We would just want to clarify that the hard cheese collection is only consist of ~40 samples.
This amount of samples is mostly sufficient in order to assess feasibility, however it is NOT sufficient amount in order to create a robust and generic hard cheese application.
This data collection is provided as a preliminary data set which should help users taking the first steps with SCiO and SCiO Lab applications.
As for SCiO accuracy we would like to emphasize: the accuracy depends on the application and on the quality and size of the database. The greater the specificity and the higher number of scans in the database, the more accurate the application will be.
For example, an item containing few components, such as a mixture of water and sugar, will be considered more specific and therefore its application will generally be more accurate than that of juice, which largely contains water and sugar but also various additional ingredients.
Temperature as well as other experimental conditions significantly affect the spectrum. The hard cheese data collection which we provide should be tested by hard cheese samples in room temperature. The dairy application, for example, which will be released soon by us, will support materials at a range of temperatures: 4 degree Celsius to 35 degree Celsius.
Regarding the ‘Confidence level’ value, this feature is currently under development and will be provided in future versions of SCiO Lab application.
Also, in terms of hardware: the performance of the next generation SCiO device was shown to be significantly improved comparing to the current device. It may improve consistency and accuracy issues, among others.
Keep us posted!
The Consumer Physics Team