Abstract
The importance of deployed machine learning solutions has increased significantly in the past years due to the availability of data sources, computing capabilities and convenient tooling. However, technical challenges such as limited resources and computing power arise in many applications. We consider a scenario where a machine learning model is deployed in an environment where all computations need to be performed on a local computing unit. Furthermore, after deployment, the model does not receive any ground truth labels as feedback. We develop a two-step prediction method which combines an outlier detection with a robust machine learning model. This approach is evaluated based on a data set from a large German OEM. We can show that the prediction performance is increased significantly with our approach while fulfilling the restrictions in terms of memory and computational power. This way, we contribute to the practical applicability of machine learning models for real-world applications.
Keywords
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Adler, P.S., Clark, K.B.: Behind the learning curve: a sketch of the learning process. Manage. Sci. 37(3), 267–281 (1991)
Aggarwal, C.C.: Data Mining. The Textbook. Springer (2015). https://doi.org/10.1007/978-3-319-14142-8
Alsheikh, M.A., Lin, S., Niyato, D., Tan, H.P.: Machine learning in wireless sensor networks: algorithms, strategies, and applications. IEEE Commun. Surv. Tutorials 16, 1996–2018 (2014)
An, X., Zhou, X., Lü, X., Lin, F., Yang, L.: Sample selected extreme learning machine based intrusion detection in fog computing and MEC. Wireless Commun. Mob. Comput. 2018 (2018)
Anguita, D., Ghio, A., Oneto, L., Parra, X., Reyes-Ortiz, J.L.: Human activity recognition on smartphones using a multiclass hardware-friendly support vector machine. In: Bravo, J., Hervas, R., Rodriguez, M. (eds.)International Workshop on Ambient Assisted Living, pp. 216–223. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-35395-6_30
Anguita, D., Ghio, A., Pischiutta, S., Ridella, S.: A hardware-friendly support vector machine for embedded automotive applications. In: International Joint Conference on Neural Networks (IJCNN), pp. 1360–1364 (2007)
Armstrong, J.S., Collopy, F.: Error measures for generalizing about forecasting methods: empirical comparisons. Int. J. Forecasting 8(1), 69–80 (1992)
Baier, L., Hofmann, M., Kühl, N., Mohr, M., Satzger, G.: Handling concept drifts in regression problems–the error intersection approach. In: International Conference on Wirtschaftsinformatik (2020)
Baier, L., Kühl, N., Satzger, G.: How to cope with change?-preserving validity of predictive services over time. In: Proceedings of the 52nd Hawaii International Conference on System Sciences (2019)
Barnett, V., Lewis, T.: Outliers in Statistical Data. Wiley, New York (1994)
Bergstra, J., Yoshua, B.: Random search for hyper-parameter optimization. J. Mach. Learn. Res. 13, 281–305 (2012)
Cavalcante, R.C., Minku, L.L., Oliveira, A.L.: FEDD: feature extraction for explicit concept drift detection in time series. In: International Joint Conference on Neural Networks (IJCNN), pp. 740–747 (2016)
Chandola, V., Banerjee, A., Kumar, V.: Outlier detection: a survey. ACM Comput. Surv. 14, 15 (2007)
Chen, H., Chiang, R., Storey, V.: Business intelligence and analytics: from big data to big impact. MIS Q. 36(4), 1165–1188 (2012)
Dal Pozzolo, A., Boracchi, G., Caelen, O., Alippi, C., Bontempi, G.: Credit card fraud detection: a realistic modeling and a novel learning strategy. IEEE Trans. Neural Netw. Learn. Syst. 29(8), 3784–3797 (2017)
De Maesschalck, R., Jouan-Rimbaud, D., Massart, D.L.: The Mahalanobis distance. Chemometr. Intell. Lab. Syst. 40, 1–18 (2000)
Gama, J., Žliobaitė, I., Bifet, A., Pechenizkiy, M., Bouchachia, A.: A survey on concept drift adaptation. ACM Comput. Surv. 46(4), 1–37 (2014)
Golub, G.H., Heath, M., Wahba, G.: Generalized cross-validation as a method for choosing a good ridge parameter. Technometrics 21, 215–223 (1979)
Gupta, S., Agrawal, A., Gopalakrishnan, K., Narayanan, P.: Deep learning with limited numerical precision. In: International Conference on Machine Learning, pp. 1737–1746 (2015)
Hodge, V.J., Austin, J.: A survey of outlier detection methodologies. Artif. Intell. Rev. 22, 85–126 (2004)
Fei, H., Hao, Q.: Intelligent Sensor Networks: The Integration of Sensor Networks, Signal Processing and Machine Learning. CRC Press, Boca Raton (2012)
Jordan, M.I., Mitchell, T.M.: Machine learning: trends, perspectives, and prospects. Science 349(6245), 255–260 (2015)
Kadlec, P., Gabrys, B.: Local learning-based adaptive soft sensor for catalyst activation prediction. AIChE J. 57(5), 1288–1301 (2011)
Kanungo, T., Mount, D.M., Netanyahu, N.S., Piatko, C.D., Silverman, R., Wu, A.Y.: An efficient k-means clustering algorithm: analysis and implementation. IEEE Trans. Pattern Anal. Mach. Intell. 24(7), 881–892 (2002)
Malikopoulos, A.A., Papalambros, P.Y., Assanis, D.N.: A learning algorithm for optimal internal combustion engine calibration in real time. In: ASME International Design Engineering Technical Conferences, pp. 91–100. American Society of Mechanical Engineers (2007)
Oneto, L., Ghio, A., Ridella, S., Anguita, D.: Learning resource-aware classifiers for mobile devices: from regularization to energy efficiency. Neurocomputing 169, 225–235 (2015)
Orair, G.H., Teixeira, C.H., Meira Jr., W., Wang, Y., Parthasarathy, S.: Distance-based outlier detection: consolidation and renewed bearing. In: Proceedings of the VLDB Endowment, vol. 3, pp. 1469–1480. VLDB Endowment (2010)
Pedregosa, F., Varoquaux, G., Gramfort, A.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011)
Raykar, V.C., et al.: Supervised learning from multiple experts: whom to trust when everyone lies a bit. In: Proceedings of the 26th Annual International Conference on Machine Learning, pp. 889–896 (2009)
Schüritz, R., Satzger., G.: Patterns of data-infused business model innovation. In: Proceedings of IEEE 18th Conference on Business Informatics (CBI), vol. 1, pp. 133–142. IEEE (2016)
Tsymbal, A.: The problem of concept drift: definitions and related work. Computer Science Department, Trinity College Dublin, 106(2) (2004)
Vong, C.-M., Wong, P.-K., Li, Y.-P.: Prediction of automotive engine power and torque using least squares support vector machines and Bayesian inference. Eng. Appl. Artif. Intell. 19(3), 277–287 (2006)
Wang, S., et al.: When edge meets learning: adaptive control for resource-constrained distributed machine learning. In: IEEE Conference on Computer Communications, pp. 63–71 (2018)
Widmer, G., Kubat, M.: Learning in the presence of concept drift and hidden contexts. Mach. Learn. 23(1), 69–101 (1996)
Xie, Y., Kistner, A., Bleile, T.: Optimal automated calibration of model-based ECU-functions in air system of diesel engines. Technical report, SAE Technical Paper (2018)
Yu, H.-F., Jain, P., Kar, P., Dhillon, I.: Large-scale multi-label learning with missing labels. In: International Conference on Machine Learning, pp. 593–601 (2014)
Zhang, Q., Cheng, L., Boutaba, R.: Cloud computing: state-of-the-art and research challenges. J. Internet Serv. Appl. 1, 7–18 (2010)
Zhou, Z.-H.: Machine learning challenges and impact: an interview with Thomas Dietterich. Nat. Sci. Rev. 5(1), 54–58 (2017)
Zimek, A., Schubert, E., Kriegel, H.-P.: A survey on unsupervised outlier detection in high-dimensional numerical data. Stat. Anal. Data Min. ASA Data Sci. J. 5(5), 363–387 (2012)
Žliobaitė, I.: Learning under concept drift: an overview. arXiv preprint arXiv:1010.4784 (2010)
Žliobaite, I., Pechenizkiy, M., Gama, J.: An overview of concept drift applications. Big Data Analysis: New Algorithms for a New Society, pp. 91–114 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Baier, L., Kühl, N., Schmitt, J. (2022). Increasing Robustness for Machine Learning Services in Challenging Environments: Limited Resources and No Label Feedback. In: Arai, K. (eds) Intelligent Systems and Applications. IntelliSys 2021. Lecture Notes in Networks and Systems, vol 294. Springer, Cham. https://doi.org/10.1007/978-3-030-82193-7_57
Download citation
DOI: https://doi.org/10.1007/978-3-030-82193-7_57
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-82192-0
Online ISBN: 978-3-030-82193-7
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)