Abstract
In the application of breath analysis , the redundant specificities of a sensor array often exceed the needs of the discrimination application. When recognizing types of diseases, not all sensors are required. However, it is difficult to decide which sensor is more useful for an unknown sample because some sensors are cross-sensitive to the biomarkers of the diseases. In this chapter, we propose a linear discriminant analysis (LDA)-based sensor selection technique (LDASS) which chooses an optimal configuration of sensors for a particular application from a whole set of available sensors. The proposed method finds the direction \(\varvec{w}\) via the LDA such that when data are projected onto this direction, the samples from two classes are as separate as possible. It is found that after projection, the difference of means of the two distinct sample classes can be expressed as the linear combination of the responses of all the sensors in the system, and \(\varvec{w}\) can be regarded as the weight vectors for these sensors which indicate the contribution weight of each sensor. Accordingly, it is possible to determine which sensor has a greater contribution in classifying the two classes. A series of experiments on different databases show that the proposed method outperforms other sensor selection techniques, such as the sequential forward selection (SFS) and genetic algorithm (GA) in recognition accuracy and processing time. This technique is not only applicable for breath analysis, but also useful in the general applications of e-noses.
Keywords
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Alpaydin E (2004) Introduction to machine learning. The MIT Press
Amann A, Schmid A, Scholl-Burgi S, Telser S, Hinterhuber H (2005) Breath analysis for medical diagnosis and therapeutic monitoring. Spectrosc Eur 17(3):18–20
Baraldi E, Carraro S (2006) Exhaled NO and breath condensate. Paediatr Respir Rev 7:20–22
Brighenti F, Benini L, Del Rio D, Casiraghi C, Pellegrini N, Scazzina F, Jenkins D, Vantini I (2006) Colonic fermentation of indigestible carbohydrates contributes to the second-meal effect. Am J Clin Nutr 83(4):817–822
D’Amico A, Di Natale C, Paolesse R, Macagnano A, Martinelli E, Pennazza G, Santonico M, Bernabei M, Roscioni C, Galluccio G, et al (2007) Olfactory systems for medical applications. Sens Actuators B Chem 130(1):458–465
D’Amico A, Pennazza G, Santonico M, Martinelli E, Roscioni C, Galluccio G, Paolesse R, Di Natale C (2010) An investigation on electronic nose diagnosis of lung cancer. Lung Cancer 68(2):170–176
Davies S, Spanel P, Smith D (1997) Quantitative analysis of ammonia on the breath of patients in end-stage renal failure. Kidney Int 52(1):223–228
Deng C, Zhang J, Yu X, Zhang W, Zhang X (2004) Determination of acetone in human breath by gas chromatography-mass spectrometry and solid-phase microextraction with on-fiber derivatization. J Chromatogr B 810(2):269–275
Di Francesco F, Fuoco R, Trivella M, Ceccarini A (2005) Breath analysis: trends in techniques and clinical applications. Microchem J 79(1–2):405–410
Di Natale C, Macagnano A, Martinelli E, Paolesse R, D’Arcangelo G, Roscioni C, Finazzi-Agrò A, D’Amico A (2003) Lung cancer identification by the analysis of breath by means of an array of non-selective gas sensors. Biosens Bioelectron 18(10):1209–1218
Dragonieri S, Schot R, Mertens B, Le Cessie S, Gauw S, Spanevello A, Resta O, Willard N, Vink T, Rabe K et al (2007) An electronic nose in the discrimination of patients with asthma and controls. J Allergy Clin Immunol 120(4):856–862
Dragonieri S, Annema J, Schot R, van der Schee M, Spanevello A, Carratú P, Resta O, Rabe K, Sterk P (2009) An electronic nose in the discrimination of patients with non-small cell lung cancer and COPD. Lung Cancer 64(2):166–170
Dweik R, Amann A (2008) Exhaled breath analysis: the new frontier in medical testing. J Breath Res 2(030):301
Gardner J, Boilot P, Hines E (2005) Enhancing electronic nose performance by sensor selection using a new integer-based genetic algorithm approach. Sens Actuators B Chem 106(1):114–121
Gualdron O, Brezmes J, Llobet E, Amari A, Vilanova X, Bouchikhi B, Correig X (2007) Variable selection for support vector machine based multisensor systems. Sensors Actuators B Chem 122(1):259–268
Guo D, Zhang D, Li N, Zhang L, Yang J (2010) A novel breath analysis system based on electronic olfaction. IEEE Trans Biomed Eng 57(11):2753–2763
Horvath I, Loukides S, Wodehouse T, Kharitonov S, Cole P, Barnes P (1998) Increased levels of exhaled carbon monoxide in bronchiectasis: a new marker of oxidative stress. Br Med J 53(10):867–870
Hu Q, Pedrycz W, Yu D, Lang J (2009) Selecting discrete and continuous features based on neighborhood decision error minimization. IEEE Trans Syst Man Cybern Part B Cybern 40(1):137–150
Kermani B, Schiffman S, Nagle H (1998) A novel method for reducing the dimensionality in a sensor array. IEEE Trans Instrum Meas 47(3):728–741
Kharitonov S, Wells A, O’connor B, Cole P, Hansell D, Logan-Sinclair R, Barnes P, (1995) Elevated levels of exhaled nitric oxide in bronchiectasis. Am J Respir Crit Care Med 151(6):1889–1893
Le Marchand L, Wilkens L, Harwood P, Cooney R (2006) Breath hydrogen and methane in populations at different risk for colon cancer. Int J Cancer 55(6):887–890
Maziak W, Loukides S, Culpitt S, Sullivan P, Kharitonov S, Barnes P (1998) Exhaled nitric oxide in chronic obstructive pulmonary disease. Am J Respir Crit Care Med 157(3):998–1002
Miekisch W, Schubert J, Noeldge-Schomburg G (2004) Diagnostic potential of breath analysis-focus on volatile organic compounds. Clin Chimi Acta 347(1–2):25–39
Narasimhan L, Goodman W, Patel C (2001) Correlation of breath ammonia with blood urea nitrogen and creatinine during hemodialysis. Proc Nat Acad Sci 98(8):4617–4621
Pardo A, Marco S, Calaza C, Ortega A, Perera A, Sundic T, Samitier J (2001) Methods for sensors selection in pattern recognition. In: Proceedings of the seventh international symposium on olfaction and electronic noses. Taylor & Francis, pp 83–88
Phaisangittisagula E, Nagle H, Areekul V (2010) Intelligent method for sensor subset selection for machine olfaction. Sens Actuators B Chem 145(1):507–515
Phillips M, Cataneo R, Cummin A, Gagliardi A, Gleeson K, Greenberg J, Maxfield R, Rom W (2003a) Detection of Lung Cancer With Volatile Markers in the Breath. Chest 123(6):2115–2123
Phillips M, Cataneo R, Ditkoff B, Fisher P, Greenberg J, Gunawardena R, Kwon C, Rahbari-Oskoui F, Wong C (2003b) Volatile markers of breast cancer in the breath. Breast J 9(3):184–191
Phillips M, Cataneo R, Condos R, Ring Erickson G, Greenberg J, La Bombardi V, Munawar M, Tietje O (2007) Volatile biomarkers of pulmonary tuberculosis in the breath. Tuberculosis 87(1):44–52
Schubert J, Miekisch W, Geiger K, Nöldge-Schomburg G (2004) Breath analysis in critically ill patients: potential and limitations. Expert Rev Mol Diagn 4(5):619–629
Sehnert S, Jiang L, Burdick J, Risby T (2002) Breath biomarkers for detection of human liver diseases: preliminary study. Biomarkers 7(2):174–187
Shih C, Lin Y, Lee K, Chien P, Drake P (2010) Real time electronic nose based pathogen detection for respiratory intensive care patients. Chemical, Sensors and Actuators B
Subrahmanya N, Shin Y (2010) Sparse multiple kernel learning for signal processing applications. IEEE Trans Pattern Anal Mach Intell 32(5):788–798
Van Berkel J, Dallinga J, Möller G, Godschalk R, Moonen E, Wouters E, Van Schooten F (2008) Development of accurate classification method based on the analysis of volatile organic compounds from human exhaled air. J Chromatogr B 861(1):101–107
Xu Y, Yang J, Jin Z (2004a) A novel method for Fisher discriminant analysis. Pattern Recogn 37(2):381–384
Xu Y, Yang J, Yang J (2004b) A reformative kernel Fisher discriminant analysis. Pattern Recogn 37(6):1299–1302
Yu J, Byun H, So M, Huh J (2005) Analysis of diabetic patient’s breath with conducting polymer sensor array. Sens Actuators B Chem 108(1–2):305–308
Zhang S, Xie C, Zeng D, Li H, Liu Y, Cai S (2009) A sensor array optimization method for electronic noses with sub-arrays. Sens Actuators B Chem 142(1):243–252
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2017 Springer Nature Singapore Pte Ltd.
About this chapter
Cite this chapter
Zhang, D., Guo, D., Yan, K. (2017). An LDA-Based Sensor Selection Approach. In: Breath Analysis for Medical Applications. Springer, Singapore. https://doi.org/10.1007/978-981-10-4322-2_4
Download citation
DOI: https://doi.org/10.1007/978-981-10-4322-2_4
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-4321-5
Online ISBN: 978-981-10-4322-2
eBook Packages: Computer ScienceComputer Science (R0)