Developer Terms and Conditions › The Development › Molecular Sensing Models › Stock Collections from Consumer Physics
- This topic has 22 replies, 8 voices, and was last updated 8 years, 3 months ago by Ayelet.
-
AuthorPosts
-
March 3, 2016 at 6:15 am #2858DallasEntrepreneurParticipant
I just got my SCiO and am disappointed to find the app does not have stock collections from Consumer Physics. From the video trailers showing the device, it was shown we could scan fruit and pills, and inferred this database of objects would be available as part of having the device, no? So I’m rather confused as to why the app doesn’t appear to have these collections, nor a way to import/add collections other than manually creating it myself. I thought the whole idea of SCiO was crowd sourcing the “first database of matter”.
When will apps or shared collections be available so that we can actually do the stuff that it was advertised doing?
- This topic was modified 8 years, 8 months ago by DallasEntrepreneur.
March 5, 2016 at 7:43 am #2881AnthonyParticipantI was looking forward to experimenting with the sample collections as well, especially for building a test app, but the SCiO I just received (& my login that was just created on 3/2/16) are also empty (with the exception of a generic list of unlabeled “hard cheeses” which do not include the ability to initiate a scan to match a cheese sample against the cheese data collection).
Since the SCiO app appears to be driven entirely by the online account used to login, perhaps there was a “glitch” in setting up new accounts for the recipients of the most recent shipment of the SCiOs?
(hopefully we’ll receive an answer or solution to this thread soon!)
March 6, 2016 at 2:14 pm #2895AyeletKeymasterHi all,
Our SCiO Development Toolkit (DevKit) provides all the tools needed to create a chemometric model of any material, at your choice.
You need to collect and scan your samples (no less that 40 scans) to build a feasible model.
Part of the DevKit is the mobile SDK which enables you, the developers, to embed the material sensing capabilities created in SCiO lab and control SCiO from your application.
SCiO consumer app that will be released soon will offer the following:
– A number of food nutrition analysis applets, for example analyzing the nutritional values of dairy and meat 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.
After SCiO consumer app is released, 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. 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.
SCiO Lab is available via web browser here.
SCiO Mobile Lab is available to download from the App Store here (iOS), for Android here.
Let us know if you have further questions.
You can contact us at support@consumerphysics.com for more specific questions.
Ayelet,
The Consumer Physics Team
April 5, 2016 at 7:08 pm #3030AnthonyParticipantI believe I speak for many of us in saying that, after watching the SCIO introductory video & reading through all the material on the website, we had come to the same conclusion that the consumer app was already available, and that the SCIO we received could already be used to scan general materials, and that we’d all have access to that “general” (non-proprietary) scan data being contributed by the developer community in building our own custom apps. For example, one may specialize by creating proprietary scans of various wine/vintages, but they should be able to choose to include general scan data relating to other foods & drinks, enabling their app to be more user friendly & server more than a single specialized purpose.
So what you have started is that, contrary to everything we read on the website, we cannot build apps using community data, but we that only SCIO consumer apps will have access to that community data.
Now, Today, an email was sent out clearly stating that we all have an older generation SCIO v.1.0, and that consumers never received this model, and that all consumers will receive a new model SCIO v1.1. In addition, all scan data built for the SCIO v.1.1 will be not be compatible with the SCIO v.1.0, therefore, the assumption would be that the SCIO v.1.0 that all developers received will likely become obsolete, and never be able to use the upcoming SCIO consumer app?
Keep in mind some of us had just received the SCIO v.1.0 less than 30 days ago – so, in essence, we received obsolete devices that are already useless??
April 6, 2016 at 3:49 pm #3031marc.van.nuffel@dudagroup.comParticipantYeah i really do feel the same way !
Marc
April 7, 2016 at 2:44 am #3033yedaoxiang@sina.comParticipantSCIO can detect pesticide residues of fruits and vegetables?
April 7, 2016 at 12:04 pm #3034AyeletKeymasterDear Anthony,
First, we would like to clarify that we are still collecting and improving the database for our models.
As a policy, Consumer Physics does not share the raw scans of the samples, but will have an API to the molecular sensing models we will make from those samples.
As for SCiO v1.1, We understand your frustration, and will be happy to send the v1.1 free of charge to you and other developers that had just recently received SCiO v1.0 . We plan to ship around the beginning of May.
In addition, we would like to clarify the applicability of models built with SCiO 1.0 for users of SCiO 1.1. We have gone through significant engineering efforts to provide full backwards compatibility with the release of SCiO 1.1. This means that any model built with SCiO 1.0 is applicable to users of SCiO 1.1, with the same level of accuracy. In other words: if you built a successful model with your SCiO 1.0 devkit, users of SCiO 1.1 will be able to use it. Your Devkit is not obsolete and can you continue to use it to build models which will serve the whole community of SCiO users: both 1.0 and 1.1.However, please note that only one version of SCiO can be used in a single collection when creating a model and collecting data – either 1.0 or 1.1.We are committed to continually improving our products, and our customers expect us to continue innovating and delivering better products over time.As we continue innovating, backward compatibility is very important to us. We will naturally strive to continue releasing improved versions of the SCiO, but as we do this we will continue to ensure that work already done by our developer community remains effective for newer models of the product.We are sorry for the misunderstanding and feel free to contact us if you have further questions.
Ayelet,
The Consumer Physics Team
April 7, 2016 at 12:06 pm #3035AyeletKeymasterSCIO can detect pesticide residues of fruits and vegetables?
SCiO’s detection threshold varies by material, and is typically 0.1%-1%.
The typical concentrations of pesticide residues are much smaller than 0.1%. Therefore, SCiO may not support the detection of pesticide residues.
April 8, 2016 at 8:43 am #3039yedaoxiang@sina.comParticipanta series of problem
Attachments:
You must be logged in to view attached files.April 9, 2016 at 1:16 pm #3043rejsharpParticipant@ Anthony:
I hope Ayelet’s answers have made it clear that there are TWO Apps with greatly different purpose.
a) SCiO Mobile Lab: which we developers will use to create new collections and from them Apps or Applets.
– the cheese collection in there is just for us to play with.
b) SCiO App: which all users will have to scan stuff – depending on the Apps and Applets on it.– it also contains a mini workshop for user created Applets (ID of things but not values).
I have seen a test version of the latter – it certainly Exceeds Expectations, but I have no knowledge of how widely it has been circulated yet.April 11, 2016 at 2:07 am #3050yedaoxiang@sina.comParticipantHi rejsharp – a series of problem about SCIO,can you help me to solve? Please see the following Attachments.
Attachments:
You must be logged in to view attached files.April 11, 2016 at 7:27 pm #3055rejsharpParticipantHi Yedaoxiang:-
I am sorry but your questions are very unclear.
I have no idea what you mean about “orange” whilst you are displaying the attributes of a cheese collection.
Orange can mean a fruit or a colour, and has little do with cheese.Can you say clearly what you are trying to do?
You cannot download the raw spectra unless you have a Reseacher licence. Most people will NOT find the raw spectra helpful.
Consumer Physics provide the Cheese collection as an example. You can copy the structure to a new collection and make your own either for cheese, or by changing the attributes for other materials.
The advantage of cheese and similar dairy products is that you can use the values from the nutritional information on the wrappers. This is good enough to learn the ideas, but totally bad for a real model – because those values will be rather inexact.
Roger
April 12, 2016 at 7:14 am #3060AyeletKeymasterHi Yedaoxiang,
The attributes values should be based on known values, either taken from the product label or chemical analysis results.
SCiO is a learning device, it should be populated with the known values so that the machine learning algorithms can be applied in order to create a model.
Ayelet,
The Consumer Physics Team
April 12, 2016 at 8:48 am #3064yedaoxiang@sina.comParticipantHi rejsharp and Ayelet,
Take Apple for example,How should I create apple sample attribute? and how to get a attribute value?
April 12, 2016 at 5:00 pm #3067rejsharpParticipantHi yedaoxiang!
I am rally sorry, but you are not giving enough information about what you are trying to do.
a) Are you trying to make a new collection featuring apples?
b) What is your objective?c) Do you understand how to set up a new collection.
d) Do you understand that value attributes need you to have values to enter?
Maybe an example would be good.
If you wanted to create a collection on sweetness of fruit it could be very simple.First attribute could be Fruit type (mandatory string from List) – here you enter the fruits you want to test.
Second attribute could be sugar content (mandatory, value, concentration %.
– you would need a method of determining the exact sugar content – a $25 refractometer would do.
Third attribute could be sample ID (mandatory string) – here you would enter a unique ID per sample.
Fourth attribute maybe a Notes field (not mandatory string)
After creation of the empty collection, buy a lot of different Apples no more than three of the same type from any one shop
Start scanning, and during each sample squeeze some juice for the refractometer to get the independant sugar content reading
(I would cut the apple in half, and use half for the scanning, an half for the juice.)In this way you will build up a collection of scans for different sweetnesses.
When you have a lot of scans you can create the model based on sugar content to see if it works.
is this helpful?
-
AuthorPosts
- You must be logged in to reply to this topic.