,et al.  Exploratory Data Analysis of Acceleration Signals to Select Light-Weight and Accurate Features for Real-Time Activity Recognition on Smartphones , 2013, Sensors.

[52]  Diane J. Cook,et al.  Activity Learning: Discovering, Recognizing, and Predicting Human Behavior from Sensor Data , 2015 .

[53]  Eamonn J. Keogh,et al.  A symbolic representation of time series, with implications for streaming algorithms , 2003, DMKD '03.

[54]  Yolande Berbers,et al.  Mobile phones assisting with health self-care: a diabetes case study , 2008, Mobile HCI.