A Genai-Driven Risk Prediction Framework For Program Management In Embedded Media Platforms
DOI:
https://doi.org/10.29284/b8qsm433Keywords:
Generative Artificial Intelligence; Embedded Media Systems; Program Risk Prediction; Multimodal Machine Learning; Transformer-Based ArchitecturesAbstract
Embedded media systems have developed to sophisticated cyber-physical nexuses that comprise heterogeneous hardware, software subsystems, real-time data-processing pipeline, network communications, and artificial intelligence capabilities. Such architectural complexity raises the risk of program management especially in the environment of co-design of hardware-software, where a time constraint is present, supply-chain dependencies exist, and the firmware is linked in an iterative cycle of integration. The nonlinear and multimodal risk indicators in such systems are difficult to capture traditional qualitative risk matrices and the static probabilistic models. The paper analyses AI-driven risk prediction models such as probabilistic graphical models, supervised learning, ensemble, deep neural network, graph-based, and transformer-based generative approaches. A quantitative meta-analysis suggests that transformer-based and multimodal models are better than classical statistical models with the pooled AUC values around 0.89 in predicting defects and schedules. Nonetheless, the empirical validation under embedded media program settings is under-validated and structured metrics, unstructured documentation and dependency graphs are seldom employed within a single framework. A risk prediction framework of embedded media programs based on GenAI is suggested that integrates transformer-based contextual modelling, graph neural network dependency propagation, ensemble measures, reinforcement-learning-based mitigation optimization, and explainable AI attribution. optimization of mitigation by reinforcement learning and explainable AI attribution. Research gaps comprise building of domain specific benchmark data, limited combination of explainable and causal models, susceptibility to distributional changes and lack of standard validation procedures. The results indicate that generative AI has a potential to transform embedded program management to proactive and not reactive risk governance in line with industry reliability and compliance need.
References
[1] Leveson, N. G. (2011). Engineering a safer world: Systems thinking applied to safety. MIT Press.
[2] Broy, M. (2006). Challenges in automotive software engineering. In L. Osterweil, H. Rombach, & M. Litoiu (Eds.), Proceedings of the 28th International Conference on Software Engineering (pp. 33–42). IEEE.
[3] Boehm, B., & Turner, R. (2004). Balancing agility and discipline: A guide for the perplexed. Addison-Wesley.
[4] Loch, C. H., DeMeyer, A., & Pich, M. T. (2011). Managing the unknown: A new approach to managing high uncertainty and risk in projects. Wiley.
[5] Hillson, D. (2003). Effective opportunity management for projects: Exploiting positive risk. CRC Press.
[6] Khoshgoftaar, T. M., & Seliya, N. (2004). Comparative assessment of software quality classification techniques. Empirical Software Engineering, 9(3), 229–257.
[7] Jørgensen, M., & Shepperd, M. (2007). A systematic review of software development cost estimation studies. IEEE Transactions on Software Engineering, 33(1), 33–53.
[8] Fenton, N., & Neil, M. (2012). Risk assessment and decision analysis with Bayesian networks. CRC Press.
[9] Lessmann, S., Baesens, B., Mues, C., & Pietsch, S. (2008). Benchmarking classification models for software defect prediction. IEEE Transactions on Software Engineering, 34(4), 485–496.
[10] Malhotra, R. (2015). A systematic review of machine learning techniques for software fault prediction. Applied Soft Computing, 27, 504–518.
[11] Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, I. (2017). Attention is all you need. In I. Guyon et al. (Eds.), Advances in Neural Information Processing Systems (pp. 5998–6008).
[12] Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., ... & Liang, P. (2021). On the opportunities and risks of foundation models. ACM Computing Surveys, 55(3), 1–76.
[13] Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., ... & Amodei, D. (2020). Language models are few-shot learners. In H. Larochelle et al. (Eds.), Advances in Neural Information Processing Systems (pp. 1877–1901).
[14] Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., & Yu, P. S. (2021). A comprehensive survey on graph neural networks. IEEE Transactions on Neural Networks and Learning Systems, 32(1), 4–24.
[15] Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of NAACL-HLT (pp. 4171–4186). ACL.
[16] Sutton, R. S., & Barto, A. G. (2018). Reinforcement learning: An introduction (2nd ed.). MIT Press.
[17] Catal, C., & Diri, B. (2009). A systematic review of software fault prediction studies. Expert Systems with Applications, 36(4), 7346–7354.
[18] Liberatore, M. J., & Pollack-Johnson, B. (2013). Improving project management decision making by modeling risk. International Journal of Project Management, 31(4), 542–554.
[19] McNeil, A. J., Frey, R., & Embrechts, P. (2015). Quantitative risk management: Concepts, techniques and tools. Princeton University Press.
[20] Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. In I. Guyon et al. (Eds.), Advances in Neural Information Processing Systems (pp. 4765–4774).
[21] Doshi-Velez, F., & Kim, B. (2018). Considerations for evaluation and generalization in interpretable machine learning. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 32).
[22] Humble, J., & Farley, D. (2010). Continuous delivery: Reliable software releases through build, test, and deployment automation. Addison-Wesley.
[23] Tao, F., Zhang, M., Liu, Y., & Nee, A. Y. C. (2019). Digital twin-driven product design, manufacturing and service with big data. The International Journal of Advanced Manufacturing Technology, 94(9–12), 3563–3576.
[24] Fenton, N., Neil, M., & Marsh, W. (2007). Using Bayesian networks for risk assessment in software engineering. Journal of Risk Research, 10(3), 369–387.
[25] Jensen, F. V., & Nielsen, T. D. (2007). Bayesian networks and decision graphs. Springer.
[26] Ghotra, B., McIntosh, S., & Hassan, A. E. (2015). Revisiting the impact of classification techniques on defect prediction models. IEEE Transactions on Software Engineering, 41(10), 939–954.
[27] Catal, C. (2011). Software fault prediction: A literature review and current trends. Expert Systems with Applications, 38(4), 4626–4636.
[28] Hall, T., Beecham, S., Bowes, D., Gray, D., & Counsell, S. (2012). A systematic literature review on fault prediction performance in software engineering. IEEE Transactions on Software Engineering, 38(6), 1276–1304.
[29] Zhou, Y., & Leung, H. (2007). Empirical analysis of object-oriented design metrics for predicting high and low severity faults. IEEE Transactions on Software Engineering, 32(10), 771–789.
[30] Wang, S., Liu, T., Tan, L., & Zhang, X. (2016). Automatically learning semantic features for defect prediction. In Proceedings of the 38th International Conference on Software Engineering (pp. 297–308). IEEE.
[31] Li, Z., He, P., Zhu, J., & Lyu, M. R. (2017). Deep learning for just-in-time defect prediction. In Proceedings of IEEE QRS (pp. 17–28). IEEE.
[32] Allamanis, M., Brockschmidt, M., & Khademi, M. (2018). Learning to represent programs with graphs. In International Conference on Learning Representations.
[33] Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., ... & Houlsby, N. (2021). An image is worth 16×16 words: Transformers for image recognition at scale. In International Conference on Learning Representations.
[34] Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., ... & Stoyanov, V. (2019). RoBERTa: A robustly optimized BERT pretraining approach. In International Conference on Learning Representations.
[35] Yang, X., Lo, D., Xia, X., Zhang, Y., & Sun, J. (2021). Transformer-based defect prediction. Information and Software Technology, 132, 106498.
[36] Zhou, J., Chen, Y., & Zhang, Z. (2023). Foundation models in artificial intelligence: Survey and outlook. IEEE Transactions on Pattern Analysis and Machine Intelligence. Advance online publication.
[37] Pearce, H., Ahmad, B., Tan, B., & Karri, R. (2022). Asleep at the keyboard? Assessing the security of GitHub Copilot’s code contributions. In Proceedings of IEEE Symposium on Security and Privacy (pp. 754–768).
[38] Leveson, N. G. (2004). A new accident model for engineering safer systems. Safety Science, 42(4), 237–270.
[39] Zhang, H., Yang, S., & Zhao, Y. (2019). Reinforcement learning-based scheduling for cloud environments. Future Generation Computer Systems, 99, 258–269.
[40] Molnar, C. (2022). Interpretable machine learning (2nd ed.). Springer.
[41] Wiegreffe, S., & Pinter, Y. (2019). Attention is not explanation. In Proceedings of EMNLP (pp. 11–20).
[42] Khandani, A. E., Kim, A. J., & Lo, A. W. (2010). Consumer credit-risk models via machine-learning algorithms. Journal of Banking & Finance, 34(11), 2767–2787.
[43] Pearl, J. (2009). Causality: Models, reasoning, and inference (2nd ed.). Cambridge University Press.
[44] Menzies, T., Greenwald, J., & Frank, A. (2007). Data mining static code attributes to learn defect predictors. IEEE Transactions on Software Engineering, 33(1), 2–13.
[45] Turhan, B., Menzies, T., Bener, A. B., & Di Stefano, J. (2009). On the relative value of cross-company and within-company data for defect prediction. Empirical Software Engineering, 14(5), 540–578.
[46] Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference (pp. 785–794). ACM.
[47] Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780.
[48] Kim, Y. (2014). Convolutional neural networks for sentence classification. In Proceedings of EMNLP (pp. 1746–1751).
[49] Kipf, T. N., & Welling, M. (2017). Semi-supervised classification with graph convolutional networks. In International Conference on Learning Representations.
[50] Tay, Y., Dehghani, M., Bahri, D., & Metzler, D. (2022). Efficient transformers: A survey. ACM Computing Surveys, 55(6), 1–28.
[51] Zhang, J., Li, X., & Wang, J. (2019). A deep learning-based approach for software defect prediction. IEEE Access, 7, 19141–19153.
[52] Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., ... & Liu, P. J. (2020). Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of Machine Learning Research, 21(140), 1–67.
[53] Powers, D. M. W. (2011). Evaluation: From precision, recall and F-measure to ROC, informedness, markedness and correlation. Journal of Machine Learning Technologies, 2(1), 37–63.
[54] Rudin, C. (2019). Stop explaining black box models for high stakes decisions. Nature Machine Intelligence, 1, 206–215.
[55] Jiang, Y., Li, J., & Wang, Z. (2022). Transformer-based fault prediction in complex systems. Reliability Engineering & System Safety, 219, 108172.
[56] Wen, J., Li, S., Lin, Z., Hu, Y., & Huang, C. (2012). Systematic literature review of machine learning-based software development effort estimation models. Information and Software Technology, 54(1), 41–59.
[57] Clark, K., Khandelwal, U., Levy, O., & Manning, C. D. (2020). What does BERT look at? An analysis of attention in transformer models. Transactions of the Association for Computational Linguistics, 8, 276–292.
[58] Baltrušaitis, T., Ahuja, C., & Morency, L. (2019). Multimodal machine learning: A survey and taxonomy. IEEE Transactions on Pattern Analysis and Machine Intelligence, 41(2), 423–443.
[59] Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). “Why should I trust you?” Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD International Conference (pp. 1135–1144). ACM.
[60] Shepperd, M., Bowes, D., & Hall, T. (2014). Researcher bias: The use of machine learning in software defect prediction. IEEE Transactions on Software Engineering, 40(6), 603–616.
[61] Tsai, Y.-H. H., Bai, S., Yamada, M., Morency, L., & Salakhutdinov, R. (2019). Multimodal transformer for unaligned multimodal language sequences. In Proceedings of ACL (pp. 6558–6569).
[62] Li, Y. (2018). Deep reinforcement learning: An overview. Frontiers of Information Technology & Electronic Engineering, 19(1), 1–26.
[63] Spirtes, P., Glymour, C., & Scheines, R. (2000). Causation, prediction, and search (2nd ed.). MIT Press.
[64] Fuller, A., Fan, Z., Day, C., & Barlow, C. (2020). Digital twin: Enabling technologies, challenges and open research. IEEE Access, 8, 108952–108971.
[65] Gal, Y., & Ghahramani, Z. (2016). Dropout as a Bayesian approximation: Representing model uncertainty in deep learning. In Proceedings of ICML (pp. 1050–1059).
[66] Amershi, S., Weld, D. S., Vorvoreanu, M., Fourney, A., Nushi, B., Collisson, P., ... & Horvitz, E. (2019). Guidelines for human-AI interaction. In Proceedings of the CHI Conference on Human Factors in Computing Systems (pp. 1–13). ACM.
[67] Broy, M., Krüger, I. H., Pretschner, A., & Salzmann, C. (2007). Engineering automotive software. Proceedings of the IEEE, 95(2), 356–373.
[68] Neil, M., Fenton, N., & Nielsen, L. (2000). Building large-scale Bayesian networks. The Knowledge Engineering Review, 15(3), 257–284.
[69] Gunning, D., & Aha, D. (2019). DARPA’s explainable artificial intelligence (XAI) program. AI Magazine, 40(2), 44–58.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
