Optimizing Machine Learning Pipelines via Adaptive Hybrid Classification Models: Toward Scalable, Self-Updating AI Architectures
DOI:
https://doi.org/10.32628/IJSRSET251262Keywords:
Stacking Ensemble, Explainable AI, Adaptive Classification, ML PipelineAbstract
The increasing complexity of real-world data requires machine learning systems that are not only precise but also adaptable, scalable, and transparent. This study suggests a strong, modular ML pipeline that can help AI architectures that can update themselves by using adaptive hybrid classification models. The framework starts with getting a dataset of network traffic and doing some exploratory analysis on it. Then, it moves on to standardisation and domain-specific feature engineering. To make sure the evaluation is fair, the data is split into training and testing sets, and a variety of base classifiers are trained. These models are then put together in a stacking ensemble with a meta-learner that smartly combines their outputs, using their strengths to make up for their weaknesses. Using standard metrics like accuracy, precision, recall, F1-score, and ROC-AUC, we look at the model's performance. The study employs XA techniques, specifically SHAP to improve transparency and trust by offering an interpretable perspective on feature contributions in real-time packet classification. The findings validate that the optimised stacking ensemble markedly surpasses individual models, offering a dependable and comprehensible method for fault detection. This work not only shows how useful hybrid classification and continuous learning are, but it also sets the stage for AI solutions that can grow and change on their own and can be used in important areas like cybersecurity and real-time anomaly detection.
📊 Article Downloads
References
Sundari, M. S., Jadala, V. C., & Vikkurty, S. (2025). Design and evaluation of hybrid explainable AI interfaces for vision restoration in next-generation retinal prosthetics. Journal of Theoretical and Applied Information Technology, 103(13), 4673.
Arora, T. S., Sharma, A., Panwar, P., & Rathore, V. S. (2025). A clustering ensemble approach to improving text classification adding anti-dictionary. In Lecture Notes in Networks and Systems (Vol. 1255, pp. 133–146). Springer. https://doi.org/10.1007/978-981-96-1747-0_11 DOI: https://doi.org/10.1007/978-981-96-1747-0_11
Chen, Y., Chan, W. H., Su, E. L. M., & Diao, Q. (2025). Multi-objective optimization for smart cities: A systematic review of algorithms, challenges, and future directions. PeerJ Computer Science, 11, Article e3042. https://doi.org/10.7717/peerj-cs.3042 DOI: https://doi.org/10.7717/peerj-cs.3042
Kumar, V., Gupta, S. K., Hussain, A., & Sharma, A. (2025). A systematic approach to prevent threats using IDS in IoT-based devices. GMSARN International Journal, 19(1), 107–112.
Gebler, R., Reinecke, I., Sedlmayr, M., & Goldammer, M. (2025). Enhancing clinical data infrastructure for AI research: Comparative evaluation of data management architectures. Journal of Medical Internet Research, 27, Article e74976. https://doi.org/10.2196/74976 DOI: https://doi.org/10.2196/74976
Liu, Z., Chen, X., Liang, X., Sun, Z., Yang, F., Ou, W., Li, L., & Qin, X. (2025). A Transformer-LSTM-SVR hybrid model for AI-driven emotional optimization in NEV embedded interior systems. Scientific Reports, 15, Article 30236. https://doi.org/10.1038/s41598-025-15808-w DOI: https://doi.org/10.1038/s41598-025-15808-w
Vyas, N., Sundar, K., Sharma, A., & Adhikari, P. S. (2025). Leveraging Sentinel-2 multispectral data and machine learning algorithms for land use land cover mapping in semi-arid regions. In Proceedings of the 3rd International Conference on Advancement in Computation and Computer Technologies (InCACCT 2025) (pp. 439–443). IEEE. https://doi.org/10.1109/InCACCT65424.2025.11011472 DOI: https://doi.org/10.1109/InCACCT65424.2025.11011472
Danach, K., & Aly, W. H. F. (2025). Adaptive hyper heuristic framework for hyperparameter tuning: A Q-learning-based heuristic selection approach with simulated annealing acceptance criteria. European Journal of Pure and Applied Mathematics, 18(3), Article 6348. https://doi.org/10.29020/nybg.ejpam.v18i3.6348 DOI: https://doi.org/10.29020/nybg.ejpam.v18i3.6348
Aramide, O. O. (2025). Advanced network telemetry for AI-driven network optimization in ultra ethernet and infiniband interconnects. SAMRIDDHI: A Journal of Physical Sciences, Engineering and Technology, 17(1), 18–27. https://doi.org/10.18090/samriddhi.v17i01.04 DOI: https://doi.org/10.18090/samriddhi.v17i01.04
Alhammadi, N. A. M., & Mabrouk, M. (2025). A multi-agent-based deep learning model for protecting cloud computing environment against distributed denial of service flooding attacks. Journal of Soft Computing and Data Mining, 6(1), 406–422. https://doi.org/10.30880/jscdm.2025.06.01.027
Sharma, A., & Hussain, A. (2025). AI-powered automated detection of cervical cancer using deep learning techniques: A CNN and transfer learning approach. In Obaid, A. J., Polkowski, Z., Burlea-Schiopoiu, A., & Muthmainnah, M. (Eds.), Frontiers in AI and Computational Technologies. ICONEST 2024. Information Systems Engineering and Management (Vol. 40). Springer. https://doi.org/10.1007/978-3-031-89960-7_24 DOI: https://doi.org/10.1007/978-3-031-89960-7_24
Rane, N. L., Choudhary, S. P., & Rane, J. (2024). Ensemble deep learning and machine learning: Applications, opportunities, challenges, and future directions. Studies in Medical and Health Sciences, 5(2), 18–41. https://doi.org/10.48185/smhs.v1i2.1225 DOI: https://doi.org/10.48185/smhs.v1i2.1225
Wang, C., Baratchi, M., Bäck, T., Hoos, H. H., Limmer, S., & Olhofer, M. (2022). Towards time-series feature engineering in automated machine learning for multi-step-ahead forecasting. Engineering Proceedings, 18(1), Article 17. https://doi.org/10.3390/engproc2022018017 DOI: https://doi.org/10.3390/engproc2022018017
Mishra, S., Tripathy, H. K., Mallick, P. K., Bhoi, A. K., & Barsocchi, P. (2020). EAGA-MLP: An enhanced and adaptive hybrid classification model for diabetes diagnosis. Sensors, 20(14), Article 4036. https://doi.org/10.3390/s20144036 DOI: https://doi.org/10.3390/s20144036
Garg, P., & Sharma, A. (2018). A distributed algorithm for local decision of cluster heads in wireless sensor networks. In IEEE International Conference on Power, Control, Signals and Instrumentation Engineering (ICPCSI 2017) (pp. 2411–2415). IEEE. https://doi.org/10.1109/ICPCSI.2017.8392150 DOI: https://doi.org/10.1109/ICPCSI.2017.8392150
Sharma, A., & Sharma, A. (2017). KNN-DBSCAN: Using k-nearest neighbor information for parameter-free density-based clustering. In 2017 International Conference on Intelligent Computing, Instrumentation and Control Technologies (ICICICT 2017) (Vol. 2018-January, pp. 787–792). IEEE. https://doi.org/10.1109/ICICICT1.2017.8342664 DOI: https://doi.org/10.1109/ICICICT1.2017.8342664
Sharma, P., & Sharma, A. (2017). Online K-means clustering with adaptive dual cost functions. In 2017 International Conference on Intelligent Computing, Instrumentation and Control Technologies (ICICICT 2017) (Vol. 2018-January, pp. 793–799). IEEE. https://doi.org/10.1109/ICICICT1.2017.8342665 DOI: https://doi.org/10.1109/ICICICT1.2017.8342665
Dadhich, D., & Sharma, A. (2017). Improved online k-means algorithm. In 11th INDIACom; 4th International Conference on Computing for Sustainable Global Development (INDIACom 2017) (pp. 1286–1292). https://www.scopus.com/inward/record.uri?eid=2-s2.0-105010812740
Mittal, N., & Sharma, A. (2017). Energy-efficient fuzzy-logic based cluster selection for heterogeneous mobile nodes in wireless sensor networks. In 11th INDIACom; 4th International Conference on Computing for Sustainable Global Development (INDIACom 2017) (pp. 876–881). https://www.scopus.com/inward/record.uri?eid=2-s2.0-105010821301
Shukla, A. (2025). System design for AI engineering: Adaptive architectures for real-world scalable AI applications. International Journal of Computer Applications, 187, 975–8887. https://doi.org/10.5120/ijca2025925445 DOI: https://doi.org/10.5120/ijca2025925445
Qadir, H. M., Suleman, M. T., Khan, R. A., & others. (2025). Optimizing learning outcomes: A deep dive into hybrid AI models for adaptive educational feedback. Journal of Big Data, 12, Article 144. https://doi.org/10.1186/s40537-025-01187-6 DOI: https://doi.org/10.1186/s40537-025-01187-6
Al Saadi, M., & Al Saadi, B. (2026). Optimizing neural network architectures with TensorFlow and Keras for scalable deep learning. Journal of Intelligent Systems and Internet of Things, 18(1), 114–125. https://doi.org/10.54216/JISIoT.180108 DOI: https://doi.org/10.54216/JISIoT.180108
Breiman, L. (1996). Stacked regressions. Machine Learning, 24, 49–64. https://doi.org/10.1007/BF00117832 DOI: https://doi.org/10.1023/A:1018046112532
Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. In Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS'17). https://doi.org/10.48550/arXiv.1705.07874
Downloads
Published
Issue
Section
License
Copyright (c) 2025 International Journal of Scientific Research in Science, Engineering and Technology
This work is licensed under a Creative Commons Attribution 4.0 International License.
