Power and accuracy trade-offs in sound-based context recognition systems

This paper presents an empirical design methodology to optimize a context recognition system with respect to a trade-off between power consumption and recognition performance rather than straightforward maximization of the recognition rate. As illustration, we present a case study in which the interaction with different household appliances is detected by means of a wrist worn microphone and accelerometers. This example, which is embedded in the larger context of an assisted living scenario, demonstrates that the proposed method leads to improvements in battery lifetime by a factor of 2-4 with only little degradation in recognition performance. For a specific sensor node, we show that a recognition rate of 94% can be achieved with a power consumption of just 3.3 mW, resulting in a battery lifetime of 168 h.

[1]  Luca Benini,et al.  Dynamic voltage scaling and power management for portable systems , 2001, Proceedings of the 38th Design Automation Conference (IEEE Cat. No.01CH37232).

[2]  Daniel P. Siewiorek,et al.  A case study of a system-level approach to power-aware computing , 2003, TECS.

[3]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[4]  Mahmut T. Kandemir,et al.  The design and use of simplePower: a cycle-accurate energy estimation tool , 2000, Proceedings 37th Design Automation Conference.

[5]  A.P. Chandrakasan,et al.  A micropower programmable DSP using approximate signal processing based on distributed arithmetic , 2004, IEEE Journal of Solid-State Circuits.

[6]  Daniel P. Siewiorek,et al.  A system-level approach to power/performance optimization in wearable computers , 2000, Proceedings IEEE Computer Society Workshop on VLSI 2000. System Design for a System-on-Chip Era.

[7]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques with Java implementations , 2002, SGMD.

[8]  Ishwar K. Sethi,et al.  Classification of general audio data for content-based retrieval , 2001, Pattern Recognit. Lett..

[9]  Adam Krzyżak,et al.  Methods of combining multiple classifiers and their applications to handwriting recognition , 1992, IEEE Trans. Syst. Man Cybern..

[10]  Ning Liu,et al.  Bathroom Activity Monitoring Based on Sound , 2005, Pervasive.

[11]  Nathan Ickes,et al.  Instruction level and operating system profiling for energy exposed software , 2003, IEEE Trans. Very Large Scale Integr. Syst..

[12]  Mathias Stäger,et al.  Empirical Study of Design Choices in Multi-Sensor Context Recognition Systems , 2005 .

[13]  Leonard J. Bass,et al.  Adtranz: a mobile computing system for maintenance and collaboration , 1998, Digest of Papers. Second International Symposium on Wearable Computers (Cat. No.98EX215).

[14]  Gregory D. Abowd,et al.  Context-Awareness in Wearable and Ubiquitous Computing , 1997, SEMWEB.

[15]  Kristof Van Laerhoven,et al.  Spine versus porcupine: a study in distributed wearable activity recognition , 2004, Eighth International Symposium on Wearable Computers.

[16]  Thomas F. La Porta,et al.  Using Information Theory to Design ContextSensing Wearable Systems , 2006 .

[17]  Jürgen Teich,et al.  System-Level Synthesis Using Evolutionary Algorithms , 1998, Des. Autom. Embed. Syst..

[18]  Albrecht Schmidt,et al.  Building intelligent environments with Smart-Its , 2004, IEEE Computer Graphics and Applications.

[19]  Gerhard Tröster,et al.  Towards Wearable Autonomous Microsystems , 2004, Pervasive.

[20]  Paul Lukowicz,et al.  WearNET: A Distributed Multi-sensor System for Context Aware Wearables , 2002, UbiComp.

[21]  Paul Lukowicz,et al.  Sampling frequency, signal resolution and the accuracy of wearable context recognition systems , 2004, Eighth International Symposium on Wearable Computers.

[22]  Bernt Schiele,et al.  A model for human interruptability: experimental evaluation and automatic estimation from wearable sensors , 2004, Eighth International Symposium on Wearable Computers.

[23]  Niraj K. Jha,et al.  Low-power system scheduling, synthesis and displays , 2005 .

[24]  L. Thiele,et al.  The case for reconfigurable hardware in wearable computing , 2003, Personal and Ubiquitous Computing.

[25]  Paul Lukowicz,et al.  Power and size optimized multi-sensor context recognition platform , 2005, Ninth IEEE International Symposium on Wearable Computers (ISWC'05).

[26]  Sampling Frequency , 2009, Encyclopedia of Biometrics.

[27]  Erik Brockmeyer,et al.  Data and memory optimization techniques for embedded systems , 2001, TODE.

[28]  David E. Culler,et al.  Telos: enabling ultra-low power wireless research , 2005, IPSN 2005. Fourth International Symposium on Information Processing in Sensor Networks, 2005..

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

[30]  Paul Lukowicz,et al.  Using multiple sensors for mobile sign language recognition , 2003, Seventh IEEE International Symposium on Wearable Computers, 2003. Proceedings..

[31]  Douglas L. Jones,et al.  Real-valued fast Fourier transform algorithms , 1987, IEEE Trans. Acoust. Speech Signal Process..

[32]  Aiko M. Hormann,et al.  Programs for Machine Learning. Part I , 1962, Inf. Control..

[33]  Mark C. Johnson,et al.  Software design for low power , 1997 .

[34]  Lloyd A. Smith,et al.  Practical feature subset selection for machine learning , 1998 .

[35]  Paul Lukowicz,et al.  Gesture spotting using wrist worn microphone and 3-axis accelerometer , 2005, sOc-EUSAI '05.

[36]  Paul Lukowicz,et al.  Recognizing Workshop Activity Using Body Worn Microphones and Accelerometers , 2004, Pervasive.

[37]  Ling Bao,et al.  Activity Recognition from User-Annotated Acceleration Data , 2004, Pervasive.

[38]  Andrew Wolfe,et al.  Compilation techniques for low energy: an overview , 1994, Proceedings of 1994 IEEE Symposium on Low Power Electronics.

[39]  Luca Benini,et al.  A survey of design techniques for system-level dynamic power management , 2000, IEEE Trans. Very Large Scale Integr. Syst..

[40]  M. Hannikainen,et al.  Wireless sensor prototype platform , 2003, IECON'03. 29th Annual Conference of the IEEE Industrial Electronics Society (IEEE Cat. No.03CH37468).

[41]  Paul Lukowicz,et al.  PadNET: wearable physical activity detection network , 2003, Seventh IEEE International Symposium on Wearable Computers, 2003. Proceedings..

[42]  Paul Lukowicz,et al.  Implementation and evaluation of a low-power sound-based user activity recognition system , 2004, Eighth International Symposium on Wearable Computers.

[43]  Paul Lukowicz,et al.  A systematic approach to the design of distributed wearable systems , 2004, IEEE Transactions on Computers.

[44]  Sharad Malik,et al.  Power analysis of embedded software: a first step towards software power minimization , 1994, IEEE Trans. Very Large Scale Integr. Syst..

[45]  Eric Senn,et al.  Power Estimation of a C Algorithm Based on the Functional-Level Power Analysis of a Digital Signal Processor , 2002, ISHPC.

[46]  Paul Lukowicz,et al.  Design Methodology for Context-Aware Wearable Sensor Systems , 2005, Pervasive.

[47]  Margaret Martonosi,et al.  Wattch: a framework for architectural-level power analysis and optimizations , 2000, Proceedings of 27th International Symposium on Computer Architecture (IEEE Cat. No.RS00201).

[48]  Kristof Van Laerhoven,et al.  Context awareness in Systems with Limited Resources , 2002 .

[49]  Sargur N. Srihari,et al.  Decision Combination in Multiple Classifier Systems , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[50]  Thomas F. La Porta,et al.  Sensor Network Operations , 2006 .

[51]  Naveen Verma,et al.  Design considerations for ultra-low energy wireless microsensor nodes , 2005, IEEE Transactions on Computers.

[52]  Jiri Matas,et al.  On Combining Classifiers , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[53]  Paul Lukowicz,et al.  SoundButton: design of a low power wearable audio classification system , 2003, Seventh IEEE International Symposium on Wearable Computers, 2003. Proceedings..

[54]  Vesa T. Peltonen,et al.  Computational auditory scene recognition , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[55]  David V. Anderson,et al.  Low-power audio classification for ubiquitous sensor networks , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[56]  Roberto Battiti,et al.  Using mutual information for selecting features in supervised neural net learning , 1994, IEEE Trans. Neural Networks.

[57]  Andreas Krause,et al.  Trading off prediction accuracy and power consumption for context-aware wearable computing , 2005, Ninth IEEE International Symposium on Wearable Computers (ISWC'05).

[58]  Huan Liu,et al.  Feature Selection for Classification , 1997, Intell. Data Anal..