docs: use synonyms for affect and reword relearning part

Author: danfke

docs/final-report/final-report.pdf

@@ -72,9 +72,9 @@ $$P_{\text{Noise}} = \text{Power of noise}$$
 
 Once the refinement process is done, the refined separation vector is accepted based on a user-defined threshold of either the silhouette score between the signal and the noise or the pulse-to-noise ratio. The silhouette score is defined in **\@ref(eq:sil)** and is calculated using the signal and noise clusters in the MUSTs [@negro_muceli_castronovo_holobar_farina_2016]. The pulse-to-noise ratio is defined in **\@ref(eq:pnr)**. The accepted separation vectors correspond to the MUs that the blind source separation algorithm extracts from the raw signal.
 
-A further improvement to the algorithm that we did not have time to implement would be a re-learning feature. The user would run the algorithm on a sample of the data, and then identify inaccurate firing times (false positives) based on physiological limits of MU firing rates. The algorithm would use this information to no longer make similar mistakes in the rest of the decomposition. Implementing this feature would be quite complex because it is unclear how this would be implemented programmatically.
+A further improvement to the algorithm that we did not have time to implement would be a re-learning feature. The user would run the algorithm on a sample of the data, and then identify inaccurate firing times (false positives) based on physiological limits of MU firing rates. The algorithm would use this information to no longer make similar mistakes in the rest of the decomposition. Implementing this feature would be quite complex because it is unclear how this would be programmed into the algorithm.
 
-The stakeholders affected by our blind source separation algorithm are researchers and those that would be affected by their research. This is why our algorithm must work properly so that researchers' results are accurate and do not affect the general public adversely down the line. For example, if someone uses `EMGdecomPy` and obtains inaccurate results which are  used to inform a neuromuscular diagnosis, it could greatly affect someone's life. Periodically, the results of our algorithm should be compared to others to obtain a second opinion on the decomposition of the EMG signal. 
+The stakeholders affected by our blind source separation algorithm are researchers and those that rely on their research. This is why our algorithm must work properly so that researchers' results are accurate and do not impact the general public adversely down the line. For example, if someone uses `EMGdecomPy` and obtains inaccurate results which are used to inform a neuromuscular diagnosis, it could greatly affect someone's life. Periodically, the results of our algorithm should be compared to others to obtain a second opinion on the decomposition of the EMG signal. 
 
 The data provided by @Hug2021 contains EMGs and their decomposition results from many different muscles at different voluntary muscle contraction intensities (100% being the most intensely the subject can contract their muscle). We have not had the chance to thoroughly validate our algorithm using this data, as the debugging process took a great deal of time. We have only received qualitative results, obtained by visually comparing MUAP shapes identified by `EMGdecomPy` and those @Hug2021 identified using `DEMUSE`, a commercial software created by @holobar_2016. There are concerns with this approach as `DEMUSE` uses a similar but different algorithm than @negro_muceli_castronovo_holobar_farina_2016. `DEMUSE` is a highly used software in comparison to `OTBioLab+`, and therefore the partner wishes to compare our results to theirs.