May 5, 2016 at 5:24 am #3154
I am new to the forums here but have been fallowing CS and there product since CES if not before then and just have a few questions on the developer side that i hope someone in the community will shed a little light on for me.. Apologizes if some of my questions are a little noobish i am no botanist or scientist but i do have a love for science & Tech and am a quick study.
My current understating of how a spectramator works and how it reads the chemical makeup/fingerprint of an item or martial is pretty solid other than this.
Say for ex i have 5 different kinds of tomatoes plants all different strains of tomatoes. Now say i forget to label each tomato if i scan each tomato will it simply out put that its a tomato plant with the makeup of chemical compounds in it ie water, nutrients, whatever makes up a tomato plant. Or will it give me a border read out such as this is a Azorean Red tomato with a chemical make up of these compounds….
Now if my understandings are right the scanner/app should out put this is an Azorean tomato, this is a Better boy tomato, this is a Black Cherry tomato etc with the fallowing chemical makeup of each, because even tho they are all tomatoes each variant of the tomato has its own gentiaclly different structure or fingerprint. Right? and then from there that data will show the makeup or contents of the tomato in question such as: 80% percent water, 8%fiber, 2%ash, 4%fructose 3%protein 3% glucose(not actual ratio of contents of a tomato)
My current understanding is this, SCiO database is, currently compromised of the 40 or more samples that the SCiO team has gathered on various foods, drinks, martial etc . SO say for example i scanned a breed of tomato but it just comes back and tells me its a tomato with contents of such and such but i know its a beefsteak how would i go about classifying this as a beefsteak tomato so the next time i or someone is a far away land scans a beefsteak tomato the results would say beefsteak tomato as a dev would that be where the model comes into play and i need o create a model and classifaction system right? if so how would i go about obating a solid bases of sample for others to refer to?
I am a developer who whats to create an app/database to identify different tomato plants but the SCiO database is lacking on the varies tomato’s and samples.. so how would/what would be the best method to go about collecting raw data viable data as a basis for others to refer to when they go to scan a tomato? Im aware i need to scan at least 40 different samples to get as accurate as possible readout( sorry if i just repeated myself. I was trying to word this more understandably.)
But now how does this work when say theirs a active chemical compound not yet classified in the SCiO database would you need to get a pure contraction of such compound to use for a gauge in regards to percent level outputs?
Also if you guys could tell i do not yet have my SCio devkit yet i wanna order it but was waiting to see if it was legit so far im liking what i see and wanna order one asap however are you guys shipping the devkits to those who haven’t backed you guys on kick starter and if not when do you plan on shipping out the devkits to devs who order through the site?
May 5, 2016 at 9:30 am #3162
- This topic was modified 7 years, 10 months ago by email@example.com.
Below is a detailed explanation regarding spectroscopy and how SCiO works. I believe it will clarify most of the issues:
SCiO includes a light source that illuminates the sample and an optical sensor called a spectrometer that collects the light reflected from the sample.
The spectrometer breaks down the light to its spectrum (the spectra), which includes all the information required to detect the result of this interaction between the illuminated light and the molecules in the sample. This means that SCiO analyses the overall spectra that is received and, comparing it to different algorithms and information provided, identifies or evaluates it.
For example, if you know the basic spectra of a watermelon, and then see that as the watermelon gets sweeter, meaning it has more sugar content, the spectra gradually changes in a specific manner, you will be able to build an algorithm in accordance.
In recognizing the existence of a specific material, such as marijuana, in a sample, you will need to see if the reflectance of the material changes in a specific manner when the marijuana is present. Thus, you will need two samples of the material – with and without marijuana.
The basic idea is that we look at the overall reflectance and the why it changes – we do not separate and analyse it per specific molecules, rather we look at the whole composition.
This is why if your chemical composition varies between samples significantly and not only because of the factor you wish to analyse, you will need more samples, as with saliva.
We suggest you check out https://www.consumerphysics.com/myscio/technology and https://www.consumerphysics.com/myscio/images/dynamic/pdf/Spectroscopy.pdf for further information on spectroscopy.
Specifically, as for tomatoes, 40 is the amount of samples that we mention as a rule of thumb as a properly sized collection for a feasibility test. However, a comprehensive application should be based on hundreds of samples and thousands of scans.
Since SCiO applies machine learning algorithms, it should be noted that building the database for such an application requires not only access to samples but also their chemical characteristics.
This can be done either by us or by the SCiO developer community using our SCiO Development Toolkit (DevKit), which allows users to create models and apps. More info about the DevKit can be found here and It can be purchased here.
Let me know if you have further questions.
The Consumer Physics TeamMay 6, 2016 at 6:43 am #3166
Okay yeah that helped out a lil more so okay so let me pose this question to you then. Cannabis or Marijuana has many active ingredients or cannaboids such as: THC, CBD, THCA etc would it in theroy be possibly to tell the percentage of THC in a cannabis strain… AND be able to classify it as to what strain it is. I understand that you would need many samples so if conditions were right plenty of samples and the chemical makeups (THC, CBD, CBN, THCA) of the strain of cannabis in theory would it be possible to create a Database that can analyze the chemical components and spit out answer.May 6, 2016 at 7:12 pm #3168
NVM i understand fully now Thank you very much when i first read this my brain wasn’t working right lolMay 8, 2016 at 6:43 am #3169
- You must be logged in to reply to this topic.