Forthcoming Articles

International Journal of Computational Intelligence Studies

International Journal of Computational Intelligence Studies (IJCIStudies)

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 Articles will not be published until the final proofs are validated by their authors.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 Computational Intelligence Studies (3 papers in press)

Regular Issues

  • Improvement and application of a new FOA for image processing technology   Order a copy of this article
    by Qianlan Liu, Zhenhua Dai 
    Abstract: This study proposes a novel image dual resolution optimisation algorithm (IDROA) that integrates a global immune-inspired search strategy with dual dictionary learning to meet high-definition image reconstruction and compression requirements. By combining an improved ResNet50 with a binary masking mechanism, the method overcomes the local optima limitations of traditional techniques and enhances reconstruction fidelity and compression performance. Experiments on Urban100, Set5, and Set14 show that IDROA achieves high reconstruction quality, with an average RMSE of 0.0401 and a compression ratio of 34.57%. Although its average processing time (2.605 s) and memory usage (523.32 MB) are slightly higher than conventional methods, it surpasses leading deep learning models such as SRGAN and ESRGAN in both accuracy and perceptual quality. The algorithm also demonstrates strong feature extraction capability, achieving an average similarity of 0.9153, highlighting its potential for high-quality imaging tasks under limited computing resources.
    Keywords: image processing; image reconstruction; compression efficiency; dual resolution optimisation algorithm; IDROA; ResNet50; feature extraction.
    DOI: 10.1504/IJCISTUDIES.2026.10076771
     
  • Entity-driven attention: lightweight adaptation through frequency-guided scaling   Order a copy of this article
    by Shifa Pan, Mianzhu Peng, Shiyan Zheng, Chengquan Zhu, Jinmei Wu, Jinfa Wei 
    Abstract: Transformers allocate attention uniformly even when local information density varies substantially across tokens. Existing adaptive attention approaches often introduce additional parameters or complex routing, which is undesirable for resource-constrained deployment. We propose a zero-parameter entity frequency-guided scaling method that adjusts attention logits using normalised token frequency statistics within the context window. Across five repeated shakespeare char runs, the method reduces validation loss from 1.4740 to 1.4631 (0.74% relative improvement; absolute gain 0.0109, 95% CI: +-0.00076) with unchanged parameter count, while additional experiments on text8 and enwik8 show small and dataset-dependent effects. These results indicate that simple statistical adaptation can provide consistent gains on character-level data, and also clarify where this strategy does not generalise.
    Keywords: transformers; attention scaling; information density; parameter-efficient adaptation; character-level language modelling.
    DOI: 10.1504/IJCISTUDIES.2026.10078512
     
  • Intelligent investment research systems and investment decision optimisation empowered by large models   Order a copy of this article
    by Renguang Song, Ruohong Liu, Xibo Bai, Zhe Fang, Shasha Chang 
    Abstract: Unstructured data complicates investment research, prolonging decisions and intensifying risk constraints. This study develops an intelligent research framework centred on fin-alpha-LLM, a financial large language model. It employs text-numerical gating fusion to generate linguistic signals, which combined with traditional factors drive multi-task return and risk predictions. A multi-objective reinforcement learning engine then optimises for return, volatility, CVaR, and transaction costs. Empirical tests on Shanghai and Shenzhen A-shares (2015-2024) show the framework outperforms multi-factor and machine learning baselines in IC, AUC, annualised return, and Sharpe ratio, with lower drawdowns and greater stability in extreme markets. Ablation studies confirm that enhanced retrieval and human-machine collaboration are critical to performance and risk control.
    Keywords: large language model; retrieval-augmented generation; text-factor fusion; multi-task prediction; constrained portfolio optimisation; Q-learning.

 

Return to top