[vapor]

I ordered one but missed the pre order so mine will be here in march....
I have been chatting with the company nice fellers....
here is a radio interview
https://www.cannainsider.com/daniel-yazbeck-cdx/

They say it will not be as precise as a big GCMS or hplc etc. So from what i understand they are letting the beta testers out very soon. And they are going to use the feedback over the next few months to tweek unit for the march release....

[Pangea]

It sounds like its trying to match samples to pre existing database of strains, which sounds like the cannabinoid analysis would be based on pre existing averaged data from GC and LC methods.

I hope im wrong though...

[vapor]

I think it is actually giving you a % of cannabanoids of terpenes aka chemical profile. via the sample you put in the sampler. so as you sample the plant as it grows you will see the % changing.

[Pangea]

That would be sweet!

[audiohi]

This is from a CDx Life email

Data Analysis and Sensor Algorithm Development
Our current strain match software utilizes a proprietary algorithm that leverages Support Vector Machine (SVM) methodology. These are supervised learning models with associated learning algorithms that analyze data and recognize patterns, used for classification and regression analysis. With the Data that AZ Med (our partner testing lab) populates, the text documents are taken and input into a directory. The software processes the data in the text documents and passes it through the SVM algorithm. The algorithm predicts the strain based upon learned training sets and outputs the processed data identifying it's strain name. If no strain is found, the software will indicate an unidentified match.

Results
Based upon the current database (over 250 samples tested), and the current algorithm developed, we can identify and match strains with an accuracy of 90%. Meaning out of 100 samples that will be analyzed via a MyDx unit, 90 are accurately identified. As we continue to populate the database, we can continue conditioning and monitoring this accuracy. The many more samples we plan on testing before December will drive this number closer to 100% accuracy for strain match. We will reach this goal by by increasing the sample size and number of scans per sample.


Here's an interview with the CEO

https://cdxlife.com/an-interview-of-...-cannainsider/

[amannamedtruth]

LOL, you can't match strains simply by cannabinoid and terpene profile. I'd like to see this machine try to tell the diff. between Sour D and Headband.

[lumberjack.mr]

gry ?

[oldchuck]

Update: The company has published its most comprehensive report on the device yet, You can find it here:

https://us3.campaign-archive1.com/?u=...&id=87610fb7fa

I am expecting mine any day now.

[mccleud]

Hi Oldchuck,

So, what do you thing about the mydx?

[exploziv]

Well, by reading that I get that they are behind on it.. and they just showed us sampling will cost more than anticipated, cause sensor life is under 6 months and every samples need the clean sample box to be contained in for testing. not so easy and cheap to use as they lead us to belive before.