Abstract
The work described in this chapter combines the different techniques discussed in previous chapters into case studies for the biomedical specimen identification. Section 9.1 outlines the THz experiment setup. In Sect. 9.2, an improvement in classification accuracy is demonstrated by applying wavelet-based techniques in the preprocessing of T-ray pulsed signals. In Sect. 9.3, three system identification schemes for discriminating between lactose, mandelic acid, and DL-mandelic acid THz transients is proposed, with application of a discrimination metric for the evaluation of classification performance. Section 9.4 represents the implication of AR and ARMA models on the WTs of measured T-ray pulse data for automatic classification of THz measurements, highlighting their potential in biomedical, pharmaceutical, and security applications. Section 9.5 illustrates that SVM learning algorithms are sufficiently powerful to detect patterns within noisy biomedical measurements. Case studies show effective discrimination of RNA samples and various powdered substances.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abbott-D. (2000). Directions in terahertz technology, Proceedings 22nd IEEE GaAs IC Symposium, Seattle, WA, pp. 263–266.
Bengio-Y., and Grandvalet-Y. (2004). No unbiased estimator of the variance of k-fold cross-validation, Journal of Machine Learning Research, 5, pp. 1089–1105.
Cai-J., and Li-Y. (2005). Lecture Notes in Computer Science, Springer, Berlin, Heidelberg.
Canu-S., Grandvalet-Y., Guigue-V., and Rakotomamonjy-A. (2005). SVM and kernel methods matlab toolbox, Perception Systèmes et Information, INSA de Rouen, Rouen, France.
Chang-C.-C., and Lin-C.-J. (2001). Libsvm: a library for support vector machines, Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm.
Daubechies-I. (1988). Orthonormal bases of compactly supported wavelets, Communications on Pure & Applied Mathematics, 41(7), pp. 909–996.
Daubechies-I. (1992). Ten lectures on wavelets, Society for Industrial and Applied Mathematics, Philadelphia, PA, USA.
Divine-D. V., and Godtliebsen-F. (2007). Bayesian modeling and significant features exploration in wavelet power spectra, Nonlinear Processes in Geophysics, 14, pp. 79–88.
Donoho-D. L. (1995). De-noising by soft thresholding, IEEE Transactions on Information Theory, 41(3), pp. 613–627.
Duvillaret-L., Garet-F., and Coutaz-L. (1996). A reliable method for extraction of material parameters in terahertz time-domain spectroscopy, IEEE Journal of Selected Topics in Quantum Electronics, 2(3), pp. 739–746.
Federici-J. F., Schulkin-B., Huang-F., Gary-D., Barat-R., Oliveira-F., and Zimdars-D. (2005). THz imaging and sensing for security applications-explosives, weapons and drugs, Semicond. Sci. Technol., 20, pp. S266–S280.
Ferguson-B., and Abbott-D. (2001a). De-noising techniques for terahertz responses of biological samples, Microelectronics Journal (Elsevier), 32(12), pp. 943–953.
Ferguson-B., Liu-H., Hay-S., Finlay-D., Zhang-X.-C., and Abbott-D. (2004). In vitro osteosacoma biosensing using THz time domain spectroscopy, in J. Neev., and M. Reed. (eds.), Proc. of SPIE BioMEMS and Nanotechnology, Vol. 5275, Bellingham, Australia, pp. 304–316.
Ferguson-B., Wang-S., Gray-D., Abbott-D., and Zhang-X. C. (2002a). T-ray computed tomography, Optics Letters, 27(15), pp. 1312–1314.
Ferguson-B., Wang-S., Zhong-H., Abbott-D., and Zhang-X.-C. (2003). Powder retection with T-ray imaging, Proceeding of SPIE Terahertz for Military and Security Applications, Vol. 5070, pp. 7–16.
Fischer-B., Hoffmann-M., H. Helm-R. W., Rutz-F., Kleine-Ostmann-T., Koch-M., and Jepsen-P. U. (2005b). Terahertz time-domain spectroscopy and imaging of artificial RNA, Optics Express, 13(14), pp. 5205–5215.
Fukunaga-K., and Hummels-D. M. (1989). Leave-one-out procedures for nonparametric error estimates, IEEE Transactions on Pattern Analysis and Machine Intelligence, II(4), pp. 421–423.
Fukunaga-K., and Kessell-D. L. (1973). Nonparametric Bayes error estimation using unclassified samples, IEEE Transactions on Information Theory, IT-19(4), pp. 434–440.
Guyon-I., Weston-J., and Barnhill-S. (2002). Gene selection for cancer classification using support vector machines, Machine Learning, 46, pp. 389–422.
Hadjiloucas-S., Galvõ-R. K. H., Becerra-V. M., Bowen-J. W., Martini-R., Brucherseifer-M., Pellemans-H. P. M., Haring BolÃvar-P., Kurz-H., and Chamberlain-J. M. (2004). Comparison of state space and ARX models of a waveguide’s THz transient response after optimal wavelet filtering, IEEE Transactions on Microwave Theory and Techniques MTT, 52(10), pp. 2409–2419.
Hastie-T., Tibshirani-R., and Friedman-J. H. (2003). The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Springer, New York.
Kawase-K., Ogawa-Y., Watanabe-Y., and Inoue-H. (2003). Non-destructive terahertz imaging of illicit drugs using spectral fingerprints, Optics Express, 11(20), pp. 2549–2554.
Kim-K. I., Jung-K., Park-S. H., and Kim-H. J. (2002). Support vector machines for texture classification, IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(11), pp. 1542–1550.
Ljung-L. (1999). System Identification: Theory for the User, 2nd edn, Prentice Hall PTR, New Jersey, USA.
Mallat-S. (1989). A theory for multiresolution signal decomposition: The wavelet representation, IEEE Transactions on Pattern Analysis and Machine Intelligence, 14(7), pp. 674–693.
Mallat-S. G. (1999). A Wavelet Tour of Signal Processing, San Diego : Academic Press, CA.
Mittleman-D., Neelamani-R., Rudd-R. B. J., and Koch-M. (1999). Recent advances in terahertz imaging, Applied Physics B - Lasers and Optics, 68(6), pp. 1085–1094.
Percival-D., and Walden-A. (2000). Wavelet Methods for Time Series Analysis, Cambridge University Press, Cambridge, England.
Qian-S. (2002). Time-Frequency and Wavelet Transforms, 1st edn, Prentice Hall, Inc., New Jersey, USA
Schalkoff-R. (1992). Pattern Classification: Statistical, Structural and Neural Approaches, John Wiley and Sons, Inc., New York, USA.
Sherlock-B. G., and Monro-D. M. (1998). On the space of orthonormal wavelets, IEEE Transactions on Signal Processing, 46(6), pp. 1716–1720.
Siegel-P. H. (2004). Terahertz technology in biology and medicine, IEEE Transactions on Microwave Theory and Techniques, 52(10), pp. 2438–2447.
Strachan-C. J., Taday-P. F., Newnham-D. A., Gordon-K. C., Zeitler-J. A., Pepper-M., and Rades-T. (2005). Using terahertz pulsed spectroscopy to quantify pharmaceutical polymorphism and crystallinity, Journal of Pharmaceutical Sciences, 94(4), pp. 837–846.
Strang-G., and Nguyen-T. (1996). Wavelets and Filter Banks, 1st edn, Wellesley-Cambridge Press, Wellesley, USA.
Therrien-C., and Oppenheim-A. (1992). Discrete Random Signals and Statistical Signal Processing, Prentice Hall, New Jersey, USA.
Tuqun-J., and Vaidyanathan-P. P. (2000). A state-space approach to the design of globally optimal FIR energy compaction filters, IEEE Transaction Signal Processing, 48(10), pp. 2822–2838.
Vaidyanathan-P. P. (1993). Multirate Systems and Filter Banks, Prentice Hall, New Jersey, USA.
Vetterli-M., and Kovacevic-J. (1995). Wavelets and Subband Coding, Prentice-Hall PTR, New Jersey.
Wang-S., Ferguson-B., and Zhang-X.-C. (2004a). Pulsed terahertz tomography, Journal of Physics D Applied Physics, 37(4), pp. R1–R36.
Watanabe-Y., Kawase-K., Ikari-T., Ito-H., Ishikawa-Y., and Minamide-H. (2003). Spatial pattern separation of chemicals and frequency-independent components using terahertz spectroscopic imaging, Applied Optics, 42(28), pp. 5744–5748.
Weston-J., Gretton-A., and Elisseeff-A. (2003). SVM practical session (how to get good results without cheating), Machine Learning Summer School, Tuebingen, Germany.
Withayachumnankul-W., Ferguson-B., Rainsford-T., Mickan-S., and Abbott-D. (2005). Simple material parameter estimation via terahertz time-domain spectroscopy, IEE Electron Letters, 41(14), pp. 801–802.
Woodward-R. M., Cole-B., Walace-V. P., Arnone-D. D., Pye-R., Linfield-E. H., Pepper-M., and Davies-A. G. (2002). Terahertz pulse imaging in reflection geometry of human skin cancer and skin tissue, Physics in Medicine and Biology, 47(21), pp. 3853–3863.
Yin-X.-X., Ng-W.-H. B., Ferguson-B., and Abbott-D. (2007a). Application of auto-regressive models and wavelet sub-bands for classifying terahertz pulse measurements, Journal of Biological Systems, 15, pp. 551–571.
Yin-X.-X., Ng-W.-H. B., Fischer-B. M., Ferguson-B., Mickan-P. S., and Abbott-D. (2006). Feature extraction from terahertz pulses for classification of RNA data via support vector machines, in J.-C. Chiao., A. S. Dzurak., C. Jagadish., and D. V. Thiel. (eds.), Proceeding of SPIE Micro and Nanotechnology: Materials, Processes, Packaging, and Systems III, Vol. 6415, Adelaide, Australia, Art. No. 641516.
Zeitler-J. A., Shen-Y., Baker-C., Taday-P. F., Pepper-M., and Rades-T. (2007a). Analysis of coating structures and interfaces in solid oral dosage forms by three dimensional terahertz pulsed imaging, Journal of Pharmaceutical Sciences, 96(2), pp. 330–340.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer Science+Business Media, LLC
About this chapter
Cite this chapter
Yin, X., Ng, B.WH., Abbott, D. (2012). THz Pattern Recognition Experiments. In: Terahertz Imaging for Biomedical Applications. Springer, New York, NY. https://doi.org/10.1007/978-1-4614-1821-4_9
Download citation
DOI: https://doi.org/10.1007/978-1-4614-1821-4_9
Published:
Publisher Name: Springer, New York, NY
Print ISBN: 978-1-4614-1820-7
Online ISBN: 978-1-4614-1821-4
eBook Packages: EngineeringEngineering (R0)