Identification of Listeria Species Using a Low-Cost Surface-Enhanced Raman Scattering System With Wavelet-Based Signal Processing
ABSTRACT We investigated the ability to distinguish between six species within the Listeria genus (including the human pathogen Listeria monocytogenes ) based on a bacteria sample's surface-enhanced Raman scattering (SERS) spectrum. Our measurement system consists of a portable low-cost Raman spectral acquisition unit and associated signal processing and classification modules. First, Listeria was cultured and then adsorbed onto silver colloidal nanoparticles for SERS measurements. A total of 483 SERS spectra were collected and preprocessed (using a stationary wavelet transform decomposition) to remove noise and baseline artifact. Distinguishing features were extracted by retaining detail wavelet coefficients of significant value across multiple scales. Using a linear classifier in association with ldquoleave one outrdquo cross-validation, the system achieved maximum classification accuracies of 96.1% (six-category) and 97.9% (two-category, L. monocytogenes versus all others). Dimensionality reduction was used to decrease the number of features from 74 to 5 while maintaining similar classification accuracy. In the future, it is envisioned that a measurement system such as this, which is a combination of low-cost hardware with sophisticated signal processing, could play a complementary role with existing methods in realizing a rapid inexpensive means of identifying food-borne bacterial pathogens.
- [show abstract] [hide abstract]
ABSTRACT: Raman spectroscopy is emerging as an important nondestructive, noninvasive, analytical tool for the analysis of biologic materials. This study presents a procedure to make use of commercial off-the-shelf components to construct a portable dispersive Raman system and evaluates it for discrimination of bacteria by surface-enhanced Raman scattering (SERS). The system consists of a semiconductor laser (784.8 nm), a fiber optic probe (∼135 µm focal spot), a mini spectrometer and a computer. UV-visible spectroscopy and transmission electron microscopy analysis of four silver colloid preparations produced in this study, together with the SERS spectra of Listeria innocua adsorbed on colloidal particles, indicated that silver colloids with the extinction maximum at >415 nm (particle size >75 nm) and a larger long wavelength tail are capable of promoting SERS of bacteria. The SERS spectra of Listeria monocytogenes, Escherichia coli O157:H7 and Salmonella enterica were acquired with the system, leading to an unambiguous identification of these bacterial foodborne pathogens on the basis of their unique spectral bands. This study demonstrated the feasibility of constructing a low-cost compact Raman system using commercially available components to perform the SERS analysis of bacteria.PRACTICAL APPLICATIONSCommercial off-the-shelf components such as a semiconductor laser, a fiber optic probe and a mini spectrometer can be used to construct a portable, low-cost dispersive Raman system. Such system allows for the acquisition of SERS spectra of bacteria adsorbed on silver colloidal nanoparticles, as exemplified by three important bacterial foodborne pathogens L. monocytogenes (serotype 4b), E. coli O157:H7 and S. enterica (serotype Typhimurium DT 104). An unambiguous identification of these pathogens was achieved based on their unique spectral bands, indicating that an inexpensive dispersive Raman system such as the one described here may be built for the rapid characterization of bacteria isolates from food, clinical and environment samples using SERS spectral fingerprints.Journal of Rapid Methods & Automation in Microbiology 09/2008; 16(3):238 - 255. · 0.58 Impact Factor
- [show abstract] [hide abstract]
ABSTRACT: Gas identification represents a big challenge for pattern recognition systems due to several particular problems such as nonselectivity and drift. The purpose of this paper is twofold: 1) to compare the accuracy of a range of advanced and classical pattern recognition algorithms for gas identification for the in-house sensor array signals and 2) to propose a gas identification ensemble machine (GIEM), which combines various gas identification algorithms, to obtain a unified decision with improved accuracy. An integrated sensor array has been designed with the aim of identifying combustion gases. The classification accuracy of different density models is compared with several neural network architectures. On the gas sensors data used in this paper, Gaussian mixture models achieved the best performance with higher than 94% accuracy. A committee machine is implemented by assembling the outputs of these gas identification algorithms through advanced voting machines using a weighting and classification confidence function. Experiments on real sensors' data proved the effectiveness of the system with an improved accuracy over the individual classifiers. An average performance of 97% was achieved using the proposed committee machineIEEE Transactions on Instrumentation and Measurement 11/2006; · 1.36 Impact Factor
- [show abstract] [hide abstract]
ABSTRACT: Differentiation of the species within the genus Listeria is important for the food industry but only a few reliable methods are available so far. While a number of studies have used Fourier transform infrared (FTIR) spectroscopy to identify bacteria, the extraction of complex pattern information from the infrared spectra remains difficult. Here, we apply artificial neural network technology (ANN), which is an advanced multivariate data-processing method of pattern analysis, to identify Listeria infrared spectra at the species level. A hierarchical classification system based on ANN analysis for Listeria FTIR spectra was created, based on a comprehensive reference spectral database including 243 well-defined reference strains of Listeria monocytogenes, L. innocua, L. ivanovii, L. seeligeri, and L. welshimeri. In parallel, a univariate FTIR identification model was developed. To evaluate the potentials of these models, a set of 277 isolates of diverse geographical origins, but not included in the reference database, were assembled and used as an independent external validation for species discrimination. Univariate FTIR analysis allowed the correct identification of 85.2% of all strains and of 93% of the L. monocytogenes strains. ANN-based analysis enhanced differentiation success to 96% for all Listeria species, including a success rate of 99.2% for correct L. monocytogenes identification. The identity of the 277-strain test set was also determined with the standard phenotypical API Listeria system. This kit was able to identify 88% of the test isolates and 93% of L. monocytogenes strains. These results demonstrate the high reliability and strong potential of ANN-based FTIR spectrum analysis for identification of the five Listeria species under investigation. Starting from a pure culture, this technique allows the cost-efficient and rapid identification of Listeria species within 25 h and is suitable for use in a routine food microbiological laboratory.Applied and Environmental Microbiology 03/2006; 72(2):994-1000. · 3.68 Impact Factor