Forthcoming Articles

International Journal of Information and Communication Technology

International Journal of Information and Communication Technology (IJICT)

Forthcoming articles have been peer-reviewed and accepted for publication but are pending final changes, are not yet published and may not appear here in their final order of publication until they are assigned to issues. Therefore, the content conforms to our standards but the presentation (e.g. typesetting and proof-reading) is not necessarily up to the Inderscience standard. Additionally, titles, authors, abstracts and keywords may change before publication. Articles will not be published until the final proofs are validated by their authors.

Forthcoming articles must be purchased for the purposes of research, teaching and private study only. These articles can be cited using the expression "in press". For example: Smith, J. (in press). Article Title. Journal Title.

Articles marked with this shopping trolley icon are available for purchase - click on the icon to send an email request to purchase.

Online First articles are also listed here. Online First articles are fully citeable, complete with a DOI. They can be cited, read, and downloaded. Online First articles are published as Open Access (OA) articles to make the latest research available as early as possible.

Open AccessArticles marked with this Open Access icon are Online First articles. They are freely available and openly accessible to all without any restriction except the ones stated in their respective CC licenses.

Register for our alerting service, which notifies you by email when new issues are published online.

International Journal of Information and Communication Technology (24 papers in press)

Regular Issues

  •   Free full-text access Open AccessApplication research of a LightGBM-based predictive evaluation model for college English learning behaviour
    ( Free Full-text Access ) CC-BY-NC-ND
    by Xinxin Yang 
    Abstract: In order to meet the demand for the digital modelling and intelligent analysis of students learning behaviour, a predictive evaluation framework is proposed, which combines feature engineering with LightGBM. Through the construction of tags and the extraction of training samples from college English course behaviour log, the construction strategy and interpretable output mechanism of the model are discussed. The results show that the proposed model achieves an F1-score of 0.889 on the test set, with an average response latency of less than 230 ms, and a performance fluctuation of less than 1.6% in 5 times cross validation, demonstrating robust deployment stability and generalisation.
    Keywords: learning behaviour prediction; LightGBM algorithm; educational data mining; Intelligent teaching analytics; learning behaviour modelling.
    DOI: 10.1504/IJICT.2027.10080149
     
  •   Free full-text access Open AccessComprehensive evaluation of key indexes of power engineering based on K-nearest neighbour algorithm
    ( Free Full-text Access ) CC-BY-NC-ND
    by Yulong Li, Wei Ni, Bo Chen 
    Abstract: To improve the accuracy of key indicator evaluation in power engineering, this study proposes a comprehensive evaluation method based on K-nearest neighbour (KNN) algorithm. Aiming at the limitations of traditional methods in processing nonlinear and high-dimensional data, an evaluation system including ten key indicators such as engineering cost, construction period, and equipment performance was constructed to conduct experiments on 50 power engineering project data in a certain region. The results show that compared with traditional methods, the KNN model has a 15% improvement in evaluation accuracy, a more reasonable allocation of indicator weights, and can effectively identify key factors affecting engineering quality and efficiency. It also exhibits strong robustness in dealing with nonlinear problems and is suitable for power engineering of different scales and types. This method provides a scientific basis for decision-making in power engineering and has promotional value.
    Keywords: KNN algorithm; power engineering; index analysis; comprehensive evaluation.
    DOI: 10.1504/IJICT.2026.10080314
     
  • An international communication influence model for intangible cultural heritage using graph transformers and MoE architecture
    by Jing Zeng 
    Abstract: International dissemination of intangible cultural heritage (ICH) is difficult to assess because relevant data are heterogeneous, relational, and dynamically evolving. We propose GT-MoE-NIA, an influence assessment model that combines a graph transformer with a mixture-of-experts (MoE) architecture. A heterogeneous graph represents ICH projects, countries or regions, media, audiences, and their interactions. The graph transformer captures global structural and semantic dependencies, while a gating network dynamically routes representations to specialised experts for influence prediction. We evaluate the model on the Global Non-Material Cultural Heritage Propagation Dataset (GNCPD), integrating UNESCO inventories, GDELT news, Twitter data, and Wikipedia page views. Compared with GCN, GAT, and GraphSAGE baselines, GT-MoE-NIA reduces root mean square error by 18.7% and improves NDCG@10 by 22.4%. Expert-activation patterns also provide interpretable evidence of how dissemination modes affect influence, supporting data-driven resource allocation for international cultural promotion.
    Keywords: intangible cultural heritage; ICH; international dissemination; influence model; graph transformer; mixture of experts; heterogeneous graph neural network.
    This article is being considered for Open AccessThis article is being considered for Open Access
     
  •   Free full-text access Open AccessResearch on human-computer collaborative cross-language translation architecture based on cognitive computing and large language model
    ( Free Full-text Access ) CC-BY-NC-ND
    by Ran Cao 
    Abstract: This study proposes a multi-agent cross-language cognitive computing framework grounded in cognitive translation studies to enhance humanmachine collaborative translation. The framework integrates specialised agents for drafting, contextual reasoning, knowledge retrieval, revision, and evaluation, aiming to address hallucinations and logical inconsistencies in large language model-based translation. A computational simulation involving 50 virtual professional translators was conducted to evaluate translation quality and simulated cognitive workload. The framework achieved COMET-22 scores of 0.871 in general translation and 0.846 in biomedical translation, with approximately 85% fewer factual hallucinations in the simulated environment. The simulated key stroke correction rate decreased to 6.2%, alongside reductions in simulated gaze time and peak pupil dilation. These findings suggest potential benefits for translation quality and cognitive offloading. All translator behaviours, eye-tracking measurements, keystroke dynamics, and cognitive-load data were synthetically generated; no human participants were involved.
    Keywords: cognitive translation studies; large language models; LLMs; human-in-the-loop translation; multi-agent cognitive computing; cognitive load; factuality hallucination.
    DOI: 10.1504/IJICT.2026.10082146
     
  •   Free full-text access Open AccessAn interpretable machine learning approach to temporal motion segmentation of center-of-gravity trajectory in aerobics instruction
    ( Free Full-text Access ) CC-BY-NC-ND
    by Can Jia 
    Abstract: Coaches divide aerobics stages visually, which is slow and inconsistent. Deep-learning models segment actions well but are black boxes needing large labeled sets. We propose an interpretable machine-learning framework, CGTTS, that extracts center-of-gravity kinematic featuresvelocity, acceleration, speed magnitudeand learns a velocity-acceleration joint criterion (VAJC) to segment continuous aerobics sequences into biomechanically meaningful units. Boundaries are set at velocity extrema and acceleration zero-crossings, giving physically interpretable decisions. Cast as frame-level boundary classification and validated by five-fold cross-validation on 30 subjects, VAJC reaches 0.882 accuracy, beating force-time peak detection by 14.8 points and the deep-learning MS-TCRNet baseline on trajectory accuracy (0.842) and phase consistency (0.803), gains of 8.1% and 10.5%. The framework offers a data-efficient, transparent tool that cuts subjective teaching variability.
    Keywords: temporal motion segmentation; velocity-acceleration criterion; interpretable machine learning; biomechanical analysis; aerobics instruction.
    DOI: 10.1504/IJICT.2026.10082172
     
  •   Free full-text access Open AccessControllable generation and difficulty ranking of mathematical problems using diffusion models
    ( Free Full-text Access ) CC-BY-NC-ND
    by Zhi Liu 
    Abstract: In standardised tests and online education, math question supply still relies on manual creation, which is inefficient and fails to meet the differentiated needs of learners. Existing automated methods treat difficulty as a post-generation attribute rather than a pre-specified condition, making on-demand generation difficult. Difficulty ranking also lacks objective quantification, and manual annotation introduces subjectivity that hinders intelligent question bank management. To address these issues, this paper proposes diffusion-based math item generation, which uses difficulty coefficients and knowledge point labels as explicit conditions, synthesises question text via gradual denoising in continuous space, and incorporates item response theory for quantitative difficulty estimation and ranking. Experiments show that diffusion-based math item generation achieves a difficulty mean absolute error of 0.087, 59.3% lower than diffusion models without explicit difficulty modelling, and a ranking consistency of 0.912, 24.1% higher than the best baseline, confirming the effectiveness of embedding difficulty priors into diffusion generation.
    Keywords: diffusion model; controllable text generation; test difficulty; item response theory; IRT.
    DOI: 10.1504/IJICT.2026.10082173
     
  •   Free full-text access Open AccessPerturbation and reshaping of hand-eye interaction in mobile painting driven by AI aesthetic feedback
    ( Free Full-text Access ) CC-BY-NC-ND
    by Xinyun Li 
    Abstract: When AI aesthetic feedback is introduced into the hand-eye interaction loop of mobile painting, it can perturb the users coordination patterns and drive their reshaping, but lacks quantitative characterisation and optimisation methods. To address this, this paper first incorporates hand-eye movements into an eight-dimensional state space, quantifies baseline coupling with mutual information, and defines instantaneous perturbation with normalised state distance. Then, a Bayesian dynamics model is constructed to recursively estimate the internal aesthetic learning rate using Kalman filtering, and a reshaping index is defined to discriminate coordination structural changes. Furthermore, priority replay and adaptive exploration noise are used to improve the deep deterministic policy gradient algorithm, jointly optimising feedback modality and update timing. Experiments imply that the suggested approach reduces instantaneous perturbation intensity by 38.2% compared to the best baseline and improves reshaping level by 13.2%, verifying the effectiveness of the suggested method.
    Keywords: mobile painting; AI aesthetic feedback; hand-eye interaction; perturbation and reshaping; reinforcement learning.
    DOI: 10.1504/IJICT.2026.10082174
     
  • Cross-domain secure sharing mechanism for government databased on federated learning and blockchain
    by Xianwei Chen, Lixiang Zhou, Min Zhang 
    Abstract: Cross-domain government data sharing faces an inherent tension between the requirement that sensitive data must not leave its domain and the strong demand for cross-departmental collaboration driven by heterogeneity. Traditional centralised schemes struggle to simultaneously satisfy privacy protection, feature alignment, and process auditability in untrusted environments. To address this, we propose a secure sharing model integrating federated learning, differential privacy, blockchain, and graph convolutional networks. Local federated training blocks direct raw data aggregation, while differential privacy noise quantitatively resists parameter reconstruction attacks. Government departments are mapped to graph nodes with business interaction strength as edge weights, and graph convolutional networks extract implicit cross-departmental dependencies to alleviate heterogeneous feature alignment difficulties. Blockchain-calculated client confidence serves as the trusted weight for federated aggregation, replacing sample-size-based weighting. Experiments show 97.53% average accuracy, 0.198 ms average transmission time, and 99.50% decryption success, significantly outperforming comparison models.
    Keywords: federated learning; FL; blockchain technology; BT; data sharing; cross-domain security; differential privacy; DP; graph convolutional network; GCN.
    This article is being considered for Open AccessThis article is being considered for Open Access
     
  •   Free full-text access Open AccessArtificial intelligence and the reconstruction of the deep structure of Shanxi's intangible cultural heritage dance tradition
    ( Free Full-text Access ) CC-BY-NC-ND
    by Qian Ren, Junze Han 
    Abstract: Traditional dance preservation in Shanxi faces generational gaps, cultural deterioration, incomplete documentation of intangible cultural assets, and limited digital reconstruction tools. To tackle these challenges, this study proposes an artificial intelligence-based deep heritage reconstruction model (AI-DHRM) for reconstructing the deep structure of Shanxi traditional dances. The system extracts the stylistic features of the historical dances, finds the hidden movement features, and maps the cultural meanings to the semantic dance features. It combines motion pattern recognition, deep neural feature extraction, cultural semantic mapping, and adaptive sequence learning to uncover hidden stylistic elements. AI-DHRM enhances dance interpretability and reconstructs original structures using multimodal inputs, such as motion-capture data, archived films, and ethnographic annotations. The model achieved a 95.85% recall, 97.08% reconstruction accuracy (RA), and a 95.23% semantic preservation score (SPS). AI-DHRM provides a solution to the preservation, restoration, and transmission of the intangible dance heritage of Shanxi, while retaining symbolism, rhythm, cultural semantics, and continuity.
    Keywords: artificial intelligence; AI; intangible cultural heritage; ICH; Shanxi dance traditions; deep learning; cultural reconstruction; motion pattern recognition; digital heritage preservation; AI-DHRM.
    DOI: 10.1504/IJICT.2026.10082242
     
  •   Free full-text access Open AccessAn IoT-edge framework for real-time crowd evacuation optimisation in urban rail transit emergency scenarios
    ( Free Full-text Access ) CC-BY-NC-ND
    by Wen Jiang 
    Abstract: Urban rail transit (URT) systems face critical evacuation challenges during emergencies due to high density, complex layouts, and dynamic crowd behaviour. This paper presents an IoT and edge computing framework for real-time crowd evacuation optimisation, integrating intelligent sensing, adaptive decision making, and low-latency responses. Using the URT Evacuation Behaviour Dataset comprising CCTV, heat/smoke sensors, Wi-Fi/RFID logs, and simulated paths data are pre-processed via resizing, Butterworth filtering, cleaning, normalisation, and synchronisation. A MobileNetV2-based CNN estimates crowd density, while the APPFN model (autoencoder for anomaly detection, graph neural network for flow prediction, and proximal policy optimisation for adaptive routing) generates optimal evacuation strategies. MATLAB simulations based on the URT Evacuation Behaviour Dataset and station-level scenario settings achieve a benchmark evacuation time of 260 s in the comparative evaluation and scenario-specific evacuation times of 340388 s across the tested emergency scenarios, with a mean absolute error of 22.98, demonstrating significant improvements over conventional methods.
    Keywords: crowd evacuation; decision making; smart transit infrastructures; routes; detection; graph neural network; GNN.
    DOI: 10.1504/IJICT.2026.10082251
     
  •   Free full-text access Open AccessApplying explainable artificial intelligence frameworks to interpret deep neural network decision pathways in advanced persistent threat detection workflows
    ( Free Full-text Access ) CC-BY-NC-ND
    by Sufang Du 
    Abstract: Traditional intrusion detection systems and black-box deep learning (DL) models often fail to provide transparent reasoning behind threat classification, thereby limiting trust, interpretability, and incident response efficiency in cybersecurity operations. To address these challenges, this research proposes an explainable artificial intelligence (XAI)-driven DL framework to interpret decision pathways in APT detection workflows. The proposed approach integrates a white shark optimiser-driven deep neural network with an attention-mechanism (WSO-DNN-AM) for behavioural analysis to identify and interpret malicious network activities from high-dimensional traffic data. The proposed approach performs multilayer analysis of abnormal connections, traffic behaviour profiles, and intrusion patterns to detect stealthy APT activities. On the APT detection traffic analytics dataset, the model achieved 98.65% detection accuracy and outperformed the compared conventional methods under the same experimental protocol. Furthermore, the interpretability modules provide transparent reasoning for threat predictions, enabling cybersecurity analysts to understand critical attack indicators, improve decision-making, and strengthen proactive cyber defense mechanisms in advanced enterprise security environments.
    Keywords: artificial intelligence; advanced persistent threat detection; deep neural network; cyber threat intelligence; network traffic analysis.
    DOI: 10.1504/IJICT.2026.10082252
     
  •   Free full-text access Open AccessA dynamic model for predicting employee turnover risk based on a GAT-BiLSTM fusion
    ( Free Full-text Access ) CC-BY-NC-ND
    by Yingda Wu, Junhao Qiu 
    Abstract: Employee turnover is shaped by individual behavioural trajectories and organisational relationship structures. Existing models treat employees independently, neglecting peer influence through collaboration networks, while static approaches fail to capture the gradual evolution of turnover intention. This paper proposes the graph attention-bidirectional long short-term memory for attrition prediction model, which encodes management reporting and project collaboration ties as a graph structure. The graph attention network captures structural positions, and the bidirectional long short-term memory network models behavioural dynamics including satisfaction and performance over time, enabling joint feature interaction. Experiments on four-year anonymised data from 8,326 employees show that the model achieves an area under the curve of 0.957, outperforming the transformer baseline by 2.0%, and attains a dynamic warning timeliness of 3.4 quarters, surpassing the baseline by 0.6 quarters, confirming its ability to issue early warnings nearly one year before departure.
    Keywords: employee attrition prediction; graph attention network; GAT; bidirectional long short-term memory; dynamic risk modelling.
    DOI: 10.1504/IJICT.2026.10082253
     
  •   Free full-text access Open AccessCausal effect magnitude quantification of industry-education integration policies using potential outcome representation learning
    ( Free Full-text Access ) CC-BY-NC-ND
    by Nailing Li 
    Abstract: Can policies promoting industry-education integration truly improve corporate productivity? Non-random selection in pilot programs often leads to evaluation bias. This paper introduces a latent outcome framework and balanced representation learning, using neural networks to map companies multidimensional characteristics into comparable abstract representations, thereby approximating randomised controlled conditions in the observed data and quantifying the causal effects of the policies. Using the 2021 national pilot program as a quasi-experiment and drawing on data from A-share companies from 2016 to 2024, the model estimates that the policy increased total factor productivity by an average of 11.3%, nearly 30% higher than the 8.7% estimated by traditional difference-in-differences methods; when identifying firms positively affected by the policy, the area under the curve reached 0.874, outperforming the 0.791 achieved by causal forests. The results indicate that, after correcting for selection bias, the policys actual effectiveness is more pronounced than that shown by traditional methods.
    Keywords: industry-education integration; causal effects; potential outcomes; representation learning; policy evaluation.
    DOI: 10.1504/IJICT.2026.10082254
     
  •   Free full-text access Open AccessCross-modal semantic fusion and link discovery in historical documents on the League of Nations aid to China
    ( Free Full-text Access ) CC-BY-NC-ND
    by Yiwei Wang 
    Abstract: League of Nations technical cooperation with China produced reports, maps, inventories, and correspondence that form essential evidence for studying modern international aid. Yet scattered storage and semantic gaps across modalities have long constrained systematic analysis. This paper proposes dual-modal semantic fusion, which introduces adaptive fusion weights to balance text and visual features in a shared space and leverages graph structures to discover cross-modal associations. On the CuLi test split containing 5,726 image-text pairs (7:1:2 split), the framework achieves an area under the curve of 0.876, a 6.3-percentage-point improvement over the strongest baseline language-aligned Chinese contrastive language-image pre-training, alongside a semantic consistency score of 0.743 and a cross-modal link density of 0.612, indicating over sixty percent of graph connections bridge text and images. Adaptive weighting improves the area under the curve from 0.835 to 0.876 over equal-weight fusion, filling the gap of dedicated cross-modal fusion for historical archives.
    Keywords: cross-modal fusion; historical archives; semantic consistency; linkage discovery.
    DOI: 10.1504/IJICT.2026.10082255
     
  •   Free full-text access Open AccessDeep reinforcement learning for dynamic scheduling and cost minimisation in low-carbon supply chains
    ( Free Full-text Access ) CC-BY-NC-ND
    by Jing Zhang 
    Abstract: In supply chain operations, dynamic disturbances such as demand fluctuations, transportation disruptions, and carbon price changes persist. Traditional scheduling models treat emissions as a rigid constraint rather than an optimisation objective, failing to balance cost and emissions dynamically. Existing methods lack real-time adaptability under frequent disturbances. This paper proposes the carbon-aware hierarchical reinforcement learning framework, which decomposes decisions into strategic and tactical layers, and introduces a Pareto-optimal reward mechanism with adaptive weights to resolve multi-objective conflicts. Experiments on public logistics datasets show that Compared to the optimal hierarchical reinforcement learning baseline, the framework reduces total cost by 6.0% and carbon emission intensity by 6.5%. Against the single-layer deep reinforcement learning baseline, the on-time delivery rate rises by 1.9 percentage points and the scheduling stability index falls by 20.5%. This framework bridges carbon-cost optimisation and real-time response in dynamic scheduling, offering a feasible path for intelligent scheduling under carbon constraints.
    Keywords: supply chain scheduling; deep reinforcement learning; DRL; carbon emission reduction; multi-objective optimisation.
    DOI: 10.1504/IJICT.2026.10082256
     
  •   Free full-text access Open AccessKnowledge graph walk-enhanced attainment prediction for higher education course objectives
    ( Free Full-text Access ) CC-BY-NC-ND
    by Ling Xia 
    Abstract: The degree to which course objectives are met serves as a key basis for engineering education accreditation and program evaluation; however, existing prediction methods overlook the topological dependencies among knowledge points and rely on final exams, resulting in delays. To address this, we introduce knowledge graphs and random walks to propose a dual-mode walking prediction framework: we construct a course graph based on the syllabus and assessments; capture hierarchical relationships and functional similarities through structural and semantic walks; and map sparse behavioural data to a variable space. Validated using data from three courses involving over 4,286 students, this method achieved an accuracy of 88.7% and an area under the curve of 0.956, representing improvements of 2.5 and 2.2 percentage points, respectively, over the graph attention network baseline. The results confirm that knowledge graph-based random walks can effectively mitigate data sparsity and enhance interpretability.
    Keywords: knowledge graph; random walk; course objective achievement; learning prediction.
    DOI: 10.1504/IJICT.2026.10082257
     
  •   Free full-text access Open AccessAn emotional resonance evolution graph via multimodal semantic alignment for values education classrooms
    ( Free Full-text Access ) CC-BY-NC-ND
    by Hao Zhang 
    Abstract: Emotional resonance in values education lies in speech, text, and facial expressions. Due to the multimodal semantic gap, existing models fail to capture the awakening and migration of value identification from cross-modal signals, and lack a computable evolutionary framework. This paper proposes the emotional resonance computation evolutionary graph, which maps teaching events to graph nodes and encodes resonance states as edge trajectories via cross-modal alignment and state transition regularisation, enabling structured tracking of the awakening-reinforcement-internalisation process. Experiments show accuracy improves from 75.2% to 78.6% and area under the curve from 0.817 to 0.841 over the strongest baseline self-supervised multi-task multimodal. On CMU-MOSEI, the emotional resonance coefficient rises from 0.62 to 0.74, and value identification consistency increases by 33.3% over the best baseline. These results demonstrate the framework fills the gap in computable evolutionary modelling of emotional resonance for values education, offering a quantitative tool for classroom assessment.
    Keywords: emotional resonance; semantic alignment; evolutionary graph; multimodal learning.
    DOI: 10.1504/IJICT.2026.10082244
     
  •   Free full-text access Open AccessResearch on instruction dataset construction and domain-adaptive fine-tuning benchmark for multi-service scenarios in the energy industry
    ( Free Full-text Access ) CC-BY-NC-ND
    by Liang Chen, Danni Chen, You Wen, Ke Xiong, Jiakai Tang 
    Abstract: With the widespread application of large language models in various industries, the issues of insufficient professional data and the lack of evaluation benchmarks in the energy sector have become increasingly prominent. In complex energy business scenarios covering power generation, transmission and distribution, marketing, and material supply chains, the application capabilities demonstrated by traditional large models are gradually becoming inadequate. To address this problem, this paper constructs an instruction dataset for the energy sector covering multiple energy business scenarios, proposes a two-stage fine-tuning method integrating retrieval-augmented generation and low-rank adaptation, and establishes a multi-dimensional evaluation benchmark for professional large language models in the energy field, which includes modules for stress testing and hallucination suppression. Experimental results show that the 7B-scale energy-domain large model optimised by the proposed method achieves a significant performance improvement compared with traditional general-purpose large models, with a regulatory citation accuracy of 84.2%. This work lays a benchmark foundation and provides a feasible solution for the subsequent development of large models in the energy sector. The principal contribution is a unified, source-traceable workflow that connects multi-scenario instruction construction, two-stage domain adaptation, and compliance-oriented evaluation.
    Keywords: energy industry; instruction dataset; domain adaptation; retrieval augmented generation; low-rank adaptation; evaluation benchmark.
    DOI: 10.1504/IJICT.2026.10082318
     
  •   Free full-text access Open AccessRetrieval-augmented large language models with hallucination verification for English-Chinese scientific and technological innovation terminology database construction
    ( Free Full-text Access ) CC-BY-NC-ND
    by Jin Niu 
    Abstract: The continuous emergence of new terms in science and technology poses challenges to English-Chinese bilingual term bank construction, including fuzzy boundaries and alignment difficulties. Therefore, this paper first refines candidate term boundaries layer by layer through a boundary-aware mechanism. An optimal evidence granularity is selected via a multi-granularity intent-aware router, and the stability of generation is enhanced by a hierarchical decoupling prompt. Furthermore, this paper designs verification mechanisms including atomic proposition checking, semantic manifold consistency, and cognitive uncertainty quantification to ensure entry quality. Experiments on public benchmarks and a hundred-thousand-scale bilingual terminology database for the Beijing-Tianjin-Hebei sci-tech innovation industry imply that the suggested method achieves a hallucination verification F1 score of 94.1%, and BERTScore values of 0.902 and 0.894 for definition and translation generation, respectively, thereby providing core terminological support for the language service system of the sci-tech innovation industry.
    Keywords: large language model; science and technology innovation knowledge; English-Chinese terminology database construction; retrieval enhancement.
    DOI: 10.1504/IJICT.2026.10082319
     
  •   Free full-text access Open AccessAn interactive design style transfer system integrating semantic awareness and user feedback
    ( Free Full-text Access ) CC-BY-NC-ND
    by Weiwei Xu 
    Abstract: Design style transfer applies artistic styles from reference images to target content while preserving semantic structure. Existing neural approaches operate as single-pass generators without semantic understanding or user interaction, producing outputs that frequently misalign with user intentions. A novel framework integrating semantic perception with iterative user feedback is proposed for controllable style transfer. A semantic perception module extracts hierarchical content representations through a vision-language encoder. A multi-scale style encoder captures design patterns across multiple granularity levels. An adaptive transfer generator synthesises outputs conditioned on semantic features, style codes, and a dynamic user preference embedding updated through iterative ratings. Evaluation on the WikiArt benchmark demonstrates improvements of 8.4 percentage points in user satisfaction, 12.6 percent in structural similarity, and 9.3 percentage points in style consistency over the strongest baseline, confirming that joint semantic awareness and interactive feedback substantially enhance transfer quality.
    Keywords: style transfer; semantic perception; user feedback; interactive optimisation; design generation.
    DOI: 10.1504/IJICT.2026.10082320
     
  •   Free full-text access Open AccessImproved spatiotemporal attention GNN for scenic silver-haired long-tail passenger flow prediction with multi-source data synergy
    ( Free Full-text Access ) CC-BY-NC-ND
    by Zhou Ziying 
    Abstract: Current research on scenic spot passenger flow prediction lacks consideration of long-tail characteristics, synergistic driving mechanisms, and deep multi-source data fusion. To overcome these limitations, this study proposes a long-tail passenger flow prediction framework based on the integration of heterogeneous data with the synergistic effects of silver-haired tourism and cultural tourism consumption upgrading. A multi-stage fusion workflow is proposed to integrate behavioural, consumption and policy data, including quality assessment, hierarchical cleaning, alignment and verification to depict the passenger flow influence chain. A coupling coordination degree framework quantifies the dual-system synergy and transforms it into interpretable prediction factors. An improved spatial-temporal attention graph neural network incorporates dual-scale temporal and dynamic spatial attention to capture low volatility, long cycles and evolving spatial correlations. Experimental results show errors of 8.2% and 9.5%, respectively, improving accuracy by 2.0%-6.6% over benchmarks, with strong model stability and generalisation in different scenic environments.
    Keywords: multi-source heterogeneous data; silver-haired group; deep tourism; long-tail passenger flow; cultural tourism consumption; synergistic driving.
    DOI: 10.1504/IJICT.2026.10082366
     
  •   Free full-text access Open AccessAging product interaction design empowered by virtual digital art: an immersive companion system based on human-computer intelligent interaction and emotional computing
    ( Free Full-text Access ) CC-BY-NC-ND
    by YingJie Jia, Chen Li 
    Abstract: To address the growing demand for emotional companionship in ageing societies, this study develops an immersive companion system integrating virtual digital art, human-computer interaction, and affective computing. The system combines 5G, edge computing, and IoT for communication, while using multimodal physiological signals and graph neural networks to recognise emotions and adapt digital art content. Experimental results show that the proposed architecture achieves 16 ms interaction latency, 890 Mbps transmission throughput, and a 0.22% packet loss rate under high concurrency. After 100 days of continuous use, the timeout rate decreased from 4.5% to 1.0%, daily active interactions increased from 16 to 51, and emotion recognition accuracy improved significantly compared with the control group (p < 0.01). These findings demonstrate that integrating advanced communication technologies, emotional computing, and virtual digital art can enhance user experience and emotional well-being among older adults, supporting the transition of ageing products from functional assistance to artistic companionship.
    Keywords: virtual digital art; aging product interaction design; human-computer intelligent interaction; HCII; affective computing; immersive companion systems; 5G edge computing.

  •   Free full-text access Open AccessLightweight intelligent design of product form based on U-Net image segmentation
    ( Free Full-text Access ) CC-BY-NC-ND
    by Yan Ling, Qinjian Yang, Yanfeng Xu 
    Abstract: This study proposes a lightweight intelligent method for product form design using U-Net image segmentation to overcome the limitations of traditional CAD in handling complex product aesthetics and form perception. A public industrial product image dataset containing consumer electronics and mechanical accessories is preprocessed through resizing, normalisation and non-local means denoising. Convolutional neural networks extract features for aesthetic and quality prediction. A beetle antennae search optimised lightweight U-Net, named BAS-LWU-Net, is designed to accurately segment product contours and structures, and is integrated into a conceptual design environment for automated form generation without physical prototyping. Experimental results demonstrate that BAS-LWU-Net achieves an Intersection over union of 0.982, mean pixel accuracy of 0.984 and 65.6 frames per second. Comparative analysis confirms its effectiveness for intelligent product form optimisation.
    Keywords: lightweight U-Net; image segmentation; consumer products; industrial products; electronic devices.

  •   Free full-text access Open AccessFederated multi-task learning for cross-institutional prediction of child welfare intervention needs while preserving data privacy and local heterogeneity
    ( Free Full-text Access ) CC-BY-NC-ND
    by Xiuzhuo Wei, Shanshan Zhao, Wei Wu 
    Abstract: Child welfare organisations need intelligent systems to predict intervention needs while preserving data privacy across institutions. This paper proposes a beluga whale optimised multi-task deep neural network (BWO-ML-DNN) model for cross-institutional prediction of child welfare intervention needs. The Kaggle dataset with 7,000 records and 55 indicators is used. Preprocessing handles missing values and applies min-max normalisation, while principal component analysis extracts informative features and reduces dimensionality. The ML-DNN component learns shared and task-specific representations for abuse risk assessment, mental health intervention, educational support and family assistance prioritisation. The BWO algorithm optimises hyperparameters to improve convergence and generalisation. The model is evaluated using accuracy, precision, recall and F1-score. The proposed BWO-ML-DNN achieves 98.3% accuracy, outperforming existing models such as HBCE-FL. Results demonstrate robustness, reliability, and effectiveness for privacy-preserving, personalised, and scalable child welfare intervention prediction.
    Keywords: federated multi-task learning; FMTL; child welfare prediction; privacy-preserving cross-institutional learning; intervention need prediction; federated learning; FL.