I believe (as do many others) that these two topics are crucial to unraveling key information from data mining results, especially biological DM. However, my observation is that these 2 key topics are not getting the attention they deserve in the biology and medical communities - please correct me if I am wrong....
Terms like "signal" and "noise" are probably more common in engineering. In biomedical sciences, people would rather use terms like "machine learning", "models", "model testing", "statistical significance". The goal is usually to build a mathematical model that would be able to predict an outcome of a biological/medical experiment from experimental conditions. A good practice is then to calculate how probable would be to obtain a predicted outcome using a null model. The null model is usually some kind of randomness, that is, noise.
Here are just couple (of many) example of books on this subject:
https://books.google.com/books?id=ektozphE8GYC&printsec=frontcover&source=gbs_ViewAPI#v=onepage&q&f=false
https://books.google.com/books?id=v_06DwAAQBAJ&printsec=frontcover&source=gbs_ViewAPI#v=onepage&q&f=false
@DmitriKireev: When mathematically modeled (abstracted), engineering and biomedical problems become indistinguishable. This is the beauty (and elegance!) of using mathematics -- abstraction of the problem.
I agree. I just meant that if one's looking for books on signal detection in biomedical sciences then different keywords need to be used.
@DmitriKireev: I am actually using electrical engineering, applied mathematics and mathematical physics books & treatises when studying signal detection theory and signal optimization methods, because, as I have mentioned in my original question, these subjects are not popular (and at times, completely unheard of) among biomedical researchers and life scientists.
- Badges
- Science topic
- Similar topics
- Books