Information Theoretic Analysis for Input Vector Selection in Black Box Modeling

2002 ◽  
Author(s):  
Brett Martin ◽  
Peter H. Meckl ◽  
Benjamin J. Zwissler
Keyword(s):  
Model Building ◽  
Mean Squared Error ◽  
Black Box ◽  
Input Vector ◽  
Data Sets ◽  
Theoretic Analysis ◽  
Validation Data ◽  
Information Theoretic ◽  
Past Data ◽  
The Relationship

When developing a black box model, the precise functional relationship between inputs and output is unknown. Engineers and scientists have turned to various regression tools in order to effectively capture the relationship based on past data observations. When modeling this data, however, it is important to only use inputs that provide information about the output. This paper presents a method of selecting the most informational input vectors for use in regression model building. This information-theoretic analysis for input vector selection requires only past data observations. Experimental results show that models built on the most informational input vectors produce less mean squared error on both training and validation data sets.

Predicting OSS Development Success

2013 ◽  
pp. 315-336
Author(s):  
Uzma Raja ◽  
Marietta J. Tretter
Keyword(s):  
User Involvement ◽  
Data Sets ◽  
Validation Data ◽  
Multiple Data ◽  
Competing Models ◽  
New Variables ◽  
End User Involvement ◽  
The Relationship ◽  
Communication Methods ◽  
Best Fit

Open Source Software (OSS) has reached new levels of sophistication and acceptance by users and commercial software vendors. This research creates tests and validates a model for predicting successful development of OSS projects. Widely available archival data was used for OSS projects from Sourceforge.net. The data is analyzed with multiple Data Mining techniques. Initially three competing models are created using Logistic Regression, Decision Trees and Neural Networks. These models are compared for precision and are refined in several phases. Text Mining is used to create new variables that improve the predictive power of the models. The final model is chosen based on best fit to separate training and validation data sets and the ability to explain the relationship among variables. Model robustness is determined by testing it on a new dataset extracted from the SF repository. The results indicate that end-user involvement, project age, functionality, usage, project management techniques, project type and team communication methods have a significant impact on the development of OSS projects.

SaltSeg: Automatic 3D salt segmentation using a deep convolutional neural network

2019 ◽  
Vol 7 (3) ◽  
pp. SE113-SE122 ◽  
Author(s):  
Yunzhi Shi ◽  
Xinming Wu ◽  
Sergey Fomel
Keyword(s):  
Large Scale ◽  
Model Building ◽  
Ground Truth ◽  
Velocity Model ◽  
Training Data ◽  
Data Sets ◽  
Validation Data ◽  
Data Set ◽  
Seismic Image ◽  
Data Generator

Salt boundary interpretation is important for the understanding of salt tectonics and velocity model building for seismic migration. Conventional methods consist of computing salt attributes and extracting salt boundaries. We have formulated the problem as 3D image segmentation and evaluated an efficient approach based on deep convolutional neural networks (CNNs) with an encoder-decoder architecture. To train the model, we design a data generator that extracts randomly positioned subvolumes from large-scale 3D training data set followed by data augmentation, then feed a large number of subvolumes into the network while using salt/nonsalt binary labels generated by thresholding the velocity model as ground truth labels. We test the model on validation data sets and compare the blind test predictions with the ground truth. Our results indicate that our method is capable of automatically capturing subtle salt features from the 3D seismic image with less or no need for manual input. We further test the model on a field example to indicate the generalization of this deep CNN method across different data sets.

Predicting OSS Development Success

2011 ◽  
Vol 2 (4) ◽  
pp. 27-48
Author(s):  
Uzma Raja ◽  
Marietta J. Tretter
Keyword(s):  
User Involvement ◽  
Data Sets ◽  
Validation Data ◽  
Final Model ◽  
Multiple Data ◽  
Competing Models ◽  
New Variables ◽  
End User Involvement ◽  
The Relationship ◽  
Communication Methods

Open Source Software (OSS) has reached new levels of sophistication and acceptance by users and commercial software vendors. This research creates tests and validates a model for predicting successful development of OSS projects. Widely available archival data was used for OSS projects from Sourceforge.net. The data is analyzed with multiple Data Mining techniques. Initially three competing models are created using Logistic Regression, Decision Trees and Neural Networks. These models are compared for precision and are refined in several phases. Text Mining is used to create new variables that improve the predictive power of the models. The final model is chosen based on best fit to separate training and validation data sets and the ability to explain the relationship among variables. Model robustness is determined by testing it on a new dataset extracted from the SF repository. The results indicate that end-user involvement, project age, functionality, usage, project management techniques, project type and team communication methods have a significant impact on the development of OSS projects.

Theoretical, methodological and practical issues of choice models

2018 ◽  
Vol 1 (1) ◽  
pp. 21-37
Author(s):  
Bharat P. Bhatta
Keyword(s):  
Discrete Choice ◽  
Model Building ◽  
Estimation Method ◽  
Choice Models ◽  
Discrete Choice Models ◽  
Decision Makers ◽  
Model Formulation ◽  
Random Utility Maximization ◽  
The Relationship ◽  
Method Model

This paper analyzes and synthesizes the fundamentals of discrete choice models. This paper alsodiscusses the basic concept and theory underlying the econometrics of discrete choice, specific choicemodels, estimation method, model building and tests, and applications of discrete choice models. Thiswork highlights the relationship between economic theory and discrete choice models: how economictheory contributes to choice modeling and vice versa. Keywords: Discrete choice models; Random utility maximization; Decision makers; Utility function;Model formulation

ANALYSIS OF THE INFLUENCE OF DIMENSIONS OF THE ROPE MIDWATER TRAWLS ON THEIR PERFORMANCE SUBJECT TO GEOMETRIC PROPERTIES OF CONE SHELLS

2017 ◽  
pp. 25-33
Author(s):  
Alexander Vasilievich Dvernik
Keyword(s):  
Surface Properties ◽  
Conical Shell ◽  
Side Surface ◽  
Theoretic Analysis ◽  
Good Convergence ◽  
Large Size ◽  
Quality Coefficient ◽  
Geometric Quality ◽  
The Relationship ◽  
Parameters Calculation

The article studies different shell constructions of mid-water trawls and their properties. The problem settled is suggested to be solved taking into account real geometric interrelations between spacious and surface properties of cone shells. The author suggests to accept a so-called geometric quality coefficient as a criterion of the properties of a conical shell, which represents the ratio of the shell to the area of its side surface and by analogy to use it to the shell of the trawl. The relationship between the trawl dimensions and geometric quality coefficient have been studied. Comparing these figures with the actual characteristics of trawls showed good convergence. According to the results of theoretic analysis and parameters calculation, trawl large-size shells will always have advantages in geometric characteristics over mid-size and, especially, small-size shells. The results of the analysis can be used for approximate calculations of the parameters of the trawl and justification of ways to improve the performance of existing mid-water trawls.

The visual arrays task…visual storage capacity or attention control?

2019 ◽  
Author(s):  
Jessie Martin ◽  
Jason S. Tsukahara ◽  
Christopher Draheim ◽  
Zach Shipstead ◽  
Cody Mashburn ◽  
...  
Keyword(s):  
Working Memory ◽  
Storage Capacity ◽  
Working Memory Capacity ◽  
Memory Capacity ◽  
Attention Control ◽  
Data Sets ◽  
Independent Data ◽  
Visual Storage ◽  
Design Selection ◽  
The Relationship

**The uploaded manuscript is still in preparation** In this study, we tested the relationship between visual arrays tasks and working memory capacity and attention control. Specifically, we tested whether task design (selection or non-selection demands) impacted the relationship between visual arrays measures and constructs of working memory capacity and attention control. Using analyses from 4 independent data sets we showed that the degree to which visual arrays measures rely on selection influences the degree to which they reflect domain-general attention control.

Epidemiological Evidence that Maternal Influenza Contributes to the Aetiology of Schizophrenia

1993 ◽  
Vol 163 (4) ◽  
pp. 522-534 ◽  
Author(s):  
W. Adams ◽  
R. E. Kendell ◽  
E. H. Hare ◽  
P. Munk-Jørgensen
Keyword(s):  
Data Sets ◽  
Time Lags ◽  
Epidemiological Evidence ◽  
Intrauterine Development ◽  
Increased Risk ◽  
Schizophrenic Patients ◽  
The Relationship ◽  
Monthly Incidence ◽  
Maternal Influenza

The epidemiological evidence that the offspring of women exposed to influenza in pregnancy are at increased risk of schizophrenia is conflicting. In an attempt to clarify the issue we explored the relationship between the monthly incidence of influenza (and measles) in the general population and the distribution of birth dates of three large series of schizophrenic patients - 16 960 Scottish patients born in 1932–60; 22 021 English patients born in 1921–60; and 18 723 Danish patients born in 1911–65. Exposure to the 1957 epidemic of A2 influenza in midpregnancy was associated with an increased incidence of schizophrenia, at least in females, in all three data sets. We also confirmed the previous report of a statistically significant long-term relationship between patients' birth dates and outbreaks of influenza in the English series, with time lags of - 2 and - 3 months (the sixth and seventh months of pregnancy). Despite several other negative studies by ourselves and others we conclude that these relationships are probably both genuine and causal; and that maternal influenza during the middle third of intrauterine development, or something closely associated with it, is implicated in the aetiology of some cases of schizophrenia.

Information Theoretic Analysis and Performance Gains of 3-Color Shift Keying

2021 ◽  
pp. 1-1
Author(s):  
Alexandros E. Tzikas ◽  
Panagiotis D. Diamantoulakis ◽  
George K. Karagiannidis
Keyword(s):  
Theoretic Analysis ◽  
Information Theoretic ◽  
Color Shift ◽  
Shift Keying ◽  
And Performance ◽  
Performance Gains
Sign in / Sign up

Export Citation Format

Share Document