2.2. New Approaches 707 2.2.1. Optical Sensor Systems 707 2.2.2. Mass Spectrometry 708 2.2.3. Ion Mobility Spectrometry 708 2.2.4. Gas Chromatography 709 2.2.5. Infrared Spectroscopy 709 2.2.6. Use of Substance-Class-Specific Sensors 709 2.3. Combined Technologies 710 3. Companies 710 4. Application Areas 710 4.1. Food and Beverage 712 4.2. Environmental Monitoring 715 4.3. Disease Diagnosis 716 5. Research and Development Trends 718 5.1. Sample Handling 719 5.2. Filters and Analyte Gas Separation 719 5.3. Data Evaluation 720 6. Conclusion 721 7. References 722

/pdf/electronic-nose-current-status-and-future-trends-475b22mugv.pdf

Electronic nose: current status and future trends.

This chapter introduces the subject of statistical pattern recognition (SPR). It starts by considering how features are defined and emphasizes that the nearest neighbor algorithm achieves error rates comparable with those of an ideal Bayes’ classifier. The concepts of an optimal number of features, representativeness of the training data, and the need to avoid overfitting to the training data are stressed. The chapter shows that methods such as the support vector machine and artificial neural networks are subject to these same training limitations, although each has its advantages. For neural networks, the multilayer perceptron architecture and back-propagation algorithm are described. The chapter distinguishes between supervised and unsupervised learning, demonstrating the advantages of the latter and showing how methods such as clustering and principal components analysis fit into the SPR framework. The chapter also defines the receiver operating characteristic, which allows an optimum balance between false positives and false negatives to be achieved.

Statistical Pattern Recognition

Chem. Pharm. Bull.(オピニオン)

Supervised pattern recognition in food analysis.

Compared to free enzymes in solution, immobilized enzymes are more robust and more resistant to environmental changes. More importantly, the heterogeneity of the immo-bilized enzyme systems allows an easy recovery of both enzymes and products, multiple re-use of enzymes, continuous operation of enzymatic processes, rapid termination of reactions, and greater variety of bioreactor designs. This paper is a review of the recent literatures on enzyme immobilization by various techniques, the need for immobilization and different applications in industry, covering the last two decades. The most recent papers, patents, and reviews on immobilization strategies and application are reviewed.

/pdf/enzyme-immobilization-an-update-50qcq3j6oo.pdf

Enzyme immobilization: an update

Over the last decades, alginates, natural multifunctional polymers, have increasingly drawn attention as attractive compounds in the biomedical and pharmaceutical fields due to their unique physicochemical properties and versatile biological activities. The focus of the paper is to describe biological and pharmacological activity of alginates and to discuss the present use and future possibilities of alginates as a tool in drug formulation. The recent technological advancements with using alginates, issues related to alginates suitability as matrix for three-dimensional tissue cultures, adjuvants of antibiotics, and antiviral agents in cell transplantation in diabetes or neurodegenerative diseases treatment, and an update on the antimicrobial and antiviral therapy of the alginate based drugs are also highlighted.

/pdf/alginate-current-use-and-future-perspectives-in-5b9ql22d3j.pdf

Alginate: Current Use and Future Perspectives in Pharmaceutical and Biomedical Applications

Electronic tongue systems are multisensor devices dedicated to automatic analysis of complicated composition samples and to the recognition of their characteristic properties. Recently, the number of publications covering this topic has significantly increased. Many possible architectures of such devices were proposed: potentiometric, voltammetric, as well as approaches embracing mass- and optical-sensors. For the analysis of sensor array data, various pattern recognition systems were proposed. All of these topics are summarized in this review. Moreover, additional problems are considered: miniaturization of electronic tongues and hybrid systems for liquid sensing.

Sensor arrays for liquid sensing – electronic tongue systems

A sensor array composed of selective and partially selective electrodes is applied to milk recognition. The task of the system is to distinguish among five brands of milk. For this purpose, five pattern recognition (PARC) procedures are employed: three linear (K-nearest neighbours, partial least squares, soft independent modelling of class analogy) and two nonlinear (back propagation neural networks and learning vector quantization). Classification accuracy is compared and some analogies with general rules referring to electronic nose were found. LVQ networks are proved to exhibit the best performance. Their further advantages, such as fast training and robustness, make them the suggested pattern classifiers for sensor array data.

The analysis of sensor array data with various pattern recognition techniques

An electronic tongue based on the sensor array of ion-selective electrodes (ISEs) combined with pattern recognition tools is applied to qualitative analysis of mineral waters and apple juices. The procedure of reducing of total number of the sensors in the array is described. Before and after reducing of number of the sensors, this device is capable of reliable discrimination between different brands of mineral waters and apple juices. Validation of this method is also confirmed using artificial neural networks as a classifier. The ability to recognize different brands of waters and juices after reduction of number of the sensors in the array is comparable to the ability to recognize the same samples by the system before reduction of number of the sensors. This method enables to specify quantitatively the capability of a sensor to discriminate between different classes of samples and can be used for any electronic tongues and noses applications.

/pdf/classification-of-beverages-using-a-reduced-sensor-array-1hrenrmdn1.pdf

Patrycja Ciosek

Papers

Alginate: Current Use and Future Perspectives in Pharmaceutical and Biomedical Applications

Sensor arrays for liquid sensing – electronic tongue systems

The analysis of sensor array data with various pattern recognition techniques

Classification of beverages using a reduced sensor array

Direct and two-stage data analysis procedures based on PCA, PLS-DA and ANN for ISE-based electronic tongue-Effect of supervised feature extraction.