Application of Machine Learning Techniques to an Agent-Based Model of Pantoea

Agent-based modeling (ABM) is a powerful simulation technique which describes a complex dynamic system based on its interacting constituent entities. While the flexibility of ABM enables broad application, the complexity of real-world models demands intensive computing resources and computational time; however, a metamodel may be constructed to gain insight at less computational expense. Here, we developed a model in NetLogo to describe the growth of a microbial population consisting of Pantoea. We applied 13 parameters that defined the model and actively changed seven of the parameters to modulate the evolution of the population curve in response to these changes. We efficiently performed more than 3,000 simulations using a Python wrapper, NL4Py. Upon evaluation of the correlation between the active parameters and outputs by random forest regression, we found that the parameters which define the depth of medium and glucose concentration affect the population curves significantly. Subsequently, we constructed a metamodel, a dense neural network, to predict the simulation outputs from the active parameters and found that it achieves high prediction accuracy, reaching an R2 coefficient of determination value up to 0.92. Our approach of using a combination of ABM with random forest regression and neural network reduces the number of required ABM simulations. The simplified and refined metamodels may provide insights into the complex dynamic system before their transition to more sophisticated models that run on high-performance computing systems. The ultimate goal is to build a bridge between simulation and experiment, allowing model validation by comparing the simulated data to experimental data in microbiology.

Internal well-being as a complex dynamic system

Introduction. The relevance of the study of the internal well-being of a person as a complex dynamic system is due to the need for empirical verification of post-non-classical ideas about complex psychological phenomena, which involves the comparison of various theoretical constructs and research tools related to the studied psychological phenomenon. Materials and methods. The sample was made up of cadets of the power university in the number of 169 people. Three methods of studying internal well-being based on different theoretical constructs were used: the author's method "Self-assessment of emotional and personal well-being (SEPWB-24)", "Scale of psychological well-being" by K. Riff, the method "Subjective well-being" by R. M. Shamionov, T. V. Beskova. Results. On the basis of the Spearman correlation analysis, reliable (at p ≤ 0,001) relationships between all scales of the three methods used were confirmed. This can be seen as the presence of the general G-factor of "inner well-being". Differences in the strength of the relationships between the scales within the methods and between the scales of different methods are revealed, and different solutions are obtained in the factor analysis, which indicates the presence of S and U factors-determinants of internal well-being as a complex dynamic system.

Oral English Development of EFL Learners from the Perspective of Complexity Dynamic Theory

With the development of economic globalization and cultural integration, the learning of a second language has become increasingly important for economic, political, and cultural exchanges in the world today. Complex dynamic system theory is an important research theory of foreign language learning methods for nonnative speakers. However, the research and application of the complex dynamic system theory in oral foreign language learning of English as a Foreign Language (EFL) learners are not prominent. The purpose of this paper is to explore the learning situation of oral English of EFL learners from the perspective of the complex dynamic system theory and provide some new learning methods and suggestions for EFL learners’ oral English learning based on the research of complex dynamic system theory. First, this article discusses and analyzes the current situation of oral English learning of EFL learners through literature research and a questionnaire survey. Then, based on the related research on the theory of complex dynamic systems, this article proposes countermeasures and learning method recommendations for the problems existing in the current oral English learning of EFL learners. After that, this paper sets up a controlled test of oral English learning through the learning method formulated by the complex dynamic system theory and verifies the learning effect of the oral English learning method proposed in this paper according to the mathematical theory research method of the complex dynamic system. Finally, this article discusses the reliability of the experimental research conclusions based on the error analysis and confidence level estimation of the experimental results. The research results show shows that there is 95% confidence that the second language learning method proposed in this paper under the perspective of the complex dynamic system theory has a positive effect on the oral English learning of EFL learners.

Fixed and Dynamic Predictors of Willingness to Communicate in L2: A Review on New Paradigms of Individual Differences

Willingness to communicate (WTC), a recent affective construct of SLA research, has experienced a paradigm shift regarding its nature. Current WTC research tends to define it as a dynamic and context-bound structure rather being in a linear and static disposition. New conceptualization is based on Complex Dynamic System (CDS) theory. This theory has been applied to SLA research to explain dynamic, non-linear and complex nature of SLA process. The convenience of CDS theory’s basic principles has led existing WTC structure to be re-shaped and revised to define it as a dynamic structure in contrast to its former definition which would recall WTC as a static and trait-like variable.

Principles of neural control and variants of neural network architecture, applied to a complex dynamic system of sea-vessel

В статье рассматриваются возможности, особенности и перспективы внедрения принципов нейроуправления в контур регулирования, контроля и эксплуатации сложной динамической системы СЭУ-СУДНО. Отдельное внимание уделено базовым характеристикам и принципам нейроуправления. Рассмотрена структурная схема и принцип проектирования нейрорегулятора применительно к данной системе. Кроме того, формализована процедура настройки нейронной сети на моделирование входа/выхода объекта управления, а также принцип выбора архитектуры, определения критериев оптимизации нейронной сети для управления СЭУ-СУДНО. Рассмотрены альтернативные варианты для создания нейросетевой системы управления СЭУ-СУДНО. Отдельное внимание уделено принципам работы системы нейроуправления и ее ключевым характеристикам. Также формализована процедура выбора архитектуры нейронной сети для управления СЭУ-СУДНО и предложено несколько вариантов нейронных сетей для разных исходных параметров. The article discusses the possibilities, features and prospects of introducing the principles of neurocontrol for the regulation, control and operation of a complex dynamic system ship power plant. Special attention is paid to the basic characteristics and principles of neurocontrol. The block diagram and design principle of the neuroregulator in relation to this system are considered. In addition, the procedure for setting up a neural network for modeling the input / output of a control object has been formalized, as well as the principle of choosing an architecture, determining the criteria for optimizing a neural network for controlling the ship power plant-VESSEL. Alternative options for creating a neural network control system the ship power plant-VESSEL are considered. Special attention is paid to the principles of the neurocontrol system and its key characteristics. Also, the procedure for choosing the architecture of a neural network for controlling the ship power plant-VESSEL was formalized and several options for neural networks for different initial parameters were proposed.

Brief Analysis of Hierarchy of Human’s Spiritual World

By studying human’s spiritual world earnestly and comprehensively, you can learn that human’s spiritual world is hierarchical. The spiritual world is an extremely complex dynamic system consisting of 4 interconnected hierarchies. The dynamic system is composed of cognitive system, dynamical system, reflection-controlling system and operating system. Human’s spiritual world determines people’s way of response and action. All the thoughts and behaviors of people are the result of all the subsystems in human spiritual world.