rss_2.0Sciendo RSS Feed for Applied Mathematics and Nonlinear Scienceshttps://sciendo.com/journal/AMNShttps://www.sciendo.comhttps://sciendo-parsed.s3.eu-central-1.amazonaws.com/6470a2f171e4585e08aa1c67/cover-image.jpghttps://sciendo.com/journal/AMNS140216https://sciendo.com/article/10.2478/amns.2023.2.00409<abstract><title style='display:none'>Abstract</title> <p>This paper first explores the basic process and characteristics of the intelligent algorithm, calculates its fitness function after setting and initializing the intelligent algorithm population, and iterates continuously to obtain a satisfactory optimal solution on the basis of the initialized stochastic solution. Then the optimization of the firefly algorithm is studied. After initializing the firefly population, the random attraction model and the probability factor are introduced to optimize the algorithm. Then, the power scheduling intelligent agent strategy is studied in depth, and the structure and operation process of the intelligent agent operation strategy is determined, as well as its application areas are studied. Finally, the effect of grid load forecasting by power dispatching intelligent agents is analyzed and compared before and after the application of intelligent agent operation strategy in the power system. In terms of grid load prediction accuracy, the actual and prediction errors are basically between 0.02-0.16, which is very close to the actual value. In terms of user satisfaction, the previous user satisfaction was basically 0.75-0.8, and the maximum satisfaction was basically increased to more than 0.9 after applying the intelligent agent operation strategy. The intelligent agent operation strategy based on an intelligent optimization algorithm can effectively dispatch the power system and improve user satisfaction.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/amns.2023.2.004092023-09-30T00:00:00.000+00:00https://sciendo.com/article/10.2478/amns.2023.2.00404<abstract><title style='display:none'>Abstract</title> <p>In order to explore the challenges and optimization paths faced by ideological and political education in colleges and universities under the Internet environment. This paper establishes a comprehensive evaluation model for the ranking of university online public opinion, conducts quantitative posture analysis based on rank affiliation function, starts qualitative posture analysis based on language grade evaluation, determines objective weights of quantitative and qualitative posture ranking indicators by using deviation method, uses binary, ordered ratio method to determine for expert weights, and integrates subjective and objective assignments based on empirical factors. After establishing the comprehensive evaluation of the posture level of college network public opinion, the influence of network public opinion on thinking and political education was analyzed: bad network information can easily distort college students’ ideology and value orientation, and the posture level evaluation of the influence of network public opinion on college students’ values reached −0.85. Meanwhile, the network public opinion hinders the formation of the moral sentiment of college students, and the posture level evaluation of the influence reached −0.67. This study analyzes the influence of college network public opinion on thinking and politics from both qualitative and quantitative aspects and provides an intentional reference for college thinking and politics education to respond effectively to the network environment.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/amns.2023.2.004042023-09-30T00:00:00.000+00:00https://sciendo.com/article/10.2478/amns.2023.2.00389<abstract><title style='display:none'>Abstract</title> <p>Intelligent control of heavy dielectric coal beneficiation in coal plants is achieved with the help of deep learning models to optimize the control effect. In this paper, through the study of heavy dielectric coal separation methods and processes, a coal separation control optimization strategy based on a radial basis neural network optimized by the ant colony algorithm is proposed, and the RBF network is optimized by clustering using ant colony algorithm, which is used to determine the center and radius of the basic function of the RBF network. The suspension density, ash content of the fine coal and the level of the Hopper bucket, which affect the control effect, are selected as the inputs of the optimized model, and the control strategy is formulated according to the effect after adjusting the parameters. The experimental simulation results show that the ACO-RBF model has less oscillation when the ash value is changed, the final change is smoother, and the root mean square error of the ash value is 0.075%, which is 36.6% less than that of the PID algorithm. With the control strategy optimized by deep learning, the fluctuation range of the level of the qualified media barrel is controlled between 15 and 25 cm, and the volatility pattern of the level is more regular. The control system based on deep learning can better meet the requirements of the coal processing process and effectively improve the efficiency of a coal processing plant.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/amns.2023.2.003892023-09-27T00:00:00.000+00:00https://sciendo.com/article/10.2478/amns.2023.2.00391<abstract><title style='display:none'>Abstract</title> <p>Risk analysis of investment decision-making behavior is to improve the ability to prevent investment risks in order to guarantee the success rate of investment decisions. In this paper, the risk evaluation level is determined by calculating the correlation degree of risk indicators through the establishment of the material topology matrix, and the gray evaluation coefficients are determined by using the gray correlation analysis of the whitening weight function to construct the gray evaluation model. The risk index factors and the overall gray evaluation were analyzed by using the material topology model and the gray evaluation model. From the physical topology evaluation, the market risk correlation is −0.00825, which means the special level risk. From the grey comprehensive evaluation score, the overall evaluation score is 6.884 overall risk level is medium grade line. This shows that using the model constructed in this paper can effectively realize the risk analysis of investment decisions and provide a guidance basis for investors to take effective measures for different types of risks.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/amns.2023.2.003912023-09-27T00:00:00.000+00:00https://sciendo.com/article/10.2478/amns.2023.2.00407<abstract><title style='display:none'>Abstract</title> <p>This paper begins with the multi-level processing of instructional multi-source data using information fusion techniques, with varying degrees of abstraction of the raw data for each level of processing. The set of all possible outcomes that an instructional framework can recognize for a given instructional problem is identified through D-S evidence theory. Secondly, the <italic>m</italic> factors that affect the object of teaching evaluation are grouped into the set of factors affecting the evaluation by fuzzy evaluation method, and their factor set weight values are calculated. Finally, the teaching quality evaluation system was constructed based on the factor set weight values. The results show that the experimental obtained Kendall’s harmony coefficient reaches 0.9028, and the evaluation is reliable. The overall score rate in teaching and assessment evaluation is 0.71 to reach the expected value, which indicates that the teaching quality evaluation index system established this time has relatively good internal consistency. The evaluation index system constructed in this paper makes the classroom teaching evaluation highly operable, which can be accepted by students and teachers in the evaluation process and ensures the accuracy of the evaluation results.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/amns.2023.2.004072023-09-30T00:00:00.000+00:00https://sciendo.com/article/10.2478/amns.2023.2.00408<abstract><title style='display:none'>Abstract</title> <p>A more effective instructional method is proposed to address the shortcomings of current college soccer training activities. In this paper, 30 students with comparable soccer quality in colleges and universities were selected and divided equally into experimental and control groups, with the experimental group using SAQ training methods and the control group using traditional training methods. The square dribbling test, 15-meter zigzag dribbling test, straight line with the ball around the barrel test and DAT non-directional dribbling test were selected as the dribbling ability test indexes, and the cross quadrant jump, Illinois test, cross disguised running and Nebraska test were selected as the agility quality test indexes. The analysis of the data measured before and after the experiment by factor analysis showed that the Р values of the players in the experimental group were less than 0.05 in the square dribble and DAT non-directional dribble test, and the Р values were greater than 0.05 in the comparison of the linear barrel test. This study used a scientific analysis method to investigate soccer training activities in colleges and universities, which can effectively optimize the instructional methods of soccer training.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/amns.2023.2.004082023-09-30T00:00:00.000+00:00https://sciendo.com/article/10.2478/amns.2023.2.00397<abstract><title style='display:none'>Abstract</title> <p>The current hotspots of empirical analysis of piano performance skills mainly focus on the recognition of single notes, and there are some limitations in recognition accuracy and noise resistance performance. In this paper, to address this problem, firstly, on the basis of big data, we propose to realize the segmentation of the music section and noise section based on the single-port limit energy difference method and perform note onset and stop detection for the music section based on LMS adaptive filtering algorithm, using the musical characteristics of piano to identify the energy jumping point, which effectively improves the accuracy of note onset and stop detection and avoids the situation of missing and wrong diagnosis. Then the piano piece was played as an example, and the scientific evaluation of the piano performance skills was made based on the results of the determination of note types. The results showed that the errors of the eight notes of the piece were 0.9%, 0.30%, 0.24%, 0.28%, 0.34%, 0.11%, 0.63% and 0.28%. The correct rate of determining the types of notes in the performance technique of the music was 100%, and the error of determining all notes was controlled within 1%. This study provides a reference standard for evaluating the quality of music performance and has broad application prospects in the fields of family leisure, music tutoring, etc.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/amns.2023.2.003972023-09-30T00:00:00.000+00:00https://sciendo.com/article/10.2478/amns.2023.2.00388<abstract><title style='display:none'>Abstract</title> <p>Optimizing the intelligent decision-making system of coal processing plants is better to improve the economic efficiency of coal processing plants and realize the high-quality development of coal processing plants. In this paper, an integrated intelligent decision-making platform for a coal processing plant is constructed based on big data technology, and the intelligent data analysis techniques of the platform are optimized by using an improved whale optimization algorithm and BP neural network. Examples analyze the optimized crude coal slurry and flotation systems’ processes, and the economic benefits are analyzed. From the optimization of the crude coal slurry sorting system, the ash content in the 0.25mm particle size region was reduced from 55.37% to 13.12%, and the ash content in the −0.125mm particle size region was reduced from 42.68% to 15.96%. From the flotation system optimization, when the flotation time increases from 120s to 180s, the ash content increases from 16.27% to 17.19%, and then to 240s, the ash content increases to 19.44%. Using the integrated intelligent decision-making platform can achieve a net increase in revenue of 4,276,800 yuan for the crude coal slurry sorting system and a net increase of 11,274,200 yuan for the flotation system. This shows that the integrated intelligent decision-making platform can improve the coal processing plant’s quality and efficiency and promote intelligent production.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/amns.2023.2.003882023-09-27T00:00:00.000+00:00https://sciendo.com/article/10.2478/amns.2023.2.00383<abstract><title style='display:none'>Abstract</title> <p>In this paper, firstly, based on the application model of optimal scheduling of machining system for green manufacturing, two application models of the energy-saving scheduling model and energy-saving and noise-reducing scheduling model in a multi-model framework are combined, and the resource environment coefficient matrix of the two application models is established as well as the solution process is studied with the parallel machine problem. Then the system's architecture is constructed, and its basic operation flow, functional modules, etc., are designed and conceived. The application of the system is studied in conjunction with a gear machining workshop of a machine tool factory, and the machining system's energy and noise reduction performance is verified based on experiments. The results show that the energy consumption of the machining system is reduced by 0.514 kW-h by machining only the above six gear parts with a small difference in the maximum machining completion time and that the spindle speed has the most significant effect on the machine tool machining noise at a significance level <italic>α</italic> of 0.05. The analysis of this study verifies that the energy-saving and noise-reducing scheduling arrangement method can reduce the system machining energy consumption and noise, which is important for green manufacturing.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/amns.2023.2.003832023-09-27T00:00:00.000+00:00https://sciendo.com/article/10.2478/amns.2023.2.00381<abstract><title style='display:none'>Abstract</title> <p>This paper firstly analyzes the network topology model of the UAV cluster network and wireless 5G communication channel model by modeling and briefly analyzes the idea of topology movement control for flying self-organized networks. Then, a cluster-based structure and reinforcement learning clustered routing protocol is proposed for the problem of easy breakage of routing forwarding paths caused by smart inspection of transmission lines based on UAV clusters for 5G communication. Finally, a cluster structure-based precedence routing protocol is designed, an adaptive routing protocol based on location and link quality Q-learning is used between clusters, and fast and reliable routing is achieved by combining the routing table maintained by itself. The simulation results show that ARP-L-Q (average end-to-end delay 4.22, average packet loss rate 88.09%, average packet rate 2.37, average control overhead 2.52) protocol performs better than GPSR and GACB protocols, and the experiment verifies that ARP-L-Q protocol can better achieve the high dynamic reconfiguration, high stability and reliability, and low communication delay of UAV cluster-based 5G communication network. Characteristics and requirements. This study has application prospects in both civil emergency and military mobile communication and has certain military significance, theoretical value and application value for thus promoting UAV innovation.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/amns.2023.2.003812023-09-27T00:00:00.000+00:00https://sciendo.com/article/10.2478/amns.2023.2.00375<abstract><title style='display:none'>Abstract</title> <p>This paper firstly constructs a reasonable education resource model according to the features of Civic Education Resources (CERs) and proposes an integration scheme of CER Library in universities based on information fusion technology. Secondly, the storage structure of Lucene’s inverted index is optimized for the management features of the CER Model, and a full-text index library of educational resources for resource retrieval is constructed. Then the advantages and features of information fusion techniques are used to provide college students with exclusive, practical, personalized and customized Civic Education measures to innovate the concept of ideological and political education (IPE) in colleges and universities. Finally, through the subject index of ideological education resources constructed based on the LDA model, the semantic processing of user queries, the design of effective experimentations to confirm the accuracy of the retrieval of ideological education resources, and its evaluation indexes are considered comprehensively from several aspects such as retrieval speed and accuracy rate. The results show that the maximum <italic>P</italic> @ <italic>N</italic> value of improved Lucene index retrieval is 1, which is 0.4 larger than that of traditional Lucene-based index retrieval, and the average performance of improved Lucene index retrieval is improved than that of traditional Lucene-based index retrieval in <italic>P</italic> @ <italic>N</italic> indexes. This study helps universities to innovate the concept of IPE to retain the ideas up to date and retain pace with the times.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/amns.2023.2.003752023-09-27T00:00:00.000+00:00https://sciendo.com/article/10.2478/amns.2023.2.00373<abstract><title style='display:none'>Abstract</title> <p>This paper combines machine learning with acoustic features to design an automatic pronunciation error correction system. The article first adopts Meier’s inverse spectral coefficients and random forest algorithm to classify and detect learners’ pronunciation errors and clarify learners’ pronunciation problems, from which the MFCC-RF model is proposed. Then, using the feature self-learning capability of deep belief networks and the OneClass idea of SVM, we proposed a DBN-SVM model to overcome the shortcomings of the MFCC-RF model in pronunciation classification and error detection due to unbalanced samples and missing data, which resulted in low error detection rate and poor coverage of error types. By comparing the model’s performance for pronunciation error detection, the DBN-SVM model was more accurate than the other two algorithms in detecting the three error types with a stable accuracy of around 80%. Finally, when the experimental class was taught with the automatic pronunciation error correction system, the experimental class improved by 19.5 points after one semester of study, while the control class only improved by 6.8 points. Hence, the DBN-SVM model-based pronunciation mistake correction system has significantly impacted the speed of change and advancement in English teaching techniques while substantially enhancing the quality of oral pronunciation and learning efficiency of English learners.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/amns.2023.2.003732023-09-27T00:00:00.000+00:00https://sciendo.com/article/10.2478/amns.2023.2.00360<abstract> <title style='display:none'>Abstract</title> <p>In this paper, we first investigate the steps to implement a fusion algorithm that determines the quality function through fuzzy theory. Then, we utilize D-S evidence theory for decision-level fusion to identify the target data based on the collected data. The two algorithms, fuzzy theory and D-S evidence theory, are then combined. The affiliation function in fuzzy theory calculates the information collected from the sensors to find out the confidence level and patterns. Finally, the information fusion technology was analyzed in terms of its usage rate in music theory teaching, its impact on piano playing, and its impact on music theory teaching. In terms of utilization rate, 21 student teachers had information fusion technology utilization rate between 50% and 60%, and 21 student teachers had information fusion technology utilization rate between 50% and 60%. In terms of the impact of information fusion technology on the teaching of music theory, a comparative analysis of the pre and post test data T=−6.55 (P&lt;0.0001) showed that the difference in the post test data was significantly higher than that of the pre test. This indicates that the facilitating effect of information fusion technology on music theory teaching is obvious.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/amns.2023.2.003602023-09-23T00:00:00.000+00:00https://sciendo.com/article/10.2478/amns.2023.2.00356<abstract> <title style='display:none'>Abstract</title> <p>In this paper, the inertia weighting strategy of the particle swarm is improved by using the properties of periodicity and fixed upper and lower bounds of sinusoidal function to model the task scheduling problem in cloud computing as a mathematical problem, and the improved particle swarm algorithm is discretized, and the improved discrete particle swarm algorithm is applied to task scheduling by corresponding encoding method. The task scheduling algorithm (PSOACO) that fuses the fast convergence and small computational power of the particle swarm algorithm with the global exploration capability of the ant colony algorithm for scheduling tasks is proposed. Two test cases, PageRank and wordcount, are selected to measure the performance of the PSO-ACO algorithm. In the performance comparison running the PageRank test case, the PSO-ACO algorithm obtains a performance speedup ratio of 3.8 times that of the native Domino when 50,000 pages are added. In the execution time comparison for the wordcount test case with an additional data set, the PSO-ACO algorithm is nearly 2.8 times faster than the native Domino when adding 1GB of data. Thus, the fusion algorithm reduces the task completion time and achieves a balance between the algorithm’s computational effort and the scheduling’s convergence performance.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/amns.2023.2.003562023-09-23T00:00:00.000+00:00https://sciendo.com/article/10.2478/amns.2023.2.00362<abstract> <title style='display:none'>Abstract</title> <p>Employment management in higher education institutions has an important influence on the employment situation of graduates, and this study aims to give corresponding countermeasures by analyzing the current situation of employment management. This paper investigates and studies the employment situation and the perceptions of employment management of graduates from higher education institutions and obtains relevant data on employment and employment management. The correlation between career guidance courses, career guidance methods and career guidance websites and graduates’ employment rate is analyzed using multiple regression methods to develop countermeasures for employment management optimization. The regression coefficients of professional construction, ideological construction and psychological counseling of career guidance courses on their comprehensive evaluation were 0.1654, 0.0872 and −0.0475, respectively. The regression coefficients of the three influencing factors on the comprehensive evaluation of the career guidance website were 0.7485, −0.0213 and 0.1457. the regression coefficients of the three influencing factors on the comprehensive evaluation of career guidance methods were 0.7485, −0.0213 and 0.1457. The multiple regression models achieved good significance. Based on the multiple regression analysis, the key factors of employment management in higher education institutions were clarified by data modeling methods, which helped to better propose countermeasures for employment management.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/amns.2023.2.003622023-09-23T00:00:00.000+00:00https://sciendo.com/article/10.2478/amns.2023.2.00410<abstract><title style='display:none'>Abstract</title> <p>In this paper, a decision model for grid fault diagnosis based on multi-source information fusion is established, and the probability of component fault is obtained by using the change of switching quantity characteristic information and electrical quantity characteristic information during grid fault, and the static fault degree obtained by switching quantity information and the voltage and current energy distortion degree and fault degree obtained by electrical quantity information is used as independent evidence bodies, which are fused by improved D-S evidence fusion technique, and the fused The results are decided by improved fuzzy C-mean decision model to finally determine the fault components. Then, the optimal control of the grid is studied, and the corresponding self-healing control model is established according to the different operating conditions of the system so as to propose a self-healing control strategy of the microgrid based on the improved particle swarm algorithm. After analysis and verification, the accuracy of the grid fault diagnosis method proposed in this paper reaches 0.9681, and the diagnosis results are consistent with the pre-defined fault elements compared with FCM. The system network loss decreases from 0.146 kW to 0.031 kW, and the maximum power supply capacity increases from 1.574 to 2.468 after using the improved particle swarm algorithm-based microgrid self-healing control strategy. Therefore, the method in this paper can improve the reliability of grid operation and resist the risk of accidents.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/amns.2023.2.004102023-09-30T00:00:00.000+00:00https://sciendo.com/article/10.2478/amns.2023.2.00406<abstract><title style='display:none'>Abstract</title> <p>Exploring the majorization strategy of the power system (PS) dispatching operation is to achieve economic cost reduction and reduce environmental pollution. In this paper, starting from the PS dispatching model, the adaptive Corsi variance is introduced to get rid of the local optimum using particle swarm majorization procedure, and the adaptive Corsi variance multiple swarm coevolutionary procedure is constructed through coevolutionary strategy and information sharing strategy. The MCPSO-ACPM procedure is used to optimize the PS scheduling operation model, and experiments are conducted on both load and unit for the optimized scheduling model. From the load majorization results, the peak-to-valley variance is concentrated from 176.02KW to 110.51KW compared with the original load, and the peak-to-valley ratio is reduced by 0.718, which saves customers 98.63 yuan in electricity purchase cost. From the scheduling majorization prediction, the PS output power prediction value of 1 min during the day is closest to the actual measured value of output power, and its prediction deviation is about 2.67%. This shows that the use of a multi-objective majorization procedure can realize the optimal dispatch of PS and achieve the reduction of economic cost.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/amns.2023.2.004062023-09-30T00:00:00.000+00:00https://sciendo.com/article/10.2478/amns.2023.2.00405<abstract><title style='display:none'>Abstract</title> <p>Teaching behavior recognition has a wide range of applications in the smart classroom and is one of the important means to achieve educational intelligence. To improve the performance of indoor teaching behavior recognition using CSI in complex scenes, this paper proposes an indoor teaching behavior recognition algorithm based on multi-feature fusion MLSTM by eliminating background noise to circumvent the influence of the experimental environment on CSI. To address the problem, the model cannot generalize in recognizing new users, and the labeled samples of new users are difficult to obtain in large quantities in a short period of time. In this paper, a new user recognition algorithm based on the SSGAN model is constructed, and then the input and output of MLSTM are modified as the discriminator of SSGAN to improve the recognition performance of the model for new users by semi-supervised learning. The recognition accuracy of the M-LSTM model on the sports, daily, and dance datasets is 0.985, 0.966, and 0.944, respectively, and the recognition accuracy of the SSGAN model on the three datasets is also around 90%, as verified by different experiments. The p-value is less than 0.05, and the student’s interest in physical education in the experimental group is 2.6 times higher than that in the control group. Therefore, the model proposed in this paper has good practicality.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/amns.2023.2.004052023-09-30T00:00:00.000+00:00https://sciendo.com/article/10.2478/amns.2023.2.00403<abstract><title style='display:none'>Abstract</title> <p>Although research into big data technologies is advancing quickly, it has not yet been used for the “party building + political thinking” paradigm of grassroots mass organizations. The structure, purpose, and method of clustering analysis in data mining technology, as well as the various data types involved in clustering analysis technology, are studied in this paper after first analyzing the development status of data mining technology and the issues in the process of data mining. Secondly, we investigate the advantages of big data mining for “Party formation + Civic Affairs” at the local level, including four points, the management of grassroots party members, the education of party members, the ideological dynamics of party members and cadres, and the development of the relationship between party groups and teachers and students. Moreover, the “task assessment quantification table” from the “party building + thinking and politics” model was utilized as the data source, and cluster analysis was carried out using the k-mean technique. The percentages of the three categories of grades in the cluster assessment, which were 30%, 62%, and 8%, were found to be compatible with the percentages of the three categories of scores, which were 21%, 68%, and 11%. This study brings some reference significance to both party building and thinking and the government work of college counselors; this contributes to raising the bar for political thinking, party organization, and governance.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/amns.2023.2.004032023-09-30T00:00:00.000+00:00https://sciendo.com/article/10.2478/amns.2023.2.00400<abstract><title style='display:none'>Abstract</title> <p>As society requires a deeper understanding and demand for the actual abilities of students in higher education institutions, traditional assessment tests no longer meet the current needs. This paper first divides assessment techniques into two main categories from an application perspective: assessment of student learning performance and in-depth cognitive diagnosis. Students are automatically provided with appropriate learning content based on their ability level and learning style, providing them with accurate and timely feedback. Secondly, a new fuzzy inference model is proposed to determine students’ student outcomes by addressing the obvious shortcomings of the fuzzy sets usually used for student outcome assessment. Finally, the validity and usefulness of its assessment model are verified by the student learning performance on a real data set. The results show that the fuzzy inference assessment model designed in this paper can obtain an assessment accuracy of 85.8% for the learner’s learning outcomes, which has a good assessment effect. And the fuzzy inference assessment model also retains the greatest advantage of linear fitting regression, which reflects the correlation between the parameters of students’ learning behaviors and the final learning outcomes. The assessment method based on the fuzzy inference model predicts learners’ learning risks and provides learning interventions in advance for smart learning, and also provides new ideas for deepening education reform.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/amns.2023.2.004002023-09-30T00:00:00.000+00:00en-us-1