Name
Abstract | ||
|---|---|---|
Gas chemical sensors are strongly affected by drift, i.e., changes in sensors’ response with time, that may turn statistical models commonly used for classification completely useless after a period of time. This paper presents a new classifier that embeds an adaptive stage able to reduce drift effects. The proposed system exploits a state-of-the-art evolutionary strategy to iteratively tweak the coefficients of a linear transformation able to transparently transform raw measures in order to mitigate the negative effects of the drift. The system operates continuously. The optimal correction strategy is learnt without a-priori models or other hypothesis on the behavior of physical-chemical sensors. Experimental results demonstrate the efficacy of the approach on a real problem. |
Year | DOI | Venue |
|---|---|---|
2010 | 10.1007/978-3-642-12239-2_43 | EvoApplications (1) |
Keywords | Field | DocType |
exploiting evolution,optimal correction strategy,adaptive drift-robust classifier,a-priori model,negative effect,gas chemical sensor,drift effect,proposed system,linear transformation,adaptive stage,state-of-the-art evolutionary strategy,statistical model,value function,evolutionary strategy | Computer science,Exploit,Evolution strategy,Linear map,Artificial intelligence,Statistical model,Classifier (linguistics),Machine learning | Conference |
Volume | ISSN | ISBN |
6024 | 0302-9743 | 3-642-12238-8 |
Citations | PageRank | References |
2 | 0.51 | 3 |
Authors | ||
6 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Stefano Di Carlo | 1 | 293 | 46.01 |
| Matteo Falasconi | 2 | 11 | 2.31 |
| Ernesto Sánchez | 3 | 123 | 16.56 |
| Alberto Scionti | 4 | 60 | 11.97 |
| Giovanni Squillero | 5 | 992 | 103.07 |
| Alberto Tonda | 6 | 119 | 9.86 |