Margaret Hamilton

Sarah Almaghrabi, Mashud Rana, Margaret Hamilton et al.

Accurate and reliable prediction of Photovoltaic (PV) power output is critical to electricity grid stability and power dispatching capabilities. However, Photovoltaic (PV) power generation is highly volatile and unstable due to different reasons. The Wavelet Transform (WT) has been utilised in time series applications, such as Photovoltaic (PV) power prediction, to model the stochastic volatility and reduce prediction errors. Yet the existing Wavelet Transform (WT) approach has a limitation in terms of time complexity. It requires reconstructing the decomposed components and modelling them separately and thus needs more time for reconstruction, model configuration and training. The aim of this study is to improve the efficiency of applying Wavelet Transform (WT) by proposing a new method that uses a single simplified model. Given a time series and its Wavelet Transform (WT) coefficients, it trains one model with the coefficients as features and the original time series as labels. This eliminates the need for component reconstruction and training numerous models. This work contributes to the day-ahead aggregated solar Photovoltaic (PV) power time series prediction problem by proposing and comprehensively evaluating a new approach of employing WT. The proposed approach is evaluated using 17 months of aggregated solar Photovoltaic (PV) power data from two real-world datasets. The evaluation includes the use of a variety of prediction models, including Linear Regression, Random Forest, Support Vector Regression, and Convolutional Neural Networks. The results indicate that using a coefficients-based strategy can give predictions that are comparable to those obtained using the components-based approach while requiring fewer models and less computational time.

Farzana Afrin, Mohammad Saiedur Rahaman, Margaret Hamilton

The identification and analysis of student satisfaction is a challenging issue. This is becoming increasingly important since a measure of student satisfaction is taken as an indication of how well a course has been taught. However, it remains a challenging problem as student satisfaction has various aspects. In this paper, we formulate the student satisfaction estimation as a prediction problem where we predict different levels of student satisfaction and infer the influential predictors related to course and instructor. We present five different aspects of student satisfaction in terms of 1) course content, 2) class participation, 3) achievement of initial expectations about the course, 4) relevancy towards professional development, and 5) if the course connects them and helps to explore the real-world situations. We employ state-of-the-art machine learning techniques to predict each of these aspects of student satisfaction levels. For our experiment, we utilize a large student evaluation dataset which includes student perception using different attributes related to courses and the instructors. Our experimental results and comprehensive analysis reveal that student satisfaction is more influenced by course attributes in comparison to instructor related attributes.

Irvan B. Arief-Ang, Flora D. Salim, Margaret Hamilton

Human occupancy information is crucial for any modern Building Management System (BMS). Implementing pervasive sensing and leveraging Carbon Dioxide data from BMS sensor, we present Carbon Dioxide - Human Occupancy Counter (CD-HOC), a novel way to estimate the number of people within a closed space from a single carbon dioxide sensor. CD-HOC de-noises and pre-processes the carbon dioxide data. We utilise both seasonal-trend decomposition based on Loess and seasonal-trend decomposition with moving average to factorise carbon dioxide data. For each trend, seasonal and irregular component, we model different regression algorithms to predict each respective human occupancy component value. We propose a zero pattern adjustment model to increase the accuracy and finally, we use additive decomposition to reconstruct the prediction value. We run our model in two different locations that have different contexts. The first location is an academic staff room and the second is a cinema theatre. Our results show an average of 4.33% increment in accuracy for the small room with 94.68% indoor human occupancy counting and 8.46% increase for the cinema theatre in comparison to the accuracy of the baseline method, support vector regression.