2013
DOI: 10.3390/s130302967
|View full text |Cite
|
Sign up to set email alerts
|

Gas Sensors Characterization and Multilayer Perceptron (MLP) Hardware Implementation for Gas Identification Using a Field Programmable Gate Array (FPGA)

Abstract: This paper develops a primitive gas recognition system for discriminating between industrial gas species. The system under investigation consists of an array of eight micro-hotplate-based SnO2 thin film gas sensors with different selectivity patterns. The output signals are processed through a signal conditioning and analyzing system. These signals feed a decision-making classifier, which is obtained via a Field Programmable Gate Array (FPGA) with Very High-Speed Integrated Circuit Hardware Description Languag… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
32
0
1

Year Published

2014
2014
2021
2021

Publication Types

Select...
6
1
1

Relationship

0
8

Authors

Journals

citations
Cited by 38 publications
(33 citation statements)
references
References 15 publications
0
32
0
1
Order By: Relevance
“…When highly sensitive sensors respond to target gases, their resistance drops to 1/10,000 from 1/1000 compared to their resistance in air ambient. Thus, before decision making process, we convert the dynamic ranges of the sensors comparable by unity-based normalized data of each sensor to the interval [0,1] using the following linear transformation [34,35]: s[i]=s[i]SminSmaxSmin, 0in, where s[i] is the normalized sensor response and Smin, Smax are minimum, maximum value of filtered data among s[0], …, s[n], respectively. In most cases, Smax indicates baseline sensor resistance where sensor is in air ambient and Smin indicates sensor resistance exposed to maximum concentration of toxic gases.…”
Section: Methodsmentioning
confidence: 99%
“…When highly sensitive sensors respond to target gases, their resistance drops to 1/10,000 from 1/1000 compared to their resistance in air ambient. Thus, before decision making process, we convert the dynamic ranges of the sensors comparable by unity-based normalized data of each sensor to the interval [0,1] using the following linear transformation [34,35]: s[i]=s[i]SminSmaxSmin, 0in, where s[i] is the normalized sensor response and Smin, Smax are minimum, maximum value of filtered data among s[0], …, s[n], respectively. In most cases, Smax indicates baseline sensor resistance where sensor is in air ambient and Smin indicates sensor resistance exposed to maximum concentration of toxic gases.…”
Section: Methodsmentioning
confidence: 99%
“…The gas identification system presented in [16] is also implemented on an FPGA. An MLP based identification system and its implementation on FPGA is presented in [17]. Similarly to [16], an array of eight micro-hotplate-based SnO 2 thin film gas sensors is used in the EN to solve problems related to the non-selectivity issue and euclidean normalization is used.…”
Section: Related Workmentioning
confidence: 99%
“…[21] presents a software based EN implementation. It is based on the same type of gas sensors compared to [16] and [17]. However, it has double the number of sensors, which is 16.…”
Section: Related Workmentioning
confidence: 99%
“…A trained neural network is as an "expert" in the category of information it has been given to analyze. In our study, we employed an artificial neural network (ANN), [140][141][142] activation functions, respectively, and Levenberg Marquardt algorithm (LMA) was the back propagation algorithm adopted for the training process. 143,144 The data used for classification was split into train (for network learning) and test data in the ratio 3:2, and 10 validation checks were performed.…”
Section: Discrimination Of Such Response Data Obtained From Differentmentioning
confidence: 99%
“…After training, once more new data is fed into the classifier, it efficiently discriminates the data. The performance of the classifiers is estimated using accuracy, sensitivity, and specificity as described below [141][142][143]. Accuracy is the proportion of true results correctly classified and is computedas = Sensitivity represents the proportion of correctly identified true positives and is calculated as = + (3.2) Finally, specificity is the proportion of correctly identified true negatives and is determined by classification allows in evaluating the discriminating ability of the sensor.…”
mentioning
confidence: 99%