Abstract
This paper proposes a way for drift compensation in electronic noses (e-nose) that often suffers from uncertain and unpredictable sensor drift. Traditional machine learning methods for odor recognition require consistent data distribution, which makes the model trained with previous data less generalized. In the actual application scenario, the data collected previously and the data collected later may have different data distributions due to the sensor drift. If the dataset without sensor drift is treated as a source domain and the dataset with sensor drift as a target domain, a domain correction based on kernel transformation (DCKT) method is proposed to compensate the sensor drift. The proposed method makes the distribution consistency of two domains greatly improved through mapping to a high-dimensional reproducing kernel space and reducing the domain distance. A public benchmark sensor drift dataset is used to verify the effectiveness and efficiency of the proposed DCKT method. The experimental result shows that the proposed method yields the highest average accuracies compared to other considered methods.
Highlights
The electronic nose (e-nose) is an intelligent system consisting of a set of sensors combined with corresponding pattern recognition algorithms to identify gases
2, it bebe seen that traditional machine itstraining own training sample, transfer learning stores knowledge gained from solving problem own sample, whilewhile transfer learning stores knowledge gained from solving oneone problem and and applies it to a different but related problem
A novel domain correction based on the kernel transformation method (DCKT) is proposed for drift compensation in an e-nose
Summary
The electronic nose (e-nose) is an intelligent system consisting of a set of sensors combined with corresponding pattern recognition algorithms to identify gases. Zhang et al [16] proposed a hybrid linear DA (LDA)-based These algorithms are classical classification algorithms in machine learning, and are often used to identify the gas in e-nose systems. Because the the traditional traditional machine machine learning learning algorithms algorithms require require that that the the data data distribution distribution between between the the source and target data be the same, the models trained by source domain data cannot be used directly source and target data be the same, the models trained by source domain data cannot be used directly on on target target domain domain for for prediction This limits limits the the application application and and development development of of the the e-nose, e-nose, so so the the focus focus of of this this paper paper is is to to suppress suppress drift drift and and improve improve recognition recognition accuracy accuracy from from the the perspective perspective of of domain correction. (DCKT)method methodto tosolve solve this this issue, propose a domain correction based ononkernel issue, which onon source and target domain data.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
