Skip to content
2000
Volume 3, Issue 1
  • ISSN: 2950-3752
  • E-ISSN: 2950-3760

Abstract

Introduction

A well-known limitation of Machine Learning (ML) approaches is the inability to automatically interpret their results as a clear data transformation procedure. This opacity arises because a neural network, for instance, is essentially a set of coefficients that model the synapses and structures connecting artificial neurons.

Methods

The proposed solution involves constructing a hierarchical system of pattern recognition models. The lower level processes the outcomes of recognition and classification performed by ML methods or algorithmic procedures. The middle levels represent the static aspect of a scene, captured through object properties and logical connections, which are expressed as syntactic patterns. The higher levels describe an information flow of events derived from the low-level model data.

Results

We propose the application of the logical language Logtalk for constructing syntactic Pattern Recognition (PR) models and for transformational interpretation. Two use cases are presented: 1) the automatic generation of Java source code for objects representing modules of a Big Data analysis library, and 2) the recognition of PDF structure in documents generated according to a common template.

Discussion

A technique is proposed to justify the correctness of ML results by evaluating their correspondence to a structure with predefined relations. This is achieved by utilizing these results within a first-order logic inference procedure of an applied theory. A successful inference indicates that the ML results are consistent with the logical theory, thereby providing a higher degree of confidence in their accuracy. The integration of syntactic PR with neural networks and analysis techniques based on large linguistic models allows for the automated validation of results against the possibility of such logical inference.

Conclusion

This technique enables software developers to utilize ML results as input data for syntactic pattern recognition, thereby facilitating the description of dynamic processes. Significant emphasis is placed on modeling the interpretation of recognition results as a transformation of an information model.

© 2026 Bentham Science Publishers
Loading

Article metrics loading...

/content/journals/cai/10.2174/0129503752359989250901065548
2025-09-19
2026-03-08

  • From This Site

    /content/journals/cai/10.2174/0129503752359989250901065548
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. BardinS. JhaS. GaneshV. Machine learning and logical reasoning: The new frontier (Dagstuhl Seminar 22291).Dagstuhl Rep.20238011110.4230/DagRep.12.7.80
     [Google Scholar]
  2. DaiW-Z. XuQ. YuY. ZhouZh-H. Bridging machine learning and logical reasoning by abductive learning.Adv Neu Infor Proc Sys20193215
     [Google Scholar]
  3. DuppeB. MeiserM. AnisimovA.A. AntakliA. MuazM. ZinnikusI. Combining machine learning with inductive logic learning to detect deviations from daily routines in ambient intelligent environments.IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology202110.1145/3486622.3493942
     [Google Scholar]
  4. LiT. WangS. LillisD. YangZ. Combining machine learning and logical reasoning to improve requirements traceability recovery.Appl. Sci.20201020725310.3390/app10207253
     [Google Scholar]
  5. LisiF.A. EspositoF. Combining logic programming with description logics and machine learning for the semantic web.2008Available from: https://ceur-ws.org/Vol-434/paper3.pdf
  6. MarraG. GianniniF. DiligentiM. GoriM. LYRICS: A general interface layer to integrate logic inference and deep learning.Machine Learning and Knowledge Discovery in Databases ECML PKDD 2019. Brefeld U Fromont E HothoA Knobbe A Cham: Springer202010.1007/978‑3‑030‑46147‑8_17
     [Google Scholar]
  7. ZhangH. ZhengT. LiY. GaoJ. SuL. LiB. Profanity-avoiding training framework for seq2seq models with certified robustness.Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing20215151516110.18653/v1/2021.emnlp‑main.418
     [Google Scholar]
  8. KwonT. YooW.G. LeeW.J. KimW. KimD-W. Next-generation sequencing data analysis on cloud computing.Genes Genomics201537648950110.1007/s13258‑015‑0280‑7
     [Google Scholar]
  9. ZhaoS. WatrousK. ZhangCh. ZhangB. Cloud computing for next-generation sequencing data analysis.Cloud Computing – Architecture and Applications. SenJ. IntechOpen Limited2017295110.5772/66732
     [Google Scholar]
  10. LangmeadB. NelloreA. Cloud computing for genomic data analysis and collaboration.Nat. Rev. Genet.201819420821910.1038/nrg.2017.113 29379135
     [Google Scholar]
  11. AmstutzP. CrusoeM.R. TijanicN. ChapmanB. Common workflow language.figshare20161510.6084/m9.figshare.3115156.v2
     [Google Scholar]
  12. BakerQ.B. Al-RashdanW. JararwehY. Cloud-based tools for next-generation sequencing data analysis.2018 Fifth International Conference on Social Networks Analysis, Management and Security (SNAMS)201810.1109/SNAMS.2018.8554515
     [Google Scholar]
  13. BatutB. HiltemannS. BagnacaniA. BakerD. BhardwajV. Community-driven data analysis training for biology.Cell Syst.20186675275810.1016/j.cels.2018.05.012
     [Google Scholar]
  14. RoseR GolosovaO SukhomlinovD TiunovA ProsperiM Flexible design of multiple metagenomics classification pipelines with UGENE Bioinformatics201935111963510.1093/bioinformatics/bty901 30358807
     [Google Scholar]
  15. MilicchioF. RoseR. BianJ. MinJ. ProsperiM. Visual programming for next-generation sequencing data analytics.BioData Min.2016911610.1186/s13040‑016‑0095‑3 27127540
     [Google Scholar]
  16. ETU "LETI"2022Available from: https://etu.ru/en/university/
  17. INRTU is a university with the best traditions. 2022Available from: https://eng.istu.edu/
  18. Lan’L.M.S. LMS lan.2022Available from: https://lanbook.ru
  19. HoganA. BlomqvistE. CochezM. D’AmatoC. Knowledge graphs.2020Available from: https://arxiv.org/abs/2003.02320v5
  20. Berners-LeeT. HendlerJ. LassilaO. The semantic web: A new form of web content that is meaningful to computers will unleash a revolution of new possibilities.Sci. Am.20012845344310.1038/scientificamerican0501‑34
     [Google Scholar]
  21. WielemakerJ. BeekW. HildebrandM. van OssenbruggenJ. ClioPatria: A SWI-Prolog infrastructure for the Semantic Web.Semant. Web20167552954110.3233/SW‑150191
     [Google Scholar]
  22. WielemakerJ. SchrijversT. TriskaM. LagerT. SWI-prolog.Theory Pract. Log. Program.2011121-26796
     [Google Scholar]
  23. LagerT. WielemakerJ. Pengines: Web logic programming made easy.Theory Pract. Log. Program.2014144-553955210.1017/S1471068414000192
     [Google Scholar]
  24. CherkashinE. ShigarovA. ParamonovV. Representation of MDA transformation with logical objects. 2019 International Multi-Conference on Engineering, Computer and Information Sciences.SIBIRCON201910.1109/SIBIRCON48586.2019.8958008
     [Google Scholar]
  25. BizerC. HeathT. Berners-LeeT. Linked data - the story so far.Int. J. Semantic Web Inf. Syst.20095312210.4018/jswis.2009081901
     [Google Scholar]
  26. LeeE.A. MesserschmittD.G. Synchronous data flow.Proc. IEEE19877591235124510.1109/PROC.1987.13876
     [Google Scholar]
  27. MouraP. Programming patterns for Logtalk parametric objects.Applications of Declarative Programming and Knowledge Management INAP 2009. AbreuS Seipel D BerlinHeidelberg: Springer201110.1007/978‑3‑642‑20589‑7_4
     [Google Scholar]
  28. BratkoI. Prolog Programming for Artificial Intelligence.Harlow, EnglandPearson Addison-Wesley20003
     [Google Scholar]
  29. SchlossP.D. WestcottS.L. RyabinT. Introducing mothur: Open-source, platform-independent, community-supported software for describing and comparing microbial communities.Appl. Environ. Microbiol.200975237537754110.1128/AEM.01541‑09 19801464
     [Google Scholar]
  30. A LuaLaTeX class for authoring course descriptions.2022Available from: https://github.com/eugeneai/sucourse
/content/journals/cai/10.2174/0129503752359989250901065548
Loading
Structural Pattern Recognition and Interpretation Infrastructure Based on Knowledge Graphs and Logical Inference
Curr Arti Intell 3, E29503752359989 (2025); https://doi.org/10.2174/0129503752359989250901065548
/content/journals/cai/10.2174/0129503752359989250901065548
/content/journals/cai/10.2174/0129503752359989250901065548
Loading

Data & Media loading...


  • Article Type:     Research Article
Keyword(s): Explainable AI; first-order logic; generative programming; knowledge graph; logical inference; model-driven architecture; syntactic pattern recognition

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test