Using neural network for the evaluation of physical education teaching in colleges and universities

Han, Qiuhong

doi:10.1007/s00500-022-06848-9

Cited by 12 publications

(8 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(ii) Stage 2: initialize the fundamental parameters of the joint nerve method, such as h and f, V max , P, and Q, establish the FNN network topology, and initialize the weighting and sensitivities. (iii) Stage 3: use formula (13) to start the population of the joint nerve algorithm, and then use the FNN model to get weights and thresholds to start everyone in each population at the same place.…”

Section: Computational Intelligence and Neurosciencementioning

confidence: 99%

“…As a novel technology, artificial neural networks have nonlinear processing, adaptive learning, and great fault tolerance. Liu et al [ 13 ] illustrated an AI “Neural Network Back-Propagation (BP)” algorithm and stress difficulty is used to evaluate undergraduate education quality. Bai [ 15 ] achieved the current state of college students' English learning (EL) adaptability supported by AI; this study investigates and analyses college students' EL adaptability supported by AI and proposes strategies to improve students' adaptability.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A Fuzzy Neural Network-Based Evaluation Method for Physical Education Teaching Management in Colleges

Zhao

Liu

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

A novel Fuzzy Neural Network (FNN) teaching quality assessment model of physical education (PE) is presented at colleges and universities to enhance the validity of PE teaching quality evaluation. It is being done to enhance the accuracy of quality evaluations of PE instruction. In the first phase, out of 4 aspects of teaching material, teaching method, teaching attitude, and teaching effect, a multi-index assessment process of university physical education teacher performance based on the analytic hierarchy process (AHP) is created. The effectiveness of college PE instructors is assessed using this approach. The FNN model is used to develop a teaching quality assessment model for college PE courses. The FNN’s parameter is the score data, and the FNN’s output vector is equipped with better college PE (excellent, good, average, and low). In terms of assessing the instructional excellence of PE courses in colleges and universities, FNN has been proven to have superior classification accuracy, specificity, sensitivity, and F1 score when compared to other methods. When compared to other countries, this is the case. The proposed approaches resulted in a score of 96% for accuracy, 95% for specificity, 90% for sensitivity, and an F1 score of 94% for performance. The effectiveness of the proposed approach is shown by comparing the outcomes to those of standard physical education teaching strategies.

show abstract

Section: Computational Intelligence and Neurosciencementioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

A Fuzzy Neural Network-Based Evaluation Method for Physical Education Teaching Management in Colleges

Zhao

Liu

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…Additionally, Yu and Chen (2023) propose an evaluation model for entrepreneurship education based on a BP neural network, underscoring the role of such systems in promoting innovation and enterprise among students. The literature also explores diverse domains within college education, such as music art teaching quality evaluation (Xu & Xia, 2022; Lan & Fan, 2022), physical education teaching assessment (Han, 2022), and the organic integration of ideological and political education with entrepreneurship education (Yongliang, 2023). These studies collectively contribute to a comprehensive understanding of assessment methodologies and their applications across various disciplines and educational contexts.…”

Section: Related Workmentioning

confidence: 99%

“…During the training process, the network learns to recognize patterns and correlations between input parameters and desired outcomes, such as academic success or personal growth. [16] Through iterative adjustments of weights and biases, the network optimizes its performance in predicting these outcomes based on the input data.…”

Section: Introductionmentioning

confidence: 99%

Design And Realization of A Comprehensive Quality Assessment System for College Students Based on the Bp Neural Network

2024

jes

View full text Add to dashboard Cite

Educational evaluation plays a crucial role in ensuring the quality and effectiveness of teaching, learning, and institutional performance. Traditional evaluation methods often struggle to capture the complex and multifaceted nature of educational processes, leading to limitations in assessing quality comprehensively. In response, this paper introduces the Fuzzy Interface Memetic Algorithm for Quality Assessment (FIMA-QA), a novel framework that integrates fuzzy logic modeling with memetic algorithm optimization to provide a nuanced and adaptable approach to educational evaluation. FIMA-QA leverages fuzzy logic principles to represent input variables and assessment criteria in linguistic terms, allowing for the expression of qualitative relationships and uncertainties inherent in educational assessment. Through memetic algorithm optimization, FIMA-QA iteratively refines fuzzy rule bases to enhance assessment accuracy and reliability over successive generations. This combination of fuzzy logic modeling and evolutionary optimization enables FIMA-QA to effectively evaluate various dimensions of educational quality, including teaching effectiveness, student engagement, learning outcomes, and institutional performance. Empirical studies demonstrate the efficacy of FIMA-QA in capturing the qualitative nature of assessment criteria and providing accurate and comprehensive evaluations of educational processes. For instance, teaching effectiveness assessments ranged from 7.5 to 9.8, student engagement from 8.2 to 9.5, learning outcomes from 8.0 to 8.9, and institutional performance from 8.7 to 9.4, showcasing the numerical precision of FIMA-QA.

show abstract

“…To comprehensively assess the effectiveness of both regional economic development and the cultivation of applied undergraduate students in the context of data science, a robust evaluation index framework is imperative [4]. This framework becomes the linchpin for policymakers and researchers, offering a systematic approach to gauge the impact and outcomes of initiatives and programs.…”

Section: Literature Reviewmentioning

confidence: 99%

A Mixed-Methods Data Approach Integrating Importance-Performance Analysis (IPA) and Kaiser-Meyer-Olkin (KMO) in Applied Talent Cultivation

2024

J. Appl. Data Sci.

View full text Add to dashboard Cite

This study endeavors to establish an assessment framework for cultivating undergraduate applied talent, specifically emphasizing data science competencies, in alignment with the development of China's regional economy. A mixed-methods approach, integrating focus group interviews and questionnaire surveys conducted over three rounds of data collection, was employed. The collected data underwent rigorous reliability and validity analyses utilizing SPSS software. An Importance-Performance Analysis (IPA) was executed to construct a performance chart, evaluating the effectiveness of a 24-item framework designed to encompass key aspects of data science education. The initial internal consistency α coefficients for Questionnaire 2 and Questionnaire 3 were found to be .892 and .913, respectively, surpassing the 0.7 threshold, indicating a high level of reliability for all items related to data science competencies. The Kaiser-Meyer-Olkin (KMO) measurements approaching approximately 0.9 affirmed the efficiency of the questionnaire, specifically designed to gauge the relevance and effectiveness of data science-related indicators in the context of applied talent cultivation and regional economic development. Furthermore, the study underscores the significance of indicators such as teamwork, regional market research, and business opportunity identification within the domain of data science. It identifies gaps between key indicators and lower-performing indicators, proposing strategic improvement measures to enhance the alignment of applied talent cultivation objectives with the evolving needs of regional economic development, particularly in the data science landscape. The research findings not only contribute to a foundational understanding of data science competencies in applied talent cultivation but also lay the groundwork for innovative reforms in future talent cultivation models. By clarifying objectives and better aligning them with the dynamic demands of regional economic development, this study sets the stage for transformative advancements in the field of applied talent cultivation, particularly within the realm of data science.

show abstract

Using neural network for the evaluation of physical education teaching in colleges and universities

Cited by 12 publications

References 5 publications

A Fuzzy Neural Network-Based Evaluation Method for Physical Education Teaching Management in Colleges

A Fuzzy Neural Network-Based Evaluation Method for Physical Education Teaching Management in Colleges

Design And Realization of A Comprehensive Quality Assessment System for College Students Based on the Bp Neural Network

A Mixed-Methods Data Approach Integrating Importance-Performance Analysis (IPA) and Kaiser-Meyer-Olkin (KMO) in Applied Talent Cultivation

Contact Info

Product

Resources

About