Unlock instant, AI-driven research and patent intelligence for your innovation.

Sensor tuning-sensor specific selection for internet of things electronic nose applications using gradient boosted decision trees

A technology of sensors and sensor arrays, applied in the fields of instruments, scientific instruments, and material analysis through electromagnetic means

Pending Publication Date: 2022-07-08
INT BUSINESS MASCH CORP
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Currently used electronic noses lack selectivity for different applications

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Sensor tuning-sensor specific selection for internet of things electronic nose applications using gradient boosted decision trees
  • Sensor tuning-sensor specific selection for internet of things electronic nose applications using gradient boosted decision trees
  • Sensor tuning-sensor specific selection for internet of things electronic nose applications using gradient boosted decision trees

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0060] EVA Electronics NOSE Platform Setup

[0061] Set up an EVA electronic nose platform (developed in-house and figure 1 shown in ), where six metal oxide gas (MOX) sensors are each attached to six corresponding modules integrated within the EVA platform. The six MOX sensors are identified by the following names: GGS1330, GGS2330, MICS5914, TGS2600, TGS2611, and TGS8100. The EVA sensor platform runs with open source based A software program (Python Software Foundation, Beaverton, Oregon, USA) developed in-house to control the six modules of the EVA platform and the gas sensors attached to it. Computer-controlled selector element ( A Multipurpose Actuator Movement Control Unit, Valco Instruments Co., Inc., Houston, TX, USA) was connected to a sealed chamber containing six MOX sensors. Selector elements are used to collect vapor from the headspace of individual vials containing samples for testing. A vacuum pump (Parker model B.1F15E1.A12VDC, Parker Hannifin, Hollis, NH,...

example 2

[0063] EVA platform for biological applications

[0064] For biological applications, the EVA of Example 1 was tested with normal human urine samples (NHU), NHU samples inoculated with E. coli, and NHU samples inoculated with E. coli and tryptic soy broth (TSB). Platform, two E. coli samples formed an infected urine sample similar to a urinary tract infection (UTI). The NHU and two UTI samples were each placed in 4 mL Wheaton septum top vials (DWK Life Sciences, Millville, NJ, USA). Three 4 mL sample vials plus a fourth 20 mL vial with control lab air were attached to the selector element. Measurements were acquired by sequentially connecting three individual sample vials to the sensor chamber via a selector element for a duration of 10 minutes during which headspace measurements were taken from each vial. During the measurement, three samples were incubated at 27°C to aid in the evaporation of trapped volatiles. Between data acquisitions, the MOX sensor was flushed with la...

Embodiment 3

[0068] EVA Platform for Food / Beverage Applications

[0069] For food / beverage applications, the EVA platform of Example 1 was tested with the following five beverage samples: apple juice, orange juice, lemon juice, beer, and white wine, each placed in a 5 mL Wheaton septum top vial. Five 5 mL sample vials plus a fourth 20 mL vial with control lab air were attached to the selector element. Training and test data were acquired by sequentially connecting five individual sample vials to the sensor chamber via a selector element for a duration of 10 minutes during which headspace measurements were taken from each vial. During the measurement, five samples were incubated at 27°C to aid in the evaporation of trapped volatiles. Between data acquisitions, the MOX sensor was flushed with laboratory air for 5 min to facilitate sensor recovery by connecting an empty 20 mL vial to the sensor chamber and allowing the airflow to remove vapors from previous samples. Through the selector ele...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

A system and method for tuning a sensor array to enable selection of the most suitable sensor for a target application. After extracting features from sensor raw data, the extracted features are ranked with a gradient boosted decision tree to assign an importance value to each extracted feature. Thresholds are calculated for the entire set of extracted features, and importance scores are calculated for individual sensors of the array. An individual sensor having an importance score equal to or higher than a threshold is selected for a target application.

Description

technical field [0001] The present invention relates generally to gas sensors, and more particularly to systems and methods for tuning gas sensors for targeted applications. Background technique [0002] Electronic noses are smart sensing devices that detect smells or tastes by applying pattern recognition. A typical electronic nose includes an odor detection system, a sample delivery system, and a pattern recognition computing system. The odor detection system is an array of gas sensors; the sample delivery system delivers the sample headspace into the detection system; and the pattern recognition system evaluates the composition of the odor, analyzes its chemical composition, and compares the composition and chemical composition of the odor with known fragrances comparison in order to identify the odor. Typical uses of electronic noses include sensing ambient VOCs (volatile organic compounds), sensing biological VOCs, and sensing VOCs emitted by food. Currently used ele...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G01N27/00
CPCG01N33/0031G06F18/2113G16Y40/10G16Y20/10G16Y40/35G06N20/20G06F2218/08
Inventor M·阿布迪A·阿德比伊A·曼纳里A·法索利R·拉比L·D·博扎诺P·乔德哈利A·阿布多拉希
Owner INT BUSINESS MASCH CORP
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com