Forum Replies Created
-
Posts
-
Hi,
1. First, note the color should not affect the measurements.
Generally speaking, colors may change the IR spectrum, making it impossible to identify black plastics, for example, since they might practically have no spectral signature for SCiO to measure.
However, this is not the case with fruits.
2. Waxed apples were measured in our laboratory, and it seems that the wax layer has no significant affect on the results.
However, the wax can be washed off the apple sample, if you wish so, as part of your experiment preparation.
3. Since moisture’s molecular signature is very intensive, it is recommended to dry up the samples before scanning.
4. We recommend scanning in different locations in order to reach a sufficient variance in sugar content, for example, within the sample.
We recommend populating the attributes regarding the different locations during the experiment for further analysis.
5. Please note that in order to develop an Apple juice application, the samples and scans which are collected for this manner, should be juice samples as well.
As long as the juice is squeezed, the seeds or pill should not affect the results and will not be detectable by SCiO.
The video presented grounded meat with fat for demonstration purposes.
I hope it was helpful.
Ayelet,
The Consumer Physics Team
Hi,
There are many planned features in our road map for SCiO lab applications.
We recommend collecting specific data in each data collection and there are no plans to create sub-collections at the moment.
Regarding the other features request – thanks, it will be transferred to our Product Manager.
Regards,
Ayelet
The Consumer Physics Team
Hi Gustav,
Our software team will update the error message.
Please contact us with additional questions or if you are in need of any assistance.
Ayelet,
The Consumer Physics Team
Hi Aby,
SCiO is a complete solution, including the spectrometer, a light source and optimized analysis algorithms.
The optimized algorithms are part of our intellectual property and we cannot disclose them.
Additional technical information may be shared in the future once SCiO officially launches and is widely available to the public.
As for hyperspectral use cases, SCiO cannot be used as an hyperspectral imaging device.
For cooperation and business related issues, please contact support@consumerphysics.com and we will provide you with further information.
Regards,
Ayelet,
The Consumer Physics Team
Hi Adam,
We have some experience in fruit and vegetables analysis as well as raw meat analysis.
I transferred the question to our application R&D team and I will let you know soon what are the best practices in these fields.
Regards,
Ayelet
The Consumer Physics Team
Hi Zaki,
Sorry for the delayed response.
Unfortunately, the answer is no.
Using ‘Test Model’ button you can only evaluate the performance of models created based on a specific data collection (collected in your account).
Other developers applications may be downloaded in the future via Google Play and App Store.
However, you cannot access other developers database at the moment.
P.S – We recommend sending technical questions like this one to our e-mail address: support@consumerphysics.com.
Best regards,
Ayelet
Hi Steve,
As I mentioned in previous posts, our experiments show that SCiO can detect alcohol and carbohydrate levels in drinks with good accuracy. We conducted these tests as part of our feasibility study for future applications we will develop. We are continuing to build these data collections and models to make them available for future use.
Evaluating for other ingredients in the beverage and volatile acidity level may also be possible, although we have not tried it ourselves. It should be noted that any component in the beverage which is below a concentration of 0.1% will not be detectable by SCiO. In addition, as SCiO is currently designed for the scanning of solid samples, a liquid sampling accessory (available in the near future) will be required in order to sample.
As for your second question – can you elaborate? what kind of profiles are you looking for?
Ayelet,
The Consumer physics Team
Dear Mike,
a. CP models
1. SCiO consumer app will offer:
– A number of food nutrition analysis applets, for example analyzing the nutritional values and macronutrients of dairy products.
– Identification applets, such as the ability to identify and analyze pills.
– An application that allows you to work with the spectrometer by collecting material data and building analysis applets for your own materials.
– 2 2. After SCiO consumer app is released (within Q1-Q2 this year), new applications will be developed and released regularly. Some of the applications planned for development include an evaluation of produce, sugar and ethanol content in drinks and the macronutrients of raw meat. At the same time, we will continue to broaden our existing application databases, such as increasing the number of pills (which already stands at +/- 250 OTC pills). Additional applications are also under research, such as ones for breads and body fat percentage.
b. Developer community models
1+2. Any SCiO developer that has purchased the development kit is provided access to a cloud-based environment that allows you to protect your database.
The various samples you collect for application development are your proprietary data. Any SCiO developer that has purchased the development kit is provided access to a cloud-based environment that allows you to protect your database.
3. Therefore, in order to share your models with others, a corresponding application must be developed and released to the public via App store or Google store.
Copying data collections from one user account of SCiO lab to another is possible. We can do so at your request, so that you can collaborate with your colleagues as you wish.
c. Additional models
1. DietSensor is an application developed by one of our partners. For additional information you may visit http://www.dietsensor.com or contact DietSensor at info@dietsensor.com
Other applications of third-party sources are under development at these days.
Additional information may be shared in the future once the applications officially launch and are widely available to the public.
2. See point b.1+2.
-=-
Regards,
Ayelet,
The Consumer Physics Team
Hi Paul and Paul,
Subtracting the background is a nice feature, but will require some work. There also a hidden assumption that you can fully compensate for the different backgrounds which is not 100% true.
As for scanning cups, PTFE is indeed a recommended material.
Feel free to ask further questions.
Ayelet and Guy,
The Consumer Physics Team
Hi Dshedoo,
Our experiments show that SCiO can detect alcohol levels in drinks with good accuracy. We conducted these tests as part of our feasibility study for future applications we will develop. We are continuing to build these data collections and models to make them available for future use.
Evaluating for other ingredients in the beverage may also be possible, although we have not tried it ourselves. It should be noted that any component in the beverage which is below a concentration of 1% will not be detectable by SCiO. In addition, as SCiO is currently designed for the scanning of solid samples, a liquid sampling accessory (available soon) will be required in order to sample.
Unfortunately your suggestion to scan blood for insights about components found in concentrations of few ppm is not likely to be feasible with SCiO. While we have not tested these thoroughly, we believe that SCiO’s NIR spectroscopy technology is most likely NOT suitable for trace detection of such components due to their low concentrations, which are below SCiO’s range of at least 0.1%.
However, scanning in concentrations above 0.1% with SCiO is generally feasible.
Ayelet,
The Consumer Physics Team
Hi Joao,
There are no pubic models at the moment.
However, we can guide you through all the steps of creating your own model.
Make sure you have access to proper amount of data – as much as possible and as varied as possible. This point is critical for the success of your collections. By data we mean both spectrum and meta-data (attributes). The meta-data should be obtained from a reliable source (such as an external lab or a different measurement device).
Ayelet,
The Consumer Physics Team
Hi Celia,
Otto is right. Penetration depth heavily depends on the sample – both material and density.
Usually, SCiO penetrates food for 3-4 mm and less than 1 mm for pills (which have compressed powder in them).
While in principle SCiO can penetrate wrapping such as the plastic bags, individual scans will depend on material type, thickness, and transparency.
We recommend scanning the object directly to get the most accurate read.
Regarding fruit and vegetable peels, we are able to scan accurately through vegetables and fruits with a thin rind or skin (such as apples, pears, cucumbers etc.) since the illumination beam light is still returned to the sensor and our algorithms eliminate their effect. In some cases we are also able to scan and return data regarding fruits with a thick rind, such as melon and watermelons, because to an extent, the content of the rind correlates to the content of the actual fruit.
Ayelet,
The Consumer Physics Team
Hi,
By pressing ‘done’, the application reloads the new scans. The process might be corrupted due to some kind of connection problems (Internet, Wifi).
The issue was improved in the last version.
Please make sure you use the most updated version, you may update via the app store.
Ayelet,
The Consumer Physics Team
