International Peer-Reviewed JournalOpen AccessISSN 2456-8880
irejournals@gmail.com+91-7433024337

Home / Current Issue / Paper 1719451

1719451PublishedVol 10 · Issue 1

Intelligent Software Defect Prediction Using Multimodal Deep Learning Through the Integration of Source Code, Software Metrics and Historical Development Data

Pooja Ganesh Dhone Dr. Brijendra Gupta

Subject area: Science,Engineering and Technology  ·  Area of research: Deep Learning

DOI: https://doi.org/10.64388/IREV10I1-1719451

Abstract

Software defect prediction has historically relied on a single view of source code — either handcrafted metrics, token sequences, or structural representations in isolation. Multimodal deep learning addresses the fundamental limitation that no single code view captures the full richness of software artifacts: their syntax, structure, semantics, history, and natural-language context. This report provides a comprehensive survey of multimodal deep learning approaches for software defect prediction, covering the major modalities (lexical/semantic, structural/AST, control-and-data-flow, metric-based, and natural language) and the fusion architectures that combine them — concatenation, attention-gating, cross-attention, and contrastive multi-view learning. We synthesize findings from over 50 recent publications (2020-2026), including GMCA-SDP cross-attention fusion, FusionVul multimodal vulnerability detection, hierarchical CNN fusion of AST/CFG/DDG, and emerging vision-language model applications. We benchmark performance across datasets, analyze fusion strategy trade-offs, address challenges in modality alignment and missing data, and map the trajectory toward unified multimodal foundation models for software quality assurance.

How to cite this paper

Pooja Ganesh Dhone, Dr. Brijendra Gupta "Intelligent Software Defect Prediction Using Multimodal Deep Learning Through the Integration of Source Code, Software Metrics and Historical Development Data" Iconic Research And Engineering Journals Volume 10 Issue 1 2026 Page 226-235 https://doi.org/10.64388/IREV10I1-1719451
Pooja Ganesh Dhone, Dr. Brijendra Gupta "Intelligent Software Defect Prediction Using Multimodal Deep Learning Through the Integration of Source Code, Software Metrics and Historical Development Data" Iconic Research And Engineering Journals, vol. 10, no. 1, Jul. 2026, doi: https://doi.org/10.64388/IREV10I1-1719451
Pooja Ganesh Dhone, Dr. Brijendra Gupta (2026). Intelligent Software Defect Prediction Using Multimodal Deep Learning Through the Integration of Source Code, Software Metrics and Historical Development Data. Iconic Research And Engineering Journals, 10(1). doi: https://doi.org/10.64388/IREV10I1-1719451
Pooja Ganesh Dhone, Dr. Brijendra Gupta "Intelligent Software Defect Prediction Using Multimodal Deep Learning Through the Integration of Source Code, Software Metrics and Historical Development Data" Iconic Research And Engineering Journals, vol. 10, no. 1, Jul. 2026. Crossref, https://doi.org/10.64388/IREV10I1-1719451
@article{1719451,
      author = {Pooja Ganesh Dhone, Dr. Brijendra Gupta},
      title = {Intelligent Software Defect Prediction Using Multimodal Deep Learning Through the Integration of Source Code, Software Metrics and Historical Development Data},
      journal = {Iconic Research And Engineering Journals},
      year = {2026},
      volume = {10},
      number = {1},
      pages = {226-235},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1719451.pdf},
      abstract = {Software defect prediction has historically relied on a single view of source code — either handcrafted metrics, token sequences, or structural representations in isolation. Multimodal deep learning addresses the fundamental limitation that no single code view captures the full richness of software artifacts: their syntax, structure, semantics, history, and natural-language context. This report provides a comprehensive survey of multimodal deep learning approaches for software defect prediction, covering the major modalities (lexical/semantic, structural/AST, control-and-data-flow, metric-based, and natural language) and the fusion architectures that combine them — concatenation, attention-gating, cross-attention, and contrastive multi-view learning. We synthesize findings from over 50 recent publications (2020-2026), including GMCA-SDP cross-attention fusion, FusionVul multimodal vulnerability detection, hierarchical CNN fusion of AST/CFG/DDG, and emerging vision-language model applications. We benchmark performance across datasets, analyze fusion strategy trade-offs, address challenges in modality alignment and missing data, and map the trajectory toward unified multimodal foundation models for software quality assurance.},
      month = {July},
      doi = {https://doi.org/10.64388/IREV10I1-1719451}
  }