| 1. |
- Asadi, Sahar, 1983-, et al.
(författare)
-
TD Kernel DM+V : time-dependent statistical gas distribution modelling on simulated measurements
- 2011
-
Ingår i: Olfaction and Electronic Nose. - : Springer Science+Business Media B.V.. - 9780735409200 ; , s. 281-282
-
Konferensbidrag (refereegranskat)abstract
- To study gas dispersion, several statistical gas distribution modelling approaches have been proposed recently. A crucial assumption in these approaches is that gas distribution models are learned from measurements that are generated by a time-invariant random process. While a time-independent random process can capture certain fluctuations in the gas distribution, more accurate models can be obtained by modelling changes in the random process over time. In this work we propose a time-scale parameter that relates the age of measurements to their validity for building the gas distribution model in a recency function. The parameters of the recency function define a time-scale and can be learned. The time-scale represents a compromise between two conflicting requirements for obtaining accurate gas distribution models: using as many measurements as possible and using only very recent measurements. We have studied several recency functions in a time-dependent extension of the Kernel DM+V algorithm (TD Kernel DM+V). Based on real-world experiments and simulations of gas dispersal (presented in this paper) we demonstrate that TD Kernel DM+V improves the obtained gas distribution models in dynamic situations. This represents an important step towards statistical modelling of evolving gas distributions.
|
|
| 2. |
- Berna, Amalia, et al.
(författare)
-
Evaluating zeolite-modified sensors : towards a faster set of chemical sensors
- 2011
-
Ingår i: Olfaction and electronic nose. - : American Institute of Physics (AIP). - 9780735409200 ; , s. 50-52
-
Konferensbidrag (refereegranskat)abstract
- The response of zeolite-modified sensors, prepared by screen printing layers of chromium titanium oxide (CTO), were compared to unmodified tin oxide sensors using amplitude and transient responses. For transient responses we used a family of features, derived from the exponential moving average (EMA), to characterize chemo-resistive responses. All sensors were tested simultaneously against 20 individual volatile compounds from four chemical groups. The responses of the two types of sensors showed some independence. The zeolite modified CTO sensors discriminated compounds better using either amplitude response or EMA features and CTO-modified sensors also responded three times faster.
|
|
| 3. |
- Murguia, Jose, et al.
(författare)
-
Classification of optical sensor response cues with a bidimensional wavelet transform approach
- 2011
-
Ingår i: Olfaction and electronic nose. - Stony Brook NY : American Institute of Physics (AIP). - 9780735409200 ; , s. 255-257
-
Konferensbidrag (refereegranskat)abstract
- In this work is used the two-dimensional discrete wavelet transform as a feature extractor of time responses from a porous silicon optical gas sensor for gas identification. The wavelet decomposition allows us to have a more in-deep sight of the sensor response. In addition, using a linear support vector machine (SVM) as classifier we evaluate our approach for a six-analyte discrimination problem.
|
|
| 4. |
- Trincavelli, Marco, 1981-, et al.
(författare)
-
Optimizing the operating temperature for an array of MOX sensors on an open sampling system
- 2011
-
Ingår i: Olfaction and electronic nose. - : AIP. - 9780735409200 ; , s. 225-227
-
Konferensbidrag (refereegranskat)abstract
- Chemo-resistive transduction is essential for capturing the spatio-temporal structure of chemical compounds dispersed in different environments. Due to gas dispersion mechanisms, namely diffusion, turbulence and advection, the sensors in an open sampling system, i.e. directly exposed to the environment to be monitored, are exposed to low concentrations of gases with many fluctuations making, as a consequence, the identification and monitoring of the gases even more complicated and challenging than in a controlled laboratory setting. Therefore, tuning the value of the operating temperature becomes crucial for successfully identifying and monitoring the pollutant gases, particularly in applications such as exploration of hazardous areas, air pollution monitoring, and search and rescue I. In this study we demonstrate the benefit of optimizing the sensor's operating temperature when the sensors are deployed in an open sampling system, i.e. directly exposed to the environment to be monitored.
|
|
