| 摘要 |
A statistical metric, based on the magnitude and standard deviations along linear projections of clustered array response data, is utilized to facilitate an evaluation of the performance of detector arrays in various vapor classification tasks. This approach allows quantification of the ability of arrays of different types including carbon black-insulating polymer composite chemiresistor sensors, tin oxide sensors and bulk conducting organic polymer sensors to distinguish between analytes. The evaluation of questions such as the optimal number of detectors required for a specific task, whether improved performance is obtained by increasing the number of detectors in a detector array, and how to assess statistically the diversity of a collection of detectors in order to understand more fully which properties are underrepresented in a particular set of array elements, are addressed. |
