Pattern recognition analysis of optical sensor array data to detect nitroaromatic compound vapors

Bakken, Gregory A.; Kauffman, Gregory W.; Jurs, Peter C.; Albert, Keith J.; Stitzel, Shannon E.

doi:10.1016/s0925-4005(01)00781-x

Cited by 34 publications

(34 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other efforts have looked at characteristics of raw data in the full response of sensors including rates of change in polymer sensor resistances [49], time averages and slopes of fiber optic bead sensors [50], and actual reproductions of calibrated sensor odors [51], to name a few.…”

Section: Other Featuresmentioning

confidence: 99%

Array Optimization and Preprocessing Techniques for Chemical Sensing Microsystems

et al. 2002

View full text Add to dashboard Cite

Physical sensors, defined by their direct chemical interaction with the sensing environment, are a valuable and often essential contribution to the solution of stringent chemical sensing problems. Methods for conditioning signals from these sensors to optimize their presentation to subsequent decision-making models in the signal processing flow are presented. The assembly of sensors into an array and the preprocessing of these signals are the two primary techniques for conditioning a chemical image for concentration detection, chemical discrimination, and, in some cases, odor localization. Array optimization involves locating the point at which adding additional sensors to an array generates more noise than information and is highly dependent on the application and number of analytes to be sensed or differentiated. Signal preprocessing techniques include noise reduction, feature extraction, the reduction of array inputs, and the scaling of individual sensor signals and provide a means by which to reconstruct an array of chemical sensor signals into a subset of information that enables a decisionmaking model to do its job with greater efficiency and accuracy. In this chapter, surveys of methods are accompanied by representative examples employing a wide variety of sensors including ChemFETs, chemiresistors, acoustic wave devices, and surface plasmon resonance sensors.

show abstract

Section: Other Featuresmentioning

confidence: 99%

Array Optimization and Preprocessing Techniques for Chemical Sensing Microsystems

et al. 2002

View full text Add to dashboard Cite

show abstract

“…These have greatly enhanced monitoring of complex infrastructure and the natural environment, allowing the study of fundamental processes in the environment, as well as hazard warnings, such as flood (Hart and Martinez 2006;Martinez and Hart 2004;Zhou and Roure 2007) and pollution alerts (Hochbaum and Fishbain 2011), in a new way. In conjunction new hardware designs and algorithmic approaches to support these networks have emerged (Ramanathan et al 2006;Budde et al 2012;Denzer 2005;Kranz et al 2010;Bakken et al 2001). The focus of most of these studies is an efficient operation of the network and failure tolerance and therefore they do not provide new insights on the monitored environments.…”

Section: Introductionmentioning

confidence: 99%

Framework for Analyzing Environmental Indicators Measurements Acquired by Wireless Distributed Sensory Network – Air Pollution Showcase

Fishbain

2014

Environmental Indicators

View full text Add to dashboard Cite

Distributed continuous in situ monitoring of the environment is an essential component in assessing environmental indicators as their changes take place on different spatial and temporal scales. Recent sensory and communication technological developments have led to the emergence of Wireless Distributed Environmental Sensing Networks (WDESNs) that consist mainly of MicroSensory-Units (MSUs). The set of skills and expertise that are called for developing these WDESNs are from different fields and research disciplines, where each discipline has its own jargon. To allow cross-disciplinary discussion, a comprehensive, yet simple framework for discussing data acquired by WDESNs is presented. The terminology presented here allows for describing complex multi-modal environmental sensory networks and the integration of the observed environmental indicators' into a holistic understanding of the environment. The usage of the presented framework is demonstrated in describing a recently reported data acquired by air-pollution WDESN.

show abstract

“…The concentration and polarity of the vapor can be monitored by Nile Red by means of time-dependent spectral changes (excitation/emission shifts and/or intensity change), which form unique patterns for each odor [1,17,18]. These fluorescence-based microbeads have proven to be effective sensors for detecting lowlevel nitroaromatic compound vapors [1,2,9,19,20] and discriminating simple and complex odors [1,21]. As reported herein, these unique and reproducible sensor odor patterns can be used to identify, or decode, different types of sensor when they are combined and randomly distributed on a high-density array platform.…”

Section: Introductionmentioning

confidence: 99%

“…As reported herein, these unique and reproducible sensor odor patterns can be used to identify, or decode, different types of sensor when they are combined and randomly distributed on a high-density array platform. This paper does not elaborate on odor discrimination, which has previously been documented for similar types of sensors [1,2,4,9,19,20,21,22].…”

Section: Introductionmentioning

confidence: 99%

“…Each fiber bundle is then positioned on a microscope-based imaging system with a CCD detector and vacuum-controlled sparging apparatus odor-delivery unit [18]. Single-sensor homogeneous arrays are effective detection platforms, but to create an array with multiple sensor types many arrays must be combined, bundled, and aligned [1,20]. Depending on the number of arrays one wishes to combine, complications can arise.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic decoding of sensor types within randomly ordered, high-density optical sensor arrays

et al. 2002

Self Cite

View full text Add to dashboard Cite

In this paper automatic sensor identification of sensor classes within a high-density randomized array, without a priori knowledge of sensor locations, is demonstrated. Two different fluorescence-based sensor types, with hundreds of replicates each, were randomly distributed into an optical imaging fiber array platform. The sensor element types were vapor-sensitive microspheres with the environmentally-sensitive fluorescent dye Nile Red adsorbed on their surface. Nile Red undergoes spectral changes when exposed to different microenvironmental polarity conditions, e.g. microsphere surface polarity or odor exposure. These reproducible sensor spectral changes, or sensor-response profiles, enable sensors within a randomized array to be grouped into categories by optical decoding methods. Two computational decoding methods (supervised and unsupervised) are introduced; equal classification rates were achieved for both. By comparing sensor responses from a randomized array with those obtained from known (control) arrays, 587 sensors were correctly classified with 99.32% accuracy. Although both methods were equally effective, the unsupervised method, which uses sensor response changes to odor exposure, is a better decoding model for the vapor-sensitive arrays studied, because it relies only on the odor-response profiles. Another decoding technique employed the emission spectra of the sensors and is more applicable to other types of multiplexed fluorescence-based arrays and assays. The sensor-decoding techniques are compared to demonstrate that sensors within high-density optical chemosensor arrays can be positionally-registered, or decoded, with no additional overhead in time or expense other than collecting the sensor-response profiles.

show abstract

Pattern recognition analysis of optical sensor array data to detect nitroaromatic compound vapors

Cited by 34 publications

References 37 publications

Array Optimization and Preprocessing Techniques for Chemical Sensing Microsystems

Array Optimization and Preprocessing Techniques for Chemical Sensing Microsystems

Framework for Analyzing Environmental Indicators Measurements Acquired by Wireless Distributed Sensory Network – Air Pollution Showcase

Automatic decoding of sensor types within randomly ordered, high-density optical sensor arrays

Contact Info

Product

Resources

About