Methodology for improving classification accuracy using ontologies: application in the recognition of activities of daily living

  • A. G. SalgueroEmail author
  • J. Medina
  • P. Delatorre
  • M. Espinilla
Original Research


Feature construction and selection are two key factors in the field of machine learning (ML). Usually, these are very time-consuming and complex tasks because the features have to be manually crafted. The features are aggregated, combined or split to create features from raw data. In this paper, we propose a methodology that makes use of ontologies to automatically generate features for the ML algorithms. The features are generated by combining the concepts and relationships that are already in the knowledge base, expressed in form of ontology. The proposed methodology has been evaluated with three different activities of a popular dataset, showing its effectiveness in the recognition of activities of daily living (ADL). The obtained successful results indicate that the use of extended feature vectors provided by the use of ontologies offers a better accuracy, regarding the original feature vectors of the classic approach, where each feature corresponds to the activation of a sensor. Although the classic approach produces classifiers with accuracies above 92%, the proposed methodology improves those results by 1.9%, on average, without adding more information to the dataset.


Machine learning Ontology Feature learning Activity recognition Activities of daily living Smart environments Data-driven approaches Knowledge-driven approaches 



This project has received partial support from the REMIND Project from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement no 734355 as well as from the Spanish government by research project TIN2015-66524-P.


  1. Alemdar H, Ersoy C (2017) Multi-resident activity tracking and recognition in smart environments. J Ambient Intell Hum Comput 8(4):513–529. CrossRefGoogle Scholar
  2. Bae IH (2014) An ontology-based approach to adl recognition in smart homes. Future Gener Comput Syst 33:32–41CrossRefGoogle Scholar
  3. Bengio Y, Courville A, Vincent P (2013) Representation learning: a review and new perspectives. IEEE Trans Pattern Anal Mach Intell 35(8):1798–1828CrossRefGoogle Scholar
  4. Böhmann L, Lehmann J, Westphal P (2016) Dl-learner-a framework for inductive learning on the semantic web. Web Semant Sci Serv Agents World Wide Web 39(Supplement C):15–24. CrossRefGoogle Scholar
  5. Brown M, Hua G, Winder S (2011) Discriminative learning of local image descriptors. IEEE Trans Pattern Anal Mach Intell 33(1):43–57CrossRefGoogle Scholar
  6. Chandrasekaran B, Josephson J, Benjamins V (1999) What are ontologies, and why do we need them? IEEE Intell Syst Appl 14(1):20–26CrossRefGoogle Scholar
  7. Chen L, Nugent C (2009a) Ontology-based activity recognition in intelligent pervasive environments. Int J Web Inf Syst 5(4):410–430CrossRefGoogle Scholar
  8. Chen L, Nugent C (2009b) Ontology-based activity recognition in intelligent pervasive environments. Int J Web Inf Syst 5(4):410–430CrossRefGoogle Scholar
  9. Chen L, Nugent C, Okeyo G (2014) An ontology-based hybrid approach to activity modeling for smart homes. IEEE Trans Hum Mach Syst 44(1):92–105. CrossRefGoogle Scholar
  10. Cheng W, Kasneci G, Graepel T, Stern D, Herbrich R (2011) Automated feature generation from structured knowledge. In: Proceedings of the 20th ACM international conference on Information and knowledge management, ACM, pp 1395–1404Google Scholar
  11. Espinilla M, Nugent C (2017) Computational intelligence for smart environments. Int J Comput Intell Syst 10(1):1250–1251CrossRefGoogle Scholar
  12. Espinilla M, Medina J, Calzada A, Liu J, Martinez L, Nugent C (2017) Optimizing the configuration of an heterogeneous architecture of sensors for activity recognition, using the extended belief rule-based inference methodology. Microprocess Microsyst 52(Supplement C):381–390. CrossRefGoogle Scholar
  13. Even S (2011) Graph algorithms. Cambridge University Press, CambridgezbMATHCrossRefGoogle Scholar
  14. Fang H, He L, Si H, Liu P, Xie X (2014) Human activity recognition based on feature selection in smart home using back-propagation algorithm. ISA Trans 53(5):1629–1638CrossRefGoogle Scholar
  15. Ferrández-Pastor FJ, Mora-Mora H, Sánchez-Romero JL, Nieto-Hidalgo M, García-Chamizo JM (2017) Interpreting human activity from electrical consumption data using reconfigurable hardware and hidden markov models. J Ambient Intell Hum Comput 8(4):469–483CrossRefGoogle Scholar
  16. Gupta P, Dallas T (2014) Feature selection and activity recognition system using a single triaxial accelerometer. IEEE Trans Biomed Eng 61(6):1780–1786CrossRefGoogle Scholar
  17. Hall MA, Holmes G (2003) Benchmarking attribute selection techniques for discrete class data mining. IEEE Trans Knowl Data Eng 15(6):1437–1447CrossRefGoogle Scholar
  18. Hopcroft J, Tarjan R (1974) Efficient planarity testing. JACM 21(4):549–568MathSciNetzbMATHCrossRefGoogle Scholar
  19. Horridge M, Drummond N, Goodwin J, Rector A, Wang HH (2006) The manchester owl syntax. In: Proc. of the 2006 OWL experiences and directions workshop (OWL-ED2006Google Scholar
  20. Horrocks I (2008) Ontologies and the semantic web. Commun ACM 51(12):58–67CrossRefGoogle Scholar
  21. Horrocks I, Patel-Schneider P, Van Harmelen F (2003) From SHIQ and RDF to OWL: the making of a web ontology language. Web Semant 1(1):7–26CrossRefGoogle Scholar
  22. Kanter JM, Veeramachaneni K (2015) Deep feature synthesis: towards automating data science endeavors. In: Data science and advanced analytics (DSAA), 2015. 36678 2015. IEEE international conference on, IEEE, pp 1–10Google Scholar
  23. Knijff J, Frasincar F, Hogenboom F (2013) Domain taxonomy learning from text: The subsumption method versus hierarchical clustering. Data Knowl Eng 83:54–69. CrossRefGoogle Scholar
  24. Kohler J, Philippi S, Specht M, Ruegg A (2006) Ontology based text indexing and querying for the semantic web. Knowl Based Syst 19(8):744–754CrossRefGoogle Scholar
  25. Korhonen I, Parkka J, Van Gils M (2003) Health monitoring in the home of the future. IEEE Eng Med Biol Mag 22(3):66–73CrossRefGoogle Scholar
  26. Lehmann J, Auer S, Bëhmann L, Tramp S (2011) Class expression learning for ontology engineering. Web Semant Sci Serv Agents World Wide Web 9(1):71–81. CrossRefGoogle Scholar
  27. Li C, Lin M, Yang L, Ding C (2014) Integrating the enriched feature with machine learning algorithms for human movement and fall detection. J Supercomput 67(3):854–865CrossRefGoogle Scholar
  28. López Gutiérrez, de la Franca C, Hervás R, Johnson E, Mondéjar T, Bravo J (2017) Extended body-angles algorithm to recognize activities within intelligent environments. J Ambient Intell Hum Comput 8(4):531–549. CrossRefGoogle Scholar
  29. Maedche A, Staab S (2001) Ontology learning for the semantic web. IEEE Intell Syst Appl 16(2):72–79CrossRefGoogle Scholar
  30. Mingers J (1989) An empirical comparison of pruning methods for decision tree induction. Mach Learn 4(2):227–243CrossRefGoogle Scholar
  31. Motik B, Patel-Schneider PF, Parsia B (2012) Owl 2 web ontology language. structural specification and functional–style syntax (second edition). Accessed 30 Oct 2017
  32. Noor MHM, Salcic Z, Kevin I, Wang K (2018) Ontology-based sensor fusion activity recognition. J Ambient Intell Hum Comput 1–15.
  33. Okeyo G, Chen L, Wang H, Sterritt R (2014) Dynamic sensor data segmentation for real-time knowledge-driven activity recognition. Pervas Mob Comput 10:155–172CrossRefGoogle Scholar
  34. Ordóñez FJ, Roggen D (2016) Deep convolutional and lstm recurrent neural networks for multimodal wearable activity recognition. Sensors 16(1):115CrossRefGoogle Scholar
  35. Ordónez FJ, de Toledo P, Sanchis A (2013) Activity recognition using hybrid generative/discriminative models on home environments using binary sensors. Sensors 13(5):5460–5477CrossRefGoogle Scholar
  36. Oukrich N, El Bouazzaoui C, Maach A, Driss E (2017) Human activities recognition based on autoencoder pre-training and back-propagation algorithm. J Theor Appl Inf Technol 95(19):5194–5202Google Scholar
  37. Paulheim H (2012) Generating possible interpretations for statistics from linked open data. Research and applications, the semantic web, pp 560–574Google Scholar
  38. Quesada FJ, Moya F, Medina J, Martínez L, Nugent C, Espinilla M (2015) Generation of a partitioned dataset with single, interleave and multioccupancy daily living activities, vol 9454. Springer, Cham, pp 60–71Google Scholar
  39. Rafferty J, Chen L, Nugent C, Liu J (2015) Goal lifecycles and ontological models for intention based assistive living within smart environments. Comput Syst Sci Eng 30(1):7–18Google Scholar
  40. Riboni D, Bettini C (2011) Owl 2 modeling and reasoning with complex human activities. Pervas Mob Comput 7(3):379–395CrossRefGoogle Scholar
  41. Ristoski P (2015) Towards linked open data enabled data mining. In: European semantic web conference, Springer, pp 772–782Google Scholar
  42. Ristoski P, Bizer C, Paulheim H (2015) Mining the web of linked data with rapidminer. Web Semant Sci Serv Agents World Wide Web 35(Part 3):142–151. (semantic Web Challenge 2014)CrossRefGoogle Scholar
  43. Salguero A, Espinilla M (2017) A flexible text analyzer based on ontologies: an application for detecting discriminatory language. Lang Resour Eval. CrossRefGoogle Scholar
  44. Shewell C, Medina-Quero J, Espinilla M, Nugent C, Donnelly M, Wang H (2017) Comparison of fiducial marker detection and object interaction in activities of daily living utilising a wearable vision sensor. Int J Commun Syst 30(5):e3223. CrossRefGoogle Scholar
  45. Singh D, Merdivan E, Hanke S, Kropf J, Geist M, Holzinger A (2017) Convolutional and recurrent neural networks for activity recognition in smart environment. In: Towards integrative machine learning and knowledge extraction, Springer, pp 194–205Google Scholar
  46. Sirin E, Parsia B, Grau B, Kalyanpur A, Katz Y (2007) Pellet: a practical owl-dl reasoner. Web Semant 5(2):51–53CrossRefGoogle Scholar
  47. Terziev Y (2016) Feature generation using ontologies during induction of decision trees on linked data. In: ISWC PhD SymposiumGoogle Scholar
  48. Uschold M, Gruninger M (1996) Ontologies: principles, methods and applications. Knowl Eng Rev 11(2):93–136CrossRefGoogle Scholar
  49. van Kasteren TLM et al (2011) Activity recognition for health monitoring elderly using temporal probabilistic models. ASCIGoogle Scholar
  50. Villalonga C, Razzaq MA, Khan WA, Pomares H, Rojas I, Lee S, Banos O (2016) Ontology-based high-level context inference for human behavior identification. Sensors. CrossRefGoogle Scholar
  51. Wei T, Lu Y, Chang H, Zhou Q, Bao X (2015) A semantic approach for text clustering using wordnet and lexical chains. Expert Syst Appl 42(4):2264–2275. CrossRefGoogle Scholar
  52. Witten IH, Frank E, Hall MA, Pal CJ (2016) Data Mining: practical machine learning tools and techniques. Morgan Kaufmann, CambridgeGoogle Scholar
  53. Xu C, Zhang X, He J (2016) Human activity recognition based on quantization on feature’s classification capability (preprints) Google Scholar
  54. Zhang F, Ma Z, Li W (2015) Storing owl ontologies in object-oriented databases. Knowl Based Syst 76:240–255. CrossRefGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Universidad de CádizCádizSpain
  2. 2.Universidad de JaénJaénSpain

Personalised recommendations