Filtering by
- All Subjects: Jazz
My nearly 10 month thesis project of trying to complete a study yielded considerable ‘learning opportunities’ in large part due to my inexperience. I made numerous errors in sequencing tasks, grossly under-scoping elapsed time and hours for other tasks, completely overlooking other critical tasks, and being insensitive to how irrelevant I and my project were to the many professionals whose help I needed to complete the study. Based upon the knowledge I gained through this process, I will describe the design of a future study of retrospective patient data that will assess whether PSC patients in Phoenix, Arizona follow racial/ethnic trends. I chose Phoenix as an ideal location to perform this proposed study because of the diverse racial/ethnic population in the greater Phoenix area. The goal will be to obtain and review 20 years of retrospective patient data from three large hospital groups in Phoenix, identify the races/ethnicities of PSC patients, and quantify the prevalence and incidence of PSC in such races/ethnicities. The lack of IRB uniformity among the subject hospitals/clinics will pose a challenge, but a detailed outline of how to approach the IRB approval process and obtain PSC patient data from each institution is provided.
The purpose of this project is to create a useful tool for musicians that utilizes the harmonic content of their playing to recommend new, relevant chords to play. This is done by training various Long Short-Term Memory (LSTM) Recurrent Neural Networks (RNNs) on the lead sheets of 100 different jazz standards. A total of 200 unique datasets were produced and tested, resulting in the prediction of nearly 51 million chords. A note-prediction accuracy of 82.1% and a chord-prediction accuracy of 34.5% were achieved across all datasets. Methods of data representation that were rooted in valid music theory frameworks were found to increase the efficacy of harmonic prediction by up to 6%. Optimal LSTM input sizes were also determined for each method of data representation.
My proposed project is an educational application that will seek to simplify the<br/>process of internalizing the chord symbols most commonly seen by those learning<br/>musical improvisation. The application will operate like a game, encouraging the<br/>user to identify chord tones within time limits and award points for successfully<br/>doing so.