International Journal of Continuing Engineering Education and Life-Long Learning (19 papers in press)

Regular Issues

• Open Access

  Application of deep reinforcement learning in intelligent interaction design of virtual practice scenarios for labour education in colleges and universities ( Free Full-text Access )

  by Wei Wang, Rui Liu, Zhuo Liu 
  Abstract: This paper proposes an adaptive interaction strategy model based on DQN (Deep Q-Network) to break through the limitations of traditional static design. The proposed model first extracts behavioural features from students’ operation data through CNN (Convolutional Neural Network) to construct state representation. Then, a reward function with task completion and learning efficiency as the goals is designed. Next, the deep Q-network algorithm is used to train the intelligent agent to dynamically adjust the task difficulty, environmental variables, and guidance strategies. Finally, the model is deployed to the virtual platform to achieve real-time optimisation interaction. Experimental results show that the proposed model extracts students’ operation features through CNN, and dynamically adjusts task difficulty and guidance feedback based on DQN, so that students’ participation score reaches 92 points, and the average learning efficiency score reaches 97 points, providing an efficient and personalized solution for labour education in colleges and universities.
  Keywords: deep reinforcement learning; adaptive interaction model; labour education; virtual practice; student participation.
  DOI: 10.1504/IJCEELL.2026.10077148
   
  

• Open Access

  Optimisation of intelligent English grammar error correction based on multi-strategy Pinyin detection and hierarchical enhancement ( Free Full-text Access )

  by Lingling Song 
  Abstract: This study proposes an intelligent grammar correction method integrating multi-strategy Pinyin detection and hierarchical data augmentation to address common errors in Chinese English learners’ writing. A dual-strategy Pinyin detection algorithm combines syllable tree matching and linguistic rules to accurately identify and preserve Pinyin segments. A hierarchical data augmentation approach employs rule-based and model-based back-translation to build diverse parallel corpora targeting typical learner errors. Based on the Transformer architecture, the grammar correction model treats error correction as a sequence-to-sequence task. Results show the Pinyin detector achieves 99.95% accuracy, processing 5,386 words/second with 13.02 MB memory usage. The correction model attains a 40.58 F_{0.5} score and 49.56% accuracy on CoNLL-2014. On CLEC subsets, it achieves 87.5%, 90.2%, and 85.9% accuracy for article, subject-verb agreement, and verb tense errors, respectively. Pinyin false corrections dropped from 65% to 1.8%, demonstrating significant improvement in handling Chinese learners’ English writing.
  Keywords: grammar error correction; GEC; Pinyin detection; data augmentation; Transformer; English.
  DOI: 10.1504/IJCEELL.2026.10077491
   
  

• Open Access

  Teaching quality management in vocational training based on evaluation data processing and improved BPNN ( Free Full-text Access )

  by Ning Li 
  Abstract: In the context of diversified vocational training scenarios, traditional static evaluation is difficult to control teaching quality fluctuations and anomalies in real time and accurately. Therefore, a method has been proposed to integrate the backpropagation neural network model with an improved particle swarm optimisation algorithm. Quantify the impact of input features on teaching quality through MIV, screen key features to reduce data dimensionality, and dynamically adjust the search step size of particle swarm optimisation algorithm accordingly. Capture nonlinear relationships through backpropagation neural networks and improve global optimisation capabilities through particle swarm optimisation. In precision testing, the accuracy of the research model on the test set reached 99.56%. The error rate significantly decreased from the initial 4.02% to the final 2.13%, indicating its strong generalisation ability. This model solves the problem of failing to identify potential teaching risks. It provides a new method for teaching quality management in vocational training.
  Keywords: back propagation neural network; BPNN; particle swarm optimisation; PSO; teaching quality; mean impact value; MIV; management.
  DOI: 10.1504/IJCEELL.2026.10077526
   
  

• Open Access

  Assessing laboratory designs in CDIO implementation for technology and engineering education via fuzzy TOPSIS approach: evidence in the Philippines ( Free Full-text Access )

  by Ryan H. Teo, Rideen M. Sardual, Harvey F. Pangandoyon, Manuel D. Arranguez Jr., Joanna Hel P. Lim, Francis E. Villamor, Noel P. Burgos, Melanie M. Himang 
  Abstract: The implementation of the conceive, design, implement and operate (CDIO) approach in higher education requires laboratories that effectively support hands-on, experiential learning. Although various laboratory configurations have been documented, a structured and comparative decision support framework remains limited for evaluating which designs best enhance student learning, performance, and satisfaction, particularly for evidence-informed curriculum and infrastructure planning. This study applies fuzzy technique for order preference by similarity to ideal solution (TOPSIS) with bootstrap resampling to systematically aggregate expert judgments in evaluating four laboratory designs using five decision criteria, with weights derived from the assessments of eight domain experts. Uncertainty associated with subjective evaluations is addressed through fuzzy modelling and resampling techniques, extending existing applications of fuzzy multi-criteria decision making in CDIO laboratory assessment. The analysis is bounded by expert-based inputs and the set of evaluated laboratory designs, yet it provides practical guidance for academic administrators in selecting laboratory configurations that align with desired educational outcomes. Results indicate that virtual laboratories exhibit the highest overall impact.
  Keywords: CDIO framework; fuzzy TOPSIS; state university; laboratory designs; virtual laboratory; Philippines.
  DOI: 10.1504/IJCEELL.2026.10077591
   
  

Special Issue on: Intelligent Learning Ecosystems AI, Metaverse and Emerging Technologies for Continuing Engineering Education

• Open Access

  Dynamic scene motion target segmentation method for physical education ( Free Full-text Access )

  by Tao Lei, Yi Huang, Zhijuan Zhou 
  Abstract: This paper proposes a segmentation algorithm integrating a spatial attention mechanism with a Mask R-CNN to address safety risks in dynamic physical education scenes and improve motion target segmentation. The method first performs target segmentation using Mask R-CNN, enhances feature representation through spatial attention, and completes monitoring and localization via a visual processor and a conditional convolution instance segmentation model. Experiments show strong performance: a segmentation boundary value of 0.967, F1-score of 96.75%, and 3.27% average absolute error on the YouTube-VOS dataset, with false negative and false positive rates of 1.47% and 1.81%. On the CDnet 2014 dataset, pixel accuracy reaches 95.42% with an iteration time of 4.95 s. On a self-constructed dataset, the method achieves 0.972 average precision and 0.984 panoptic quality. These results demonstrate accurate and efficient motion target segmentation, supporting intelligent physical education applications.
  Keywords: dynamic scene; motion target; physical education; spatial attention mechanism; mask region-based convolutional neural network; MRCNN; volume integral; conditional convolutions for instance segmentation; CondInst.
  DOI: 10.1504/IJCEELL.2026.10077490
   
  

• Open Access

  Learning path planning method for engineering education based on course group knowledge graph and learner portrait ( Free Full-text Access )

  by Nanping Wang, Yuanlin Wang, Ming Jiang 
  Abstract: With the increasing demand for personalised learning support and intelligent recommendation in engineering education, traditional learning path planning methods still face challenges in handling multi-source learner profiles and complex course associations, resulting in low path matching rates and high recommendation latency. To address these issues, this study proposes a learning path recommendation framework integrating knowledge graph modelling and multi-source behaviour perception. The framework combines dynamic knowledge tracing with hierarchical regularised user modelling and knowledge graph embedding with an upper confidence bound strategy to achieve accurate path recommendation. Experimental results show that the proposed model achieves an F1-score of 93.22% on a public dataset, while the average response delay is within 2 seconds. Under noise disturbances, the fluctuation of path similarity remains within ±2.5%, and the course completion rate reaches 97.3% across four engineering disciplines, demonstrating strong accuracy, real-time performance and adaptability.
  Keywords: engineering education; learning path planning; knowledge graph; user profiling; intelligent recommendation.
  DOI: 10.1504/IJCEELL.2026.10077493
   
  

Special Issue on: OA Intelligent Learning Ecosystems AI Metaverse and Emerging Technologies for Continuing Engineering Education

• Open Access

  Construction and application effect analysis of engineering education knowledge graph based on graph convolutional network ( Free Full-text Access )

  by Aijiang Liu, Lixia Zhao 
  Abstract: To address complex knowledge associations in engineering education and the lack of quantitative teaching decision support, this study proposes a knowledge graph (KG) construction method integrating graph convolutional networks. The model employs a transferred dimension embedding approach to enhance entity representation and uses a BERT-BiLSTM-CRF architecture for entity-relationship extraction. Experimental results show the model achieves a mean reciprocal rank of 92.4% in link prediction and an F1 score of 91.2% on an engineering education dataset, significantly improving entity and relation extraction accuracy. A dynamic inference mechanism based on graph attention network also improves multi-hop reasoning performance. The constructed KG effectively maps relationships between courses and graduation requirements, providing data support for teaching intervention and curriculum optimisation.
  Keywords: graph convolutional networks; GCN; engineering education; KG; trans D; transformers; bidirectional long short-term memory networks.
  DOI: 10.1504/IJCEELL.2026.10077085
   
  

• Open Access

  Intelligent English translation scoring method based on multi-angle semantic feature calculation model ( Free Full-text Access )

  by Qiongjie Jing 
  Abstract: The research aims to construct an intelligent scoring model based on multi-angle semantic feature calculation to deal with the deficiencies of traditional methods. The research proposes a multi-angle semantic feature computing model based on a multi-level semantic collaboration mechanism (MMSF-ISM). This model organically integrates the deep semantic representation of BERT, the global attention of transformer, the long-term dependency modelling of LSTM, and the local feature extraction capabilities of convolutional networks through a semantic gating fusion mechanism, achieving four-dimensional collaborative evaluation at the lexical, grammatical, semantic, and text levels. The findings denote that the Pearson correlation coefficients between the intelligent scoring model based on multi-angle semantic feature calculation and manual scoring reach 89% and 85%, respectively, which is more than 40% higher than traditional methods. This model demonstrates good generalisation ability in practical application scenarios, making it important for advancing the progress of intelligent education technology.
  Keywords: English translation intelligent scoring; multi-angle semantic features; BERT; long short-term memory; LSTM; feature fusion; error detection.
  DOI: 10.1504/IJCEELL.2026.10077149
   
  

Special Issue on: OA Smart and Continuing Education and Life Long Learning

• Open Access

  Design and implementation of a real-time intelligent translation system for network language based on incremental learning ( Free Full-text Access )

  by Ying Liu 
  Abstract: This paper proposes a real-time intelligent system based on incremental learning for translating network language, in order to solve the problem of traditional translation systems being unable to cope with language changes, resulting in insufficient translation accuracy and adaptability. This paper adopts a converter model to construct a translation architecture, which effectively processes complex language structures using its self-attention mechanism while receiving and processing network language data in real-time, ensuring the efficiency of data flow. The introduction of incremental learning mechanism enables the model to dynamically absorb new language features, and in the process of continuously inputting new data, the translation results can be continuously optimised. The experimental results show that the incremental learning model outperforms the traditional model in bilingual evaluation understudy (BLEU) score and accuracy, and significantly outperforms the traditional model in training time (5 hours) and average translation time (0.4 seconds).
  Keywords: incremental learning; network language; transformer model; real-time translation; intelligent translation system; system design; implementation.
  DOI: 10.1504/IJCEELL.2025.10075328
   
  

• Open Access

  Low-cost smart devices and personalised learning for AI-driven preschool education ( Free Full-text Access )

  by Xiaoyu Ou 
  Abstract: This paper develops low-cost intelligent devices and designs personalised learning algorithms to optimise the effectiveness of early childhood education driven by artificial intelligence (AI). Firstly, this paper designs a teacher technical literacy training module and uses a virtual reality simulator to enhance teachers’ ability to operate artificial intelligence tools. Secondly, based on children’s behavioural data, this paper applies collaborative filtering algorithms and long short-term memory (LSTM) models to construct an adaptive learning system. Finally, with the help of 3D modelling software and spatial audio technology, this paper constructs a virtual reality interactive scene to enhance the immersive learning experience, improves the security and usability of the human-computer interaction interface through natural language processing models and touch interaction optimisation. The research results indicate that in interactive teaching scenarios, the AR rendering delay of high-end devices is only 25 ms, while the AR rendering delay of low-end devices is 40 ms.
  Keywords: artificial intelligence; preschool education; low-cost smart devices; personalised learning; adaptive learning system.
  DOI: 10.1504/IJCEELL.2026.10077050
   
  

• Open Access

  Optimisation of hybrid teaching mode of college dance based on human-computer interaction technology ( Free Full-text Access )

  by Zhe Huang 
  Abstract: At present, there are still some shortcomings in blended dance teaching, such as low information level and limited application scope, which hinder the development of blended dance teaching. Therefore, this paper analyses the advantages of dance blended learning and the goals of curriculum construction, and studies the application effect of human-computer interaction in dance blended learning. Based on the current situation, this paper implements corresponding optimisation strategies to achieve collaborative construction of dance education projects. Among them, the teaching quality of dance blended learning under human-computer interaction is 9.8% higher than the original dance teaching, the teaching quality is 6.4% higher than the original dance teaching, the dance level is 8.0% higher than the original dance teaching, and the comprehensive evaluation effect is 7.2% higher than the original dance teaching. In short, human-computer interaction can greatly increase the inertia frequency between students and machines, making students' dance movements more standardised.
  Keywords: dance teaching; human-computer interaction; mixed teaching; teaching mode research.
  DOI: 10.1504/IJCEELL.2026.10077150
   
  

Special Issue on: OA Smart and Continuing Education and Life Long Learning Part 3

• Open Access

  Simulation of multimodal education mode based on artificial intelligence ( Free Full-text Access )

  by Ying Bai, Bin Fang, Long Cai, Yanhua Liu 
  Abstract: To promote the technical development of integrating artificial intelligence into education and the continuous progress of society, a multimodal education model based on artificial intelligence is proposed. Under the influence of artificial intelligence, profound changes are taking place in education. The multimodal education model is an urgent and essential research topic. For the teaching-learning-based optimisation (TLBO) algorithm, when solving high-dimensional, complex, multimodal optimisation problems, the population can prematurely fall into local search, leading to the loss of global optimal solutions. This suggests an improved TLBO optimisation algorithm (MTLBO). An improved TLBO optimisation algorithm (MTLBO) is proposed. The algorithm improves the ‘teaching’ and ‘learning’ processes in the standard TLBO in a more human-like way and introduces a new ‘self-study’ mechanism to strengthen students’ innovative learning ability, thereby effectively improving the algorithms global search capability.
  Keywords: artificial intelligence; multimodal; education optimisation algorithm; simulation study.
  DOI: 10.1504/IJCEELL.2026.10077492
   
  

Special Issue on: OA Smart and Continuing Education and Life-Long Learning

• Open Access

  Design of distance English translation teaching system based on digital multimedia intelligent equipment ( Free Full-text Access )

  by Fali Liang 
  Abstract: With the development of science and technology and network technology, the application of artificial intelligence technology, and the advent of the internet era, computer multimedia-assisted foreign language teaching technology has been continuously innovated and improved. First, suitable digital multimedia equipment, including large database software, mobile multimedia intelligent servers, and equipment that supports voice recognition and machine translation, are selected. The system realises interaction and resource sharing between students and teachers through computer networks and database management functions. At the same time, multi-language recognition technology, voice synchronisation translation equipment, and multimedia teaching software are used to support cross-border translation and remote video conferencing interfaces, realising flexible and traceable remote teaching. The results of this experiment show that in the post-test scores of the experimental group (Group M) and the control group (Group N), the average score of group M is 9.708, and the average score of group N is 8.74.
  Keywords: English translation teaching; digital multimedia; distance teaching; intelligent assistance; teaching and training.
  DOI: 10.1504/IJCEELL.2025.10074868
   
  

Special Issue on: Smart and Continuing Education and Life Long Learning

• Open Access

  AI-driven personalised English learning path planning algorithm and blended learning platform construction ( Free Full-text Access )

  by Shuling Yang, Dongqing Hao 
  Abstract: In response to the contradiction between algorithm recommendation precision and learner autonomy in personalised English learning path planning and the problem of weak personalisation of blended learning platforms, this paper focuses on the AI-driven personalised English learning path planning algorithm and the construction of a blended learning platform. First, a knowledge graph is used to model the structure of English learning content and achieve semantic associations between knowledge points. Subsequently, a multi-dimensional learner profile is constructed by combining bidirectional encoder representations from transformers (BERT) and light gradient boosting machine (LightGBM) to precisely capture learning behaviours and characteristics. Finally, a deep Q-network (DQN) algorithm is applied to dynamically generate personalised learning paths based on learner status. At the same time, a blended learning system is built based on the Open EdX open source platform, and combined with the AI-driven personalised English learning path planning algorithm proposed in this paper, online AI and offline teaching are organically integrated. Experimental verification shows that this solution increases learner engagement by 55.45% compared to traditional teaching methods and improves overall autonomous learning ability by an average of 12.7%, meeting personalised needs and providing a new path for English teaching reform.
  Keywords: artificial intelligence; blended learning; path planning algorithm; knowledge graph modelling; personalised English learning.
  DOI: 10.1504/IJCEELL.2026.10077377
   
  

• Open Access

  English learning behaviour analysis and intelligent recommendation system driven by big data ( Free Full-text Access )

  by Shuling Yang, Dongqing Hao 
  Abstract: This paper proposes a dynamic privacy preserving intelligent recommendation method under a joint learning framework to address the contradiction between privacy protection and recommendation accuracy caused by cross platform data silos in English learning recommendations. Firstly, this paper conducts an in-depth analysis of multimodal English learning behaviour and uses transformers to capture cross modal semantic associations; secondly, this paper innovatively designs a data sensitivity evaluation mechanism based on Kullback Leibler (KL) divergence to achieve dynamic allocation of differential privacy budget; finally, this paper proposes a federated attention mechanism to achieve cross platform user interest transfer. The experiment shows that this method increases the hit rate by 37% in cold start scenarios, reduces communication overhead by 76%, and controls the success rate of member inference attacks at 0.13, effectively solving the collaborative optimisation problems of privacy security, recommendation accuracy, and communication efficiency in cross platform English learning recommendations.
  Keywords: dynamic privacy protection; English learning behaviour analysis; cross-platform recommendation; intelligent recommendation system; federated learning.
  DOI: 10.1504/IJCEELL.2026.10077378
   
  

Special Issue on: Smart and Continuing Education and Life Long Learning Part 3

• Open Access

  Development and testing of a teaching quality assessment and examination data collection system based on artificial intelligence ( Free Full-text Access )

  by Huihui Yin 
  Abstract: Conventional teaching quality assessment and data collection are time-consuming and inefficient, and they cannot easily meet people's needs in the current situation of massive data. The development of a new system can save time and improve efficiency in teaching and is conducive to mining abundant teaching data information, thus providing additional directions for teaching strategies. The efficiency of data processing and decision-making in the education field can be improved by introducing artificial intelligence and a decision-making algorithm, and the shortcomings of existing teaching quality evaluation and data collection methods can be resolved. Through an analysis of system requirements, this study employs artificial intelligence to develop a new teaching quality assessment system and compares it with the conventional system. Compare the accuracy, evaluation frequency, data collection efficiency, and running speed of the two systems. Comparison results show that accuracy, number of evaluations, online rate, and running speed increased by 14.2%, 39.1%, 26.3%, and 61.5%, respectively. The new system based on artificial intelligence has numerous advantages in teaching quality evaluation and data collection and can meet current needs.
  Keywords: system development; data collection system; teaching quality assessment; artificial intelligence; data mining.
  DOI: 10.1504/IJCEELL.2026.10076138
   
  

• Open Access

  Knowledge graphs to build a networked teaching system for Chinese grammar ( Free Full-text Access )

  by Chunhua Liu, Yong Peng 
  Abstract: The way that Chinese grammar is currently taught is disjointed and unclear. Pupils struggle to understand the basic relationships between intricate systems of grammatical rules. The paper presents a networked Chinese grammar teaching model that incorporates a knowledge graph. In order to construct a knowledge network of grammatical elements and their logical connections, fundamental grammatical rules and structural relationships are taken from Chinese grammar using natural language processing (NLP) technology. A visual learning module offers a visual depiction of the connections and hierarchical structure of the grammatical system. This model has been further integrated into an online learning platform that dynamically modifies the learning sequence according to students' practice progress while reinforcing the learning process through collaborative tools and real-time feedback.
  Keywords: knowledge graphs; Chinese grammar; online teaching; learning platform; grammar rules.
  DOI: 10.1504/IJCEELL.2026.10076139
   
  

• Open Access

  Interactive teaching practice of music classroom based on human-computer interaction situation ( Free Full-text Access )

  by Yaqiong Guo, Lujing Zheng 
  Abstract: Interactive teaching practices improve the understandability of lessons and subjects through audio-visual representations with human-computer interaction (HCI) serving as a foundational enabler. In particular, voice-assisted interfaces facilitate natural, hands-free information exchange between students and digital systems, allowing real-time feedback, note recognition, and adaptive instruction in music classrooms. This teaching is backboned with human-computer interactions for touch and voice-assisted interfaces for information exchange. In this article, an itinerary interaction module for note procedures (IIM-NP) in music classrooms is designed for improving the understandability and applications of music notes. This method first stores voluptuous musical notes for introduction, understanding, and application of tones. The stored notes are filtered based on the students understandability aiding ease of teaching. In the processing phase, the understandable and hard note teaching practices are differentiated for which itinerary interactions are planned. This planning relies on teaching recommendations as provided by the state learning. The understandable and hard note teaching interactions are transited based on the itinerary steps pursued. In the transition changes, the understandability level serves as the reward factor from which the procedures are simplified or improved for further interactions. The different transitions balance the understandability levels of students of different ages and learning abilities.
  Keywords: human-computer interaction; HCI; interactive teaching; music classroom; state learning.
  DOI: 10.1504/IJCEELL.2026.10076140
   
  

• Open Access

  Exploration and practice of human-computer interactive open education based on OBE education concept ( Free Full-text Access )

  by Nannan Xie 
  Abstract: Today’s society is an information-based and open society. Social informatisation makes school education enter a comprehensive open teaching. An open society requires teachers to face educational reform with a broad vision. Looking at the basic education reform in the world today, the main goal is to cultivate students’ overall quality, creativity and practical ability, which is what China’s current basic education lacks. Through the research on open education, this paper mainly explained its characteristics, direction and principles. Through the analytic hierarchy process (AHP), the teaching situation was scored, and the classroom atmosphere and students’ learning situation of open education and traditional education were compared. The results showed that the open education based on outcome-based education (OBE) education concept had a better classroom atmosphere. Compared with traditional education, the number of students who failed in open education had decreased by 20%, and the number of students with excellent conditions had increased by 40%, which also showed that open education was more suitable for teaching.
  Keywords: educational exploration and practice; open education; OBE education philosophy; analytic hierarchy process; AHP.
  DOI: 10.1504/IJCEELL.2026.10077240