This master's thesis is about the design and development of a flower pot sensor, which monitors data related to the cultivation of houseplants. The sensor sends the data to the cloud, where the analysis is performed and the evaluated living conditions of the monitored plant are displayed to the user.

This article draws analogies between the activities of statisticians and of chefs. It suggests how these analogies can be used in teaching, both to help understanding of what statistics is about and to increase motivation to learn the subject.

Intraday stock trading is an infamously difficult and risky strategy. Momentum and reversal strategies and long short-term memory (LSTM) neural networks have been shown to be effective for selecting stocks to buy and sell over time periods of multiple days. To explore whether these strategies can be effective for intraday trading, their implementations were simulated using intraday price data for stocks in the S&P 500 index, collected at 1-second intervals between February 11, 2021 and March 9, 2021 inclusive. The study tested 160 variations of momentum and reversal strategies for profitability in long, short, and market-neutral portfolios, totaling 480 portfolios. Long and short portfolios for each strategy were also compared to the market to observe excess returns. Eight reversal portfolios yielded statistically significant profits, and 16 yielded significant excess returns. Tests of these strategies on another set of 16 days failed to yield statistically significant returns, though average returns remained profitable. Four LSTM network configurations were tested on the same original set of days, with no strategy yielding statistically significant returns. Close examination of the stocks chosen by LSTM networks suggests that the networks expect stocks to exhibit a momentum effect. Further studies may explore whether an intraday reversal effect can be observed over time during different market conditions and whether different configurations of LSTM networks can generate significant returns.

Spectral density function (SDF) plays a critical role in spatio-temporal data analysis, where the data are analyzed in the frequency domain. Although many methods have been proposed for SDF estimation, real-world applications in many research fields, such as neuroscience and environmental science, call for better methodologies. In this thesis, we focus on the spectral density functions for time series and spatial data, develop new estimation algorithms, and use the estimators as features for clustering and classification purposes. The first topic is motivated by clustering electroencephalogram (EEG) data in the spectral domain. To identify synchronized brain regions that share similar oscillations and waveforms, we develop two robust clustering methods based on the functional data ranking of the estimated SDFs. The two proposed clustering methods use different dissimilarity measures and their performance is examined by simulation studies in which two types of contaminations are included to show the robustness. We apply the methods to two sets of resting-state EEG data collected from a male college student. Then, we propose an efficient collective estimation algorithm for a group of SDFs. We use two sets of basis functions to represent the SDFs for dimension reduction, and then, the scores (the coefficients of the basis) estimated by maximizing the penalized Whittle likelihood are used for clustering the SDFs in a much lower dimension. For spatial data, an additional penalty is applied to the likelihood to encourage the spatial homogeneity of the clusters. The proposed methods are applied to cluster the EEG data and the soil moisture data. Finally, we propose a parametric estimation method for the quantile spectrum. We approximate the quantile spectrum by the ordinary spectral density of an AR process at each quantile level. The AR coefficients are estimated by solving Yule- Walker equations using the Levinson algorithm. Numerical results from simulation studies show that the proposed method outperforms other conventional smoothing techniques. We build a convolutional neural network (CNN) to classify the estimated quantile spectra of the earthquake data in Oklahoma and achieve a 99.25% accuracy on testing sets, which is 1.25% higher than using ordinary periodograms.

No description available.

No

No

The design of mineral processing circuits is a complex, open-ended process.  While several tools and methodologies are available, extensive data collection accompanied with trial-and-error simulation are often the predominant technical measures utilized throughout the process.  Unfortunately, this approach often produces sub-optimal solutions, while squandering time and financial resources.  This work proposes several new and refined methodologies intended to assist during all stages of circuit design.  First, an algorithm has been developed to automatically determine circuit analytical solutions from a user-defined circuit configuration.  This analytical solution may then be used to rank circuits by traditional derivative-based linear circuit analysis or one of several newly proposed objective functions, including a yield indicator (the yield score) or a value-based indicator (the moment of inertia). Second, this work presents a four-reactor flotation model which considers both process kinetics and machine carrying capacity.  The simulator is suitable for scaling laboratory data to predict full-scale performance.  By first using circuit analysis to reduce the number of design alternatives, experimental and simulation efforts may be focused to those configurations which have the best likelihood of enhanced performance while meeting secondary process objectives.  Finally, this work verifies the circuit analysis methodology through a virtual experimental analysis of 17 circuit configurations.  A hypothetical electrostatic separator was implemented into a dynamic physics-based discrete element modeling environment.  The virtual experiment was used to quantify the selectivity of each circuit configuration, and the final results validate the initial circuit analysis projections. / Ph. D.

The improved spectral resolution of modern hyperspectral sensors provides a means for discriminating subtly different classes of on ground materials in remotely sensed images. However, in order to obtain statistically reliable classification results, the number of necessary training samples can increase exponentially as the number of spectral bands increases. Obtaining the necessary number of training signals for these high-dimensional datasets may not be feasible. The problem can be overcome by preprocessing the data to reduce the dimensionality and thus reduce the number of required training samples. In this thesis, three dimensionality reduction methods, all based on parametric projection pursuits, are investigated. These methods are the Sequential Parametric Projection Pursuits (SPPP), Parallel Parametric Projection Pursuits (PPPP), and Projection Pursuits Best Band Selection (PPBBS). The methods are applied to very high spectral resolution data to transform the hyperspectral data to a lower-dimension subspace. Feature extractors and classifiers are then applied to the lower-dimensional data to obtain target detection accuracies. The three projection pursuit methods are compared to each other, as well as to the case of using no dimensionality reduction preprocessing. When applied to hyperspectral data in a precision agriculture application, discriminating sicklepod and cocklebur weeds, the results showed that the SPPP method was optimum in terms of accuracy, resulting in a classification accuracy of >95% when using a nearest mean, maximum likelihood, or nearest neighbor classifier. The PPPP method encountered optimization problems when the hyperspectral dimensionality was very high, e.g. in the thousands. The PPBBS method resulted in high classification accuracies, >95%, when the maximum likelihood classifier was utilized; however, this method resulted in lower accuracies when the nearest mean or nearest neighbor classifiers were used. When using no projection pursuit preprocessing, the classification accuracies ranged between ~50% and 95%; however, for this case the accuracies greatly depended on the type of classifier being utilized.

No description available.