0000000000617849
AUTHOR
Bernt Viggo Matheussen
Modeling Snow Dynamics Using a Bayesian Network
In this paper we propose a novel snow accumulation and melt model, formulated as a Dynamic Bayesian Network DBN. We encode uncertainty explicitly and train the DBN using Monte Carlo analysis, carried out with a deterministic hydrology model under a wide range of plausible parameter configurations. The trained DBN was tested against field observations of snow water equivalents SWE. The results indicate that our DBN can be used to reason about uncertainty, without doing resampling from the deterministic model. In all brevity, the DBN's ability to reproduce the mean of the observations was similar to what could be obtained with the deterministic hydrology model, but with a more realistic repre…
Using the Tsetlin Machine to Learn Human-Interpretable Rules for High-Accuracy Text Categorization With Medical Applications
Medical applications challenge today's text categorization techniques by demanding both high accuracy and ease-of-interpretation. Although deep learning has provided a leap ahead in accuracy, this leap comes at the sacrifice of interpretability. To address this accuracy-interpretability challenge, we here introduce, for the first time, a text categorization approach that leverages the recently introduced Tsetlin Machine. In all brevity, we represent the terms of a text as propositional variables. From these, we capture categories using simple propositional formulae, such as: if "rash" and "reaction" and "penicillin" then Allergy. The Tsetlin Machine learns these formulae from a labelled tex…
Hydropower Optimization Using Split-Window, Meta-Heuristic and Genetic Algorithms
In this paper, we try to find the most efficient optimization algorithm that can be used to resolve the hydropower optimization problem. We propose a novel optimization technique is called the Split-window method. The method is relatively simple and reduces the complexity of the optimization problem by split-ting the planning horizon (and datasets) into equal windows and assigning the same values to policies(actions) within each part. After splitting, a meta-heuristic technique is used to optimize the actions, and the dataset is split again until a split contains only one instance (timestep). The unique values to be optimized during each iteration is equal to the number of splits which make…
Hydropower Optimization Using Deep Learning
This paper demonstrates how deep learning can be used to find optimal reservoir operating policies in hydropower river systems. The method that we propose is based on the implicit stochastic optimization (ISO) framework, using direct policy search methods combined with deep neural networks (DNN). The findings from a real-world two-reservoir hydropower system in southern Norway suggest that DNNs can learn how to map input (price, inflow, starting reservoir levels) to the optimal production pattern directly. Due to the speed of evaluating the DNN, this approach is from an operational standpoint computationally inexpensive and may potentially address the long-standing problem of high dimension…
A Learning Automata Local Contribution Sampling Applied to Hydropower Production Optimisation
Learning Automata (LA) is a powerful approach for solving complex, non-linear and stochastic optimisation problems. However, existing solutions struggle with high-dimensional problems due to slow convergence, arguably caused by the global nature of feedback. In this paper we introduce a novel Learning Automata (LA) scheme to attack this challenge. The scheme is based on a parallel form of Local Contribution Sampling (LCS), which means that the LA receive individually directed feedback, designed to speed up convergence. Furthermore, our scheme is highly decentralized, allowing parallel execution on GPU architectures. To demonstrate the power of our scheme, the LA LCS is applied to hydropower…