AI Article Synopsis

  • This paper introduces a symbiotic adaptive neuro-evolutionary algorithm designed to create optimized neural network models specifically for hydrological modeling in the River Ouse catchment.
  • It enhances traditional methods by evolving individual neurons and allows experimentation with various objective functions, not just the standard sum squared error, which recent studies indicate may not yield the best models.
  • Results demonstrate that these evolved neural networks perform better than conventional models, particularly at longer lead times (6 and 24 hours), and highlight the limitations of using sum squared error as an objective function.

Article Abstract

This paper uses a symbiotic adaptive neuro-evolutionary algorithm to breed neural network models for the River Ouse catchment. It advances on traditional evolutionary approaches by evolving and optimising individual neurons. Furthermore, it is ideal for experimentation with alternative objective functions. Recent research suggests that sum squared error may not result in the most appropriate models from a hydrological perspective. Models are bred for lead times of 6 and 24 hours and compared with conventional neural network models trained using backpropagation. The algorithm is also modified to use different objective functions in the optimisation process: mean squared error, relative error and the Nash-Sutcliffe coefficient of efficiency. The results show that at longer lead times the evolved neural networks outperform the conventional ones in terms of overall performance. It is also shown that the sum squared error objective function does not result in the best performing model from a hydrological perspective.

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.neunet.2006.01.009DOI Listing

Publication Analysis

Top Keywords

squared error
12
symbiotic adaptive
8
neural network
8
network models
8
objective functions
8
sum squared
8
hydrological perspective
8
lead times
8
adaptive neuro-evolution
4
neuro-evolution applied
4

Similar Publications

Effects of long-term steroid therapy on the results of dental age estimation using pulp/tooth ratio.

J Forensic Odontostomatol

December 2024

Department of Medicine and Health Science "Vincenzo Tiberio", University of Molise, AgeEstimation Project, Campobasso, Italy.

Forensic age estimation is performed by assessing pulp chamber constrictions due to physiological age-related changes in dental radiographs; however, the estimated ages occasionally deviate from the actual ages. In particular, long-term steroid users tend to demonstrate pulp chamber constrictions in all teeth. Because this is uncommon among younger age groups, caution should be exercised when evaluating pulp chamber constriction.

View Article and Find Full Text PDF

Purpose: To examine the prevalence and associations of anisometropia with spherical ametropia, cylindrical power, age, and sex.

Methods: Anisometropia was analyzed for subjective refraction. In total, 134,603 refractive surgery candidates were included in the period from 2010 to 2020 at the CARE Vision Refractive Centers in Germany.

View Article and Find Full Text PDF

Background: The onset of the COVID-19 pandemic precipitated a rapid shift to virtual care in health care settings, inclusive of mental health care. Understanding clients' perspectives on virtual mental health care quality will be critical to informing future policies and practices.

Objective: This study aimed to outline the process of redesigning and validating the Virtual Client Experience Survey (VCES), which can be used to evaluate client and family experiences of virtual care, specifically virtual mental health and addiction care.

View Article and Find Full Text PDF

Background: Mitochondrial bioenergetics are essential for cellular function, specifically the intricacies of the electron transport chain (ETC), with Complex IV playing a crucial role in unraveling the mechanisms governing energy production. Mathematical models offer a valuable approach to simulate these complex processes, providing insights into normal mitochondrial function and aberrations associated with various diseases, including neurodegenerative disorders. Our research focuses on introducing and refining a mathematical model, emphasizing Complex IV in the ETC, with objectives including incorporating mitochondrial activity modulation using inhibiting and uncoupling reagents, akin to oxygen consumption experiments.

View Article and Find Full Text PDF

Background: AD prevention and early interventions require tools for evaluation of people during aging for diagnosis and prognosis of AD conversion. Since AD is a complicated continuum of neurodegenerative processes, developing of such tools have been difficult because it needs longitudinal and multimodal data which are often complicated and incomplete. To address this challenge, we are developing AI4AD framework using ADNI data.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!