International Journal of Data Mining and Bioinformatics (5 papers in press)

Special Issue on: Big Data Industrial Application and Computing Innovation Part Three

• Open Access

  End-to-end learning algorithm for intelligent annotation and knowledge extraction of cross-modal scientific big data ( Free Full-text Access )

  by Zhi Shao, Shuqiang Liu 
  Abstract: This paper proposes an end-to-end learning algorithm for intelligent annotation and knowledge extraction of cross modal scientific research big data. Firstly, this paper takes scientific text, images, formulas, and tables as inputs, extracts heterogeneous features, and maps them to a shared semantic space using scientific bidirectional encoders from transformers, visual transformers, and tree transformers, respectively. Then, this paper weights and sums the annotation cross entropy loss, relationship extraction classification loss, and cross modal comparison alignment loss to form a joint loss function, which drives the collaborative optimisation of all module parameters in a single backpropagation. The results showed that on the benchmark dataset of scientific literature, the F1 score of cross modal named entity recognition reached 87.3%, the accuracy of relation triple extraction reached 83.6%, the accuracy of cross modal semantic alignment reached 85.1%, and the coverage rate.
  Keywords: cross-modal semantic alignment; end-to-end learning; intelligent data annotation; knowledge graph extraction; scientific big data.
  DOI: 10.1504/IJDMB.2026.10080104
   
  

Special Issue on: Hyperautomation and Big Data Methodologies Interactivity and Applications

• Open Access

  Museum social media content generation and personalised push algorithms based on social networking technology ( Free Full-text Access )

  by Shuo Wang, Jiahui Li, Yuxiang Wang, Mengyao Guo, Ze Gao, Kangcheng Deng 
  Abstract: The social media platforms used by museums face various challenges, such as inaccurate generation of cultural information, difficulty in accurately matching changes in user interests, and insufficient ability to adapt to immersive cross platform experiences. To address these issues, this study proposes an intelligent content generation and personalised push algorithm framework. This paper first develops an intelligent content generation model based on graph convolutional network (GCN) transformer, then proposes a dynamic interest model that includes context aware users, and finally proposes a push decision mechanism based on multi-objective particle swarm optimisation deep Q network (MOPSO-DQN). The experiment shows that the average historical matching accuracy of the GCN Transformer model is 92.27%, the cultural accuracy is 95.35%, the semantic consistency is 94.38%, 2 S. Wang et al. and the factual accuracy is 96.79%. The algorithm framework proposed in this study provides a reliable technical solution for the intelligent and digital distribution of museums.
  Keywords: social networking technology; museum social media; knowledge graph; KG; content generation; personalised recommendation; context-aware interest modelling.
  DOI: 10.1504/IJDMB.2026.10078865
   
  

Special Issue on: OA Big Data Industrial Application and Computing Innovation - Part 3

• Open Access

  Standardised storage model for exercise physiological data from wearable devices and mobile terminals ( Free Full-text Access )

  by Jun Xie, Wenbin Chen 
  Abstract: The existing system has low efficiency in data fusion and unified storage, making it difficult to support cross device data integration and longterm management. Therefore, this paper constructs a standardised storage model for multi terminal sports physiology data. This paper first designs a unified data description structure to standardise core fields such as user ID, device ID, timestamp, and data type, and then constructs a hierarchical storage architecture for sports physiology time series data. Finally, by combining batch writing and data compression mechanisms, this paper designs a unified data encoding rule and time index structure to improve data storage efficiency and query performance. The experiment shows that the standardised storage model proposed in this paper has significant advantages in write speed, query speed, compression, and scalability. The average accuracy of data fusion reaches 99.4%; query latency less than 100 ms.
  Keywords: wearable device data integration; mobile terminal health monitoring; standardised data storage; multi-source physiological data; time-series data management.
  DOI: 10.1504/IJDMB.2026.10080250
   
  

Special Issue on: OA Explainable AI for Text Mining Interoperability and Transparency

• Open Access

  Core genes and pathways underlying ferroptosis in chondrosarcoma pathogenesis: through bioinformatics analysis ( Free Full-text Access )

  by Zhiqiang Ye, Zhaoyuan Wang, Zhuo Zhao, Yongxu Zhang, Bowen Zheng, Lianbo Yang, Jinghang Lu, Haidong Liang 
  Abstract: Chondrosarcoma (CS) often resists standard radiotherapy and chemotherapy. Our study explores ferroptosis as a novel tactic to counter this resistance, investigating molecular mechanisms in CS and identifying core genes impacting patient survival rates. The database was screened for 2821 DEGs and 471 ferroptosis-related genes. Further analysis by Gene-miRNA and PPI networks identified nine core genes (IL6, TP53, MAPK1, CAV1, GJA1, SMAD7, TXNIP, MAP3K5, and DUSP1 ) related to ferroptosis in CS. Lower expression of IL6, TP53, MAPK1, and SMAD7, alongside higher expression of CAV1, GJA1, TXNIP, MAP3K5, and DUSP1 were noted in CS tissues. Survival analysis demonstrated higher survival rates in CS patients with low GJA1 and high IL6 expression. In conclusions, GJA1 and IL6 may play pivotal roles in the regulation of ferroptosis in CS, and are tightly associated with the prognosis of CS patients.
  Keywords: ferroptosis; chondrosarcoma;GJA1; IL6.
  DOI: 10.1504/IJDMB.2026.10079732
   
  

Special Issue on: OA Hyperautomation and Big Data Methodologies Interactivity and Applications

• Open Access

  Sports rehabilitation training methods based on deep reinforcement learning in brain-computer interface ( Free Full-text Access )

  by Jianhua Hao 
  Abstract: The existing traditional rehabilitation training methods have complex signal processing, low decoding accuracy, and low training efficiency. Therefore, this paper uses deep reinforcement learning (DRL) algorithm to optimise the brain computer interface (BCI) system and optimise and improve the sports rehabilitation training method. Firstly, this paper introduces the current application status of brain computer interface technology in sports rehabilitation and points out the limitations of traditional methods. Then, this paper explains the BCI system implemented using deep reinforcement learning and highlights the benefits of using deep neural networks and proximal strategy optimisation techniques to collect and process patient electroencephalogram (EEG) data. According to the experimental results, compared with traditional methods, the BCI system based on deep reinforcement learning significantly improves training effectiveness and patient engagement, and shortens rehabilitation and recovery time by 4-5 days.
  Keywords: brain computer interface; BCI; deep reinforcement learning; DRL; sports rehabilitation training; signal processing; personalised rehabilitation; training effect.
  DOI: 10.1504/IJDMB.2026.10080328