Forum Replies Created
-
Posts
-
Thanks Ayelet, Below are answers to your questions.
1. Have you scanned new samples in different temperatures? (specifically different temperatures than measured when collecting the database). I SCANNED THE COLLECTION SAMPLES AND TEST SAMPLES UNDER THE SAME CONDITION. THE TEMPERATURE MIGHT BE SLIGHTLY DIFFERENT AS I DID NOT TRY TO CONTROL THE TEMPERATURE EXACTLY.
2. Have you used actual different samples or scanned multiple scans for identical samples and referred them as new samples? I USED THE SAME PHYSICAL SAMPLE FOR 3 DATA COLLECTION SAMPLES (THE PHYSICAL SAMPLE IS JUST POSITIONED DIFFERENTLY IN EACH DATA COLLECTION SAMPLE). SO IN MY DATA COLLECTION, I HAVE 48 SAMPLES. THAT’S ACTUALLY FROM 16 DIFFERENT PHYSICAL SAMPLES.
3. Did you use the solid sample holder? I USED THE SOLID SAMPLE HOLDER. I’M ATTACHING PICTURES. I FIRST CRUSHED THE RICE SAMPLES INTO POWDERS AND FILLED THE SOLID SAMPLE HOLDER WITH 4 GRAMS OF POWDER.
Ayelet, I added more samples to the database. Now it contains 48 samples (12 samples of 4 brands each). I still have a fairly high correlation (F1=0.96), but when i go and test the model, the performance is not accurate. not even close. Please see the attached file. I would appreciate it if you can point me in the right direction.
Thanks. Can you answer the question below?
Also, i saw that i need at least 40 samples to make a model. How do people get the meta data for 40 samples? isn’t that a pretty expensive and difficult proposition? They would need lab test reports on all these 40 samples?
Ayelet, the correlation is actually very high despite the small size of the database. Why would the performance be weak if the correlation is high?
Thank you Ayelet.
Which pre-processing method is best for powder form? I plan to crush the rice grains into fine powder and use the small items container to collect data. This would allow me to control the consistency of the measurement conditions.
Also, i saw that i need at least 40 samples to make a model. How do people get the meta data for 40 samples? isn’t that a pretty expensive and difficult proposition? They would need lab test reports on all these 40 samples?
