NEW APPROACH FOR MODELING GENERALIZED MICROBIAL GROWTH CURVES USING ARTIFICIAL NEURAL NETWORKS

2000 ◽  
Vol 8 (4) ◽  
pp. 265-283 ◽  
Author(s):  
M.N. HAJMEER ◽  
I.A. BASHEER ◽  
J.L. MARSDEN ◽  
D.Y.C. FUNG
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Microbial Growth ◽  
Growth Curves ◽  
New Approach ◽  
Artificial Neural

A New Approach to Evaluating Business Ethics

2011 ◽  
pp. 23-39
Author(s):  
Mo Adam Mahmood ◽  
Gary L. Sullivan ◽  
Ray-Lin Tung
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Business Ethics ◽  
Ethical Decision ◽  
Ethical Decision Making ◽  
Exploratory Research ◽  
Multiple Discriminant Analysis ◽  
Comparative Performance ◽  
New Approach ◽  
Artificial Neural

Stimulated by recent high-profile incidents, concerns about business ethics have increased over the last decade. In response, research has focused on developing theoretical and empirical frameworks to understand ethical decision making. So far, empirical studies have used traditional quantitative tools, such as regression or multiple discriminant analysis (MDA), in ethics research. More advanced tools are needed. In this exploratory research, a new approach to classifying, categorizing and analyzing ethical decision situations is presented. A comparative performance analysis of artificial neural networks, MDA and chance showed that artificial neural networks predict better in both training and testing phases. While some limitations of this approach were noted, in the field of business ethics, such networks are promising as an alternative to traditional analytic tools like MDA.

Correcting Biases in Historical Bathythermograph Data Using Artificial Neural Networks

2020 ◽  
Vol 37 (10) ◽  
pp. 1781-1800
Author(s):  
Aaron Bagnell ◽  
Timothy DeVries
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Heat Content ◽  
Temperature Measurements ◽  
Multiple Sources ◽  
High Quality ◽  
New Approach ◽  
Calibration Methods ◽  
Artificial Neural ◽  
Instrument Comparison

AbstractHistorical estimates of ocean heat content (OHC) are important for understanding the climate sensitivity of the Earth system and for tracking changes in Earth’s energy balance over time. Prior to 2004, these estimates rely primarily on temperature measurements from mechanical and expendable bathythermograph (BT) instruments that were deployed on large scales by naval vessels and ships of opportunity. These BT temperature measurements are subject to well-documented biases, but even the best calibration methods still exhibit residual biases when compared with high-quality temperature datasets. Here, we use a new approach to reduce biases in historical BT data after binning them to a regular grid such as would be used for estimating OHC. Our method consists of an ensemble of artificial neural networks that corrects biases with respect to depth, year, and water temperature in the top 10 m. A global correction and corrections optimized to specific BT probe types are presented for the top 1800 m. Our approach differs from most prior studies by accounting for multiple sources of error in a single correction instead of separating the bias into several independent components. These new global and probe-specific corrections perform on par with widely used calibration methods on a series of metrics that examine the residual temperature biases with respect to a high-quality reference dataset. However, distinct patterns emerge across these various calibration methods when they are extrapolated to BT data that are not included in our cross-instrument comparison, contributing to uncertainty that will ultimately impact estimates of OHC.

Sign in / Sign up

Export Citation Format

Share Document