Missouri University of Science and Technology

About: Missouri University of Science and Technology is a education organization based out in Rolla, Missouri, United States. It is known for research contribution in the topics: Control theory & Artificial neural network. The organization has 9380 authors who have published 21161 publications receiving 462544 citations. The organization is also known as: Missouri S&T & University of Missouri–Rolla.

Homogeneous nucleation rate measurements for water over a wide range of temperature and nucleation rate

Abstract: An expansion cloud chamber was used to measure the homogeneous nucleation rate for water over a wide range of temperature from 230–290 K and nucleation rates of 1–106 drops cm−3 s−1. The comprehensive and extensive nature of this data allows a much more detailed comparison between theory and experiment than has previously been possible. The expansion chamber technique employs continuous pressure measurement and an adiabatic pulse of supersaturation to give the time history of supersaturation and temperature during the nucleation. The resulting drop concentration is determined using photographic techniques. The experimental observations are presented in tabular form and from them an empirical nucleation rate formula is determined: J=S2 exp[328.124−5.582 43T+0.030 365T2−5.0319E−5T3 −(999.814−4.100 87 T+3.010 84E−3 T2)ln−2S], where J is the nucleation rate in units of drops cm−3 s−1. S is the supersaturation ratio and T is the temperature in K.

Spin coating epitaxial films.

Abstract: Spin-coated films, such as photoresists for lithography or perovskite films for solar cells, are either amorphous or polycrystalline. We show that epitaxial films of inorganic materials such as cesium lead bromide (CsPbBr3), lead(II) iodide (PbI2), zinc oxide (ZnO), and sodium chloride (NaCl) can be deposited onto a variety of single-crystal and single-crystal-like substrates by simply spin coating either solutions of the material or precursors to the material. The out-of-plane and in-plane orientations of the spin-coated films are determined by the substrate. The thin stagnant layer of supersaturated solution produced during spin coating promotes heterogeneous nucleation of the material onto the single-crystal substrate over homogeneous nucleation in the bulk solution, and ordered anion adlayers may lower the activation energy for nucleation on the surface. The method can be used to produce functional materials such as inorganic semiconductors or to deposit water-soluble materials such as NaCl that can serve as growth templates.

Predicting the daily return direction of the stock market using hybrid machine learning algorithms

Abstract: Big data analytic techniques associated with machine learning algorithms are playing an increasingly important role in various application fields, including stock market investment. However, few studies have focused on forecasting daily stock market returns, especially when using powerful machine learning techniques, such as deep neural networks (DNNs), to perform the analyses. DNNs employ various deep learning algorithms based on the combination of network structure, activation function, and model parameters, with their performance depending on the format of the data representation. This paper presents a comprehensive big data analytics process to predict the daily return direction of the SPDR S&P 500 ETF (ticker symbol: SPY) based on 60 financial and economic features. DNNs and traditional artificial neural networks (ANNs) are then deployed over the entire preprocessed but untransformed dataset, along with two datasets transformed via principal component analysis (PCA), to predict the daily direction of future stock market index returns. While controlling for overfitting, a pattern for the classification accuracy of the DNNs is detected and demonstrated as the number of the hidden layers increases gradually from 12 to 1000. Moreover, a set of hypothesis testing procedures are implemented on the classification, and the simulation results show that the DNNs using two PCA-represented datasets give significantly higher classification accuracy than those using the entire untransformed dataset, as well as several other hybrid machine learning algorithms. In addition, the trading strategies guided by the DNN classification process based on PCA-represented data perform slightly better than the others tested, including in a comparison against two standard benchmarks.