• 한국수학교육학회지시리즈E:수학교육논문집
• /
• 제34권3호
• /
• pp.215-234
• /
• 2020

AI 시대의 함께 교육에서도 AI 활용의 필요성이 제기된다. 본 연구의 목적은 예비수학교사가 인식하는 미래 수학교육에서 AI의 필요성과 AI 활용에서 교사의 역할을 조명하는 것이다. 연구 결과, 교수 측면에서 예비교사들은 학교 수학에 AI 활용이 시대적 요구이며, 다양한 유형의 수업 구현과 정확한 지식 및 정보를 전달할 수 있지만, 인지적·감정적 상호작용에 한계가 있다고 하였다. 학습 측면에서 AI는 개별화 학습을 제공하고, 학교 수업 외 보충학습에 활용할 수 있고, 학습 흥미를 자극할 수 있지만, 학생들의 주체적 사고 능력을 저해할 수 있다고 하였다. 평가의 측면에서 AI는 객관적이고 공정하며 교사의 업무를 감소할 수 있지만 서·논술형 문항과 과정 중심 평가에서 한계가 있다고 하였다. AI 활용에서 예비교사들이 생각하는 교사의 역할은 수업, 감정적 상호작용, 비정형화된 평가, 상담이었고, AI의 역할은 개별화 학습, 기계적 학습, 정형화된 평가와 행정 업무로 나타났다.

• 한국수학교육학회지시리즈A:수학교육
• /
• 제62권2호
• /
• pp.269-287
• /
• 2023

행렬이론은 수학, 자연과학, 공학뿐 아니라 사회과학과 인공지능 분야에까지 다양하게 활용되고 있다. 중·고등학교 수학에서 행렬은 학습 부담 경감을 위해 2009 개정 수학과 교육과정에서 삭제되었다가 인공지능 시대를 맞이하여 2022 개정 교육과정에 재편성될 예정이다. 이에 다른 나라에서 다루고 있는 행렬 내용을 분석함으로써 행렬 지도를 위한 의미 있는 방향을 제시하고 교과서 구성을 위한 시사점을 도출할 필요성이 있다. 이를 위해 본고에서는 독일 수학과 표준교육과정과 독일 헤센주의 수학과 교육과정을 분석하고, 독일 수학 교과서의 행렬 단원의 내용 요소 및 전개 방식의 특징을 분석하였다. 분석 결과 독일 교과서는 선형연립방정식의 풀이를 위한 행렬, 일차변환을 설명하기 위한 행렬, 전환과정을 설명하기 위한 행렬로 나누어 행렬 단원을 다루고 있으며 모두 역행렬을 다루고 있고 수학적 추론 및 수학적 모델링에 중점을 두고 행렬을 학습하는 것으로 나타났다. 분석 결과로부터 학교 수학에 행렬을 재편성할 경우 깊이 있는 개념적 이해와 수학적 추론 및 수학적 모델링에 중점을 두어 교육내용을 구성할 것을 제안하는 바이다.

• Journal of applied mathematics & informatics
• /
• 제42권4호
• /
• pp.725-737
• /
• 2024

This article introduces the concepts of Energy and Laplacian Energy (LE) of Domination in Hesitancy fuzzy graph (DHFG). Also, the adjacency matrix of a DHFG is defined and proposed the definition of the energy of domination in hesitancy fuzzy graph, and Laplacian energy of domination in hesitancy fuzzy graph is given.

• East Asian mathematical journal
• /
• 제34권4호
• /
• pp.451-462
• /
• 2018

This study analyzed the learning components of the web-based adaptive math learning programs in order to develop adaptive math learning program using artificial intelligence. The components of the web-based adaptive math learning program set for analysis are classified into learning process presentation, concept learning, problem presentation, problem solving process, and learning result processing then analyzed three programs. As a result of analysis, the typical characteristic of components is that it uses a method of repeatedly presenting the same type of problem in order to learn one concept.

• 한국수학교육학회지시리즈A:수학교육
• /
• 제61권2호
• /
• pp.257-271
• /
• 2022

본 연구는 학습분석학을 기반으로 블렌디드 수학 수업에서 발생하는 학습 데이터를 활용하여 수학 학업성취도를 예측하는 요인이 무엇인지 탐색하고, 그 결과를 활용하여 수학 학업성취도를 예측하는 인공지능 모델을 개발하고자 하였다. 초등학교 5~6학년 학생 205명의 수학 학습 성향, LMS 데이터, 평가 결과를 수집하여 랜덤포레스트 모델을 분석하였다. 수학 학습성향에는 수학학습 자신감, 수학불안, 수학교과 흥미, 수학학습 자기관리, 수학학습 전략이 포함되었다. LMS 데이터로 e학습터의 진도율, 학습 횟수, 학습 시간을 수집하였다. 평가는 진단평가와 각 단원의 단원평가 결과를 사용하였다. 분석 결과 수학 학습성향 중 수학 학습 전략이 저성취 학생을 예측에 가장 중요한 요인으로 나타났다. LMS 학습 데이터는 예측에 미미한 영향을 주었다. 본 연구는 인공지능 모델이 블렌디드 수학 수업에서 발생하는 학습 데이터로 저성취 학생을 예측할 수 있음을 시사한다. 또한 분석 결과를 통해 교사가 학생을 평가하고 피드백하는 데 구체적인 정보를 제공하여 교사의 평가 활동에 보조적인 역할을 할 수 있을 것으로 기대한다.

• Computers and Concrete
• /
• 제32권2호
• /
• pp.149-163
• /
• 2023

One of the main design parameters traditionally utilized in projects of geotechnical engineering is the uniaxial compressive strength. The present paper employed three artificial intelligence methods, i.e., the stochastic fractal search (SFS), the multi-verse optimization (MVO), and the vortex search algorithm (VSA), in order to determine the compressive strength of concrete (CSC). For the same reason, 1030 concrete specimens were subjected to compressive strength tests. According to the obtained laboratory results, the fly ash, cement, water, slag, coarse aggregates, fine aggregates, and SP were subjected to tests as the input parameters of the model in order to decide the optimum input configuration for the estimation of the compressive strength. The performance was evaluated by employing three criteria, i.e., the root mean square error (RMSE), mean absolute error (MAE), and the determination coefficient (R²). The evaluation of the error criteria and the determination coefficient obtained from the above three techniques indicates that the SFS-MLP technique outperformed the MVO-MLP and VSA-MLP methods. The developed artificial neural network models exhibit higher amounts of errors and lower correlation coefficients in comparison with other models. Nonetheless, the use of the stochastic fractal search algorithm has resulted in considerable enhancement in precision and accuracy of the evaluations conducted through the artificial neural network and has enhanced its performance. According to the results, the utilized SFS-MLP technique showed a better performance in the estimation of the compressive strength of concrete (R²=0.99932 and 0.99942, and RMSE=0.32611 and 0.24922). The novelty of our study is the use of a large dataset composed of 1030 entries and optimization of the learning scheme of the neural prediction model via a data distribution of a 20:80 testing-to-training ratio.

• Steel and Composite Structures
• /
• 제33권3호
• /
• pp.319-332
• /
• 2019

This study is aimed to predict the behaviour of channel shear connectors in composite floor systems at different temperatures. For this purpose, a soft computing approach is adopted. Two novel intelligence methods, including an Extreme Learning Machine (ELM) and a Genetic Programming (GP), are developed. In order to generate the required data for the intelligence methods, several push-out tests were conducted on various channel connectors at different temperatures. The dimension of the channel connectors, temperature, and slip are considered as the inputs of the models, and the strength of the connector is predicted as the output. Next, the performance of the ELM and GP is evaluated by developing an Artificial Neural Network (ANN). Finally, the performance of the ELM, GP, and ANN is compared with each other. Results show that ELM is capable of achieving superior performance indices in comparison with GP and ANN in the case of load prediction. Also, it is found that ELM is not only a very fast algorithm but also a more reliable model.

• Structural Engineering and Mechanics
• /
• 제91권1호
• /
• pp.1-23
• /
• 2024

This paper formulates a new integral shear deformation shell theory to investigate the free vibration response of carbon nanotube (CNT) reinforced structures with only four independent variables, unlike existing shell theories, which invariably and implicitly induce a host of unknowns. This approach guarantees traction-free boundary conditions without shear correction factors, using a non-polynomial hyperbolic warping function for transverse shear deformation and stress. By introducing undetermined integral terms, it will be possible to derive the motion equations with a low order of differentiation, which can facilitate a closed-form solution in conjunction with Navier's procedure. The mechanical properties of the CNT reinforcements are modeled to vary smoothly and gradually through the thickness coordinate, exhibiting different distribution patterns. A comparison study is performed to prove the efficacy of the formulated shell theory via obtained results from existing literature. Further numerical investigations are current and comprehensive in detailing the effects of CNT distribution patterns, volume fractions, and geometrical configurations on the fundamental frequencies of CNT-reinforced nanocomposite shells present here. The current shell theory is assumed to serve as a potent conceptual framework for designing reinforced structures and assessing their mechanical behavior.

• 공학교육연구
• /
• 제24권3호
• /
• pp.50-57
• /
• 2021

Although the mathematics education process in AI education is a very important issue, little cases are reported in developing effective methods on AI and mathematics education at the university level. The universities cover all fields of mathematics in their curriculums, but they lack in connecting and applying the math knowledge to AI in an efficient manner. Students are hardly interested in taking many math courses and it gets worse for the students in humanities, social sciences and arts. But university education is very slow in adapting to rapidly changing new technologies in the real world. AI is a technology that is changing the paradigm of the century, so every one should be familiar with this technology but it requires fundamental math knowledge. It is not fair for the students to study all math subjects and ride on the AI train. We recognize that three key elements, SW knowledge, mathematical knowledge, and domain knowledge, are required in applying AI technology to the real world problems. This study proposes a modular approach of studying mathematics knowledge while connecting the math to different domain problems using AI techniques. We also show a modular curriculum that is developed for using math for AI-driven autonomous driving.

• 한국지능시스템학회논문지
• /
• 제20권1호
• /
• pp.1-6
• /
• 2010

Ying[M.S. Ying, Linguistic quantifiers modeled by Sugeno integrals, Artificial Intelligence 170(2006) 581-606] studied a framework for modeling quantifiers in natural languages in which each linguistic quantifier is represented by a family of fuzzy measures and the truth value of a quantified proposition is evaluated by using Sugeno integral. In this paper, we consider interval-valued fuzzy measures and interval quantifiers which are the generalized concepts of fuzzy measures and quantifiers, respectively. We also investigate logical properties of a first order language with interval quantifiers modeled by the Sugeno integral with respect to an interval-valued fuzzy measures.