Learning Control for an Xpilot-AI Agent Playing Capture the Flag

2012 ◽  
Vol 3 (1) ◽  
pp. 1-12
Author(s):  
Gary Parker ◽  
Sarah Penrose
Keyword(s):  
Genetic Algorithm ◽  
Open Source ◽  
Learning Control ◽  
Autonomous Agent ◽  
Challenging Problem ◽  
Wide Range ◽  
Learning Programs ◽  
Agent Control ◽  
2D Space

Xpilot-AI is an environment where researchers can test autonomous agent control and learning programs. It is based on Xpilot, which is an open source, 2d space combat game. Xpilot-AI allows a programmer to write scripts that control an agent playing a game of Xpilot. In previous work, a wide range of techniques have been used to develop controllers that are focused on the combat skills for an Xpilot agent. In this research, a Genetic Algorithm (GA) was used to evolve the parameters for an expert agent solving the more challenging problem of capture the flag.

Theory and Practice of Quality Management in Lifelong Learning at a Public University

2018 ◽  
Vol 8 (2) ◽  
pp. 49-73
Author(s):  
Petr Adamec
Keyword(s):  
Lifelong Learning ◽  
Public University ◽  
Further Education ◽  
Point Of View ◽  
Theory And Practice ◽  
University Policy ◽  
Higher Education Act ◽  
Wide Range ◽  
Learning Programs ◽  
Education Act

The core issue of this paper is a quality in the lifelong learning. The aim of the contribution is to describe the area, level and dimensions of quality in a wide range of lifelong learning programs, respectively of further education, which are realized in the sense of § 60 and 60a of the Higher Education Act. The content of the paper also focuses on the theoretical and practical starting points of the quality phenomenon, both from the historical point of view and especially from the perspective of the current focus and concept of university policy in the European and Czech region. The paper also presents the results of a survey focusing on approaches to the quality assurance systems in the concept of components at selected public university.

Development of a Hybrid Artificial Neural Network and Genetic Algorithm Model for Regime Identification of Slurry Transport in Pipelines

2009 ◽  
Vol 4 (1) ◽  
Author(s):  
Sandip K Lahiri ◽  
Kartik Chandra Ghanta
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Artificial Neural Network ◽  
Operating Conditions ◽  
Misclassification Error ◽  
Wide Range ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Pipeline Design ◽  
Hybrid Artificial Neural Network

Four distinct regimes were found existent (namely sliding bed, saltation, heterogeneous suspension and homogeneous suspension) in slurry flow in pipeline depending upon the average velocity of flow. In the literature, few numbers of correlations has been proposed for identification of these regimes in slurry pipelines. Regime identification is important for slurry pipeline design as they are the prerequisite to apply different pressure drop correlation in different regime. However, available correlations fail to predict the regime over a wide range of conditions. Based on a databank of around 800 measurements collected from the open literature, a method has been proposed to identify the regime using artificial neural network (ANN) modeling. The method incorporates hybrid artificial neural network and genetic algorithm technique (ANN-GA) for efficient tuning of ANN meta parameters. Statistical analysis showed that the proposed method has an average misclassification error of 0.03%. A comparison with selected correlations in the literature showed that the developed ANN-GA method noticeably improved prediction of regime over a wide range of operating conditions, physical properties, and pipe diameters.

Closed-Form Correlation of Buildings Energy Use With Key Design Parameters Calibrated Using a Genetic Algorithm

2011 ◽  
Vol 133 (4) ◽  
Author(s):  
Raed I. Bourisli ◽  
Adnan A. AlAnzi
Keyword(s):  
Genetic Algorithm ◽  
Closed Form ◽  
Energy Use ◽  
Building Design ◽  
Office Buildings ◽  
Design Parameters ◽  
Wide Range ◽  
Variable Function ◽  
Real Coded Genetic Algorithm ◽  
The Difference

This work aims at developing a closed-form correlation between key building design variables and its energy use. The results can be utilized during the initial design stages to assess the different building shapes and designs according to their expected energy use. Prototypical, 20-floor office buildings were used. The relative compactness, footprint area, projection factor, and window-to-wall ratio were changed and the resulting buildings performances were simulated. In total, 729 different office buildings were developed and simulated in order to provide the training cases for optimizing the correlation’s coefficients. Simulations were done using the VisualDOE TM software with a Typical Meteorological Year data file, Kuwait City, Kuwait. A real-coded genetic algorithm (GA) was used to optimize the coefficients of a proposed function that relates the energy use of a building to its four key parameters. The figure of merit was the difference in the ratio of the annual energy use of a building normalized by that of a reference building. The objective was to minimize the difference between the simulated results and the four-variable function trying to predict them. Results show that the real-coded GA was able to come up with a function that estimates the thermal performance of a proposed design with an accuracy of around 96%, based on the number of buildings tested. The goodness of fit, roughly represented by R2, ranged from 0.950 to 0.994. In terms of the effects of the various parameters, the area was found to have the smallest role among the design parameters. It was also found that the accuracy of the function suffers the most when high window-to-wall ratios are combined with low projection factors. In such cases, the energy use develops a potential optimum compactness. The proposed function (and methodology) will be a great tool for designers to inexpensively explore a wide range of alternatives and assess them in terms of their energy use efficiency. It will also be of great use to municipality officials and building codes authors.

scholarly journals A Modified NM-PSO Method for Parameter Estimation Problems of Models

2012 ◽  
Vol 2012 ◽  
pp. 1-12 ◽  
Author(s):  
An Liu ◽  
Erwie Zahara ◽  
Ming-Ta Yang
Keyword(s):  
Genetic Algorithm ◽  
Parameter Estimation ◽  
Particle Swarm Optimization ◽  
Differential Equations ◽  
Ordinary Differential Equations ◽  
Optimization Problems ◽  
Particle Swarm ◽  
Swarm Optimization ◽  
Wide Range ◽  
Estimation Problems

Ordinary differential equations usefully describe the behavior of a wide range of dynamic physical systems. The particle swarm optimization (PSO) method has been considered an effective tool for solving the engineering optimization problems for ordinary differential equations. This paper proposes a modified hybrid Nelder-Mead simplex search and particle swarm optimization (M-NM-PSO) method for solving parameter estimation problems. The M-NM-PSO method improves the efficiency of the PSO method and the conventional NM-PSO method by rapid convergence and better objective function value. Studies are made for three well-known cases, and the solutions of the M-NM-PSO method are compared with those by other methods published in the literature. The results demonstrate that the proposed M-NM-PSO method yields better estimation results than those obtained by the genetic algorithm, the modified genetic algorithm (real-coded GA (RCGA)), the conventional particle swarm optimization (PSO) method, and the conventional NM-PSO method.

scholarly journals Design of a Didactical Activity for the Analysis of Uncertainties in Thermography through the Use of Robust Statistics as Teacher-Oriented Approach

2021 ◽  
Vol 13 (3) ◽  
pp. 402
Author(s):  
Pablo Rodríguez-Gonzálvez ◽  
Manuel Rodríguez-Martín
Keyword(s):  
Open Source ◽  
Robust Statistics ◽  
Three Dimensional ◽  
Learning Material ◽  
Novel Approach ◽  
Learning Programs ◽  
Institutional Learning ◽  
Thermographic Image ◽  
Visualization Techniques ◽  
Free Open Source

The thermography as a methodology to quantitative data acquisition is not usually addressed in the degrees of university programs. The present manuscript proposes a novel approach for the acquisition of advanced competences in engineering courses associated with the use of thermographic images via free/open-source software solutions. This strategy is established from a research based on the statistical and three-dimensional visualization techniques over thermographic imagery to improve the interpretation and comprehension of the different sources of error affecting the measurements and, thereby, the conclusions and analysis arising from them. The novelty is focused on the detection of non-normalities in thermographic images, which is illustrates in the experimental section. Additionally, the specific workflow for the generation of learning material related with this aim is raised for asynchronous and e-learning programs. These virtual materials can be easily deployed in an institutional learning management system, allowing the students to work with the models by means of free/open-source solutions easily. Subsequently, the present approach will give new tools to improve the application of professional techniques, will improve the students’ critical sense to know how to interpret the uncertainties in thermography using a single thermographic image, therefore they will be better prepared to face future challenges with more critical thinking.

An open-source R-package and web application for high-quality probabilistic predictions in hydrology

2021 ◽  
Author(s):  
Jason Hunter ◽  
Mark Thyer ◽  
Dmitri Kavetski ◽  
David McInerney
Keyword(s):  
Open Source ◽  
Web Application ◽  
R Package ◽  
Error Model ◽  
Objective Functions ◽  
High Quality ◽  
Wide Range ◽  
Probabilistic Error

<p>Probabilistic predictions provide crucial information regarding the uncertainty of hydrological predictions, which are a key input for risk-based decision-making. However, they are often excluded from hydrological modelling applications because suitable probabilistic error models can be both challenging to construct and interpret, and the quality of results are often reliant on the objective function used to calibrate the hydrological model.</p><p>We present an open-source R-package and an online web application that achieves the following two aims. Firstly, these resources are easy-to-use and accessible, so that users need not have specialised knowledge in probabilistic modelling to apply them. Secondly, the probabilistic error model that we describe provides high-quality probabilistic predictions for a wide range of commonly-used hydrological objective functions, which it is only able to do by including a new innovation that resolves a long-standing issue relating to model assumptions that previously prevented this broad application.  </p><p>We demonstrate our methods by comparing our new probabilistic error model with an existing reference error model in an empirical case study that uses 54 perennial Australian catchments, the hydrological model GR4J, 8 common objective functions and 4 performance metrics (reliability, precision, volumetric bias and errors in the flow duration curve). The existing reference error model introduces additional flow dependencies into the residual error structure when it is used with most of the study objective functions, which in turn leads to poor-quality probabilistic predictions. In contrast, the new probabilistic error model achieves high-quality probabilistic predictions for all objective functions used in this case study.</p><p>The new probabilistic error model and the open-source software and web application aims to facilitate the adoption of probabilistic predictions in the hydrological modelling community, and to improve the quality of predictions and decisions that are made using those predictions. In particular, our methods can be used to achieve high-quality probabilistic predictions from hydrological models that are calibrated with a wide range of common objective functions.</p>

Estimation of CO2 Diffusivity in Brine by Use of the Genetic Algorithm and Mixed Kernels-Based Support Vector Machine Model

2018 ◽  
Vol 141 (4) ◽  
Author(s):  
Qihong Feng ◽  
Ronghao Cui ◽  
Sen Wang ◽  
Jin Zhang ◽  
Zhe Jiang
Keyword(s):  
Genetic Algorithm ◽  
Support Vector Machine ◽  
Diffusion Coefficient ◽  
Co2 Storage ◽  
Co2 Injection ◽  
Support Vector ◽  
Hybrid Technique ◽  
Machine Model ◽  
Proposed Model ◽  
Wide Range

Diffusion coefficient of carbon dioxide (CO2), a significant parameter describing the mass transfer process, exerts a profound influence on the safety of CO2 storage in depleted reservoirs, saline aquifers, and marine ecosystems. However, experimental determination of diffusion coefficient in CO2-brine system is time-consuming and complex because the procedure requires sophisticated laboratory equipment and reasonable interpretation methods. To facilitate the acquisition of more accurate values, an intelligent model, termed MKSVM-GA, is developed using a hybrid technique of support vector machine (SVM), mixed kernels (MK), and genetic algorithm (GA). Confirmed by the statistical evaluation indicators, our proposed model exhibits excellent performance with high accuracy and strong robustness in a wide range of temperatures (273–473.15 K), pressures (0.1–49.3 MPa), and viscosities (0.139–1.950 mPa·s). Our results show that the proposed model is more applicable than the artificial neural network (ANN) model at this sample size, which is superior to four commonly used traditional empirical correlations. The technique presented in this study can provide a fast and precise prediction of CO2 diffusivity in brine at reservoir conditions for the engineering design and the technical risk assessment during the process of CO2 injection.

scholarly journals The Open Global Glacier Model (OGGM) v1.0

2018 ◽  
Author(s):  
Fabien Maussion ◽  
Anton Butenko ◽  
Julia Eis ◽  
Kévin Fourteau ◽  
Alexander H. Jarosch ◽  
...  
Keyword(s):  
Mass Balance ◽  
Open Source ◽  
Sea Level ◽  
Computational Cost ◽  
Balance Model ◽  
Climate Data ◽  
Estimation Model ◽  
Model Framework ◽  
Validation Data ◽  
Wide Range

Abstract. Despite of their importance for sea-level rise, seasonal water availability, and as source of geohazards, mountain glaciers are one of the few remaining sub-systems of the global climate system for which no globally applicable, open source, community-driven model exists. Here we present the Open Global Glacier Model (OGGM, http://www.oggm.org), developed to provide a modular and open source numerical model framework for simulating past and future change of any glacier in the world. The modelling chain comprises data downloading tools (glacier outlines, topography, climate, validation data), a preprocessing module, a mass-balance model, a distributed ice thickness estimation model, and an ice flow model. The monthly mass-balance is obtained from gridded climate data and a temperature index melt model. To our knowledge, OGGM is the first global model explicitly simulating glacier dynamics: the model relies on the shallow ice approximation to compute the depth-integrated flux of ice along multiple connected flowlines. In this paper, we describe and illustrate each processing step by applying the model to a selection of glaciers before running global simulations under idealized climate forcings. Even without an in-depth calibration, the model shows a very realistic behaviour. We are able to reproduce earlier estimates of global glacier volume by varying the ice dynamical parameters within a range of plausible values. At the same time, the increased complexity of OGGM compared to other prevalent global glacier models comes at a reasonable computational cost: several dozens of glaciers can be simulated on a personal computer, while global simulations realized in a supercomputing environment take up to a few hours per century. Thanks to the modular framework, modules of various complexity can be added to the codebase, allowing to run new kinds of model intercomparisons in a controlled environment. Future developments will add new physical processes to the model as well as tools to calibrate the model in a more comprehensive way. OGGM spans a wide range of applications, from ice-climate interaction studies at millenial time scales to estimates of the contribution of glaciers to past and future sea-level change. It has the potential to become a self-sustained, community driven model for global and regional glacier evolution.

Drag optimisation of a wing equipped with a morphing upper surface

2016 ◽  
Vol 120 (1225) ◽  
pp. 473-493 ◽  
Author(s):  
A. Koreanschi ◽  
O. Sugar-Gabor ◽  
R. M. Botez
Keyword(s):  
Genetic Algorithm ◽  
Reynolds Number ◽  
Drag Coefficient ◽  
Open Source ◽  
Experimental Testing ◽  
Shape Reconstruction ◽  
Laminar To Turbulent Transition ◽  
Wing Model ◽  
Turbulent Transition ◽  
Transition Delay

ABSTRACTThe drag coefficient and the laminar-to-turbulent transition for the aerofoil component of a wing model are optimised using an adaptive upper surface with two actuation points. The effects of the new shaped aerofoils on the global drag coefficient of the wing model are also studied. The aerofoil was optimised with an ‘in-house’ genetic algorithm program coupled with a cubic spline aerofoil shape reconstruction and XFoil 6.96 open-source aerodynamic solver. The wing model analysis was performed with the open-source solver XFLR5 and the 3D Panel Method was used for the aerodynamic calculation. The results of the aerofoil optimisation indicate improvements of both the drag coefficient and transition delay of 2% to 4%. These improvements in the aerofoil characteristics affect the global drag of the wing model, reducing it by up to 2%. The analyses were conducted for a single Reynolds number and speed over a range of angles of attack. The same cases will also be used in the experimental testing of the manufactured morphing wing model.

scholarly journals Multiple Sclerosis Recognition by Biorthogonal Wavelet Features and Fitness-Scaled Adaptive Genetic Algorithm

2021 ◽  
Vol 15 ◽  
Author(s):  
Shui-Hua Wang ◽  
Xianwei Jiang ◽  
Yu-Dong Zhang
Keyword(s):  
Multiple Sclerosis ◽  
Genetic Algorithm ◽  
Data Augmentation ◽  
Area Under The Curve ◽  
Adaptive Genetic Algorithm ◽  
Biorthogonal Wavelet ◽  
Wide Range ◽  
Wavelet Features ◽  
The Brain ◽  
Better Than

Aim: Multiple sclerosis (MS) is a disease, which can affect the brain and/or spinal cord, leading to a wide range of potential symptoms. This method aims to propose a novel MS recognition method.Methods: First, the bior4.4 wavelet is used to extract multiscale coefficients. Second, three types of biorthogonal wavelet features are proposed and calculated. Third, fitness-scaled adaptive genetic algorithm (FAGA)—a combination of standard genetic algorithm, adaptive mechanism, and power-rank fitness scaling—is harnessed as the optimization algorithm. Fourth, multiple-way data augmentation is utilized on the training set under the setting of 10 runs of 10-fold cross-validation. Our method is abbreviated as BWF-FAGA.Results: Our method achieves a sensitivity of 98.00 ± 0.95%, a specificity of 97.78 ± 0.95%, and an accuracy of 97.89 ± 0.94%. The area under the curve of our method is 0.9876.Conclusion: The results show that the proposed BWF-FAGA method is better than 10 state-of-the-art MS recognition methods, including eight artificial intelligence-based methods, and two deep learning-based methods.

Sign in / Sign up

Export Citation Format

Share Document