Modeling Problems Research Articles

Method of Identification of Combat Vehicles Based on Yolo

A method for recognizing contours of objects in a video data stream is proposed. Data will be uploaded using a video camera in real time and object recognition will be performed. We will use the YOLO network – a method of identifying and recognizing objects in real time. Recognized objects will be recorded in a video sequence showing the contours of the objects. The approach proposed in the project reasonably synthesizes methods of artificial intelligence, theories of computer vision on the one hand, and pattern recognition on the other; it makes it possible to obtain control influences and mathematical functions for decision-making at every moment of time with the possibility of analyzing the influence of external factors and forecasting the flow of processes, and refers to the fundamental problems of mathematical modeling of real processes. The installation of the neural network is shown in detail. The characteristics of the neural network are shown and its capabilities are substantiated. Approaches to computer vision for object extraction are shown. Well-known methods are methods of expanding areas, methods based on clustering, contour selection, and methods using a histogram. The work envisages building a system for rapid identification of combat vehicles based on the latest image filtering methods developed using deep learning methods. The time spent on identifying the machine will be 10 –20 % shorter, thanks to the developed new information technology for detecting objects in conditions of rapidly changing information.

F-PICNN: A physics-informed convolutional neural network for partial differential equations with space-time domain

The physics and interdisciplinary problems in science and engineering are mainly described as partial differential equations (PDEs). Recently, a novel method using physics-informed neural networks (PINNs) to solve PDEs by employing deep neural networks with physical constraints as data-driven models has been pioneered for surrogate modelling and inverse problems. However, the original PINNs based on fully connected neural networks pose intrinsic limitations and poor performance for the PDEs with nonlinearity, drastic gradients, multiscale characteristics or high dimensionality in which the complex features are hard to capture. This leads to difficulties in convergence to correct solutions and high computational costs. To address the above problems, in this paper, a novel physics-informed convolutional neural network framework based on finite discretization schemes with a stack of a series of nonlinear convolutional units (NCUs) for solving PDEs in the space-time domain without any labelled data (f-PICNN) is proposed, in which the memory mechanism can considerably speed up the convergence. Specifically, the initial conditions (ICs) are hard-encoded into the network as the first time-step solution and used to extrapolate the next time-step solution. The Dirichlet boundary conditions (BCs) are constrained by soft BC enforcement while the Neumann BCs are hard enforced. Furthermore, the loss function is designed as a set of discretized PDE residuals and optimized to conform to physics laws. Finally, the proposed auto-regressive model has been proven to be effective in a wide range of 1D and 2D nonlinear PDEs in both space and time under different finite discretization schemes (e.g., Euler, Crank Nicolson and fourth-order Runge-Kutta). The numerical results demonstrate that the proposed framework not only shows the ability to learn the PDEs efficiently but also provides an opportunity for greater conceptual simplicity, and potential for extrapolation from learning the PDEs using a limited dataset.

The Effect of Pollutantmigration on the Environmental Situation in the Zone of Chemical Weaponinfluence

The article is devoted to the issues of monitoring the environment state in the influence zone of chemically hazardous objects on the example of the environmental monitoring system of a chemical weapons storage and destruction facility (CWDF) in the city of Kambarka, Udmurt Republic. Among the components there are: production control systems and site monitoring, environmental monitoring and health monitoring, however, it is environment in the zone of the chemical waste disposal facility influence which hasthe largest area and is the most difficult to control. Here, due to large areas, the process of migration of pollutants over considerable distances is observedclearly. The importance of the system for arranging sampling points on the topographic map of the waste disposal facility is shown in order to take into account the process of pollutantmigration. Vertical and horizontal migration of pollutants can lead to the emergence of unobvious local areas of pollutantaccumulation both within and outside the influence zone of the chemical waste disposal facility. A solution to the problem of migration process modeling on a conditionally selected area of the territory within the facility influence zone is presented to show the effect pollutantmigration on the dynamics of the environmental situation within the chemical waste disposal area. It has been proven that within the area under consideration there will be a significant amount of pollutant, which, subject to further evaporation of rainwater runoff, will remain in this area. This indicates the inevitability of the appearance of local areas of pollutantaccumulation in the influence zone of chemically-disposable substances in excess of permissible standards for their concentration, which requires a revision of the arranging sampling pointsystem, taking into account the application of migration processmodeling methods. The need for dynamic observations in individual sites of the area, selected with respect to the analysis results of the pollutantmigration routes within the entire influence zone of the chemically-disposable waste disposal facility, in order to assess the degree of impact of the non-toxic waste disposal facility on the environment, is substantiated.

Research Progress of EEG-Based Emotion Recognition: A Survey

Emotion recognition based on electroencephalography (EEG) signals has emerged as a prominent research field, facilitating objective evaluation of diseases like depression and motion detection for heathy people. Starting from the basic concepts of temporal-frequency-spatial features in EEG and the methods for cross-domain feature fusion, this survey then extends the overfitting challenge of EEG single-modal to the problem of heterogeneous modality modeling in multimodal conditions. It explores issues such as feature selection, sample scarcity, cross-subject emotional transfer, physiological knowledge discovery, multimodal fusion methods, and modality missing. These findings provide clues for researchers to further investigate emotion recognition based on EEG signals.

Admittance stability model and equivalent circuit analysis of three‐phase AC systems in different coordinate systems

AbstractIn recent years, with a large number of distributed energy sources connected to the grid, the distribution network has shown a clear trend towards the use of power electronics. As a power conversion interface, the stability of the converter's interaction with the grid has received considerable attention. Adequate admittance (impedance) modeling of the three‐phase grid‐connected converter is a prerequisite for analyzing the stability and resonance characteristics of the grid‐connected system. Understanding the internal mechanisms and proposing effective solutions are crucial to enable power systems to effectively cope with the impact of power electronics. Therefore, by studying the admittance equivalence relationship and equivalent circuit of three‐phase AC systems in various coordinate systems, this paper focuses on solving the non‐uniqueness problem of impedance admittance modeling of three‐phase converter system. It is proposed that the input admittance of the three‐phase asymmetrical system in the dq and fb rotating coordinate systems is a 2‐order matrix and equivalent. The input admittance of the three‐phase unbalanced system in the αβ and “12” static coordinate systems is a 4‐order matrix and equivalent. From both theoretical analysis and simulation verification, it is shown that the number of eigenvalues of the three‐phase asymmetrical system in the stationary coordinate system is twice that in the rotating coordinate system, and the overall damping of the system is improved. The control strategy based on the stationary coordinate system will make the system more stable. The second contribution of this paper is to establish the equivalent circuit of the three‐phase symmetric converter system by the node admittance matrix and extend it to the multi‐machine system to explain the system instability mechanism by the circuit resonance mechanism. Finally, the frequency coupling phenomenon is studied for the three‐phase asymmetrical converter system, and it is explained that it cannot establish an equivalent circuit similar to the three‐phase symmetrical converter system.

How to protect those who protect: psychosocial risks in child welfare workers during the pandemic

ABSTRACT Child welfare professionals face elevated psychosocial risks, especially during the COVID-19 pandemic, yet they are often overlooked in specialized literature, especially for Spanish workers. Most studies use linear models, neglecting nonlinear relationships. This study examined the role of job demands, resources, and COVID-19 impact on burnout, psychosomatic problems, and work engagement in 196 Spanish child welfare professionals. Demands predicted burnout and psychosomatic problems in both Hierarchical Regression Modelling (HRM) and Qualitative Comparative Analysis (QCA). Resources positively predicted engagement in both analyses. COVID-19 impact was significantly related to psychosomatic problems in QCA, highlighting nuances not captured by HRM.

On the relationship of mental and biological in the problem of modeling consciousness

The problem of mental modelling and creation of thinking devices is one of the most significant and at the same time, the least studied in modern science. The main difficulties in solving it are associated with insufficient elaboration of the relationship between the mental and the biological, primarily from the conceptual apparatus and a unified methodological base. The article discusses the issues of the definition of alive, the emergence of the psyche, the concept of pan-interiorism, existing models of consciousness and their criticism from the position of non-disjunctive logic and proposes a new semiotic model based on a cultural substrate. The work is an attempt at an interdisciplinary synthesis of views on the above problems of the largest scientists of the XX and XXI centuries: V.I. Vernadsky, S.L. Rubinshtein, A.V. Brushlinsky, M.M. Bakhtin, Yu.M. Lotman and others. The possibility of building artificial intelligence based on cultural substrate is substantiated, as it is proposed to use semiotic systems, whose properties in many respects resemble the properties of a living organism: they possess the mechanism of autopoiesis, follow the Redi principle, are organized in the form of cholarchy, and exist only in a communicative environment.

Attention Guide Axial Sharing Mixed Attention (AGASMA) Network for Cloud Segmentation and Cloud Shadow Segmentation

Segmenting clouds and their shadows is a critical challenge in remote sensing image processing. The shape, texture, lighting conditions, and background of clouds and their shadows impact the effectiveness of cloud detection. Currently, architectures that maintain high resolution throughout the entire information-extraction process are rapidly emerging. This parallel architecture, combining high and low resolutions, produces detailed high-resolution representations, enhancing segmentation prediction accuracy. This paper continues the parallel architecture of high and low resolution. When handling high- and low-resolution images, this paper employs a hybrid approach combining the Transformer and CNN models. This method facilitates interaction between the two models, enabling the extraction of both semantic and spatial details from the images. To address the challenge of inadequate fusion and significant information loss between high- and low-resolution images, this paper introduces a method based on ASMA (Axial Sharing Mixed Attention). This approach establishes pixel-level dependencies between high-resolution and low-resolution images, aiming to enhance the efficiency of image fusion. In addition, to enhance the effective focus on critical information in remote sensing images, the AGM (Attention Guide Module) is introduced, to integrate attention elements from original features into ASMA, to alleviate the problem of insufficient channel modeling of the self-attention mechanism. Our experimental results on the Cloud and Cloud Shadow dataset, the SPARCS dataset, and the CSWV dataset demonstrate the effectiveness of our method, surpassing the state-of-the-art techniques for cloud and cloud shadow segmentation.

Solar Models and Astrophysical S-factors Constrained by Helioseismic Results and Updated Neutrino Fluxes

The ratio of metal abundance to hydrogen abundance of the solar photosphere, (Z/X) s , has been revised several times. Standard solar models, based on these revised solar abundances, are in disagreement with seismically inferred results. Recently, Magg et al. introduced a new value for (Z/X) s , which is still under debate in the community. The solar abundance problem or solar modeling problem remains a topic of ongoing debate. We constructed rotating solar models in accordance with various abundance scales where the effects of convection overshoot and enhanced diffusion were included. Among these models, those utilizing Magg’s abundance scale exhibit superior sound speed and density profiles compared to models using other abundance scales. Additionally, they reproduce the observed frequency separation ratios r 02 and r 13. These models also match the seismically inferred surface helium abundance and convection zone depth within the 1σ level. Furthermore, the calculated neutrino fluxes from these models agree with detected ones at the level of 1σ. We found that neutrino fluxes and density profile are influenced by nuclear reactions, allowing us to use the combination of detected neutrino fluxes and seismically inferred density for diagnosing astrophysical S-factors. This diagnostic approach shows that S 11 may be underestimated by 2%, while S 33 may be overestimated by about 3% in previous determinations. The S-factors favored by updated neutrino fluxes and helioseismic results can lead to significant improvements in solar models.

KINETIC MODELLING OF BIOCHEMICAL REACTIONS USING MATHСAD ANALYTICAL TOOLKIT

Background. The study of the kinetics of biochemical reactions provides a better understanding of how biological processes occur in living organisms. Understanding the peculiarities of such reactions is important for the development of new technologies, in particular for the production of biologically active substances and for the synthesis of drugs. A powerful tool for solving problems in biochemical reaction kinetics is mathematical modelling, which can be carried out using computer mathematical systems, in particular the MATHCAD analytical toolkit. Aim: to substantiate the feasibility and effectiveness of using the MATHCAD analytical toolkit to solve problems of kinetic modelling of biochemical reactions in pharmaceutical research, and to review the capabilities of MATHCAD for computer modelling in pharmacy. Materials and methods. In the context of studying the rate of enzymatic reactions and developing models, such as the Michaelis-Menten model, to describe reactions in which enzymes catalyze the transformation of substrates, the use of a computer mathematical system (CMS) is considered. CMS is a software package and environment for performing mathematical computations, modelling and visualization. The possibilities of using the MATHCAD system to create mathematical models of biochemical reactions based on kinetic equations are demonstrated. This involves the creation of differential equations describing changes in reagent concentrations over time. These equations were solved using numerical methods in MATHCAD. In addition, the results obtained are visualized using 3D graphics in MATHCAD. The stages of using the MATHCAD analytical toolkit in the kinetic modelling of biochemical reactions have been determined. Results. The use of MATHCAD in the kinetic modelling of biochemical reactions is effective for the study of: (1) the kinetics of enzymatic reactions, e.g. reactions in which an enzyme catalyzes the conversion of a substrate into a product; (2) biochemical reactions that take place in reaction vessels in which reagents mix and interact; (3) modelling of reactions in reaction vessels based on the solution of differential equations of reaction kinetics; (4) the effect of inhibitors or activators on enzymatic reactions; (5) scenarios of interaction of reagents to determine changes in the kinetics of reactions that occur when different active substances are introduced; (6) kinetics of biochemical reactions in cases where reactions are accompanied by diffusion of reagents through membranes or other semi-permeable barriers; (7) modelling the effect of diffusion processes on the kinetics of biochemical reactions; (8) models describing the kinetics of decomposition of substances, for example the decomposition of biologically active compounds in the body or in the environment; (9) predicting the effect of changes in the conditions of the reaction medium (temperature, pH, concentration of reagents) on the kinetics of biochemical reactions. It is substantiated that model descriptions of the kinetics of biochemical reactions are important for forming an understanding of the functions of biological systems, including metabolism, enzymatic reactions, and other physiological phenomena. Tools have been used to visualize the modelling results in the form of three-dimensional MATHCAD graphics, which improves the understanding of the reaction mechanism and allows a more thorough analysis of its kinetics. Conclusion. MATHCAD provides an optimized environment for kinetic modelling of biochemical reactions through its ergonomic interface. Particular advantages are the ability to work with symbolic expressions and to use a wide range of built-in functions and tools for exploring mathematical models and visualizing results. The obtained results may be important both for further scientific pharmaceutical research and for implementation in the training of future Masters of Pharmacy in the discipline of "Computer Modelling in Pharmacy" in higher medical education institutions.

Mathematical modeling of heat exchange for efficient automated control systems

The article deals with the problem of mathematical modeling of heat transfer processes, taking into account a large number of factors affecting these processes and a variety of mathematical modeling methods. The article discusses the idea of developing a universal and flexible model that could quickly adapt to different initial modeling conditions and take into account various parameters for further use of the mathematical model in the synthesis of automatic control systems. The paper discusses the main aspects of mathematical modeling of heat transfer and the creation of a mathematical model in distributed heat exchanger parameters with the possibility of changing the properties and parameters of the equipment. The paper analyzes previous studies and identifies the problems of existing methods of mathematical modeling of heat transfer, such as lack of versatility, complexity, and insufficient accuracy. The paper goes on to review different approaches to mathematical modeling of heat transfer, such as models with a group of parameters, models in distributed parameters, and models based on artificial intelligence. The article provides an overview of model implementation methods and their advantages and disadvantages. Based on this analysis, the authors propose a new mathematical model of heat transfer in distributed parameters, which should be universal, easy to use, and accurate in accordance with the requirements of synthesizing automated control systems. The authors also outline the methodology for achieving this goal, which includes the implementation of the geometry of the heat exchanger, the implementation of conditions and mathematical modeling, as well as the study of the influence of parameters and the formation of transients. The general conclusion of the article is that the developed mathematical model of heat transfer can be used to synthesize automatic control systems for heat exchange processes in various industries.

Version [1.1] - [2D-xtDCR-LTBEM: A Fortran code for numerical solutions to the unsteady anisotropic-DCR equation of spatio-temporal coefficients]

Variable coefficient equations are usually used as governing equations for modeling problems which are associated with Functionally Graded Materials (FGM). Version 1.1 - 2D-xtDCR-LTBEM is a Fortran code that can be used to find numerical solutions of two-dimensional (2D) initial–boundary value problems which are governed by the unsteady anisotropic-diffusion convection reaction (DCR)-type and the anisotropic-diffusion reaction (DR)-type equations with a class of space–time dependent coefficients, by utilizing a combined Laplace Transform-Boundary Element Method (LTBEM). This code may provide valuable help for simulation of problems of FGM.

Efficient state change detection method for modeling stateful time series data

AbstractTime series analysis is an important research area and has wide real applications. Time series modeling has been identified and well known as the key fundamental problem in time series analysis, and it has received lots of research attentions. The hardness of achieving sophisticated and efficient time series models depends on the characteristic of the data met. In practical, time series data are usually generated by the physical process with several working states, which are determined by the system design. In such cases, the data characteristics of each state is quite different from the other states, where the modeling problem becomes much harder and it is more challenging to design modeling methods for stateful time series data. Therefore, this paper focuses on the stateful time series data, and studies the state change detection problem, which is identified as a key fundamental problem for modeling stateful data. To achieve effective and efficient state change detection, the proposed method utilizes two essential ideas. Since the discrepancy (a.k.a. histogram) based method has been proposed and verified to be more effective by previous works, the first idea is to improve its performance by involving more temporal information and utilizing the encoder–decoder techniques to reform the data. In view of the efficiency issue of the discrepancy‐based method, the second idea is to integrate both the Bayesian and discrepancy‐based detection methods, such that a perfect tradeoff between time efficiency and detection performance can be achieved. Experiments on both real and synthetic datasets show that the proposed methods are both effective and efficient, and the state change detection problem can be solved well by them on stateful time series data.

Using group level factor models to resolve high dimensionality in model-based sampling.

Joint modeling of decisions and neural activation poses the potential to provide significant advances in linking brain and behavior. However, methods of joint modeling have been limited by difficulties in estimation, often due to high dimensionality and simultaneous estimation challenges. In the current article, we propose a method of model estimation that draws on state-of-the-art Bayesian hierarchical modeling techniques and uses factor analysis as a means of dimensionality reduction and inference at the group level. This hierarchical factor approach can adopt any model for the individual and distill the relationships of its parameters across individuals through a factor structure. We demonstrate the significant dimensionality reduction gained by factor analysis and good parameter recovery, and illustrate a variety of factor loading constraints that can be used for different purposes and research questions, as well as three applications of the method to previously analyzed data. We conclude that this method provides a flexible and usable approach with interpretable outcomes that are primarily data-driven, in contrast to the largely hypothesis-driven methods often used in joint modeling. Although we focus on joint modeling methods, this model-based estimation approach could be used for any high dimensional modeling problem. We provide open-source code and accompanying tutorial documentation to make the method accessible to any researchers. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Data-Driven Wildfire Spread Modeling of European Wildfires Using a Spatiotemporal Graph Neural Network

Wildfire spread models are an essential tool for mitigating catastrophic effects associated with wildfires. However, current operational models suffer from significant limitations regarding accuracy and transferability. Recent advances in the availability and capability of Earth observation data and artificial intelligence offer new perspectives for data-driven modeling approaches with the potential to overcome the existing limitations. Therefore, this study developed a data-driven Deep Learning wildfire spread modeling approach based on a comprehensive dataset of European wildfires and a Spatiotemporal Graph Neural Network, which was applied to this modeling problem for the first time. A country-scale model was developed on an individual wildfire time series in Portugal while a second continental-scale model was developed with wildfires from the entire Mediterranean region. While neither model was able to predict the daily spread of European wildfires with sufficient accuracy (weighted macro-mean IoU: Portugal model 0.37; Mediterranean model 0.36), the continental model was able to learn the generalized patterns of wildfire spread, achieving similar performances in various fire-prone Mediterranean countries, indicating an increased capacity in terms of transferability. Furthermore, we found that the spatial and temporal dimensions of wildfires significantly influence model performance. Inadequate reference data quality most likely contributed to the low overall performances, highlighting the current limitations of data-driven wildfire spread models.

Joint application of the Monte Carlo method and computational probabilistic analysis in problems of numerical modeling with data uncertainties

Abstract In this paper, we suggest joint application of computational probabilistic analysis and the Monte Carlo method for numerical stochastic modeling problems. We use all the capabilities of computational probabilistic analysis while maintaining all the advantages of the Monte Carlo method. Our approach allows us to efficiently implement a computational hybrid scheme. In this way, we reduce the computation time and present the results in the form of distributions. The crucial new points of our method are arithmetic operations on probability density functions and procedures for constructing on the probabilistic extensions. Relying on specific numerical examples of solving systems of linear algebraic equations with random coefficients, we present the advantages of our approach.

Multi-IRSs enhanced UAV secure semantic communication system

This paper delves into a unmanned aerial vehicle (UAV) semantic communication system featuring multiple intelligent reflecting surfaces (IRSs). The UAV transmits semantic symbols to users in the presence of eavesdropping, and thus has inevitable security problems. In order to measure secure communication performance in semantic communication, the security semantic transmission rate (SSR) based on the semantic similarity is employed. An optimization problem is formulated to enhance the average SSR by optimizing UAV trajectory, IRS reflecting coefficients, number of semantic symbols, and transmission power, while satisfying position, speed, anti-collision, and power constraints. Due to the highly dynamic nature of the environment and the difficulties in solving complex modeling problems, a novel approach based on hybrid soft actor–critic (H-SAC) deep reinforcement learning (DRL) is proposed to address this non-convex optimization problem. The algorithm addresses the challenge of dynamic environments in UAV scenarios by seamlessly accommodating both discrete and continuous action spaces such as the trajectory and the IRS reflecting coefficient within the network. This enables effective processing of actions taken by intelligent agents, ensuring adaptability to the diverse requirements of the environment without the need for separate handling mechanisms. Simulation results show that the proposed intelligent algorithm exhibits excellent convergence and achieves a well-balanced pairing of appropriate IRSs and selection of flight paths, significantly improving the average SSR of the system. Specifically, our proposed scheme enhances the secure semantic transfer rate by more than fifty percent compared to when the number of semantic symbols is fixed at two.

Surface geometry inversion of transient electromagnetic data

We investigate an emerging method called surface geometry inversion (SGI) for the inversion of transient electromagnetic (TEM) data. Conventional minimum-structure inversion methods parameterize the earth model with many mesh cells within which the physical properties are constant, and construct a physical property model that is usually smoothly varying as well as fits the observations. With these smooth models, it is difficult to extract the interface between different geologic units, and it can be especially difficult to target drillholes for thin, plate-like targets, which are frequently encountered in mineral exploration. Our SGI parameterizes the model in terms of the coordinates of the nodes (vertices) used to connect together the surfaces that define the geologic interfaces. The algorithm then inverts for the locations of these nodes, which directly provides geometric information about the target. This can be more useful than a fuzzy image of conductivity, especially for an exploration project. A genetic algorithm (GA) is used to solve the nonlinear, overdetermined optimization problem. We use a finite-element solver to solve the TEM forward-modeling problem of each candidate model in the GA population. Because forward modeling is independent for each model, we implement a hybrid message passing interface (MPI) + OpenMP parallel method to improve computational efficiency. We investigate a new parameterization method specifically designed for thin, plate-like structures, which is more efficient and can effectively avoid self-intersection. We first illustrate the effectiveness of our SGI algorithm on a synthetic block model before testing the new parameterization method on a synthetic thin plate model. Finally, we apply our SGI to a real data set collected for the exploration of thin graphitic faults in a uranium exploration project in Canada. The constructed model from our SGI corresponds well with the drilling data.

A deep learning paradigm for medical imaging data

We present a novel deep learning framework to address several challenges in medical imaging analysis. Especially for functional magnetic resonance imaging (fMRI) data, we develop a statistical sampling algorithm to augment small data for deep learning modeling. Also, the ComBat harmonization is utilized for multi-source batch effect correction. Finally, we implement the prediction uncertainty in deep learning through a dropout approximation of the deep Gaussian process. The proposed approach offers effective statistical tools to solve persistent problems in deep learning modeling for medical imaging data. To assess the performance of the proposed approach and demonstrate its effectiveness for various types of data, we apply it to autism fMRI and Pneumonia imaging datasets.

Enhancing Students’ Numeracy Skills in Solving Probability Problems through Realistic Mathematics Education

Numeracy skills can help students to solve everyday problems. The low numeracy skills of students are caused by not understanding the problem, lack of strategy, and obstacles to evaluating and interpreting the solution to the context. The teacher needs to implement the learning process by using the RME approach, which uses local context and facilitates activity to think mathematically. This study aims to investigate the RME approach in enhancing numeracy skills and to describe the numeracy skills of students in solving problems according to numeracy indicators. The explanatory sequential mixed methods were used to analyze data from tests and interviews. The research subjects were 32 Grade 8 students, and four selected students chose to do the interviews based on each numeracy skills category. The results show a significant difference between the average numeracy skills of students before and after learning with the RME approach. Students with proficient, competent, and basic competencies fulfill the numeracy indicators. Meanwhile, students who need special intervention still have difficulty modeling problems into mathematical representations, incorrectly use the concept of probability, have inappropriate problem-solving strategies, and cannot interpret mathematical solutions in the form of arguments.