International Journal of Continuing Engineering Education and Life-Long Learning (17 papers in press)

Regular Issues

• Quality improvement on minimum-storage-overhead image processing scheme in encrypted domain  
  by Shushan Zhao 
  Abstract: Image processing in encrypted domain is needed in many services while many image processing tasks are outsourced to third party cloud computing platforms for data confidentiality and privacy-preserving purposes. There are many solutions for image scaling, cropping and colour correction in this context. However, most of the solutions are not compatible with each other and there is few solutions supporting all these operations. In our previous work (Zhao, 2022), we propose a scheme that supports image scaling, cropping, and colour correction in encrypted domain with minimum storage overhead. We notice that the image quality achieved is not satisfactory in some circumstances, and in this work, we propose a quality improvement solution to address this issue. The new scheme provides satisfactory quality in all cases considered, with 2.6% storage overhead increase as analysis shows in this paper.
  Keywords: image processing; scaling; cropping; colour correction; encrypted domain.
  DOI: 10.1504/IJMIS.2023.10055512
   
  
• Applicability of the design thinking process to the development of capstone project proposals  
  by Fernando Cezar Leandro Scramim , Rui M. Lima, Hong Yuh Ching, Denise L. Rieg 
  Abstract: The purpose of this paper is to present an empirical study that explores how design thinking can be applied to develop ideas for capstone projects in undergraduate engineering programs. Action research was the research method used in this study. The collected data consisted of students’ project proposals, grades, classroom observations, and focus group findings. This study has two levels of implications: 1) for the practice of educators, as they can adjust the approach developed to help undergraduate engineering students find a potential idea for a viable and relevant capstone project; 2) for research, thereby adding to the ongoing discussion on exploring the design thinking process as a conceptual structure that provides a basis for dealing with difficult situations and solving complex problems in undergraduate courses.
  Keywords: design thinking process; capstone project; engineering education; scientific methodology course; project-based learning; PBL.
  DOI: 10.1504/IJCEELL.2024.10060500
   
  
• Intelligent Q&A system for distance education in universities based on Chinese word segmentation technology  
  by Qian Zhong, Yujie Jiang, Honglin Du 
  Abstract: In order to improve the accuracy of the question answering system, an intelligent question answering system for college distance education based on Chinese word segmentation technology is proposed and designed. First, the overall architecture of the intelligent question answering system for distance education in colleges and universities is designed, and then the user login display module, Chinese word segmentation module, algorithm module and other functional modules are designed. Finally, the system software is designed to optimise Chinese word segmentation technology through heuristic rules and pruning methods. The optimised Chinese word segmentation technology is applied to make the system better understand the questions or instructions input by users, and realise the intelligent question answering in college distance education. The experimental results show that after the application of this system, the accuracy rate of answering questions can reach 0.94, the highest value of TPS is 15.29, and the score range of user satisfaction is [87.4, 95.6], which has a good application effect.
  Keywords: Chinese word segmentation technology; distance education; wisdom in answering questions; heuristic rules; pruning method.
  DOI: 10.1504/IJCEELL.2024.10065809
   
  
• Non-technical skills in engineering education as a concept  
  by Christin Lindholm, Christian Nyberg, Ylva Oscarsson 
  Abstract: To have a successful career in engineering, students need both technical engineering skills and non-technical engineering skills (NTES) in the transition to professional life. To address NTES in engineering education, the concept of six compulsory engineering days were introduced in two engineering programs at the undergraduate level. The importance of different NTES for industry has been evaluated through a survey with industry representatives. The results from the survey support the assumption that NTES are important when working as an engineer. The concept of engineering days has also been evaluated through a survey that was taken by the final-year students. Overall, the student survey showed that the students understood what the purpose of the concept of engineering days was, and that the students estimated that they had increased their NTES. With this work, we hope to inspire teachers to focus on non-technical skills as well as technical skills.
  Keywords: non-technical skills; engineering education; soft skills; industry; higher education; survey; Bachelor of Science in Computer Engineering; Bachelor of Science Electrical in Engineering with Automation; professional life; concept; certification.
  DOI: 10.1504/IJCEELL.2024.10065547
   
  

Special Issue on: Artificial Intelligence Technologies for Education Advancements Challenges and Management

• A collaborative filtering and recommendation method for digital resources of Chinese language courses  
  by Xiancui Li, Haoli Lu 
  Abstract: A collaborative filtering and recommendation method for digital resources of Chinese language courses based on similarity algorithm is studied to solve the problem of low accuracy in recommending digital resources for Chinese language courses. Firstly, collect and normalise digital resource data; Secondly, the TF-IDF algorithm is used to calculate the feature weights of resource data; Then, learning preference features are extracted by calculating the amount of time students spend on web pages and combining that with collaborative filtering algorithms; Finally, a resource similarity matrix is constructed to achieve collaborative filtering and recommendation of digital resources for Chinese language courses based on the Pearson similarity algorithm. It has been proven that the recommendation accuracy of this method is higher than 95% through experiments, the recommendation time is lower, and the PR curve is closest to the upper right corner, indicating good recommendation performance.
  Keywords: collaborative filtering; Chinese language; feature weight; digitised resources; Pearson similarity.
  DOI: 10.1504/IJCEELL.2025.10067950
   
  
• The impact of AI technology on oral English teaching behaviour under UTAUT model  
  by Zhou Li, Huisuan Wei 
  Abstract: To improve the adaptability and universality of teachers using intelligent technology to analyse the influencing factors of English speaking, this paper proposes a study on the impact of AI technology on English speaking teaching behaviour under the UTAUT model. By identifying the influencing factors and designing a survey questionnaire, a UTAUT model was constructed to study the impact on English oral teaching behaviour. The experimental results show that this study has high adaptability and universality, with an accuracy rate consistently above 90%, indicating that the model has shown good performance in terms of analytical performance. This indicates that the research model is of great significance for a deeper understanding of the role of AI technology in English oral teaching.
  Keywords: UTAUT model; AI technology; English speaking teaching; individual attributes; willingness to use.
  DOI: 10.1504/IJCEELL.2025.10067951
   
  
• Evaluation method of the impact of AI technology application on the quality of smart teaching  
  by Lin Zeng 
  Abstract: Aiming at the problem that the evaluation error is large due to the high data dimension when evaluating the impact of AI technology application on the quality of wisdom teaching, an evaluation method based on principal component analysis (PCA) is proposed. First, the evaluation indicators were selected to build an evaluation index system. Then, covariance and sensitivity were used to improve the PCA method and reduce the data dimension. Finally, BP neural network (BPNN) was improved by steepness factor and weight adjustment to build an evaluation model for the impact of wisdom teaching quality. The experimental results show that the evaluation error of this method is up to 0.02, the satisfaction of the respondents is 96%, and the coefficient of goal achievement is 0.99, so the evaluation effect is good.
  Keywords: principal component analysis; PCA; AI technology; quality of smart teaching; impact assessment.
  DOI: 10.1504/IJCEELL.2025.10067955
   
  
• The impact of mobile learning devices on the English academic performance of college students: factor analysis  
  by Ying Song 
  Abstract: To address the issues of low accuracy and poor effectiveness of factor analysis on the impact of existing mobile learning devices on the English learning performance of college students, based on factor analysis, this study focuses on the impact of mobile learning devices on the English learning performance of college students. Firstly, collect and normalize data on factors influencing academic performance. Then, construct a factor analysis model, calculate the eigenvalues and variance contribution rate, and select common factors. Finally, a multiple linear regression model is constructed to analyze the influencing factors of mobile learning devices on the English learning performance of college students. The experimental results show that the coverage rate of the influencing factors in this method is higher than 93%, the analysis accuracy is high, and the AUC area under the ROC curve is close to 1, indicating good analysis results.
  Keywords: mobile learning devices; college students; English academic performance; factor analysis.
  DOI: 10.1504/IJCEELL.2025.10067956
   
  
• Analysing the influencing factors of mobile English learning for college students: improved principal component analysis  
  by Na Wang, Lili Wang, Yanli Li, Bin Zhang 
  Abstract: Due to the fact that traditional methods for analysing the influencing factors of mobile English learning for college students cannot handle noise and redundant information in the data, reduce data dimensions, and cannot extract the most representative and explanatory factors for data variation. To address this issue, this article proposes an analysis method for the influencing factors of mobile English learning among college students based on an improved principal component analysis method. This method utilises fuzzy association rule algorithm to mine data on the impact of mobile English learning among college students. We constructed evaluation indicators from multiple dimensions to evaluate the influencing factors of mobile English learning among college students. Construct an evaluation function and analyse the influencing factors, and determine the indicators closely related to college students mobile English learning through the score of the evaluation function. The experimental results show that the accuracy of the analysis of influencing factors in this articles method remains above 90%, and the analysis time does not exceed 2 minutes.
  Keywords: improving principal component analysis method; college students; mobile English learning; influence factor.
  DOI: 10.1504/IJCEELL.2025.10067957
   
  
• Evaluation method for the effectiveness of English oral teaching for college students in a blended learning environment  
  by Jia Li 
  Abstract: Due to the fact that traditional methods for analysing the influencing factors of mobile English learning for college students cannot handle noise and redundant information in the data, reduce data dimensions, and cannot extract the most representative and explanatory factors for data variation. To address this issue, this article proposes an analysis method for the influencing factors of mobile English learning among college students based on an improved principal component analysis method. This method utilises fuzzy association rule algorithm to mine data on the impact of mobile English learning among college students. We constructed evaluation indicators from multiple dimensions to evaluate the influencing factors of mobile English learning among college students. Construct an evaluation function and analyse the influencing factors, and determine the indicators closely related to college students’ mobile English learning through the score of the evaluation function. The experimental results show that the accuracy of the analysis of influencing factors in this article’s method remains above 90%, and the analysis time does not exceed 2 minutes.
  Keywords: blended learning environment; oral teaching; k-means data clustering; analytic hierarchy process; AHP.
  DOI: 10.1504/IJCEELL.2025.10067958
   
  
• A method for evaluating the learning effectiveness of MOOC English online education based on fuzzy clustering decision tree  
  by Xiaoxia Yu 
  Abstract: Therefore, this paper proposes a MOOC English online education learning effectiveness evaluation method based on fuzzy clustering decision tree. Firstly, determine the principles for constructing the MOOC English online education learning effectiveness evaluation system, and then use fuzzy clustering algorithm to determine the evaluation indicators. Finally, using the decision tree ID3 algorithm, calculate the attribute and information gain of evaluation indicators, determine the weight of evaluation indicators using the entropy method, construct a fuzzy evaluation matrix, and achieve learning effectiveness evaluation. Through experiments, it has been proven that the coverage rate of the evaluation indicators proposed in this article is always above 90%, and the correlation degree of the evaluation results is always above 0.88. The accuracy of the evaluation is high, and the evaluation effect is good.
  Keywords: fuzzy clustering decision tree; online education; learning effectiveness; evaluation matrix; entropy method.
  DOI: 10.1504/IJCEELL.2025.10067965
   
  
• Study on impact of multimedia technology on the quality of English oral teaching based on stepwise regression analysis  
  by Tao Wei, Xiujuan Wang 
  Abstract: Multimedia technology has a direct impact on the quality of English oral teaching, but there are certain issues with the significance of its impact and the confidence level of the biased F-test for validation. Therefore, this article proposes a study on the impact of multimedia technology on the quality of English oral teaching based on stepwise regression analysis. This study first identifies the impact of multimedia technology on teachers and constructs an impact indicator system. Then, by analyzing characteristic data such as student classroom performance, determine the impact of multimedia technology on students. Finally, using stepwise regression analysis techniques, the significance of the impact of multimedia technology on the quality of English oral teaching is verified. The experimental results indicate that the proposed method can effectively verify the significant impact of multimedia technology on the quality of English oral teaching.
  Keywords: stepwise regression analysis; multimedia technology; English oral teaching; support vector machine; learning feature data.
  DOI: 10.1504/IJCEELL.2025.10067966
   
  
• Analysis of characteristics and learning effectiveness of MOOC learners in the context of big data  
  by Tao Qi  
  Abstract: To improve the pass rate and activity of students in exams, this study proposes a method for analysing the characteristics and learning outcomes of MOOC learners based on big data. Firstly, use Kalman filtering technology to process continuous frame images and obtain the behavioural sequence of MOOC learners. Then, ARIMA model is used to construct the MOOC learning behaviour state space, extract and classify the behavioural features of learners. Finally, select the indicators suitable for learning effectiveness analysis, and calculate the comprehensive score by combining fuzzy membership function and fractal evaluation algorithm. The experimental results show that after the application of this method, the pass rate of students in the exam remains between 96.1% and 98.8%, and the highest activity can reach 0.97, indicating that its application effect is good.
  Keywords: MOOC learning platform; big data; behavioural characteristics; analysis of learning effectiveness.
  DOI: 10.1504/IJCEELL.2025.10067967
   
  
• A method for classifying and mining online teaching data in universities based on decision tree algorithm  
  by Fei Wang, Xiaoyan Wu 
  Abstract: In response to the problems of low execution efficiency and high probability of multi classification loss in the classification mining of online teaching data in universities, this paper proposes a decision tree algorithm based method for classification mining of online teaching data in universities. This method calculates multi class losses through an unbiased risk estimator and minimizes the difference between real and non real labels for data preprocessing. Then, based on the complexity of experience, the degree of feature fitting is considered to determine the set of feature data, and redundant features are removed from the perspective of two-dimensional real space for feature extraction. Finally, use decision tree algorithm for classification mining. The experimental results show that this method improves execution efficiency and reduces the risk of data loss.
  Keywords: decision tree algorithm; online teaching data in universities; classification mining; multi-classification loss; function space.
  DOI: 10.1504/IJCEELL.2025.10067968
   
  
• Intelligent recommendation method for digital teaching resources of online courses based on knowledge graph  
  by Chao Xu 
  Abstract: In order to improve the effectiveness of recommending digital teaching resources for online courses, a research on intelligent recommendation methods for digital teaching resources for online courses based on knowledge graphs is carried out. Firstly, obtain digital teaching resources for online courses, construct a knowledge graph of digital teaching resources for online courses, and then mine interaction data between users to capture their preferences for digital teaching resources for online courses. Finally, comprehensively consider user interests, resource similarity, and knowledge connectivity to complete the intelligent recommendation process design for digital teaching resources for online courses. The experimental results show that the recommendation accuracy of the proposed method is higher than 93.2%, the recall rate is higher than 94.1%, and the highest recommendation coverage can reach 94.6%, all of which are better than the comparison methods, and the application effect is good.
  Keywords: knowledge graph; online courses; digital teaching resources; intelligent recommendation.
  DOI: 10.1504/IJCEELL.2025.10067969
   
  
• Personalised recommendation method for MOOC online educational resources: collaborative filtering algorithm  
  by Min Fan 
  Abstract: In order to address the practical challenges associated with the low recall rate, accuracy, and user satisfaction in conventional personalised recommendation approaches for educational materials, a personalised recommendation method for MOOC online educational resources based on collaborative filtering algorithm is proposed. The mean shift clustering algorithm is used for clustering processing of MOOC platform data, and the MFA algorithm is used to dimensionality reduction process the clustering results. Learner interest are determined by considering the label preference based on frequency weight, time weight, comprehensive frequency and time, as well as learners’ interest preferences for label clusters. Based on the analysis of learner interest, personalised recommendation of MOOC online education resources is achieved using a collaborative filtering algorithm based on semi-supervised learning. Experimental results show that the maximum recall rate of this method is 98.3%, the maximum recommendation accuracy is 97.8%, the mean learner satisfaction is 97.95, indicating good recommendation effectiveness.
  Keywords: collaborative filtering algorithm; MOOC; online educational resources; personalised recommendation; semi-supervised learning.
  
  
• Chinese language curriculum resources pushing method based on knowledge graph and similarity algorithm  
  by Haoli Lu, Xiancui Li 
  Abstract: In order to improve the effect of Chinese course resource push, a method of Chinese course resource push based on knowledge graph and similarity algorithm is proposed. Determine the density of resource data and the dependency relationships between data, and construct a knowledge graph of Chinese language course resources; calculate Min’s distance and cosine distance to determine the continuity of resource data, search for discrete data, determine the frequency of occurrence of Chinese language course resource data with different attributes, and achieve similarity measurement of Chinese language course resources; by cross compressing the characteristics of Chinese language course resources, matching Chinese language course resource data with demanders, introducing a dual push module to push Chinese language course resources, and achieving Chinese language course resource push. The experimental results show that the proposed method can effectively reduce the similarity of push data and improve the efficiency of pushing Chinese language course resources.
  Keywords: knowledge graph; similarity algorithm; Chinese language courses; resource push; cosine distance; triplet.