diff options
| author | sotech117 <michael_foiani@brown.edu> | 2023-05-11 01:55:51 -0400 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-05-11 01:55:51 -0400 |
| commit | 2dfe71733cff155670456efe0572da10e53cfea8 (patch) | |
| tree | d1cd38bd5a7efbcd745abc3de99f07e23c2ff7b1 | |
| parent | 6181c4e264b048c073dc6219d78bbd1e68bfa891 (diff) | |
Update README.md - typo fixes
| -rw-r--r-- | README.md | 2 |
1 files changed, 1 insertions, 1 deletions
@@ -1,5 +1,5 @@ # oscilloscope -This oscilliscope uses artifical intelligence to more accurately measure the fundamental frequnciy of a sound wave based in the enviorment of Providence Rhode Island on a fine Spring day. +This oscilliscope uses artifical intelligence to more accurately measure the fundamental frequency of a sound wave based in the environment of Providence Rhode Island on a fine Spring day. ## Motivations As we were measuring the frequncies of tuning forks with electronic software, we found there to be a disparity between the frequency number on the tuning fork versus that of the computer. Hence, we deduced that somewhere in the middle would be the true frequency (since the computer was reading much too high), but the computer's microphone was not sensitive enough to read the true value. We believe an neural net applying multilinear regression would be able to fill in the gap to more accurealy meaure which frequncy the tuning fork is produced. by standardizing it's output values based on the input of multiple different, procured sounds - either tuning forks or perfect sin waves (from another computer). This is our basis for the neural network. |