Interpreting human activity from electrical consumption data using reconfigurable hardware and hidden Markov models

  • F. J. Ferrández-PastorEmail author
  • H. Mora-Mora
  • J. L. Sánchez-Romero
  • M. Nieto-Hidalgo
  • J. M. García-Chamizo
Original Research


Human activity recognition is a promising research field in a wide variety of areas: ambient assisted living, pervasive and mobile computing, surveillance based security and context aware computing are some examples. In domestic environment, daily and frequent people activities use all kind of electric devices (appliances). Appliances connection or disconnection can provide useful data to know patterns of use, usual or unusual events and people behaviour, but smart meters only provide aggregated consumption data and cannot be used by the consumers to monitor individual actions or to know people behaviour. Furthermore, specialised systems for power load and monitoring are costly to install. This work proposes the design and development of low cost and embedded hardware tools to obtain disaggregated power consumption with the aim to interpret human activity. Non-intrusive load monitoring, design based on Wavelet Transform processing and Field Programmable Gate Arrays hardware implementation provide the necessary support to develop this kind of embedded systems. Human activity is classified using Hidden Markov models.


Human activity recognition Smart sensor FPGA Wavelet transform Hidden Markov models 


  1. Akansu AN, Haddad PR (2000) Multiresolution signal decomposition: transforms, subbands, and wavelets. Academic Press, LondonzbMATHGoogle Scholar
  2. Albanesi MG, Lombardi L (1997) Wavelets for multiresolution shape recognition. In: Image analysis and processing, Springer, Berlin, pp 276–283Google Scholar
  3. Arrais E, Roda V, Neto C, Ribeiro R, Costa F (2014) Fpga versus dsp for wavelet transform based voltage sags detection. In: Instrumentation and measurement technology conference (I2MTC) proceedings, 2014 IEEE international, pp 643–647. doi: 10.1109/I2MTC.2014.6860822
  4. Bauer M, Becker C, Rothermel K (2002) Location models from the perspective of context-aware applications and mobile ad hoc networks. Personal Ubiquitous Comput 6(5–6):322–328. doi: 10.1007/s007790200036 CrossRefGoogle Scholar
  5. Bergés M, Soibelman L, Matthews HS (2010) Leveraging data from environmental sensors to enhance electrical load disaggregation algorithms. In: Proceeding of the 13th international conference on computing in civil and building engineeringGoogle Scholar
  6. Camier TR, Giroux S, Bouchard B, Bouzouane A (2013) Designing a NIALM in smart homes for cognitive assistance. Procedia Comput Sci 19:524–532. doi: 10.1016/j.procs.2013.06.070. In: The 4th international conference on ambient systems, networks and technologies (ANT 2013), the 3rd international conference on sustainable energy information technology (SEIT-2013)
  7. Celler B, Earnshaw W, Ilsar E, Betbeder-Matibet L, Harris M, Clark R, Hesketh T, Lovell N (1995) Remote monitoring of health status of the elderly at home. A multidisciplinary project on aging at the University of New South Wales. Int J Bio-Med Comput 40(2):147–155. doi: 10.1016/0020-7101(95)01139-6 (asia Pacific Association of Medical Informatics (APAMI))
  8. Chang H (2012) Non-intrusive demand monitoring and load identification for energy management systems based on transient feature analyses. Energies 5:4569–4589CrossRefGoogle Scholar
  9. Chang HH, Lin CL, Lee JK (2010) Load identification in nonintrusive load monitoring using steady-state and turn-on transient energy algorithms. In: 14th international conference on computer supported cooperative work in design (CSCWD), 2010, pp 27–32. doi: 10.1109/CSCWD.2010.5472008
  10. Chernbumroong S, Cang S, Yu H (2014) A practical multi-sensor activity recognition system for home-based care. Decis Support Syst 66:61–70. doi: 10.1016/j.dss.2014.06.005 CrossRefGoogle Scholar
  11. Chilo J, Lindblad T (2007) Real-time signal processing of infrasound data using 1d wavelet transform on fpga device. In: Real-time conference, 2007 15th IEEE-NPSS, pp 1–5. doi: 10.1109/RTC.2007.4382758
  12. Cilla R, Patricio MA, Garcıa J, Berlanga A, Molina JM (2009) Recognizing human activities from sensors using hidden markov models constructed by feature selection techniques. Algorithms 2:282–300CrossRefGoogle Scholar
  13. Costa R, Novais P, Costa Â, Lima L, Neves J (2010) Ambient intelligence and future trends. In: International symposium on ambient intelligence (ISAmI 2010), Springer Berlin Heidelberg, Berlin, Heidelberg, chap User Recognition in AAL Environments, pp 177–184Google Scholar
  14. Ding D, Cooper RA, Pasquina PF, Fici-Pasquina L (2011) Sensor technology for smart homes. Maturitas 69(2):131–136. doi: 10.1016/j.maturitas.2011.03.016 CrossRefGoogle Scholar
  15. Du J, Luo Z, Wang J (2011) High-speed real-time signal processing system design and implementation based on fpga. In: Artificial Intelligence, Management Science and Electronic Commerce (AIMSEC), 2011 2nd International Conference on, pp 7096–7099, DOI10.1109/AIMSEC.2011.6011087Google Scholar
  16. Figueiredo M, de Almeida A, Ribeiro B (2012) Home electrical signal disaggregation for non-intrusive load monitoring (NILM) systems. Neurocomputing 96(0):66–73, DOI10.1016/j.neucom.2011.10.037Google Scholar
  17. Fortin-Simard D, Bilodeau JS, Gaboury S, Bouchard B, Bouzouane A (2014) Human activity recognition in smart homes: Combining passive rfid and load signatures of electrical devices. In: 2014 IEEE symposium on intelligent agents (IA), pp 22–29, doi: 10.1109/IA.2014.7009454
  18. García GJ, Jara CA, Pomares J, Alabdo A, Poggi LM, Torres F (2014) A survey on FPGA-based sensor systems: towards intelligent and reconfigurable low-power sensors for computer vision, control and signal processing. Sensors 14(4):6247–6278. doi: 10.3390/s140406247 CrossRefGoogle Scholar
  19. García Chamizo JM, Mora Pascual JM, Mora Mora H, Signes Pont MT et al (2003) Calculation methodology for flexible arithmetic processingGoogle Scholar
  20. Gu T, Wu Z, Tao X, Pung HK, Lu J (2009) epsicar: an emerging patterns based approach to sequential, interleaved and concurrent activity recognition. In: IEEE International conference on pervasive computing and communications, 2009. PerCom 2009, pp 1–9. doi: 10.1109/PERCOM.2009.4912776
  21. Gurudath N, Riley HB (2014) Drowsy driving detection by EEG analysis using wavelet transform and k-means clustering. Procedia Comput Sci 34:400–409. doi: 10.1016/j.procs.2014.07.045 CrossRefGoogle Scholar
  22. Hariharan G, Kannan K (2014) Review of wavelet methods for the solution of reaction diffusion problems in science and engineering. Appl Math Model 38(3):799–813MathSciNetCrossRefGoogle Scholar
  23. Hart G (1992) Non-intrusive appliance load monitoring. Proc IEEE 80(12):1870–1891. doi: 10.1109/5.192069 CrossRefGoogle Scholar
  24. Hazas M, Friday A, Scott J (2011) Look back before leaping forward: four decades of domestic energy inquiry. Pervasive Comput IEEE 10(1):13–19. doi: 10.1109/MPRV.2010.89 CrossRefGoogle Scholar
  25. Kabir MH, Hoque MR, Thapa K, Yangr SH (2015) Two-layer hidden markov model for human activity recognition in home environments. Int J Distrib Sensor Netw 2016:12. doi: 10.1155/2016/4560365
  26. Lee W, Fung G, Lam H, Chan F, Lucente M (2004) Exploration on load signatures. In: Proceedings of international conference on electrical engineering (ICEE), pp 1–5Google Scholar
  27. Leonhardt U, Magee J (1998) Multi-sensor location tracking. In: Proceedings of the 4th annual ACM/IEEE international conference on mobile computing and networking, ACM, New York, NY, USA, MobiCom ’98, pp 203–214. doi: 10.1145/288235.288291
  28. Marceau M, Zmeureanu R (2000) Nonintrusive load disaggregation computer program to estimate the energy consumption of major end uses in residential buildings. Energy Convers Manage 41(13):1389–1403. doi: 10.1016/S0196-8904(99)00173-9 CrossRefGoogle Scholar
  29. Mesa H (2005) Adapted wavelets for pattern detection. Progress in pattern recognition, image analysis and applications. Springer, Berlin, pp 933–944CrossRefGoogle Scholar
  30. Mota H, Vasconcelos F, da Silva R (2005) Real-time wavelet transform algorithms for the processing of continuous streams of data. In: 2005 IEEE international workshop on intelligent signal processing, pp 346–351. doi: 10.1109/WISP.2005.1531683
  31. Pantelopoulos A, Bourbakis NG (2010) A survey on wearable sensor-based systems for health monitoring and prognosis. Trans Sys Man Cyber Part C 40(1):1–12. doi: 10.1109/TSMCC.2009.2032660 CrossRefGoogle Scholar
  32. Parson O, Ghosh S, Weal M, Rogers A (2011) Using hidden markov models for iterative non-intrusive appliance monitoring. In: Neural information processing systems workshop on machine learning for sustainability, 2011Google Scholar
  33. Patel S, Robertson T, Kientz J, Reynolds M, Abowd G (2007) At the flick of a switch: detecting and classifying unique electrical events on the residential power line. In: UbiComp 2007: ubiquitous computing, lecture notes in computer science, vol 4717, Springer Berlin Heidelberg, pp 271–288. doi: 10.1007/978-3-540-74853-316
  34. Randell C, Muller H (2000) Context awareness by analysing accelerometer data. In: The 4th international symposium on wearable computers, pp 175–176. doi: 10.1109/ISWC.2000.888488
  35. Rehman M, Khan RA (2012) A numerical method for solving boundary value problems for fractional differential equations. Appl Math Model 36(3):894–907. doi: 10.1016/j.apm.2011.07.045 MathSciNetCrossRefzbMATHGoogle Scholar
  36. Ruzzelli A, Nicolas C, Schoofs A, OHare G (2010) Real-time recognition and profiling of appliances through a single electricity sensor. In: 7th annual IEEE communications society conference on sensor mesh and ad hoc communications and networks (SECON), 2010, pp 1–9. doi: 10.1109/SECON.2010.5508244
  37. Sanchez JL, Mora H, Mora J, Jimeno A (2008) Architecture implementation of an improved decimal cordic method. In: IEEE international conference on computer design, 2008. ICCD 2008, pp 95–100. doi: 10.1109/ICCD.2008.4751846
  38. Schoofs A, Guerrieri A, Delaney DT, O’Hare GMP, Ruzzelli A (2010) ANNOT: automated electricity data annotation using wireless sensor networks. In: 7th annual IEEE communications society conference on sensor mesh and ad hoc communications and networks (SECON), 2010, pp 1–9. doi: 10.1109/SECON.2010.5508248
  39. Streubel R, Yang B (2012) Identification of electrical appliances via analysis of power consumption. In: 47th international universities power engineering conference (UPEC), 2012, pp 1–6. doi: 10.1109/UPEC.2012.6398559
  40. Tenllado C, Setoain J, Prieto M, Pinuel L, Tirado F (2008) Parallel implementation of the 2d discrete wavelet transform on graphics processing units: filter bank versus lifting. IEEE Trans Parallel Distrib Syst 19(3):299–310. doi: 10.1109/TPDS.2007.70716 CrossRefGoogle Scholar
  41. Vail DL, Veloso MM, Lafferty JD (2007) Conditional random fields for activity recognition. In: Proceedings of the 6th international joint conference on autonomous agents and multiagent systems, ACM, p 235Google Scholar
  42. Vogiatzis E, Kalogridis G, Denic S (2013) Real-time and low cost energy disaggregation of coarse meter data. In: 4th IEEE/PES innovative smart grid technologies Europe (ISGT EUROPE) conference, 2013, pp 1–5. doi: 10.1109/ISGTEurope.2013.6695417
  43. Zeifman M, Roth K (2011) Nonintrusive appliance load monitoring: review and outlook. IEEE Trans Consumer Electron 57(1):76–84. doi: 10.1109/TCE.2011.5735484 CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2016

Authors and Affiliations

  1. 1.Department of Computer TechnologyUniversity of AlicanteAlicanteSpain

Personalised recommendations