Filtering by
- All Subjects: Machine Learning
- Creators: Electrical Engineering Program
To reduce the cost of silicon solar cells and improve their efficiency, it is crucial to identify and understand the defects limiting the electrical performance in silicon wafers. Bulk defects in semiconductors produce discrete energy levels within the bandgap and may act as recombination centers. This project investigates the viability of using machine learning for characterizing bulk defects in Silicon by using a Random Forest Regressor to extract the defect energy level and capture cross section ratios for a simulated Molybdenum defect and experimental Silicon Vacancy defect. Additionally, a dual convolutional neural network is used to classify the defect energy level in the upper or lower half bandgap.
![164815-Thumbnail Image.png](https://d1rbsgppyrdqq4.cloudfront.net/s3fs-public/styles/width_400/public/2022-05/164815-thumbnail-image.png?versionId=NKg2vzgj05fLW1DrTCdfzoFeSoxiF9Ik&X-Amz-Content-Sha256=UNSIGNED-PAYLOAD&X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=AKIASBVQ3ZQ42ZLA5CUJ/20240617/us-west-2/s3/aws4_request&X-Amz-Date=20240617T153608Z&X-Amz-SignedHeaders=host&X-Amz-Expires=120&X-Amz-Signature=7751d2189739ae3fd2f1280b079578a9693085abaee7621e46d63e8ded1acaf5&itok=sHq-kHEr)
This paper serves to report the research performed towards detecting PD and the effects of medication through the use of machine learning and finger tapping data collected through mobile devices. The primary objective for this research is to prototype a PD classification model and a medication classification model that predict the following: the individual’s disease status and the medication intake time relative to performing the finger-tapping activity, respectively.
![164816-Thumbnail Image.png](https://d1rbsgppyrdqq4.cloudfront.net/s3fs-public/styles/width_400/public/2022-05/164816-thumbnail-image.png?versionId=QdBUYDD4FlLZ56Sl31xsAuE0KzHyicpD&X-Amz-Content-Sha256=UNSIGNED-PAYLOAD&X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=AKIASBVQ3ZQ42ZLA5CUJ/20240617/us-west-2/s3/aws4_request&X-Amz-Date=20240617T153608Z&X-Amz-SignedHeaders=host&X-Amz-Expires=120&X-Amz-Signature=79c9bf5f93beed34af41de6b0ba520e83c64bcea1d7c0f52da7137397ad009c6&itok=oG2inSDM)
This paper serves to report the research performed towards detecting PD and the effects of medication through the use of machine learning and finger tapping data collected through mobile devices. The primary objective for this research is to prototype a PD classification model and a medication classification model that predict the following: the individual’s disease status and the medication intake time relative to performing the finger-tapping activity, respectively.
![165107-Thumbnail Image.png](https://d1rbsgppyrdqq4.cloudfront.net/s3fs-public/styles/width_400/public/2022-05/165107-thumbnail-image.png?versionId=n0jTg3BjgKvIOt5_Mnj8ERJEvvF6wZWF&X-Amz-Content-Sha256=UNSIGNED-PAYLOAD&X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=AKIASBVQ3ZQ42ZLA5CUJ/20240617/us-west-2/s3/aws4_request&X-Amz-Date=20240617T090923Z&X-Amz-SignedHeaders=host&X-Amz-Expires=120&X-Amz-Signature=31a062d14cbaa7fff532162caf2a67f5e5741d237efb3cd560c3a242f8cf7cef&itok=U1Vx4Tzx)
The stability of cheerleading stunts is crucial to athlete safety and team success. Consistency in stunt technique contributes to success in stunting skills, giving a team the tools to win competitions. Increased stunt technique reduces the chances of falls and the severity of those falls. Proper technique also prevents injuries caused by improper positions that place pressure on the lower back and shoulders. Bases must maintain strong technique with proper lines of support in order to maximize stunt stability. Through exploration of the EmbeddedML system, involving a neural network implemented using a SensorTile, cheerleading motions can be successfully classified. Using this system, it is possible to identify motions that result in both weak and injurious positions almost instantly. By alerting athletes to these incorrect motions, improper stunt technique can be corrected quickly and without the involvement of a coach. This automated technique correction would be incredibly beneficial to the sport of competitive cheerleading
![165468-Thumbnail Image.png](https://d1rbsgppyrdqq4.cloudfront.net/s3fs-public/styles/width_400/public/2022-05/165468-thumbnail-image.png?versionId=tM53.M0sH.fJ1PVndNvn3UUJkD4sCOOq&X-Amz-Content-Sha256=UNSIGNED-PAYLOAD&X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=AKIASBVQ3ZQ42ZLA5CUJ/20240617/us-west-2/s3/aws4_request&X-Amz-Date=20240617T153608Z&X-Amz-SignedHeaders=host&X-Amz-Expires=120&X-Amz-Signature=17b5e188533015a6b27687cf85506f0e5f6b5ae2c6bd26163bc687b6a5531392&itok=uZ0TnM9m)
![164938-Thumbnail Image.png](https://d1rbsgppyrdqq4.cloudfront.net/s3fs-public/styles/width_400/public/2022-05/164938-thumbnail-image.png?versionId=8gSnVaQors5F.Fchb.h9PLPjI6KRxWzT&X-Amz-Content-Sha256=UNSIGNED-PAYLOAD&X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=AKIASBVQ3ZQ42ZLA5CUJ/20240617/us-west-2/s3/aws4_request&X-Amz-Date=20240617T153609Z&X-Amz-SignedHeaders=host&X-Amz-Expires=120&X-Amz-Signature=75eed666896ab22f9fe91694d67123788f53393ea24018688ed8429477eb111f&itok=TMdRMqfV)
In wireless communication systems, the process of data transmission includes the estimation of channels. Implementing machine learning in this process can reduce the amount of time it takes to estimate channels, thus, resulting in an increase of the system’s transmission throughput. This maximizes the performance of applications relating to device-to-device communications and 5G systems. However, applying machine learning algorithms to multi-base-station systems is not well understood in literature, which is the focus of this thesis.
![161220-Thumbnail Image.png](https://d1rbsgppyrdqq4.cloudfront.net/s3fs-public/styles/width_400/public/2022-09/161220-Thumbnail%20Image.png?versionId=u.1JlHKgCbxK3jfB7CTwqOJ7lT6pGHnd&X-Amz-Content-Sha256=UNSIGNED-PAYLOAD&X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=AKIASBVQ3ZQ42ZLA5CUJ/20240617/us-west-2/s3/aws4_request&X-Amz-Date=20240617T153609Z&X-Amz-SignedHeaders=host&X-Amz-Expires=120&X-Amz-Signature=c10b9ea8e5001ef8d2390fb194657bef12e153e4000c33d24f0754a892b11551&itok=iozA_jtU)
Classification in machine learning is quite crucial to solve many problems that the world is presented with today. Therefore, it is key to understand one’s problem and develop an efficient model to achieve a solution. One technique to achieve greater model selection and thus further ease in problem solving is estimation of the Bayes Error Rate. This paper provides the development and analysis of two methods used to estimate the Bayes Error Rate on a given set of data to evaluate performance. The first method takes a “global” approach, looking at the data as a whole, and the second is more “local”—partitioning the data at the outset and then building up to a Bayes Error Estimation of the whole. It is found that one of the methods provides an accurate estimation of the true Bayes Error Rate when the dataset is at high dimension, while the other method provides accurate estimation at large sample size. This second conclusion, in particular, can have significant ramifications on “big data” problems, as one would be able to clarify the distribution with an accurate estimation of the Bayes Error Rate by using this method.
![147596-Thumbnail Image.png](https://d1rbsgppyrdqq4.cloudfront.net/s3fs-public/styles/width_400/public/2021-07/147596-Thumbnail%20Image.png?versionId=4f7pKCJRwFFgR.CVnUZf5lc35SUqYw4r&X-Amz-Content-Sha256=UNSIGNED-PAYLOAD&X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=AKIASBVQ3ZQ42ZLA5CUJ/20240617/us-west-2/s3/aws4_request&X-Amz-Date=20240617T153609Z&X-Amz-SignedHeaders=host&X-Amz-Expires=120&X-Amz-Signature=a6aa1fc0160de33753d66c45fa3718f4677b88347b31c10153cbe0544828bc96&itok=ZDS_F13L)
The increasing demand for clean energy solutions requires more than just expansion, but also improvements in the efficiency of renewable sources, such as solar. This requires analytics for each panel regarding voltage, current, temperature, and irradiance. This project involves the development of machine learning algorithms along with a data logger for the purpose of photovoltaic (PV) monitoring and control. Machine learning is used for fault classification. Once a fault is detected, the system can change its reconfiguration to minimize the power losses. Accuracy in the fault detection was demonstrated to be at a level over 90% and topology reconfiguration showed to increase power output by as much as 5%.