Multisensor Fusion for Low-Power Wireless Microsystems

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.

[1]  D. Figeys,et al.  Lab-on-a-chip: a revolution in biological and medical sciences , 2000, Analytical chemistry.

[2]  Fabrizio Davide,et al.  A self-organizing system for pattern classification: time varying statistics and sensor drift effects , 1995 .

[3]  Kensall D. Wise.  Integrated Microsystems: Merging MEMS, micropower electronics, and wireless communications , 1999 .

[4]  P. E. Keller,et al.  Three neural network based, sensor systems for environmental monitoring , 1994, Proceedings of ELECTRO '94.

[5]  James L. McClelland.  Explorations In Parallel Distributed Processing , 1988 .

[6]  Yuzo Hirai,et al.  Hardware Implementation of PCA Neural Network , 1998, ICONIP.

[7]  P. Bergsten,et al.  The human-based multi-sensor fusion method for artificial nose and tongue sensor data , 1998, IMTC/98 Conference Proceedings. IEEE Instrumentation and Measurement Technology Conference. Where Instrumentation is Going (Cat. No.98CH36222).

[8]  Andreas Ziehe,et al.  Adaptive On-line Learning in Changing Environments , 1996, NIPS.

[9]  Tetsuya Higuchi,et al.  IXM2: a parallel associative processor , 1991, ISCA '91.

[10]  N. Jaffrezic‐Renault,et al.  A simple REFET for pH detection in differential mode , 1999 .

[11]  Bernard Widrow,et al.  Adaptive switching circuits , 1988 .

[12]  Evor L. Hines,et al.  Prediction of health of dairy cattle from breath samples using neural network with parametric model of dynamic response of array of semiconducting gas sensors , 1999 .

[13]  Alan F. Murray,et al.  Implementing Artificial Neural Networks in Analogue VLSI , 1997, ICONIP.

[14]  M. Lindquist,et al.  Virtual water quality tests with an electronic tongue , 2001, IMTC 2001. Proceedings of the 18th IEEE Instrumentation and Measurement Technology Conference. Rediscovering Measurement in the Age of Informatics (Cat. No.01CH 37188).

[15]  Fredrik Winquist,et al.  Drift counteraction in odour recognition applications: lifelong calibration method , 1997 .

[16]  M. Sjöström,et al.  Drift correction for gas sensors using multivariate methods , 2000 .

[17]  Eduard Llobet,et al.  Classification of the strain and growth phase of cyanobacteria in potable water using an electronic nose system , 2000 .

[18]  H. T. Nagle,et al.  Using neural networks and genetic algorithms to enhance performance in an electronic nose , 1999, IEEE Transactions on Biomedical Engineering.

[19]  M. A. Jabri,et al.  A low power trainable analogue neural network classifier chip , 1993, Proceedings of IEEE Custom Integrated Circuits Conference - CICC '93.

[20]  Michel Verleysen,et al.  Analog implementation of a Kohonen map with on-chip learning , 1993, IEEE Trans. Neural Networks.

[21]  A F Murray,et al.  Adaptive, integrated sensor processing to compensate for drift and uncertainty: a stochastic 'neural' approach. , 2004, IEE proceedings. Nanobiotechnology.

[22]  Josep Samitier,et al.  Electronic tongue and electronic nose data fusion in classification with neural networks and fuzzy logic based models , 2000, Proceedings of the 17th IEEE Instrumentation and Measurement Technology Conference [Cat. No. 00CH37066].

[23]  D. W. Clarke.  Sensor, actuator and plant validation , 1999 .

[24]  A. Steinhage,et al.  A robust self-calibrating data fusion architecture , 2000, IGARSS 2000. IEEE 2000 International Geoscience and Remote Sensing Symposium. Taking the Pulse of the Planet: The Role of Remote Sensing in Managing the Environment. Proceedings (Cat. No.00CH37120).

[25]  Beatrice Gralton,et al.  Washington DC - USA , 2008 .

[26]  Sergio Martinoia,et al.  Modeling H/sup +/-sensitive FETs with SPICE , 1992 .

[27]  B. Webb,et al.  Fabrication and characterization of a wind sensor for integration with a neuron circuit , 2007 .

[28]  Alan F. Murray,et al.  Adaptive Sensor Modelling and Classification using a Continuous Restricted Boltzmann Machine (CRBM) , 2007, ESANN.

[29]  R. Gutierrez-Osuna,et al.  Fusion of three sensory modalities for the multimodal characterization of red wines , 2004, IEEE Sensors Journal.

[30]  Marwan A. Jabri,et al.  A hybrid analog and digital VLSI neural network for intracardiac morphology classification , 1995 .

[31]  Robert B. Allen,et al.  Relaxation Networks for Large Supervised Learning Problems , 1990, NIPS.

[32]  Miguel Figueroa,et al.  Competitive learning with floating-gate circuits , 2002, IEEE Trans. Neural Networks.

[33]  Mietek A. Brdys,et al.  Dynamic neural controllers for induction motor , 1999, IEEE Trans. Neural Networks.

[34]  Grant Martin,et al.  System-on-Chip design , 2001, ASICON 2001. 2001 4th International Conference on ASIC Proceedings (Cat. No.01TH8549).

[35]  Chia-Chang Tong,et al.  Sensor data correction with neural network incorporating fuzzy logic , 1999, FUZZ-IEEE'99. 1999 IEEE International Fuzzy Systems. Conference Proceedings (Cat. No.99CH36315).

[36]  Geoffrey E. Hinton.  Training Products of Experts by Minimizing Contrastive Divergence , 2002, Neural Computation.

[37]  Francis L. Merat,et al.  Neural network based sensor array signal processing , 1996, 1996 IEEE/SICE/RSJ International Conference on Multisensor Fusion and Integration for Intelligent Systems (Cat. No.96TH8242).

[38]  Paul Smolensky,et al.  Information processing in dynamical systems: foundations of harmony theory , 1986 .

[39]  Jan Van der Spiegel,et al.  Linear Current-Mode Active Pixel Sensor , 2007, IEEE Journal of Solid-State Circuits.

[40]  A. Murray,et al.  Toward a miniature wireless integrated multisensor microsystem for industrial and biomedical applications , 2002 .

[41]  Alan F. Murray,et al.  A pulsed VLSI radial basis function chip , 1996, 1996 IEEE International Symposium on Circuits and Systems. Circuits and Systems Connecting the World. ISCAS 96.

[42]  Leon O. Chua,et al.  The CNN paradigm , 1993 .

[43]  Howard C. Card,et al.  Analog VLSI Circuits for Competitive Learning Networks , 1998 .

[44]  Volodymyr Turchenko,et al.  Error compensation in an intelligent sensing instrumentation system , 2001, IMTC 2001. Proceedings of the 18th IEEE Instrumentation and Measurement Technology Conference. Rediscovering Measurement in the Age of Informatics (Cat. No.01CH 37188).

[45]  Robert B. Allen,et al.  Performance of a Stochastic Learning Microchip , 1990, NIPS.

[46]  Lei Wang,et al.  Implementation of multichannel sensors for remote biomedical measurements in a microsystems format , 2004, IEEE Transactions on Biomedical Engineering.

[47]  Tobi Delbrück,et al.  A 128$\times$ 128 120 dB 15 $\mu$s Latency Asynchronous Temporal Contrast Vision Sensor , 2008, IEEE Journal of Solid-State Circuits.

[48]  S. Middelhoek,et al.  Smart sensors: when and where? , 1985 .

[49]  Jan M. Rabaey,et al.  PicoRadio Supports Ad Hoc Ultra-Low Power Wireless Networking , 2000, Computer.

[50]  José Pedro Santos,et al.  Detection of toxic gases by a tin oxide multisensor , 2002 .

[51]  Bertram E. Shi.  A low-power orientation-selective vision sensor , 2000 .

[52]  T.-H. Guo,et al.  Sensor failure detection and recovery by neural networks , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[53]  Alan F. Murray,et al.  Continuous-valued probabilistic behavior in a VLSI generative model , 2006, IEEE Transactions on Neural Networks.

[54]  S. Jamasb.  An analytical technique for counteracting drift in ion-selective field effect transistors (ISFETs) , 2004, IEEE Sensors Journal.

[55]  Alan F. Murray,et al.  Minimising Contrastive Divergence in Noisy, Mixed-mode VLSI Neurons , 2003, NIPS.

[56]  S. D. Collins,et al.  A physical model for threshold voltage instability in Si/sub 3/N/sub 4/-gate H/sup +/-sensitive FET's (pH ISFET's) , 1998 .

[57]  Alan F. Murray,et al.  Minimizing the Effect of Process Mismatch in a Neuromorphic System Using Spike-Timing-Dependent Adaptation , 2008, IEEE Transactions on Neural Networks.

[58]  Amir F. Atiya,et al.  Application of the recurrent multilayer perceptron in modeling complex process dynamics , 1994, IEEE Trans. Neural Networks.

[59]  Tughrul Arslan,et al.  A direct-sequence spread-spectrum communication system for integrated sensor microsystems , 2005, IEEE Transactions on Information Technology in Biomedicine.

[60]  David Heckerman,et al.  A Tutorial on Learning with Bayesian Networks , 1999, Innovations in Bayesian Networks.

[61]  Stuart Haber,et al.  A VLSI-efficient technique for generating multiple uncorrelated noise sources and its application to stochastic neural networks , 1991 .

[62]  Scott D. Collins,et al.  Correction of instability in ion-selective field effect transistors (ISFETs) for accurate continuous monitoring of pH , 1997, Proceedings of the 19th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 'Magnificent Milestones and Emerging Opportunities in Medical Engineering' (Cat. No.97CH36136).

[63]  Ren C. Luo,et al.  Multisensor fusion and integration: approaches, applications, and future research directions , 2002 .

[64]  Beatrice Lazzerini,et al.  Counteracting drift of olfactory sensors by appropriately selecting features , 2000 .

[65]  R. L. Smith,et al.  An Integrated Sensor for Electrochemical Measurements , 1986, IEEE Transactions on Biomedical Engineering.

[66]  Eric A. Vittoz,et al.  Very accurate dynamic current mirrors , 1989 .

[67]  A. Ortega,et al.  Gas identification with tin oxide sensor array and self organizing maps: adaptive correction of sensor drifts , 1997, IEEE Instrumentation and Measurement Technology Conference Sensing, Processing, Networking. IMTC Proceedings.

[68]  Marwan A. Jabri,et al.  Weight perturbation: an optimal architecture and learning technique for analog VLSI feedforward and recurrent multilayer networks , 1992, IEEE Trans. Neural Networks.

[69]  D. Wilson,et al.  Design of a low-power, portable sensor system using embedded neural networks and hardware preprocessing , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[70]  Ingemar Lundström,et al.  Drift correction of electronic tongue responses , 2001 .

[71]  Jenq-Neng Hwang,et al.  Finite Precision Error Analysis of Neural Network Hardware Implementations , 1993, IEEE Trans. Computers.

[72]  Alan F. Murray,et al.  Continuous restricted Boltzmann machine with an implementable training algorithm , 2003 .

[73]  C. Jutten,et al.  Improving semiconductor-based chemical sensor arrays using advanced algorithms for blind source separation , 2004, ISA/IEEE Sensors for Industry Conference, 2004. Proceedings the.

[74]  G G Yen,et al.  Winner take all experts network for sensor validation. , 2001, ISA transactions.

[75]  Charles R. Farrar,et al.  Piezoelectric Active Sensor Self-Diagnostics Using Electrical Admittance Measurements , 2006 .

[76]  Tsung-Lin Chen,et al.  A novel fault-tolerant sensor system for sensor drift compensation , 2008 .

[77]  Martine Lumbreras,et al.  Gas discrimination in an air-conditioned system , 2000, IEEE Trans. Instrum. Meas..

[78]  Hans-Georg Zimmermann,et al.  Yield curve forecasting by error correction neural networks and partial learning , 2002, ESANN.

[79]  C.S.G. Lee,et al.  Fusion-based sensor fault detection , 1993, Proceedings of 8th IEEE International Symposium on Intelligent Control.

[80]  Geoffrey E. Hinton,et al.  A time-delay neural network architecture for isolated word recognition , 1990, Neural Networks.

[81]  N. Bris,et al.  Automated pH-ISFET measurements under hydrostatic pressure for marine monitoring application , 1997 .

[82]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[83]  Joseph M. Kahn,et al.  An autonomous 16 mm/sup 3/ solar-powered node for distributed wireless sensor networks , 2002, Proceedings of IEEE Sensors.

[84]  Wen H. Ko,et al.  VLSI and intelligent transducers , 1981 .

[85]  P. Fleury,et al.  On-chip contrastive divergence learning in analogue VLSI , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[86]  Gregory J. Pottie,et al.  Wireless integrated network sensors , 2000, Commun. ACM.

[87]  Wouter Olthuis,et al.  A method of reducing oxygen induced drift in iridium oxide pH sensors , 1998 .

[88]  Geoffrey E. Hinton.  Products of experts , 1999 .

[89]  Paolo Ienne,et al.  Special-purpose digital hardware for neural networks: An architectural survey , 1996, J. VLSI Signal Process..

[90]  M. DeGrandpre,et al.  Redundant chemical sensors for calibration-impossible applications. , 2001, Talanta.

[91]  Anatoliy A. Platonov,et al.  Optimal synthesis of smart measurement systems with adaptive correction of drifts and setting errors of the sensor's working point , 1998, IEEE Trans. Instrum. Meas..

[92]  Sergio Bermejo,et al.  An on-line water monitoring system using a smart ISFET array , 2002, IEEE 2002 28th Annual Conference of the Industrial Electronics Society. IECON 02.