EvoGraph AI : An Evolutionary Graph-Based Framework for Adaptive Software Engineering and Intelligent Code Optimization
Keywords:
evolutionary computing, graph-based software engineering, intelligent code optimization, adaptive software systemsAbstract
The increasing complexity of modern software systems has created a need for intelligent engineering approaches capable of representing software dependencies, identifying structural relationships, and adapting optimization decisions to changing development conditions. Conventional code optimization methods frequently operate on isolated source files, functions, or predefined metrics, limiting their ability to reason about the broader structural and behavioral context of software systems. This research proposes Evo GraphAI, an evolutionary graph-based framework for adaptive software engineering and intelligent code optimization. The framework conceptualizes software as a dynamic graph in which source-code components, dependencies, execution relationships, interfaces, and optimization objectives are represented as interconnected entities. Evolutionary search mechanisms are then applied to graph-derived representations to identify improved code configurations while preserving functional and structural constraints. The methodological foundation integrates graph-based software representation, learning-oriented pattern extraction, adaptive candidate generation, fitness-based evaluation, and iterative optimization. The provided literature, although primarily focused on wearable sensing and human activity recognition, contributes transferable concepts concerning multimodal representation, personalization, sensor reliability, and adaptive classification. These principles are interpreted as methodological analogies for constructing context-aware software representations rather than as direct evidence of software optimization performance. The framework is further positioned in relation to EvoGraphCoder, which establishes an evolutionary graph-reasoning direction for self-adaptive software engineering (Ramamurthy et al., 2026). The proposed analysis indicates that graph-centered evolutionary reasoning can provide a coherent foundation for dependency-aware optimization, personalization of software transformations, and adaptive decision-making. However, computational overhead, graph construction complexity, fitness-function design, and preservation of semantic correctness remain important limitations requiring empirical validation.
Downloads
References
V. D. K. Eline and M. R. Marco, “Accuracy of human motion capture systems for sport applications; state-of-the-art review,” European Journal of Sport Science, vol. 18, no. 6, pp. 806–819, 2018.
A. Ferrari, D. Micucci, M. Mobilio and P. Napoletano, “On the personalization of classification models for human activity recognition,” IEEE Access, vol. 8, pp. 32066–32079, 2020.
B. Guignard, O. Ayad, H. Baillet, F. Mell, E. D. Simbaña, J. Boulanger et al., “Validity, reliability and accuracy of inertial measurement units (IMUs) to measure angles: Application in swimming,” Sports Biomech, Advance Online Publication, pp. 1–33, 2021.
I. K. Ihianle, A. O. Nwajana, S. H. Ebenuwa, R. I. Otuka, K. Owa et al., “A deep learning approach for human activities recognition from multimodal sensing devices,” IEEE Access, vol. 8, pp. 179028–179038, 2020.
O. D. Lara and M. A. Labrador, “A survey on human activity recognition using wearable sensors,” IEEE Communications Surveys & Tutorials, vol. 15, no. 3, pp. 1192–1209, 2013.
F. Malawski, “Depth versus inertial sensors in real-time sports analysis: A case study on fencing,” IEEE Sensors Journal, vol. 21, no. 4, pp. 5133–5142, 2021.
B. Muniz-Pardos, S. Sutehall, J. Gellaerts, M. Falbriard, B. Mariani et al., “Integration of wearable sensors into the evaluation of running economy and foot mechanics in elite runners,” Current Sports Medicine Reports, vol. 17, no. 12, pp. 480–488, 2018.
S. S. Tabrizi, S. Pashazadeh and V. Javani, “A deep learning approach for table tennis forehand stroke evaluation system using an IMU sensor,” Computational Intelligence and Neuroscience, vol. 9, pp. 1–15, 2021.
L. Struber, S. Ledouit, O. Daniel, P.-A. Barraud and V. Nougier, “Reliability of human running analysis with low-cost inertial and magnetic sensor arrays,” IEEE Sensors Journal, vol. 21, no. 13, pp. 15299–15307, 2021.
D. R. Seshadri, R. T. Li, J. E. Voos, J. R. Rowbottom, C. M. Alfes et al., “Wearable sensors for monitoring the physiological and biochemical profile of the athlete,” Npj Digital Medicine, vol. 2, no. 72, pp. PMC6646404, 2019.
M. T. Worsey, H. G. Espinosa, J. B. Shepherd and D. V. Thiel, “A systematic review of performance analysis in rowing using inertial sensors,” Electronics, vol. 8, no. 11, pp. 1304, 2019.
Z. Wang, J. Wang, H. Zhao, S. Qiu, J. Li et al., “Using wearable sensors to capture posture of the human lumbar spine in competitive swimming,” IEEE Transactions on Human-Machine Systems, vol. 49, no. 2, pp. 194–205, 2019.
K. Ramamurthy, R. K. Konduru and N. Amanmadov, "EvoGraphCoder: An Evolutionary Graph-Reasoning Framework for Self-Adaptive Software Engineering," in IEEE Access, vol. 14, pp. 63063-63076, 2026, doi: 10.1109/ACCESS.2026.3686019.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Nur Aisyah Rahman
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
