Agile-based Requirements Engineering for Machine Learning: A Case Study on Personalized Nutrition

Authors

  • Carlos Cunha Polytechnic Institute of Viseu, Portugal
  • Rafael Oliveira Polytechnic Institute of Viseu, Portugal
  • Rui Duarte Polytechnic Institute of Viseu, Portugal

Keywords:

requirements engineering, machine learning, deep learning, explainability, agile, user stories, acceptance criteria

Abstract

Requirements engineering is crucial in developing machine learning systems, as it establishes the foundation for successful project execution. Nevertheless, incorporating requirements engineering approaches from traditional software engineering into machine learning projects presents new challenges. These challenges arise from replacing the software logic derived from static software specifications with dynamic software logic derived from data. This paper presents a case study exploring an agile requirement engineering approach popular in traditional software projects to specify requirements in machine learning software. These requirements allow reasoning about the correctness of software and design tests for validation. The absence of software specification in machine learning software is offset by employing data quality metrics, which are assessed using cutting-edge methods for model interpretability. A case study on personalized nutrition and physical activity demonstrated the adequacy of user stories and acceptance criteria format, popular in agile projects, for specifying requirements in the machine learning domain.

Downloads

Download data is not yet available.

References

A. Vogelsang e M. Borg, «Requirements Engineering for Machine Learning: Perspectives from Data Scientists», em 2019 IEEE 27th International Requirements Engineering Conference Workshops (REW), set. 2019, pp. 245–251. doi: 10.1109/REW.2019.00050.

M. Cohn, User stories applied: for agile software development, 18. print. em Addison-Wesley signature series. Boston, Mass.: Addison-Wesley, 2013.

K. Ahmad, M. Abdelrazek, C. Arora, M. Bano, e J. Grundy, «Requirements engineering for artificial intelligence systems: A systematic mapping study», Inf. Softw. Technol., vol. 158, p. 107176, jun. 2023, doi: 10.1016/j.infsof.2023.107176.

F. Ishikawa e Y. Matsuno, «Evidence-driven Requirements Engineering for Uncertainty of Machine Learning-based Systems», em 2020 IEEE 28th International Requirements Engineering Conference (RE), ago. 2020, pp. 346–351. doi: 10.1109/RE48521.2020.00046.

X. Wang, «A framework for Requirements specification of machine-learning systems», apresentado na The 34th International Conference on Software Engineering and Knowledge Engineering, jul. 2022, pp. 7–12. doi: 10.18293/SEKE2022-143.

Z. Pei, L. Liu, C. Wang, e J. Wang, «Requirements Engineering for Machine Learning: A Review and Reflection», em 2022 IEEE 30th International Requirements Engineering Conference Workshops (REW), Melbourne, Australia: IEEE, ago. 2022, pp. 166–175. doi: 10.1109/REW56159.2022.00039.

K. M. Habibullah e J. Horkoff, «Non-functional Requirements for Machine Learning: Understanding Current Use and Challenges in Industry», em 2021 IEEE 29th International Requirements Engineering Conference (RE), Notre Dame, IN, USA: IEEE, set. 2021, pp. 13–23. doi: 10.1109/RE51729.2021.00009.

S. Nalchigar, E. Yu, e K. Keshavjee, «Modeling machine learning requirements from three perspectives: a case report from the healthcare domain», Requir. Eng., vol. 26, n.o 2, pp. 237–254, jun. 2021, doi: 10.1007/s00766-020-00343-z.

S. Nalchigar, E. Yu, e R. Ramani, «A Conceptual Modeling Framework for Business Analytics», em Conceptual Modeling, I. Comyn-Wattiau, K. Tanaka, I.-Y. Song, S. Yamamoto, e M. Saeki, Eds., em Lecture Notes in Computer Science, vol. 9974. Cham: Springer International Publishing, 2016, pp. 35–49. doi: 10.1007/978-3-319-46397-1_3.

H. Challa, N. Niu, e R. Johnson, «Faulty Requirements Made Valuable: On the Role of Data Quality in Deep Learning», em 2020 IEEE Seventh International Workshop on Artificial Intelligence for Requirements Engineering (AIRE), Zurich, Switzerland: IEEE, set. 2020, pp. 61–69. doi: 10.1109/AIRE51212.2020.00016.

H. Kuwajima, H. Yasuoka, e T. Nakae, «Engineering problems in machine learning systems», Mach. Learn., vol. 109, n.o 5, pp. 1103–1126, mai. 2020, doi: 10.1007/s10994-020-05872-w.

F. Febrero, C. Calero, e M. Ángeles Moraga, «Software reliability modeling based on ISO/IEC SQuaRE», Inf. Softw. Technol., vol. 70, pp. 18–29, fev. 2016, doi: 10.1016/j.infsof.2015.09.006.

B. D. Klein, «User Perceptions of Data Quality: Internet and Traditional Text Sources», J. Comput. Inf. Syst., vol. 41, n.o 4, pp. 9–15, 2001, doi: 10.1080/08874417.2001.11647016.

S. Hochreiter e J. Schmidhuber, «Long Short-Term Memory», Neural Comput., vol. 9, n.o 8, pp. 1735–1780, nov. 1997, doi: 10.1162/neco.1997.9.8.1735.

E. Layer, «Fitbit Tracker Data Analysis». https://www.kaggle.com/code/ericlayer/fitbit-fitness-tracker-data-analysis.

S. M. Lundberg e S.-I. Lee, «A Unified Approach to Interpreting Model Predictions», em Advances in Neural Information Processing Systems, I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, e R. Garnett, Eds., Curran Associates, Inc., 2017. [Em linha]. Disponível em: https://proceedings.neurips.cc/paper_files/paper/2017/file/8a20a8621978632d76c43dfd28b67767-Paper.pdf

R. Alenezi e S. A. Ludwig, «Explainability of Cybersecurity Threats Data Using SHAP», em 2021 IEEE Symposium Series on Computational Intelligence (SSCI), Orlando, FL, USA: IEEE, dez. 2021, pp. 01–10. doi: 10.1109/SSCI50451.2021.9659888.

S. Ahmed, S. N. Nobel, e O. Ullah, «An Effective Deep CNN Model for Multiclass Brain Tumor Detection Using MRI Images and SHAP Explainability», em 2023 International Conference on Electrical, Computer and Communication Engineering (ECCE), Chittagong, Bangladesh: IEEE, fev. 2023, pp. 1–6. doi: 10.1109/ECCE57851.2023.10101503.

M. Yap et al., «Verifying explainability of a deep learning tissue classifier trained on RNA-seq data», Sci. Rep., vol. 11, n.o 1, p. 2641, jan. 2021, doi: 10.1038/s41598-021-81773-9.

G. I. Webb, R. Hyde, H. Cao, H. L. Nguyen, e F. Petitjean, «Characterizing concept drift», Data Min. Knowl. Discov., vol. 30, n.o 4, pp. 964–994, jul. 2016, doi: 10.1007/s10618-015-0448-4.

Downloads

Published

25.12.2023

How to Cite

Cunha, C. ., Oliveira, R. ., & Duarte, R. . (2023). Agile-based Requirements Engineering for Machine Learning: A Case Study on Personalized Nutrition. International Journal of Intelligent Systems and Applications in Engineering, 12(2), 319–327. Retrieved from https://www.ijisae.org/index.php/IJISAE/article/view/4255

Issue

Vol. 12 No. 2 (2024)

Section

Research Article

License

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.

IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.