Indoor light energy harvesting plays an important role in field of renewable energy. Indoor lighting condition is usually described by level of illumination. However, measured data alone does not by classification of different light sources, result is not representative. Energy harvesting system needs to be evaluated after classification to obtain more accurate value. This is also importance of different light source classification. In this thesis, a complete set of indoor light energy harvesting system is introduced, two models are proposed to evaluate energy, robustness is improved by mixing complex light condition during data collection. Main task of this thesis is to verify importance of indoor light classification. Main contribution of this thesis is to fill a gap in energy evaluation, and built a model with superior performance. In terms of collecting data, this thesis researches influence factor of data collection to ensure reliability of accuracy. This work can more accurately collect spectral under different light conditions. Finally, light energy is evaluated by classification of indoor light. This model is proven to be closer to true energy value under real condition. The result shows that classified data is more accurate than direct calculation of energy,it has a smaller error. In addition, performance of classifier model used in this thesis has been proven to be excellent, classifier model can still carry on high-accuracy classification when measurement data are not included in training data set. This makes it a low-cost alternative to measuring light condition without spectrometer.

<p dir="ltr">This dissertation aims to understand the academic outcome disparity between underrepresented minorities in higher education when compared to other racial groups. It seeks to address the social inequities in learning, college integration, and completion rate. The focus was narrowed to a specific marginalized community that represents first-generation underrepresented minority (FGURM) students, that is, students whose parents have not obtained a post-secondary degree and identified as belonging to the following racial or ethnic group: Blacks, Hispanics/Latinos, American Indians/Alaska Natives, Native Hawaiian/Pacific Islanders, and two or more races in the United States.</p><p dir="ltr">The overall objective was to explore with predictive models how demographic factors, pre-college academic performance, socioeconomic status, targeted programs aimed at fostering integration into campus communities, and support systems can increase the likelihood of academic success within this group. Predictive models based on supervised machine learning algorithms like Random Forest in combination with ensemble learning techniques like bagging and boosting was used to assess various predictors of successful academic outcomes. To address issues like incomplete and imbalanced data, a combination of case deletion and imputation methods, such as K-Nearest Neighbor (KNN), Linear Regression, and the Synthetic Minority Over-sampling Technique - Edited Nearest Neighbors (SMOTEENN), were utilized.</p><p dir="ltr">The results suggested that pre-college academic achievements, assessed through standardized test scores (ACT/SAT), along with demographic factors such as age, gender, and ethnicity, are significant predictors of cumulative grade point average (CGPA). Furthermore, a combination of test score and CGPA was identified as a strong predictor of graduation outcome. The research further showed that student involvement particularly in academic related organizations is vital for academic achievement. Other forms of student involvement, such as participation in cultural identity groups, service-oriented and recreational groups, were also significant predictors of positive academic outcomes. Moreover, specific academic disciplines, such as engineering and nursing, were recognized as significant predictors of graduation, especially for both male and female students.</p><p dir="ltr">This study concluded that improving K-12 education to boost college preparedness, especially for FGURM students, is vital for enhanced standardized test scores and academic success in college. Additionally, universities can enhance institutional commitment and attachment by creating a sense of belonging through programs focused on cultural and ethnic diversity, service, advocacy, and recreation as well as providing encouragement and opportunities for FGURM to participate in learning activities outside the traditional classroom setting, which can ultimately enhance FGURM students' academic achievement.</p>