Window Selection Impact in Human Activity Recognition
AbstractSignal segmentation is usually applied in the pre-processing step to make the data analysis easier. Windowing approach is commonly used for signal segmentation. However, it is unclear which type of window should be used to get optimum accuracy in human activity recognition. This study aimed to evaluat e which window type yields the optimum accuracy in human activity recognition. The acceleration data of walking, jogging, and running were collected from 20 young adults. Then, the recognition accuracy of each window types is evaluated and compared to determine the impact of window selection in human movement data. From the evaluation, the overlapping 75% window with 0.1 s length provides the highest accuracy with mean, standard deviation, maximum, minimum, and energy as the features. The result of this study could be used for future researches in relation to human activity recognition.
 Dobkin BH, Xu X, Batalin M, Thomas S, Kaiser W. Reliability and validity of bilateral ankle accelerometer algorithms for activity recognition and walking speed after stroke. Stroke. 2011; 42: 2246-2250.
 Aung M, Thies S, Kenney L, Howard D, Selles R, Findlow A, Goulermas J. Automated detection of instantaneous gait events using time frequency analysis and manifold embedding. IEEE Trans. Neural Syst. Rehabil. Eng. 2013; 21: 908–916.
 Figo D, Diniz PC, Ferreira DR, Cardoso JM. Preprocessing techniques for context recognition from acceleration data. Pers. Ubiquitous Comput. 2010; 14: 645-662.
 Khan AM, Lee YK, Lee SY, Kim TS. A triaxial accelerometer-based physical-activity recognition via augmented-signal features and a hierarchical recognizer. IEEE Trans. Inf. Technol. Biomed. 2010; 14: 1166–1172.
 Dernbach S, Das B, Khrisnan NC, Thomas BL, Cook DJ. Simple and complex activity recognition through smart phones. In Proceedings of the 8th International Conference on Intelligent Environments, Guanajuato, Mexico, 26-29 June 2012. pp. 214-221.
 Yoshizawa M, Takasaki W, Ohmura R. Parameter exploration for response time reduction in accelerometer-based activity recognition. In Proceedings of the 2013 ACM Conference on Pervasive and Ubiquitous Computing, Zurich, Switzerland, 8-12 September 2013. pp. 653-664.
 Bao L, Intille SS. Activity recognition from user-annotated acceleration data. Proceedings of the Second International Conference on Pervasive Computing, Linz/Vienna, Austria, 21–23 April 2004; Volume 23, pp. 1–17.
 Preece SJ, Goulermas JY, Kenney LP, Howard D. A comparison of feature extraction methods for the classification of dynamic activities from accelerometer data. IEEE Trans. Biomed. Eng. 2009; 56: 871–879.
 Lee YS, Cho SB. Activity recognition using hierarchical hidden markov models on a smartphone with 3D accelerometer. Proceedings of the 6th International Conference on Hybrid Artificial Intelligent Systems, Wroclaw, Poland, 23–25 May 2011. pp. 460–467.
 Wang JH, Ding JJ, Chen Y, Chen HH. Real time accelerometer-based gait recognition using adaptive windowed wavelet transforms. Proceedings of the IEEE Asia Pacific Conference on Circuits and Systems, Kaohsiung, Taiwan, 2–5 December 2012. pp. 591–594.
 Nam Y, Park JW. Physical activity recognition using a single triaxial accelerometer and a barometric sensor for baby and child care in a home environment. J. Ambient Intell. Smart Environ. 2013; 5: 381–402.
 Bouten CV, Koekkoek KT, Verduin M, Kodde R, Janssen JD. A triaxial accelerometer and portable data processing unit for the assessment of daily physical activity. IEEE Trans. Biomed. Eng. 1997; 44(3): 136-147.
 Pirttikangas S, Fujinami K, Seppanen T. Feature selection and activity recognition from wearable sensors. In Proceedings of the Third International Symposium on Ubiquitous Computing Systems, Seoul, Korea, 11-13 October 2006; Volume 4239. pp. 516-527
 Stikic M, Huynh T, van Laerhovern K, Schiele B. ADL recognition based on the combination of RFID and accelerometer sensing. In Proceedings of the Second International Conference on Pervasive Computing Technologies for Healthcare, Tampere, Finland, 30 January-1 February 2008. pp. 258-263.
 Banos O, Galvez JM, Damas M, Pomares H, Rojas I. Window size impact in human activity recognition. Sensors. 2014; 14: 6474-6499.
 MATLAB R2015a. 2015. Natick, Massachusetts: The MathWorks Inc.
 Weka 3.8.1. 2016. Hamilton, New Zealand: The University of Waikato.
 Rogers MJB, Hrovat K, McPherson K, Moskowitz ME, Reckart T. Accelerometer Data Analysis and Presentation Techniques. National Aeronautics and Space Adminstration. NASA Technical Reports, 19970034695. 1997. pp. 1-48.
 Naqvi MNZ, Kumar DA, Chauhan A, Sahni K. Step Counting Using Smartphone-Based Accelerometer. Int J Comput Sci Eng. 2012; 4: 675–81.
 Chen C, Grennan K, Badner J, Zhang D, Gershon E, Jin L, et al. Removing Batch Effects in Analysis of Expression Microarray Data: An Evaluation of Six Batch Adjustment Methods. PLoS ONE. 2011; 6(2): e17238.
 Dargie W. Analysis of Time and Frequency Domain Features of Accelerometer Measurements. Proceedings of the 2009 Proceedings of 18th International Conference on Computer Communications and Networks. August 03-06, 2009. pp. 1-6.
 Maekawa T, Yanagisawa Y, Kishino Y, Ishiguro K, Kamei K, Sakurai Y, Okadome T. Object-based activity recognition with heterogeneous sensors on wrist. Pervasive. 2010. pp. 246-264.
24] Nurwulan NR, Jiang BC. Possibility of Using Entropy Method to Evaluate the Distracting Effect of Mobile Phones on Pedestrians. Entropy. 2016; 18(11): 390.
25] Shannon CE. A mathematical theory of communication. ACM SIGMOBILE Mob. Comput. Commun. Rev. 2001; 5: 3–55.
 Cortes C, Vapnik V. Support-vector networks. Machine Learning. 1995; 20(3): 273–297.
 Lara OD, Labrador MA. A survey on human activity recognition using wearable sensors. IEEE Communications Surveys and Tutorials. 2013; 15(3): 1192-1209.
 Lombriser C, Bharatula NB, Roggen D, Trosser G. On-body activity recognition in a dynamic sensor network. In Proceedings of 2nd International Body Area Networks Conference, Florence, Italy. 2007. pp.17-22.
 Kohavi R. The power of decision tables. Machine Learning: ECML-95. Springer. 1995. pp. 174-189.
 Ravi N, Dandekar N, Mysore P, Littman M.L. Activity recognition from accelerometer data. AAAI 2005. 5. 1541-1546.
 Gjoreski M, Gjoreksi H, Lustrek M, Gams M. How accurately can your wrist device recognize daily activities and detect falls? Sensors. 2016; 16(6): 800.
 Nurwulan NR, Jiang BC, Novak V. Estimation of balance-ability on healthy subjects using postural stability index. In Proceedings of 25th ISSAT International Conference on Reliability and Quality in Design, Las Vegas, Nevada, USA. 2019.
 Gao J, Hu J, Buckley T, White K, Hass C. Shannon and Renyi entropies to classify effects of mild traumatic brain injury on postural sway. PLOS ONE. 2011. 6. e24446.
 Nurwulan NR, Jiang BC, Novak V. Development of postural stability index to distinguish different stability states. Entropy. 2019; 21(3): 314.
Copyright (c) 2020 International Journal of Innovative Technology and Interdisciplinary Sciences
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.