Increasing pattern recognition accuracy for chemical sensing by evolutionary based drift compensation

► This study proposes an evolution strategy to perform gas sensor drift correction. ► The correction is learnt without hypothesis on the behavior of the sensors. ► The proposed approach transparently adapts to changes in the sensors’ response. Artificial olfaction systems, which mimic human olfactio...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Pattern recognition letters Ročník 32; číslo 13; s. 1594 - 1603
Hlavní autoři: Di Carlo, S., Falasconi, M., Sanchez, E., Scionti, A., Squillero, G., Tonda, A.
Médium: Journal Article
Jazyk:angličtina
Vydáno: Amsterdam Elsevier B.V 01.10.2011
Elsevier
Témata:
Applied sciences
Biological and medical sciences
Classification systems
Computer Science
Computerized, statistical medical data processing and models in biomedicine
Electronics
Engineering Sciences
Evolutionary strategy
Exact sciences and technology
Information, signal and communications theory
Machine Learning
Medical management aid. Diagnosis aid
Medical sciences
Neural and Evolutionary Computing
Pattern recognition
Sensor drift
Signal processing
Telecommunications and information theory
Evolutionary strategy
Sensor drift
Classification systems
State of the art
Iterative method
Pattern recognition
Chemical sensor
Adaptive method
Accuracy
Optimal strategy
Linear transformation
Safety
Diagnostic aid
Environmental monitoring
Cost lowering
classification systems
sensor drift
evolutionary strategy
ISSN:0167-8655, 1872-7344
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:► This study proposes an evolution strategy to perform gas sensor drift correction. ► The correction is learnt without hypothesis on the behavior of the sensors. ► The proposed approach transparently adapts to changes in the sensors’ response. Artificial olfaction systems, which mimic human olfaction by using arrays of gas chemical sensors combined with pattern recognition methods, represent a potentially low-cost tool in many areas of industry such as perfumery, food and drink production, clinical diagnosis, health and safety, environmental monitoring and process control. However, successful applications of these systems are still largely limited to specialized laboratories. Sensor drift, i.e., the lack of a sensor’s stability over time, still limits real industrial setups. This paper presents and discusses an evolutionary based adaptive drift-correction method designed to work with state-of-the-art classification systems. The proposed approach exploits a cutting-edge evolutionary strategy to iteratively tweak the coefficients of a linear transformation which can transparently correct raw sensors’ measures thus mitigating the negative effects of the drift. The method learns the optimal correction strategy without the use of models or other hypotheses on the behavior of the physical chemical sensors.
ISSN:0167-8655
1872-7344
DOI:10.1016/j.patrec.2011.05.019