Multisensor Fusion for Low-Power Wireless Microsystems

Part of the Springer Series in Cognitive and Neural Systems book series (SSCNS)


This chapter addresses the use of artificial neural network (ANN) as a form of multisensor fusion for low-power microsystems in wireless sensor networks. The ANN is configured to perform local preprocessing and early clustering/classification of high-dimensional sensory signals. This chapter reviews the use of ANNs applied to fuse electrochemical sensory data, and the status of state-of-the-art VLSI neural hardware is presented. The hardware-amenability of these neural algorithms creates an opportunity to integrate multiple sensors and their data fusion within a single silicon chip, thus miniaturizing the physical size of microsystems and improving the signal integrity of measurements. Besides the operation of early classification, several other practical issues (i.e., stochastic noise, time-dependent drift, and biofouling) of electrochemical sensors are also discussed. Subsequently, a multisensor microsystem named Lab-in-a-Pill is used as a case study. We demonstrate how to implement an ANN to perform early classification and thus to autocalibrate an array of electrochemical sensors online. The chapter concludes with some discussion and future research directions.


Artificial Neural Network Hide Neuron Cellular Neural Network Stochastic Noise Bayesian Belief Network 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. Alspector, J., Allen, R.B., Jayakumar, A., Zeppenfeld, T., Meir, R.: Relaxation networks for large supervised learning problems. In: Advances in Neural Processing Systems, 4, 1015–1026 (1991)Google Scholar
  2. Alspector, J., Gannett, J.W., Haber, S., Parker, M.B., Chu, R.: A VLSI-efficient technique for generating multiple uncorrelated noise sources and its application to stochastic neural networks. IEEE Transactions on Circuits and Systems 38(1), 109–123 (1991)CrossRefGoogle Scholar
  3. Alspector, J., amd R. B. Allen, B.G.: Performance of a stochastic learning microchip. In: Advances in Neural Information Processing Systems, 1, 748–760 (1989)Google Scholar
  4. Argyrakis, P., Hamilton, A., Webb, B., Zhang, Y., Gonos, T., Cheung, R.: Fabrication and characterization of a wind sensor for integration with a neuron circuit. Microelectronic Engineering 84(5–8), 1749–1753 (2007)CrossRefGoogle Scholar
  5. Artursson, T., Eklov, T., Lundstrom, I., Martensson, P., Sjostrom, M., Holmberg, M.: Drift correction for gas sensors using multivariate methods. Journal of Chemometrics 14, 711–723 (2000)CrossRefGoogle Scholar
  6. Asanovic, K., Morgan, N.: Experimental determination of precision requirements for back-propagation training of artificial neural networks. In: Proceedings of International Conference on Microelectronics for Neural Network, pp. 9–15. Munich, Germany (1991)Google Scholar
  7. Aydin, N., Arslan, T., Cumming, D.R.S.: A direct-sequence spread-spectrum communication system for integrated sensor microsystems. IEEE Transactions on Information Technology in Biomedicine 9(1), 4–12 (2005)CrossRefPubMedGoogle Scholar
  8. Bedoya, G., Jutten, C., Bermejo, S., Cabestany, J.: Improving semiconductor-based chemical sensor arrays using advanced algorithms for blind source separation. In: Proceedings of the IEEE Sensors for Industry Conference, pp. 149–154. New Orleans, Louisiana, USA (2004)Google Scholar
  9. Bermejo, S., Bedoya, G., Parisi, V., Cabestany, J.: An on-line water monitoring system using a smart ISFET array. In: Proceedings of the IEEE Conference on Industrial Electronics Society, pp. 2797–2802 (2002)Google Scholar
  10. Brdys, M.A., Kulawski, G.J.: Dynamic neural controllers for induction motor. IEEE Transactions on Neural Networks 10(2), 340–355 (1999)CrossRefPubMedGoogle Scholar
  11. Bris, N.L., Birot, D.: Automated pH-ISFET measurements under hydrostatic pressure for marine monitoring application. Analytica Chimica Acta 356, 205–215 (1997)CrossRefGoogle Scholar
  12. Cameron, K.L., Murray, A.F.: Minimizing the effect of process mismatch in a neuromorphic system using spike-timing-dependent adaptation. IEEE Transactions on Neural Networks 19(5), 899–913 (2008)CrossRefPubMedGoogle Scholar
  13. Card, H.C., McNeill, D.K., Schneider, C.R.: Analog VLSI circuits for competitive learning networks. Analog Integrated Circuits and Signal Processing 15, 291–314 (1998)CrossRefGoogle Scholar
  14. Chen, H., Fleury, P., Murray, A.F.: Minimizing Contrastive Divergence in noisy, mixed-mode VLSI neurons. In: Advances in Neural Information Processing Systems, vol. 16 (2003)Google Scholar
  15. Chen, H., Murray, A.F.: A Continuous Restricted Boltzmann Machine with an implementable training algorithm. IEE Proceedings on Vision, Image and Signal Processing 150(3), 153–158 (2003)CrossRefGoogle Scholar
  16. Chen, H., Murray, A.F.: Continuous-valued probabilistic behaviour in a vlsi generative model. IEEE Transactions on Neural Networks 17(3), 755–770 (2006)CrossRefPubMedGoogle Scholar
  17. Chen, T.L., You, R.Z.: A novel fault-tolerant sensor system for sensor drift compensation. Sensors and Actuators A: Physical 147(2), 623–632 (2008)CrossRefGoogle Scholar
  18. Chua, L.O., Roska, T.: The CNN paradigm. IEEE Transactions on Circuits and Systems-I: Fundamental Theory and Applications 40(3), 147–156 (1993)CrossRefGoogle Scholar
  19. Chung, D., Merat, F.L.: Neural network based sensor array signal processing. In: Proceedings of the IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, pp. 757–764. Washington, DC, USA (1996)Google Scholar
  20. Clarke, D.W.: Sensor, actuator and plant validation. IEE Colloquium on Intelligent and Self-Validating Sensors pp. 1–8 (1999)Google Scholar
  21. Coggins, R., Jabri, M., Flower, B., Pickard, S.: A hybrid analog and digital VLSI neural network for intracardiacmorphology classification. IEEE Journal of Solid-States Circuits 30(5), 542–550 (1995)CrossRefGoogle Scholar
  22. Errachid, A., Bausells, J., Jaffrezic-Renault, N.: A simple REFET for pH detection in differential mode. Sensors and Actuators B 60, 43–48 (1999)CrossRefGoogle Scholar
  23. Figeys, D., Pinto, D.: Lab-on-a-chip: A revolution in biological and medical sciences. Analytical Chemistry 72(9), 330A–335A (2000)CrossRefPubMedGoogle Scholar
  24. Fleury, P., Chen, H., Murray, A.F.: On-chip Contrastive Divergence learning in analogue VLSI. In: Proceedings of the International Joint Conference on Neural Networks, pp. 1723–1728. Budapest, Hungary (2004)Google Scholar
  25. Gardner, J.W., Hines, E.L., Molinier, F., Bartlett, P.N., Mottram, T.T.: Prediction of health of dairy cattle from breath samples using neural network with parametric model of dynamic response of array of semiconducting gas sensors. IEE Proceedings on Sci. Meas. Technology 146(2), 102–106 (1999)CrossRefGoogle Scholar
  26. Grattarola, M., Massobrio, G., Martinoia, S.: Modelling H + -Sensitive FET’s with SPICE. IEEE Transactions on Electron Devices 39(4), 813–819 (1992)CrossRefGoogle Scholar
  27. Guo, T.H., Nurre, J.: Sensor failure detection and recovery by neural networks. In: Proceedings of IJCNN, vol. 1, pp. 221–226. Seattle, WA, USA (1991)Google Scholar
  28. Haykin, S.: Neural Networks: A Comprehensive Foundation. Prentice Hall (1998)Google Scholar
  29. Heckerman, D.: Learning in graphical models, chap. A tutorial on learning with Bayesian networks, pp. 301–354. MIT, Cambridge, MA, USA (1999)Google Scholar
  30. Hendrikse, J., Olthuis, W., Bergveld, P.: A method of reducing oxygen induced drift in iridium oxide pH sensors. Sensors and Actuators B 53, 97–103 (1998)CrossRefGoogle Scholar
  31. Higuchi, T., Furuya, T., Handa, K., Takahashi, N., Nishiyama, H., Kokubu, A.: IXM2: A parallel associative processor. In: Proceedings of the international symposium on Computer architecture, pp. 22–31. Toronto, Ontario, Canada (1991)Google Scholar
  32. Hinton, G.E.: Products of experts. In: Proceedings of the 9th International Conference on Artificial Neural Networks, pp. 1–6. Edinburgh, Scotland (1999)Google Scholar
  33. Hinton, G.E.: Training Products of Experts by Minimizing Contrastive Divergence. Neural Computation 14, 1771–1800 (2002)CrossRefPubMedGoogle Scholar
  34. Holmberg, M., Davide, F.A.M., Natale, C.D., D’Amico, A., Winquist, F., Lundstrom, I.: Drift counteraction in odour recognition applications: lifelong calibration method. Sensors and Actuators B 42, 185–194 (1997)CrossRefGoogle Scholar
  35. Holmin, S., Krantz-Rulcker, C., Lundstrom, I., Winquist, F.: Drift correction of electronic tongue responses. Institute of Physics Measurement Science Technology 12, 1348–1354 (2001)CrossRefGoogle Scholar
  36. Holt, J.L., Hwang, J.N.: Finite precision error analysis of neural network hardware implementations. IEEE Transactions on Computers 42(3), 281–290 (1993)CrossRefGoogle Scholar
  37. Hsu, D., Figueroa, M., Diorio, C.: Competitive learning with floating-gate circuits. IEEE Transactions on Neural Networks 13(3), 732–744 (2002)CrossRefPubMedGoogle Scholar
  38. Ienne, P., Cornu, T., Kuhn, G.: Special-purpose digital hardware for neural networks: An architectural survey. Journal of VLSI Signal Processing Systems 13, 5–25 (1996)CrossRefGoogle Scholar
  39. ITRS: International technology roadmap for semiconductors update. Technical report (2008)Google Scholar
  40. Jabri, M., Flower, B.: Weight perturbation: An optimal architecture and learning technique for analog VLSI feedforward and recurrent multilayer networks. IEEE Transactions on Neural Networks 3(1), 154–157 (1992)CrossRefPubMedGoogle Scholar
  41. Jamasb, S.: An analytical technique for counteracting drift in ion-selective field effect transistor (ISFETs). IEEE Sensors Journal (2004)Google Scholar
  42. Jamasb, S., Collins, S.D., Smith, R.L.: Correction of instability in Ion-selective Field Effect Transistors for accurate continuous monitoring of pH. In: Proceedings of IEEE International Conference of EMBS, pp. 2337–2340. Chicago, IL, USA (1997)Google Scholar
  43. Jamasb, S., Collins, S.D., Smith, R.L.: A physical model for threshold voltage instability in Si 3 N 4-Gate H  + -Sensitive FET’s (pH-ISFET’s). IEEE Transactions on Electron Devices 45(6), 1239–1245 (1998)CrossRefGoogle Scholar
  44. Johannessen, E.A., Wang, L., Cui, L., Tang, T.B., Ahmadian, M., Astaras, A., Reid, S.W., Yam, S., Murray, A.F., Flynn, B.W., Beaumont, S.P., Cumming, D.R.S., Cooper, J.M.: Implementation of multichannel sensors for remote biomedical measurements in a microsystems format. IEEE Transactions on Biomedical Engineering 51(3), 525–535 (2004)CrossRefPubMedGoogle Scholar
  45. Keller, P.E., Kouzes, R.T., Kangas, L.J.: Three neural network based sensor systems for environmental monitoring. In: Proceedings of the IEEE Electro, pp. 378–382. Boston, MA, USA (1994)Google Scholar
  46. Kermani, B.G., Schiffman, S.S., Nagle, H.T.: Using neural networks and genetic algorithms to enhance performance in an electronic nose. IEEE Transactions on Biomedical Engineering 46(4), 429–439 (1999)CrossRefPubMedGoogle Scholar
  47. Ko, W.H., Fung, C.D.: VLSI and intelligent transducers. Sensors and Actuators 2, 239–250 (1982)CrossRefGoogle Scholar
  48. Lang, K.J., Waibel, A.H., Hinton, G.E.: A time-delay neural network architecture for isolated word recognition. Neural Networks 3(1), 23–43 (1990)CrossRefGoogle Scholar
  49. Lazzerini, B., Marcelloni, F.: Counteracting drift of olfactory sensors by appropriately selecting features. IEE Electronics Letters 36(6), 509–510 (2000)CrossRefGoogle Scholar
  50. Leong, P.H.W., Jabri, M.A.: A low power trainable analogue neural network classifier chip. In: Proceedings of the IEEE Custom Integrated Circuits Conference, pp. 451–454. San Diego, CA, USA (1993)Google Scholar
  51. Lichtsteiner, P., Posch, C., Delbruck, T.: A 128x128 120db 15μs latency asynchronous temporal contrast vision sensor. IEEE Journal of Solid-State Circuits 43(2), 566–576 (2008)CrossRefGoogle Scholar
  52. Lindquist, M., Wide, P.: Virtual water quality tests with an electronic tongue. In: Proceedings of the IEEE IMTC, vol. 2, pp. 1320–1324 (2001)Google Scholar
  53. Luo, R.C., Yih, C.C., Su, K.L.: Multisensor fusion and integration: Approachs, applications, and future research directions. IEEE Sensors Journal 2(2), 107–119 (2002)CrossRefGoogle Scholar
  54. Macq, D., Verleysen, M., Jespers, P., Legat, J.D.: Analog implementation of a kohonen map with on-chip learning. IEEE Transactions on Neural Networks 4(3), 456–461 (1993)CrossRefPubMedGoogle Scholar
  55. Marco, S., Ortega, A., Pardo, A., Samitier, J.: Gas identification with tin oxide sensor array and self-organizing maps: Adaptive correction of sensor drifts. IEEE Transactions on Instrumentation and Measurement 47(1), 316–321 (1998)CrossRefGoogle Scholar
  56. Martin, G., Chang, H.: System-on-chip design. In: Proceedings of International Conference on ASIC, pp. 12–17. Shanghai, China (2001)Google Scholar
  57. Mayes, D.J., Hamilton, A., Murray, A.F., Reekie, H.M.: A pulsed VLSI radial basis function chip. In: Proceedings of the IEEE International Symposium on Circuits and Systems, vol. 3, pp. 297–300. Atlanta, GA, USA (1996)Google Scholar
  58. Middelhoek, S., Hoogerwerf, A.C.: Smart Sensors: When and Where? Sensors and Actuators 8, 39–48 (1985)CrossRefGoogle Scholar
  59. Moerland, P., Fiesler, E.: Handbook of Neural Computation, chap. Chapter E1.2: Neural Network Adaptations to Hardware Implementations. Institute of Physics Publishing and Oxford University Publishing, New York, USA (1996)Google Scholar
  60. Murata, N., Muller, K., Ziehe, A., Amari, S.: Adaptive on-line learning in changing environments. In: Advance in Neural Information Processing Systems, vol. 9, pp. 599–605 (1996)Google Scholar
  61. Natale, C.D., Davide, F.A.M., D’Amico, A.: A self-organizing system for pattern classification: time varying statistics and sensor drift effects. Sensors and Actuators B 26-27, 237–241 (1995)CrossRefGoogle Scholar
  62. Nishizawa, K., Hirai, Y.: Hardware implementation of PCA neural network. In: Proceedings of ICONIP, pp. 85–88. Kitakyushu, Japan (1998)Google Scholar
  63. Park, G., Farrar, C.R., Rutherford, A.C., Robertson, A.N.: Piezoelectric active sensor self-diagnostics using electrical admittance measurements. Journal of Vibration and Acoustics 128(4), 469–476 (2006)CrossRefGoogle Scholar
  64. Park, S., Lee, C.S.G.: Fusion-based sensor fault detection. In: Proceedings of IEEE International Symposium on Intelligent Control, pp. 156–161. Chicago, IL, USA (1993)Google Scholar
  65. Parlos, A.G., Chong, K.T., Atiya, A.F.: Application of the recurrent multilayer perceptron in modelling complex process dynamics. IEEE Transactions on Neural Networks 5(2), 255–266 (1994)CrossRefPubMedGoogle Scholar
  66. Philipp, R.M., Orr, D., Gruev, V., van der Spiegel, J., Etienne-Cummings, R.: Linear current-mode active pixel sensor. IEEE Journal of Solid-State Circuits 42(11), 2482–2491 (2007)CrossRefGoogle Scholar
  67. Platonov, A.A., Szabatin, J., Jedrzejewski, K.: Optimal synthesis of smart measurement systems with adaptive correction of drifts and setting errors of the sensor’s working point. IEEE Transactions on Intrumentation and Measurement 47(3), 659–665 (1998)CrossRefGoogle Scholar
  68. Pottie, G.J., Kaiser, W.J.: Wireless integrated network sensors. Communications of the ACM 43(5), 51–58 (2000)CrossRefGoogle Scholar
  69. Rabaey, J.M., Ammer, M.J., da Silva Jr., J.L., Patel, D., Roundy, S.: PicoRadio supports ad hoc ultra-low power wireless networking. Computer 33(7), 42–48 (2000)Google Scholar
  70. Rodriguez-Mendez, M.L., Arrieta, A.A., Parra, V., Bernal, A., Vegas, A., Villanueva, S., Gutierrez-Osuna, R., de Saja, J.A.: Fusion of three sensory modalities for the multimodal characterization of red wines. IEEE Sensors Journal 4(3), 348–354 (2004)CrossRefGoogle Scholar
  71. Roppel, T., Wilson, D., Dunman, K., Becanovic, V., Padgett, M.L.: Design of a low-power, portable sensor system using embedded neural networks and hardware preprocessing. In: Proceedings of the IEEE International Joint Conference on Neural Networks, pp. 142–145 (1999)Google Scholar
  72. Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning Internal Representations by Error Propagation, Computational models of cognition and perception, vol. 1, chap. 8, pp. 319–362. MIT, Cambridge, MA, USA (1986)Google Scholar
  73. Sachenko, A., Kochan, V., Turchenko, V., Tsahouridis, K., Laopoulos, T.: Error compensation in an intelligent sensing instrumentation system. In: Proceedings of IEEE Instrumnetation and Measurement Technology Conference, pp. 869–874. Budapest, Hungary (2001)Google Scholar
  74. Sarkaria, S.: Catastrophic interference (2004).\_Learning.pdf
  75. Sarry, F., Lumbreras, M.: Gas discrimination in an air-conditioned system. IEEE Transactions on Instrumentation and Measurement 49(4), 809–812 (2000)CrossRefGoogle Scholar
  76. Sayago, I., d. C. Horrillo, M., Baluk, S., Aleixandre, M., Fernandez, M.J., Ares, L., Garcia, M., Santos, J.P., Gutierrez, J.: Detection of toxic gases by a tin oxide multisensor. IEEE Sensors Journal 2(5), 387–393 (2002)Google Scholar
  77. Seiter, J.C., DeGrandpre, M.D.: Redundant chemical sensors for calibration-impossible applications. Talanta pp. 99–106 (2001)Google Scholar
  78. Shi, B.E.: A low power orientation selective vision sensor. IEEE Transactions on Circuits and Systems-II: Analog and Digital Signal Processing 47(5), 435–440 (2002)CrossRefGoogle Scholar
  79. Shin, H.W., Llober, E., Gardner, J.W., Hines, E.L., Dow, C.S.: Classification of the strain and growth phase of Cyanobacteria in potable water using an electronic nose system. IEE Proceedings on Science, Measurement and Technology 147(4), 158–164 (2000)CrossRefGoogle Scholar
  80. Smith, R.L., Scott, D.C.: An integrated sensor for electrochemical measurements. IEEE Transactions on Biomedical Engineering 33(2), 83–90 (1986)CrossRefPubMedGoogle Scholar
  81. Smolensky, P.: Parallel Distributed Processing: Explorations in Microstructure of Cognition, vol. 1, chap. Information processing in dynamical systems: Foundations of harmony theory, pp. 195–281. MIT (1986)Google Scholar
  82. Steinhage, A., Winkel, C.: A robust self-calibrating data fusion architecture. In: Proceedings of IEEE National Geoscience and Remote Sensing Symposium, pp. 963–965. Honolulu, HI, USA (2000)Google Scholar
  83. Stetter, J.R., Penrose, W.R.: The electrochemical nose. (2001)
  84. Sundic, T., Marco, S., Samitier, J., Wide, P.: Electronic tongue and electronic nose data fusion in classification with neural networks and fuzzy logic based models. In: Proceedings of the IEEE IMTC, vol. 3, pp. 1474–1479 (2000)Google Scholar
  85. Tang, T.B., Chen, H., Murray, A.F.: Adaptive, integrated sensor processing to compensate for drift and uncertainty: a stochastic ‘neural’ approach. IEE Proceedings on Nanobiotechnology 151(1), 28–34 (2004)CrossRefGoogle Scholar
  86. Tang, T.B., Johannessen, E., Wang, L., Astaras, A., Ahmadian, M., Murray, A.F., Cooper, J.M., Beaumont, S.P., Flynn, B.W., Cumming, D.R.S.: Toward a miniature wireless integrated multisensor microsystem for industrial and biomedical applications. IEEE Sensors Journal: Special Issue on Integrated Multisensor Systems and Signal Processing 2(6), 628–635 (2002)Google Scholar
  87. Tang, T.B., Murray, A.F.: Adaptive sensor modelling and classification using a continuous restricted boltzmann machine (crbm). Neurocomputing 70(7-9), 1198–1206 (2007)CrossRefGoogle Scholar
  88. Tsai, C.S., Tong, C.C., Oh, L.E.: Sensor data correction with neural network incorporating fuzzy logic. In: Proceedings of IEEE International Fuzzy Systems Conference, pp. 66–71. Seoul, Korea (1999)Google Scholar
  89. Warneke, B.A., Scott, M.D., Leibowitz, B.S., Zhou, L., Bellew, C.L., Chediak, J.A., Kahn, J.M., Boser, B.E., Pister, K.S.J.: An autonomous 16mm3 solar-powered node for distributed wireless sensor networks. In: Proceedings of IEEE Sensors, pp. 1510–1515. Orlando, FL, USA (2002)Google Scholar
  90. Wegmann, G., Tsividis, Y.: Very accurate dynamic current mirrors. Electronics Letters 25(10), 644–646 (1989)CrossRefGoogle Scholar
  91. Wide, P., Winquist, F., Bergsten, P., Petriu, E.M.: The human-based multisensor fusion method for artificial nose and tongue sensor data. IEEE Transactions on Instrumentation and Measurement 47(5), 1072–1077 (1998)CrossRefGoogle Scholar
  92. Widrow, B., Hoff, M.E.: Adaptive switching circuits. IRE WESCON Convention Record pp. 96–104 (1960)Google Scholar
  93. Wise, K.D.: Integrated microsystems: Merging MEMS, micropower electronics, and wireless commnunications. In: Proceedings of IEEE ASIC/SoC Conference, pp. xxiii–xxix (1999)Google Scholar
  94. Woodburn, R., Murray, A.F.: Implementing artificial neural networks in analogue VLSI. In: Proceedings of the International Conference on Neural Information Processing, pp. 658–661. Dunedin, New Zealand (1997)Google Scholar
  95. Yen, G.G., Feng, W.: Winner take all experts network for sensor validation. In: Proceedings of the IEEE International Conference on Control Applications, pp. 92–97. Anchorage, Alaska, USA (2000)Google Scholar
  96. Zimmermann, H.G., Tietz, C., Grothmann, R.: Yield curve forecasting by error correction neural networks and partial learning. In: ESANN Proceedings, pp. 407–412. Bruges, Belgium (2002)Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2011

Authors and Affiliations

  1. 1.School of EngineeringThe University of EdinburghEdinburghUK

Personalised recommendations