br Data format The benchmark data

Data format The benchmark data are distributed in comma-separated value format (csv). Some basic description for each data set is also distributed in automated report files given in PDF format. The delimiter between fields in the csv files is the “,” symbol. The approximate size of the data set for a single scenario is 100Mb (50Mb in zip compression). The data tables have the following columns:
Acknowledgments This work was partially funded from the European Community’s Seventh Framework Programme (FP7/2007-2013) under grant agreement no. 216916: Biologically Inspired Computation for Chemical Sensing (NEUROChem), grant TEC2010-20886-C02- 02 and the Ramon y Cajal program from the Spanish Ministerio de Educación y Ciencia (RYC-2007-01475). CIBER-BBN is an initiative of the Spanish ISCIII.
Experimental design, materials and methods
Methods To generate the dataset, we adopted a measurement procedure consisting of the following three steps. First, in order to stabilize the sensors and measure the baseline of the Tubastatin A Supplier response, we circulated synthetic dry air (10% R.H.) through the sensing chamber during 50s. Second, we randomly added one of the analytes of interest to the carrier gas and made it circulate through the sensor chamber during 100s. Finally, we re-circulated clean dry air for the subsequent 200s to acquire the sensors׳ recovery and have the system ready for a new measurement. The sensor array was exposed to six different volatiles, each of them at different concentration levels (see Table 1). Table 2 shows the data distribution over the 36-month period. For processing purposes, the dataset is organized into ten batches, each containing the number of measurements per class and month indicated in Table 2. This reorganization of data was done to ensure having a sufficient number of experiments in each batch, as uniformly distributed as possible. Note that a few measurements, mainly in batch 7, appear at lower concentration levels than detailed in Table 2. This concentration mismatch is due to some experimental error. For the sake of completeness, we decided to include those samples in the dataset.
Acknowledgments This work has been supported by the California Institute for Telecommunications and Information Technology (CALIT2) under Grant number 2014CSRO 136.
Value of the data
Data, experimental design, materials and methods
Acknowledgements
Value of the data
Experimental design, materials and methods
Methods We compiled a very extensive dataset utilizing nine portable sensor array modules – each endowed with eight metal oxide gas sensors – positioned at six different line locations normal to the wind direction, creating thereby a total number of 54 measurement locations. In particular, our dataset consists of 10 chemical analyte species. Table 2 shows the entire list of chemical analyte as well as their nominal concentration values at the outlet of the gas source. To construct the dataset, we adopted the following procedure. First, we positioned our chemo-sensory platform, ie the 9 sensing units, in one of the six fixed line positions indicated in the wind tunnel, and set the chemical sensors to one of the predefined surface operating temperatures. One of the predefined airflows was then individually induced into the wind tunnel by the exhaust fan, generating thereby the turbulent airflow within the test section of the wind tunnel. This stage constituted a preliminary phase that allowed to reach a quasi-stationary situation and to measure the baseline of the sensor responses for 20s before the chemical analyte was released. We then randomly selected one of the ten described chemical volatiles and released it into the tunnel at the source for three minutes. The chemical analyte circulated throughout the wind tunnel while recording the generated sensor time series. Note that the concentration reported in Table 2 represents only the concentration at the outlet of the gas source. Concentration disperses as the generated gas plume spreads out along the wind tunnel. After that step, the chemical analyte was removed and the test section was ventilated utilizing clean air circulating through the sampling setting at the same wind speed for another minute. Fig. 2 shows the typical response of the sensors after a complete measurement was recorded.