Ricardo Gutierrez-Osuna

Pattern analysis for machine olfaction: a review

Pattern analysis constitutes a critical building block in the development of gas sensor array instruments capable of detecting, identifying, and measuring volatile compounds, a technology that has been proposed as an artificial substitute for the human olfactory system. The successful design of a pattern analysis system for machine olfaction requires a careful consideration of the various issues involved in processing multivariate data: signal-preprocessing, feature extraction, feature selection, classification, regression, clustering, and validation. A considerable number of methods from statistical pattern recognition, neural networks, chemometrics, machine learning, and biological cybernetics have been used to process electronic nose data. The objective of this review paper is to provide a summary and guidelines for using the most widely used pattern analysis techniques, as well as to identify research directions that are at the frontier of sensor-based machine olfaction.

The how and why of electronic noses

Witnessing the swift advances in the electronic means of seeing and hearing, scientists and engineers scent a market for systems mimicking the human nose. Already commercial systems from several companies are targeting applications, present and potential, that range from quality assurance of food and drugs to medical diagnosis, environmental monitoring, safety and security and military use. Here, the authors outline the major transducer technologies-in one sense, the key component of an electronic nose.

Attribute bagging: improving accuracy of classifier ensembles by using random feature subsets

We present attribute bagging (AB), a technique for improving the accuracy and stability of classifier ensembles induced using random subsets of features. AB is a wrapper method that can be used with any learning algorithm. It establishes an appropriate attribute subset size and then randomly selects subsets of features, creating projections of the training set on which the ensemble classifiers are built. The induced classifiers are then used for voting. This article compares the performance of our AB method with bagging and other algorithms on a hand-pose recognition dataset. It is shown that AB gives consistently better results than bagging, both in accuracy and stability. The performance of ensemble voting in bagging and the AB method as a function of the attribute subset size and the number of voters for both weighted and unweighted voting is tested and discussed. We also demonstrate that ranking the attribute subsets by their classification accuracy and voting using only the best subsets further improves the resulting performance of the ensemble.

Higher-Order Chemical Sensing

6.2. Orthogonality versus Independence 584 6.3. Cross-sensitivity and Diversity 585 6.4. Multiple Roles of Redundancy 585 7. Data Preprocessing 586 7.1. Baseline Correction 586 7.2. Scaling 587 7.2.1. Global Techniques 588 7.2.2. Local Techniques 588 7.2.3. Nonlinear Transforms 588 8. Drift Compensation 588 8.1. Univariate Drift Compensation 589 8.2. Multivariate Drift Compensation 589 9. Feature Extraction from Sensor Dynamics 591 9.1. Transient Analysis 591 9.1.1. Oversampling Procedures 592 9.1.2. Ad hoc Transient Parameters 593 9.1.3. Model-Based Parameters 593 9.1.4. Comparative Studies 595 9.2. Temperature-Modulation Analysis 596 10. Multivariate Calibration 599 10.1. Multiway Analysis 599 10.2. Dynamical Models 602 11. Array Optimization 604 11.1. Sensor Selection 604 11.2. Feature Selection 605 11.3. Optimization of Excitation Profiles 607 12. Conclusion and Outlook 608 13. References 609

A method for evaluating data-preprocessing techniques for odour classification with an array of gas sensors

The performance of a pattern recognition system is dependent on, among other things, an appropriate data-preprocessing technique, In this paper, we describe a method to evaluate the performance of a variety of these techniques for the problem of odour classification using an array of gas sensors, also referred to as an electronic nose. Four experimental odour databases with different complexities are used to score the data-preprocessing techniques. The performance measure used is the cross-validation estimate of the classification rate of a K nearest neighbor voting rule operating on Fishers linear discriminant projection subspace.

Transient response analysis for temperature-modulated chemoresistors

This article presents a sensor excitation and signal processing approach that combines temperature modulation and transient analysis to enhance the selectivity and sensitivity of metal-oxide gas sensors. A staircase waveform is applied to the sensor heater to extract transient information from multiple operating temperatures. Four different transient analysis techniques, Pade–Z-transform, multi-exponential transient spectroscopy (METS), window time slicing (WTS) and a novel ridge regression solution, are evaluated on the basis of their ability to improve the sensitivity and selectivity of the sensor array. The techniques are validated on two experimental databases containing serial dilutions and mixtures of organic solvents. Our results indicate that processing of the thermal transients significantly improves the sensitivity of metal-oxide chemoresistors when compared to the quasi-stationary temperature-modulated responses. # 2003 Elsevier Science B.V. All rights reserved.

Using Heart Rate Monitors to Detect Mental Stress

This article describes an approach to detecting mental stress using unobtrusive wearable sensors. The approach relies on estimating the state of the autonomic nervous system from an analysis of heart rate variability. Namely, we use a non-linear system identification technique known as principal dynamic modes (PDM) to predict the activation level of the two autonomic branches: sympathetic (i.e. stress-inducing) and parasympathetic (i.e. relaxation-related). We validate the method on a discrimination problem with two psychophysiological conditions, one associated with mental tasks and one induced by relaxation exercises. Our results indicate that PDM features are more stable and less subject-dependent than spectral features, though the latter provide higher classification performance within subjects. When PDM and spectral features are combined, our system discriminates stressful events with a success rate of 83% within subjects (69% between subjects).

Transient response analysis of an electronic nose using multi-exponential models

Abstract The purpose of this study is to model the transient response of conductivity-based gas sensors in the context of odor recognition with an electronic nose. Commonly, only the steady-state response of the sensor is used for pattern recognition, ignoring the transient response, which conveys useful discriminatory information. The transient response is modeled as a sum of real exponential functions that represent the different decay processes that occur during sampling of the gas into the sensor chamber and adsorption of the odor compounds onto the sensing element. Four multi-exponential models are reviewed: Gardner transform, multi-exponential transient spectroscopy, Pade-Laplace and Pade-Z transforms. Validation on experimental data from an array of conducting-polymer gas sensors shows that the Pade-Laplace and Pade-Z models have better resolution capabilities than the two spectral transforms.

Speech-driven facial animation with realistic dynamics

This work presents an integral system capable of generating animations with realistic dynamics, including the individualized nuances, of three-dimensional (3-D) human faces driven by speech acoustics. The system is capable of capturing short phenomena in the orofacial dynamics of a given speaker by tracking the 3-D location of various MPEG-4 facial points through stereovision. A perceptual transformation of the speech spectral envelope and prosodic cues are combined into an acoustic feature vector to predict 3-D orofacial dynamics by means of a nearest-neighbor algorithm. The Karhunen-Loe/spl acute/ve transformation is used to identify the principal components of orofacial motion, decoupling perceptually natural components from experimental noise. We also present a highly optimized MPEG-4 compliant player capable of generating audio-synchronized animations at 60 frames/s. The player is based on a pseudo-muscle model augmented with a nonpenetrable ellipsoidal structure to approximate the skull and the jaw. This structure adds a sense of volume that provides more realistic dynamics than existing simplified pseudo-muscle-based approaches, yet it is simple enough to work at the desired frame rate. Experimental results on an audiovisual database of compact TIMIT sentences are presented to illustrate the performance of the complete system.

Development and Evaluation of an Ambulatory Stress Monitor Based on Wearable Sensors

Chronic stress is endemic to modern society. However, as it is unfeasible for physicians to continuously monitor stress levels, its diagnosis is nontrivial. Wireless body sensor networks offer opportunities to ubiquitously detect and monitor mental stress levels, enabling improved diagnosis, and early treatment. This article describes the development of a wearable sensor platform to monitor a number of physiological correlates of mental stress. We discuss tradeoffs in both system design and sensor selection to balance information content and wearability. Using experimental signals collected from the wearable sensor, we describe a selected number of physiological features that show good correlation with mental stress. In particular, we propose a new spectral feature that estimates the balance of the autonomic nervous system by combining information from the power spectral density of respiration and heart rate variability. We validate the effectiveness of our approach on a binary discrimination problem when subjects are placed under two psychophysiological conditions: mental stress and relaxation. When used in a logistic regression model, our feature set is able to discriminate between these two mental states with a success rate of 81% across subjects.