Person identification is a process through which a person is recognized using some information about him-/herself. Usually this is performed by asking the user to perform some action, e.g., to apply a token (card), enter a PIN code, scan a finger, or something similar. This paper describes an approach for recognizing a person entering a room using door accelerations, i.e., no additional action is required. The approach analyzes the acceleration signal in time and frequency domain. For each domain two types of methods were developed: (i) feature-based – uses features to describe the acceleration and then uses classification method to identify the person; (ii) signal-based – uses the acceleration signal as input and finds the most similar ones in order to identify the person. The four methods were evaluated on a dataset of 1005 entrances recorded by 12 people. The results show that the time-domain methods achieve significantly higher accuracy compared to the frequency-domain methods, with signal-based method achieving 86% accuracy. Additionally, the four methods were combined and all 15 combinations were examined. The best performing combined method increased the accuracy to 90%. Additional experiments with varying the number of training instances, showed that around 10 to 20 training instances are enough to achieve reliable performance. The results confirm that it is possible to identify a person entering a room using only the door acceleration and that relatively high accuracy (over 95%) is expected for a limited group of dissimilar users, e.g. a typical family.
G.Al-Naymat, S.Chawla and J.Taheri, SparseDTW: A Novel Approach to Speed up Dynamic Time Warping, 2012.
4.
Apple pay, https://www.apple.com/apple--pay/.
5.
A.L.C.Bailer-Jones and K.Smith, Combining probabilities, Tecnical note, GAIA-C8-TN-MPIA-CBJ-053, Data Processing and Analysis Consortium (DPAC), Max-Planck-Institute for Astronomy, Heidelberg, 2011, available at http://www.rssd.esa.int/doc_fetch.php?id=2968255.
6.
K.Bashir, T.Xiang and S.Gong, Gait recognition without subject cooperation, Pattern Recognition Letters31 (2010), 2052–2060. doi:10.1016/j.patrec.2010.05.027.
7.
R.Bellman and R.Kalaba, On adaptive control processes. Automatic control, IRE Transactions on4(2) (1959), 1–9.
D.J.Cook, J.C.Augusto and V.R.Jakkula, Ambient intelligence: Technologies, applications, and opportunities, Pervasive and Mobile Computing.5(4) (2009), 277–298. doi:10.1016/j.pmcj.2009.04.001.
10.
J.W.Cooley and J.W.Tukey, An algorithm for the machine calculation of complex Fourier series, Mathematics of Computaiton19 (1965), 297–301. doi:10.1090/S0025-5718-1965-0178586-1.
11.
M.Gams, R.Piltaver and H.Gjoreski, Postopek identifikacije osebe, ki vstopa v prostor, patent P-201300281, Slovenian Intellectual Property Office, 2013, filed: September 19.
12.
H.Gjoreski, M.Gams and M.Luštrek, Context-based fall detection and activity recognition using inertial and location sensors, Journal of Ambient Intelligence and Smart Environments6(4) (2014), 19–433.
13.
H.Gjoreski, B.Kaluža, M.Gams, R.Milić and M.Luštrek, Context-based Ensemble Method for Human Energy Expenditure Estimation, Applied Soft Computing37 (2015), 960–970. doi:10.1016/j.asoc.2015.05.001.
14.
H.Gjoreski, S.Kozina, M.Gams, M.Luštrek, J.A.Álvarez-García, J.H.Hong, J.Ramos, A.K.Dey, M.Bocca and N.Patwari, Competitive live evaluation of activity-recognition systems, IEEE Pervasive Computing14(1) (2015), 70–77. doi:10.1109/MPRV.2015.3.
15.
H.Gjoreski, S.Kozina, M.Luštrek and M.Gams, Using multiple contexts to distinguish standing from sitting with a single accelerometer, in: European Conference on Artificial Intelligence (ECAI), 2014.
16.
H.Gjoreski, R.Piltaver and M.G.Person, Identification by analyzing door accelerations in time and frequency domain, in: 12th European Conference Ambient Intelligence, AmI, 2015, pp. 60–75. doi:10.1007/978-3-319-26005-1_5.
17.
M.Hall, E.Frank, G.Holmes, B.Pfahringer, P.Reutemann and I.H.Witten, The WEKA data mining software: An update, SIGKDD Explorations11(1) (2009), 10–18. doi:10.1145/1656274.1656278.
18.
L.Hong, Y.Wan and A.Jain, Fingerprint image enhancement: Algorithm and performance evaluation, Journal Pattern Analysis and Machine Intelligence, IEEE Transactions on20(8) (1998), 777–789. doi:10.1109/34.709565.
19.
A.Jakulin, Machine learning based on attribute interactions, PhD Dissertation, 2005.
20.
A.Juels, RFID security and privacy: A research survey, , IEEE Journal on Selected Areas in Communications24(2) (2006), 381–394.
21.
R.Kohavi and H.George, Wrappers for feature subset selection, Artificial Intelligence.97(1–2) (1997), 273–324. doi:10.1016/S0004-3702(97)00043-X.
22.
A.Kuzmanic and V.Zanchi, Hand shape classification using dtw and lcss as similarity measures for vision-based gesture recognition system, in: EUROCON, 2007. the International Conference on “Computer as a Tool”, 2007, pp. 264–269. doi:10.1109/EURCON.2007.4400350.
23.
Q.Li, J.Stankovic, M.Hanson, A.T.Barth, J.Lach and G.Zhou, Accurate, fast fall detection using gyroscopes and accelerometer-derived posture information, in: Proc. Sixth International Workshop on Wearable and Implantable Body Sensor Networks, 2009, pp. 138–143.
24.
Y.Liet al., A self-training semi-supervised SVM algorithm and its application in an EEG-based brain computer interface speller system, Pattern Recognition Letters29(9) (2008), 1285–1294. doi:10.1016/j.patrec.2008.01.030.
25.
Patent application, Door monitoring system, patent no. WO 2011011282 A2.
26.
R.Piltaver, H.Gjoreski and M.Gams, Person identification using door accelerations, in: AITAmI’15 Workshop, IJCAI, 2015.
27.
R.Piltaver, T.Vodopivec and M.Gams, Identifikacija oseb ob vstopu skozi vrata z uporabo pospeškomera in strojnega učenja, in: Proceedings of 16th International Multiconference Information Society, Vol. A, 2013, pp. 90–93.
28.
J.Platt, Fast training of support vector machines using sequential minimal optimization, in: Advances in Kernel Methods – Support Vector Learning, B.Schoelkopf, C.Burges and A.Smola, eds, 1998.
29.
R.Quinlan, C4.5: Programs for Machine Learning, Morgan Kaufmann Publishers, San Mateo, CA, 1993.
30.
H.Sakoe and S.Chiba, Dynamic programming algorithm optimization for spoken word recognition, IEEE Transactions on Acoustics, Speech and Signal Processing26(1) (1978), 43–49. doi:10.1109/TASSP.1978.1163055.
31.
S.Salvador and P.Chan, FastDTW: Toward Accurate Dynamic Time Warping in Linear Time and Space, in: KDD Workshop on Mining Temporal and Sequential Data, 2004, pp. 70–80.
32.
M.Silberman, Active learning: 101 strategies to teach any subject, Prentice-Hall, PO Box 11071, Des Moines, IA 50336-1071, 1996.
33.
C.C.Tappert, C.Y.Suen and T.Wakahara, The state of the art in online handwriting recognition, Pattern Analysis and Machine Intelligence, IEEE Transactions on12(8) (1990), 787–808. doi:10.1109/34.57669.
34.
M.A.Turk and A.P.Pentland, Face recognition using eigenfaces, in: Proceedings of 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’91), 1991, pp. 586–591.
35.
N.Vyas, J.Farringdon, D.Andre and J.Stivoric, Machine learning and sensor fusion for estimating continuous energy expenditure, in: Proc. 23rd Conference on Innovative Applications of Artificial Intelligence, IAAI, 2011, San Francisco, CA, USA, 2011, pp. 1613–1620.
36.
L.Wang, T.Tan, H.Ning and W.Hu, Silhouette analysis-based gait recognition for human identification, IEEE Transactions on Pattern Analysis and Machine Intelligence25(12) (2003), 1505–1518. doi:10.1109/TPAMI.2003.1251144.
37.
T.Warren Liao, Clustering of time series data – A survey, Pattern Recognition38(11) (2005), 1857–1874. doi:10.1016/j.patcog.2005.01.025.
