A global variable-permutation based approach for estimating tree transformation parameters used in phylogenetically controlled multivariate regression v1

This protocol provides a method to realize phylogenetic control in multivariate regression modeling while estimating tree transformation parameters en route. The protocol requires compiling a list of all possible variable combinations (at multiple model lengths) and iterating through these while estimating the transformation parameters along side the regression. A combination of AIC and the coefficient of determination can be used, for example, to select the "best" model from numerous possible model lengths. The average of the tree transformation parameters can then be used on these "best" models to perform the final phylogenetically controlled multivariate regression.

Globally Optimizing QAOA Circuit Depth for Constrained Optimization Problems

We develop a global variable substitution method that reduces n-variable monomials in combinatorial optimization problems to equivalent instances with monomials in fewer variables. We apply this technique to 3-SAT and analyze the optimal quantum unitary circuit depth needed to solve the reduced problem using the quantum approximate optimization algorithm. For benchmark 3-SAT problems, we find that the upper bound of the unitary circuit depth is smaller when the problem is formulated as a product and uses the substitution method to decompose gates than when the problem is written in the linear formulation, which requires no decomposition.

Removal of Phenols in Table Olive Processing Wastewater by Using a Mixed Inoculum of Candida boidinii and Bacillus pumilus: Effects of Inoculation Dynamics, Temperature, pH, and Effluent Age on the Abatement Efficiency

The main goal of this paper was to assess the ability of a combination of Candida boidinii and Bacillus pumilus to remove phenol in table olive processing water, as a function of some variables, like temperature, pH, a dilution of waste and the order of inoculation of the two microorganisms. At this purpose C. boidinii and B. pumilus were sequentially inoculated in two types of table olive processing water (fresh wastewater, FTOPW and wastewater stored for 3 months-aged wastewater, ATOPW). pH (6 and 9), temperature (10 and 35 °C) and dilution ratio (0, 1:1) were combined through a 2k fractional design. Data were modeled using two different approaches: Multifactorial Analysis of Variance (MANOVA) and multiple regression. A higher removal yield was achieved by inoculating B. pumilus prior to the yeast (192 vs. 127 mg/L); moreover, an increased efficiency was gained at 35 °C (mean removal of 200 mg/L). The use of two statistic approach suggested a different weight of variables; temperature was a global variable, that is a factor able to affect the yield of the process in all conditions. On the other hand, an alkaline pH could increase the removal of phenol at 10 °C (25–43%).

Progressive Open-Domain Response Generation with Multiple Controllable Attributes

It is desirable to include more controllable attributes to enhance the diversity of generated responses in open-domain dialogue systems. However, existing methods can generate responses with only one controllable attribute or lack a flexible way to generate them with multiple controllable attributes. In this paper, we propose a Progressively trained Hierarchical Encoder-Decoder (PHED) to tackle this task. More specifically, PHED deploys Conditional Variational AutoEncoder (CVAE) on Transformer to include one aspect of attributes at one stage. A vital characteristic of the CVAE is to separate the latent variables at each stage into two types: a global variable capturing the common semantic features and a specific variable absorbing the attribute information at that stage. PHED then couples the CVAE latent variables with the Transformer encoder and is trained by minimizing a newly derived ELBO and controlled losses to produce the next stage's input and produce responses as required. Finally, we conduct extensive evaluations to show that PHED significantly outperforms the state-of-the-art neural generation models and produces more diverse responses as expected.

Prediction of Power Outage Quantity of Distribution Network Users under Typhoon Disaster Based on Random Forest and Important Variables

Typhoons can have disastrous effects on power systems. They may lead to a large number of power outages for distribution network users. Therefore, this paper establishes a model to predict the power outage quantity of distribution network users under a typhoon disaster. Firstly, twenty-six explanatory variables (called global variables) covering meteorological factors, geographical factors, and power grid factors are considered as the input variables. On this basis, the correlation between each explanatory variable and response variable is analyzed. Secondly, we established a global variable model to predict the power outage quantity of distribution network users based on Random Forest (RF) algorithm. Then the importance of each explanatory variable is mined to extract the most important variables. To reduce the complexity of the model and ease the burden of data collection, eight variables are eventually selected as important variables. Afterward, we predict the power outage quantity of distribution network users again using the eight important variables. Thirdly, we compare the prediction accuracy of a model called the No-model that has been used before, Linear Regression (LR), Support Vector Regression (SVR), Decision Tree Regression (DTR), RF-global variable model, and RF-important variable model. Simulation results show that the RF-important variable model proposed in this paper has a better effect. Since fewer variables can save prediction time and make the model simplified, it is recommended to use the RF-important variable model.

Direct modeling of subway ridership at the station level: a study based on mixed geographically weighted regression

Station-level ridership modeling is one of the ways to forecast metro ridership and reveal how factors influence ridership. Previous studies assumed that the relationships between the dependent variable and independent variables are either global or local, as indicated by the global model or the geographically weighted regression (GWR) model. This study explores the possibility that some independent variables have spatially varying relationships with metro ridership while others have constant relationships by employing the mixed GWR model. Data from the Chicago metro system were used. To establish an effective forecasting model, possible influencing factors are collected. OLS model results indicate that the proportion of recreational jobs to total jobs, number of bus stops, employment density, number of high-income workers, and the type of station (transfer or terminal) are significant variables influencing station-level metro ridership. By using the mixed GWR model, we find that the proportion of recreational jobs to total jobs is a global variable while the others are local variables. By comparing the results of mixed GWR, full GWR, and OLS models, we find that mixed GWR fits the data better and the residuals are less correlated. However, results of cross-validation indicate that the prediction power of the OLS model is better than that of the full and mixed GWR models.