In each case, the novel EN was able to identify the spoiled product by means of the alterations in the pattern of volatile organic compounds (VOCs), reconstructed by principal component analysis (PCA) of the sensor responses.
To reduce data dimensionality principal component analysis (PCA) was performed on sensor responses, principal components (PCs) were sorted based on their initial Eigen value sizes and the highest three (PC1, PC2 and PC3) were used for further analysis.
With the assistance of principal component analysis (PCA) and rational design, the sensor array can illustrate the influence of the nitryl quantity and generate a separate response region of nitroaromatics for pattern recognition with 95.25% of variance explained in the measurements by the first three principal components (PCs).
PCA was applied to the sensor data.
In conjunction with a multisensor filtering scheme, an inconsistent sensor measurement detected through PCA is removed from the computation of the filtered sensor output.
When three or more sensor measurements are available, PCA can be used to detect inconsistencies and identify the inaccurate or faulty sensor from the group.
Temperature sensing elements (TSE) containing platinum-chip-sensors (Pt 1000, TYP PCA, 1.1505.10 M JUMO GmbH & Co.KG, Fulda, Germany) were used for all experiments, measuring two temperatures per second, with an accuracy of ± 0.1°C.
To avoid the artificial split of signal components due to the high dimensionality of the data, the separation of the EEG signals by an ICA method was preceded by a dimensionality reduction by Principal Component Analysis (PCA) from 121 EEG channels in the sensor space into k = 30 PCA components.
Moreover, the hexa-sensor array can be simplified into binary-sensor array using principal component analysis (PCA) method.
A Principal Component Analysis (PCA -based monitoring framework was develoPCA -basedsensor data collected fromonitoringting tunnel while the new tunnel was excavated.
