Filtering by
- All Subjects: Machine Learning
- All Subjects: Technology
- All Subjects: FMCW
- Creators: Electrical Engineering Program
- Member of: Barrett, The Honors College Thesis/Creative Project Collection
- Resource Type: Text
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.
There are quite a few readily available products that one can buy if one looks past some of their flaws. A lot of these alarms either require a user to carry an extra communication device, or they are too big or expensive. The proposed solution merges all desirable features of a bike alarm into one module. In light of this, surveys were conducted to ascertain what these qualities would need to be. The top considerations for purchasing this alarm were how costly it would be, the false detection rate, and also the battery life. Additionally, the features that were most requested was the inclusion of a GPS and a camera. In order to incorporate these features, a three year plan was formulated which would culminate into a bike network in which each bike could communicate with other bikes. This would allow for an IOT network to be established, thus far exceeding expectations. The price point for this alarm is USD $10.00-15.00 and can come in a variety of colors. Additionally, this concept can be applied to many different scenarios, from protecting boats/jet skis and other aquatic vehicles, to houses as well. Furthermore, one could miniaturize this technology to be used in jewelry or accessories.
This project considers the FPGA implementations of MLP and CNN feedforward. While FPGAs provide significant performance improvements, they come at a substantial financial cost. We explore the options of implementing these algorithms on a smaller budget. We successfully implement a multilayer perceptron that identifies handwritten digits from the MNIST dataset on a student-level DE10-Lite FPGA with a test accuracy of 91.99%. We also apply our trained network to external image data loaded through a webcam and a Raspberry Pi, but we observe lower test accuracy in these images. Later, we consider the requirements necessary to implement a more elaborate convolutional neural network on the same FPGA. The study deems the CNN implementation feasible in the criteria of memory requirements and basic architecture. We suggest the CNN implementation on the same FPGA to be worthy of further exploration.
Leveraging Machine Learning and Wireless Sensing for Robot Localization - Location Variance Analysis
Modern communication networks heavily depend upon an estimate of the communication channel, which represents the distortions that a transmitted signal takes as it moves towards a receiver. A channel can become quite complicated due to signal reflections, delays, and other undesirable effects and, as a result, varies significantly with each different location. This localization system seeks to take advantage of this distinctness by feeding channel information into a machine learning algorithm, which will be trained to associate channels with their respective locations. A device in need of localization would then only need to calculate a channel estimate and pose it to this algorithm to obtain its location.
As an additional step, the effect of location noise is investigated in this report. Once the localization system described above demonstrates promising results, the team demonstrates that the system is robust to noise on its location labels. In doing so, the team demonstrates that this system could be implemented in a continued learning environment, in which some user agents report their estimated (noisy) location over a wireless communication network, such that the model can be implemented in an environment without extensive data collection prior to release.