A k-nearest neighbors based approach applied to more realistic activity recognition datasets

Abstract

Due to the latest technological advances, the current society has the possibility to store large volumes of data in the majority of the problems of the daily life. These data are useless if there is not a set of techniques available to analyze them with the objective of obtaining knowledge that facilitates the problem resolution. This paper focuses on the techniques provided by data mining as a tool for intelligent data analysis in the field of human activity recognition, specifically in the application of two techniques of data mining capable of carrying out the extraction of knowledge from data that are not as accurate and exact as desirable. This type of data reflects the true nature of the information collected on a day-to-day basis. The proposed techniques allow performing a preprocessing of the data by means of an instance selection that improves the computational requirements of the system response, obtaining satisfactory accuracy results. Several experiments are carried out on a real world dataset and various datasets obtained from the previous one in a synthetic way to simulate more realistic datasets that illustrate the potential of the proposed techniques.

Keywords

Imperfect information fuzzy sets data mining activity recognition instance selection k-nearest neighbors behaviour modeling

Get full access to this article

View all access options for this article.

References

Agrawal, K-nearest neighbor for uncertain data, International Journal of Computer Applications105(11) (2014), 13–16.

Azorin-Lopez,

Saval-Calvo,

Fuster-Guillo and

Garcia-Rodriguez, A novel prediction method for early recognition of global human behaviour in image sequences, Neural Processing Letters43(2) (2016), 363–387. doi:10.1007/s11063-015-9412-y.

Bao and

S.S.

Intille, Activity Recognition from User-Annotated Acceleration Data, in: International Conference on Pervasive Computing (Pervasive 2004),

Ferscha and

Mattern, eds, Lecture Notes in Computer Science, Vol. 3001, Springer, Berlin, 2004, pp. 1–17. doi:10.1007/978-3-540-24646-6_1.

J.M.

Cadenas,

M.C.

Garrido,

Martínez,

Muñoz and

P.P.

Bonissone, A fuzzy k-nearest neighbor classifier to deal with imperfect data, Soft Computing22(10) (2018), 3313–3330. doi:10.1007/s00500-017-2567-x.

Chen and

Nugent, Ontology-based activity recognition in intelligent pervasive environments, International Journal of Web Information Systems5(4) (2009), 410–430. doi:10.1108/17440080911006199.

S.M.

Chen, New methods for subjective mental workload assesment and fuzzy risk analysis, Cybernetic and Systems27 (1996), 449–472. doi:10.1080/019697296126417.

Chetty and

White, Body sensor networks for human activity recognition, in: 3rd International Conference on Signal Processing and Integrated Networks, 2016, pp. 660–665.

S.L.

Chua,

Marsland and

Guesgen, A supervised learning approach for behaviour recognition in smart homes, Journal of Ambient Intelligence and Smart Environments8(3) (2016), 259–271. doi:10.3233/AIS-160378.

De Luca and

Termini, A definition of a nonprobabilistic entropy in the setting of fuzzy sets theory, Information and control20(4) (1972), 301–312. doi:10.1016/S0019-9958(72)90199-4.

10.

Derrac,

García and

Herrera, Fuzzy nearest neighbor algorithms: Taxonomy, experimental analysis and prospects, Information Sciences260 (2014), 98–119. doi:10.1016/j.ins.2013.10.038.

11.

Destercke, A k-nearest neighbours method based on imprecise probabilities, Soft Computing16(5) (2012), 833–844. doi:10.1007/s00500-011-0773-5.

12.

Diamond and

Kloeden, Metric Spaces of Fuzzy Sets: Theory and Applications, World Scientific, 1994.

13.

D.J.

Dubois, Fuzzy Sets and Systems: Theory and Applications, Academic Press, 1980.

14.

Enta, Fuzzy decision theory, in: International Congress on Applied Systems Research and Cybernetics, 1980, pp. 2980–2990.

15.

S.Z.

Erdogan and

T.T.

Bilgin, A data mining approach for fall detection by using k-nearest neighbour algorithm on wireless sensor network data, IET Communications6(18) (2012), 3281–3287. doi:10.1049/iet-com.2011.0228.

16.

Fleury,

Vacher and

Noury, SVM-based multimodal classification of activities of daily living in health smart homes: Sensors, algorithms, and first experimental result, IEEE Transactions on Information Technology in Biomedicine14(2) (2010), 274–283. doi:10.1109/TITB.2009.2037317.

17.

Garcia,

Derrac,

Cano and

Herrera, Prototype selection for nearest neighbor classification: Taxonomy and empirical study, IEEE Transactions on Pattern Analysis and Machine Intelligence34(3) (2012), 417–435. doi:10.1109/TPAMI.2011.142.

18.

Hakim,

M.S.

Huq,

Shanta and

B.S.K.K.

Ibrahim, Smartphone based data mining for fall detection: Analysis and design, Procedia Computer Science105 (2017), 46–51. doi:10.1016/j.procs.2017.01.188.

19.

P.E.

Hart, The condensed nearest neighbour rule, IEEE Transactions on Information Theory14(3) (1968), 515–516. doi:10.1109/TIT.1968.1054155.

20.

M.M.

Hassan,

M.Z.

Uddin,

Mohamed and

Almogrena, A robust human activity recognition system using smartphone sensors and deep learning, Future Generation Computer Systems81 (2018), 307–313. doi:10.1016/j.future.2017.11.029.

21.

He,

Hu and

Wang, A smart device enabled system for autonomous fall detection and alert, International Journal of Distributed Sensor Networks – Special Issue on Smart Device Enabled Sensor Networks: Theory and Practice2016 (2016), Article ID 1. doi:10.1155/2016/2308183.

22.

Kerdegari,

Mokaram,

Samsudin and

A.R.

Ramli, A pervasive neural network based fall detection system on smart phone, Journal of Ambient Intelligence and Smart Environments7(2) (2015), 221–230. doi:10.3233/AIS-150306.

23.

Kononenko and

Kukar, Machine Learning and Data Mining: Introduction to Principles and Algorithms, Horwood Publishing, 2007.

24.

Krose,

van Kasteren,

Gibson and

van den Dool CARE, Context awareness in residences for elderly, in: 6th International Conference of the International Society for Gerontechnology, 2008, pp. 101–105.

25.

S.W.

Lee and

Mase, Activity and location recognition using wearable sensors, IEEE Pervasive Computing1(3) (2002), 24–32. doi:10.1109/MPRV.2002.1037719.

26.

Lichman, Uci Machine Learning Repository, University of California, Irvine, School of Information and Computer Sciences, CA, 2013, available at http://archive.ics.uci.edu/ml.

27.

W.-C.

Lin,

C.-F.

Tsai,

S.-W.

Ke,

C.-W.

Hung and

Eberle, Learning to detect representative data for large scale instance selection, Journal of Systems and Software106 (2015), 1–8. doi:10.1016/j.jss.2015.04.038.

28.

Maurer,

Smailagic,

D.P.

Siewiorek and

Deisher, Activity recognition and monitoring using multiple sensors on different body positions, in: Internal Workshop on Wearable and Implantable Body Sensor Networks, 2006, pp. 1–4.

29.

Palumbo,

Gallicchio,

Pucci and

Micheli, Human activity recognition using multisensor data fusion based on reservoir computing, Journal of Ambient Intelligence and Smart Environments8(2) (2016), 87–107. doi:10.3233/AIS-160372.

30.

Parkka,

Ermes,

Korpipaa,

Mantyjarvi,

Peltola and

Korhonen, Activity classification using realistic data from wearable sensors, IEEE Transactions on Information Technology in Biomedicine10(1) (2006), 119–128. doi:10.1109/TITB.2005.856863.

31.

O.M.

Prabowo,

Mutijarsa and

S.H.

Supangkat, Missing data handling using machine learning for human activity recognition on mobile device, in: International Conference on ICT for Smart Society, 2016, pp. 59–62.

32.

A.L.

Ralescu and

D.A.

Ralescu, Probability and fuzziness, Information Sciences34(2) (1984), 85–92. doi:10.1016/0020-0255(84)90018-5.

33.

Ravi,

Dandekar,

Mysore and

Littman, Activity recognition from accelerometer data, in: 17th Conference on Innovative Applications of Artificial Intelligence, 2005, pp. 1541–1546.

34.

J.L.

Reyes-Ortiz,

Oneto,

Sama,

Parra and

Anguita, Transition-aware human activity recognition using smartphones, Neurocomputing171 (2016), 754–767. doi:10.1016/j.neucom.2015.07.085.

35.

Santini and

Jain, Similarity is a geometer, Multimedia Tools and Applications5(3) (1997), 277–306. doi:10.1023/A:1009651725256.

36.

Scheurer,

Tedesco,

K.N.

Brown and

O’Flynn, Human activity recognition for emergency first responders via body-worn inertial sensors, in: IEEE 14th International Conference on Wearable and Implantable Body Sensor Networks, 2017, pp. 5–8.

37.

M.V.

Sokolova,

Serrano-Cuerda,

J.C.

Castillo and

Fernández-Caballero, A fuzzy model for human fall detection in infrared video, Journal of Intelligent & Fuzzy Systems24(2) (2013), 215–228. doi:10.3233/IFS-2012-0548.

38.

Su,

Tong and

Ji, Activity recognition with smartphone sensors, Tsinghua Science and Technology19(3) (2014), 235–249. doi:10.1109/TST.2014.6838194.

39.

Vallabh,

Malekian,

Ye and

D.C.

Bogatinoska, Fall detection using machine learning algorithms, in: 24th International Conference on Software, Telecommunications and Computer Networks, 2016, pp. 1–9.

40.

Velik, A brain-inspired multimodal data mining approach for human activity recognition in elderly homes, Journal of Ambient Intelligence and Smart Environments6(4) (2014), 447–468. doi:10.3233/AIS-140266.

41.

Younes,

Abdallah and

Denœux, Fuzzy multi-label learning under veristic variables, in: Proceedings of IEEE International Conference on Fuzzy Systems, Barcelona, Spain, 18–23 July, 2010, pp. 1–8. doi:10.1109/FUZZY.2010.5584079.