Skip to content

Latest commit

 

History

History
176 lines (120 loc) · 7.78 KB

File metadata and controls

176 lines (120 loc) · 7.78 KB

Electronic nose

An electronic nose is an electronic sensing device intended to detect odors or flavors. Using a array of sensor that can detect various gases.

Can be used for quality control, estimating perceptual qualities. For food, beverages, perfumes, air quality, et.c.

The gas sensors used are often of Metal Oxide Semiconductor (MOS) type.

Keywords

  • machine olefaction

Sensors

Modules for purchase

Temperature dependence

Temperature dependence may be used as a feature.

Metal Oxide Sensors for Electronic Noses and Their Application to Food Analysis 2010, Berna "sensors run at different temperatures will show a degree of selectivity to each gas without increasing the number of sensors" https://pmc.ncbi.nlm.nih.gov/articles/PMC3274253/

"more gas features can be obtained by modulating the operating temperature of the gas sensors" https://www.mdpi.com/1424-8220/25/4/1205

Related

Air quality

Datasets

https://ieee-dataport.org/keywords/electronic-nose

https://ieee-dataport.org/documents/mixed-explosives-dataset https://ieee-dataport.org/documents/dataset-electronic-nose-various-beef-cuts https://ieee-dataport.org/documents/dataset-pork-adulteration-electronic-nose-syste

Alcohols with different structures are used frequently in hygiene products and cosmetics. It is desirable to classify these alcohols to evaluate their potential harmful effects using less costly methods. https://www.kaggle.com/datasets/chaozhuang/alcohol-qcm-sensor-dataset

5 types of sensors. QCM3, QCM6, QCM7, QCM10, QCM12 In each sensor, There is alcohol classification of five types, 1-octanol, 1-propanol, 2-butanol, 2-propanol, 1-isobutanol

https://www.kaggle.com/datasets/aryashah2k/multimodal-gas-detection-and-classification https://data.mendeley.com/datasets/zkwgkjkjn9/2 No Gas, Perfume, Smoke and Mixture of Perfume and Smoke. The dataset is collected using the seven different metal oxide gas sensors MQ2, MQ3, MQ5, MQ6, MQ7, MQ8, MQ135

MQ-3: Alcohol, MQ-7: Carbon monoxide (CO), MQ-8: Hydrogen https://www.kaggle.com/datasets/gilangbilhaq/sweet-aroma-dataset-in-coffee

Df-NH3, MQ-136, MQ-135, MQ-8, MQ-4, and MQ-2. 1- Natural Air, 2- Fresh Onion, 3- Fresh Garlic, 4- Fresh Lemon, 5- Tomato 6- Petrol, 7- Gasoline, 8- Coffee 1,2 9- Orange 10- Colonia Perfume https://www.kaggle.com/datasets/husamksalih/array-of-gas-sensors-data

The dataset for pork adulteration from electronic nose system MQ2, MQ4, MQ6, MQ9, MQ135, MQ136, MQ137, and MQ138. ground beef and ground pork bought in fresh condition. Created 7 combinations https://ieee-dataport.org/documents/dataset-pork-adulteration-electronic-nose-system

Dataset for electronic nose from various beef cuts 11 Metal-Oxide Semiconductor (MOS) gas sensors during 2220 minutes. 12 type of beef cuts. round (shank), top sirloin, tenderloin, flap meat (flank), striploin (shortloin), brisket, clod/chuck, skirt meat (plate), inside/outside, rib eye, shin, and fat. Label: discrete label, 1,2,3,4 denote “excellent”,”good”,”acceptable”, and “spoiled” https://ieee-dataport.org/documents/dataset-electronic-nose-various-beef-cuts

Electronic nose dataset for detection of wine spoilage thresholds MQ-3, MQ-4, MQ-6, MQ-3, MQ-4, MQ-6. https://data.mendeley.com/datasets/vpc887d53s/

Electronic nose dataset for recognition of eight liquor types TGS2602, TGS2611, TGS2620, TGS880, MiCS-5121, MiCS-5521, MiCS-5524, MiCS-5526, MP502 and WSP2110 eight Chinese liquor types, which are LanJinJiu with 38% alcohol concentration (LJJ38), LanJinJiu with 48% alcohol concentration (LJJ48), DaoHuaXiang with 42% alcohol concentration (DHX), LuZhouLaoJiao with 38% alcohol concentration (LZLJ), MianZhuDaQu with 38% alcohol concentration (MZDQ), QingJiu with 38% alcohol concentration (QJ), ShiLiXiang (SLX) with 40% alcohol concentration and BianFengHu with 40% alcohol concentration (BFH). https://ieee-dataport.org/documents/electronic-nose-dataset-recognition-eight-liquor-types

Dataset of Electronic Nose for Classifying Beef and Pork https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/MPJTGS

Perceptual attributes or descriptors are used to describe odor impressions, with odor perception levels ranging from 0 to 100. We used 44 single-molecule substances to predict 9 olfactory perceptionsof pleasantness, namely, sweet, fruit, fish, garlic, grass, burnt, musky aroma and decayed. https://ieee-dataport.org/documents/electronic-nose-signal

Response data for ammonia and ethanol gases was collected using the electronic nose system. To meet the need for accurate, real-time, and stable monitoring of ammonia concentration in the breeding environment in livestock and poultry breeding areas https://ieee-dataport.org/documents/electronic-nose-response-data

Electronic nose data set for seafood quality assessment (MQ136, MQ137, MQ5, MQ8) https://ieee-dataport.org/documents/electronic-nose-data-set-seafood-quality-assessment

Dataset: Electronic Nose for Quality Control of Colombian Coffee through the Detection of Defects in “Cup Tests” SP-12A, SP-31, TGS-813, TGS-842, SP-AQ3, TGS-823, ST-31, TGS-800. high quality (HQ), average quality (AQ), and low quality (LQ) https://data.mendeley.com/datasets/7spd6fpvyk/1

Reference tests? https://www.kaggle.com/datasets/thehanyss/mq-sensors-for-electronic-nose-system

TGS2600: Sensitive to air contaminants TGS2602: Detects air pollutants TGS2611: Methane gas sensor TGS2610: LP gas sensor TGS2620: Alcohol and solvent vapors sensor TGS826: Ammonia sensor Detect human diseases, with a focus on diabetes. Body odor. https://www.kaggle.com/datasets/muhammadrizwan111/enose-sensor-dataset-for-predicting-human-diseases

Dataset for non-infused aroma-based quality identification of Gambung green tea using electronic nose https://dataverse.telkomuniversity.ac.id/dataset.xhtml?persistentId=doi:10.34820/FK2/NNAL9K

Food freshness https://www.kaggle.com/datasets/mehrabmahdian/food-freshness-electronic-nose-data

Review papers

A Review on Electronic Nose: Coherent Taxonomy, Classification, Motivations, Challenges, Recommendations and Datasets. https://www.researchgate.net/publication/352817168_A_Review_on_Electronic_Nose_Coherent_Taxonomy_Classification_Motivations_Challenges_Recommendations_and_Datasets

Metal Oxide Sensors for Electronic Noses and Their Application to Food Analysis. 2010, Berna. https://pmc.ncbi.nlm.nih.gov/articles/PMC3274253/

Papers

Differentiating interstitial lung diseases from other respiratory diseases using electronic nose technology https://springernature.figshare.com/collections/Differentiating_interstitial_lung_diseases_from_other_respiratory_diseases_using_electronic_nose_technology/6917316

A Low Cost Electronic Nose System for Classification of Gayo Arabica Coffee Roasting Levels Using Stepwise Linear Discriminant and K-Nearest Neighbor https://www.iieta.org/journals/mmep/paper/10.18280/mmep.090514

Practical projects

Challenges

  • Sensors are not standardized. Many variants. Cannot assume equivalent response between different sensors for "same" gas.
  • Sensors may not be calibrated. Might have considerable per-unit variation, even for same sensor type.
  • Sensors may drift over time
  • Sensor response may be airflow dependent
  • Sensor response may be placement dependent (relative to sample)
  • Sensor response is likely to be temperature dependent. May or may not have internal compensation.
  • Sensor response may be influenced permanently or semi-permanently by what is sensed. Especially if high concentrations
  • Often quite small datasets
  • Samples may have high within-class variation
  • May need to take time-development into account