Time-adaptive Expectation MaximizationLearning Framework for HMM basedData-driven Gas Sensor Calibration [Elektronisk resurs]
-
You, Yang (författare)
-
Oechtering, Tobias J., 1975- (författare)
-
KTH Skolan för elektroteknik och datavetenskap (EECS) (utgivare)
- Publicerad: Institute of Electrical and Electronics Engineers (IEEE), 2023
- Engelska.
-
Ingår i: IEEE Transactions on Industrial Informatics. - 1551-3203. ; 19:7, 7986-7994
-
Läs hela texten
-
Läs hela texten
-
Läs hela texten
-
Läs hela texten
Sammanfattning
Ämnesord
Stäng
- In this paper, data-driven self-calibration al- gorithms for the low-cost gas sensors are designed. The sensor measurement errors happen due to the imperfect compensation for the variation of sensor component be- havior that is caused by changing of environmental fac- tors. To calibrate the sensors, the hidden Markov model is utilized to characterize the statistical dependency between the environmental factors and the variation of sensor com- ponent behavior. Considering the time-varying property of this dependency, a time-adaptive learning framework is further designed to update the hidden Markov model so that the time-varying drift process can be better tracked over a long term. More specifically, a time-adaptive expectation maximization learning approach is proposed to efficiently update the hidden Markov model parameters. A closed form of the convergence rate of this time-adaptive learning approach is derived, which provides a theoretical guaran- tee on the time efficiency as well as the computational efficiency. The performance of the scheme is illustrated in numerical experiments utilizing real data, which shows that long-term stable calibration performance can be achieved.
Ämnesord
- Engineering and Technology (hsv)
- Electrical Engineering, Electronic Engineering, Information Engineering (hsv)
- Other Electrical Engineering, Electronic Engineering, Information Engineering (hsv)
- Teknik och teknologier (hsv)
- Elektroteknik och elektronik (hsv)
- Annan elektroteknik och elektronik (hsv)
- Signal Processing (hsv)
- Signalbehandling (hsv)
- Datalogi (kth)
- Computer Science (kth)
- Informations- och kommunikationsteknik (kth)
- Information and Communication Technology (kth)
- SRA - ICT (kth)
- SRA - Informations- och kommunikationsteknik (kth)
- Electrical Engineering (kth)
- Elektro- och systemteknik (kth)
Genre
- government publication (marcgt)
Indexterm och SAB-rubrik
- Data-driven calibration
- hidden Markov model
- expectation maximization
- NDIR gas sensor
Inställningar
Hjälp
Ingår i annan publikation. Gå till titeln
IEEE Transactions on Industrial Informatics