Neural Scoring of Logical Inferences from Data using Feedback.

Allmin Susaiyah; Aki Härmä; Ehud Reiter; Milan PetkoviĆ

doi:10.9781/ijimai.2021.02.004

Authors

Allmin Susaiyah Eindhoven University of Technology
Aki Härmä Philips Research.
Ehud Reiter University of Aberdeen
Milan PetkoviĆ Eindhoven University of Technology

DOI:

https://doi.org/10.9781/ijimai.2021.02.004

Keywords:

Artificial Intelligence, Feedback, Neural Network, Self-supervised Learning, Transfer Learning, Logical Inference, Natural Language Generation, Statistical Learning

Supporting Agencies

This paper is an extension of our previous work presented at the IntelLang workshop at the ECAI 2020 conference [31]. In that, we considered user preferences that are simple and concerns at-most one type of insights at a time. In this paper, we extend this to two or more types of similar or different insights being preferred at the same time. This work was supported by the Horizon H2020 Marie SkłodowskaCurie Actions Initial Training Network European Industrial Doctorates project under grant agreement No. 812882 (PhilHumans).

Abstract

Insights derived from wearable sensors in smartwatches or sleep trackers can help users in approaching their healthy lifestyle goals. These insights should indicate significant inferences from user behaviour and their generation should adapt automatically to the preferences and goals of the user. In this paper, we propose a neural network model that generates personalised lifestyle insights based on a model of their significance, and feedback from the user. Simulated analysis of our model shows its ability to assign high scores to a) insights with statistically significant behaviour patterns and b) topics related to simple or complex user preferences at any given time. We believe that the proposed neural networks model could be adapted for any application that needs user feedback to score logical inferences from data.

Downloads

Download data is not yet available.

References

[1] M. Hingle, H. Patrick, “There are thousands of apps for that: navigating mobile technology for nutrition education and behavior,” Journal of nutrition education and behavior, vol. 48, no. 3, pp. 213–218, 2016.

[2] J. P. Higgins, “Smartphone applications for patients’ health and fitness,” The American journal of medicine, vol. 129, no. 1, pp. 11–19, 2016.

[3] A. Härmä, R. Helaoui, “Probabilistic scoring of validated in-sights for personal health services,” in 2016 IEEE Symposium Series on Computational Intelligence (SSCI), 2016, pp. 1–6, IEEE.

[4] S. J. O’Malley, R. T. Smith, B. H. Thomas, “Data mining office behavioural information from simple sensors.,” in AUIC, 2012, pp. 97–98.

[5] D. Braun, E. Reiter, A. Siddharthan, “Saferdrive: An nlg-based behaviour change support system for drivers,” Natural Language Engineering, vol. 24, no. 4, pp. 551–588, 2018.

[6] S. G. Sripada, F. Gao, “Linguistic interpretations of scuba dive computer data,” in 2007 11th International Conference Information Visualization (IV’07), 2007, pp. 436–441, IEEE.

[7] R. Agrawal, J. C. Shafer, “Parallel mining of association rules,” IEEE Transactions on knowledge and Data Engineering, vol. 8, no. 6, pp. 962– 969, 1996.

[8] A. A. Freitas, “On rule interestingness measures,” in Research and Development in Expert Systems XV, Springer, 1999, pp. 147–158.

[9] U. Fayyad, G. Piatetsky-Shapiro, P. Smyth, “From data mining to knowledge discovery in databases,” AI magazine, vol. 17, no. 3, pp. 37–37, 1996.

[10] N. Sudarsanam, N. Kumar, A. Sharma, B. Ravindran, “Rate of change analysis for interestingness measures,” Knowledge and Information Systems, pp. 1–20, 2019.

[11] H. op den Akker, M. Cabrita, R. op den Akker, V. M. Jones, H. J. Hermens, “Tailored motivational message generation: A model and practical framework for real-time physical activity coaching,” Journal of biomedical informatics, vol. 55, pp. 104–115, 2015.

[12] E. Reiter, R. Robertson, L. M. Osman, “Lessons from a failure: Generating tailored smoking cessation letters,” Artificial Intelligence, vol. 144, no. 1-2, pp. 41–58, 2003.

[13] A. Susaiyah, A. Härmä, E. Reiter, R. Helaoui, M. PetkoviĆ, et al., “Towards a generalised framework for behaviour insight mining,” in SmartPHIL: 1st Workshop on Smart Personal Health Interfaces, 2020, ACM.

[14] “Connected sleep and wake up light hf3670/60,” Mar 2020. [Online]. Available: https://www.usa.philips.com/shop/US_Air-FryerOnly/personal-care/light-therapy/smartsleep-connected-sleep-and-wake-uplight/p/HF3670_60.

[15] K. Antczak, “Deep recurrent neural networks for ecg signal denoising,” arXiv preprint arXiv:1807.11551, 2018.

[16] S. Kaymak, A. Helwan, D. Uzun, “Breast cancer image classification using artificial neural networks,” Procedia computer science, vol. 120, pp. 126–131, 2017.

[17] S. Chopra, D. Yadav, A. Chopra, “Artificial neural networks based indian stock market price prediction: before and after demonetization,” J Swarm Intel Evol Comput, vol. 8, no. 174, p. 2, 2019.

[18] K. T. Islam, G. Mujtaba, R. G. Raj, H. F. Nweke, “Handwritten digits recognition with artificial neural network,” in 2017 International Conference on Engineering Technology and Technopreneurship (ICE2T), 2017, pp. 1–4, IEEE.

[19] J. Tao, X. Fang, “Toward multi-label sentiment analysis: a transfer learning based approach,” Journal of Big Data, vol. 7, no. 1, pp. 1–26, 2020.

[20] M. Long, Y. Cao, J. Wang, M. I. Jordan, “Learning transfer-able features with deep adaptation networks,” arXiv preprint arXiv:1502.02791, 2015.

[21] T. Mikolov, I. Sutskever, K. Chen, G. S. Corrado, J. Dean, “Distributed representations of words and phrases and their compositionality,” in Advances in neural information processing systems, 2013, pp. 3111–3119.

[22] B. Settles, “Active learning literature survey,” University of WisconsinMadison Department of Computer Sciences, 2009.

[23] B. Settles, “From theories to queries: Active learning in practice,” in Active Learning and Experimental Design workshop In conjunction with AISTATS 2010, 2011, pp. 1-18.

[24] X. Zhai, A. Oliver, A. Kolesnikov, L. Beyer, “S4l: Self-supervised semisupervised learning,” in Proceedings of the IEEE international conference on computer vision, 2019, pp. 1476-1485.

[25] J. Devlin, M. W. Chang, K. Lee, K. Toutanova, “Bert: Pre-training of deep bidirectional transformers for language understanding,” arXiv preprint arXiv:1810.04805, 2018.

[26] S. Pascual, M. Ravanelli, J. Serrà, A. Bonafonte, Y. Bengio, “Learning problem-agnostic speech representations from multiple self-supervised tasks,” 2019.

[27] P. Neculoiu, M. Versteegh, M. Rotaru, “Learning text similarity with siamese recurrent networks,” in Proceedings of the 1st Workshop on Representation Learning for NLP, 2016, pp. 148-157.

[28] S. Berlemont, G. Lefebvre, S. Duffner, C. Garcia, “Siamese neural network based similarity metric for inertial gesture classification and rejection,” in International Conference on Automatic Face and Gesture Recognition, 2015, pp. 1–6.

[29] W. Sun, S. Shao, R. Zhao, R. Yan, X. Zhang, X. Chen, “A sparse autoencoder-based deep neural network approach for induction motor faults classification,” Measurement, vol. 89, pp. 171-178, 2016, doi: https://doi.org/10.1016/j.measurement.2016.04.007.

[30] K. Choi, G. Fazekas, K. Cho, M. Sandler, “The effects of noisy labels on deep convolutional neural networks for music tagging,” IEEE Transactions on Emerging Topics in Computational Intelligence, vol. 2, no. 2, pp. 139- 149, 2018, doi: 10.1109/TETCI.2017.2771298.

[31] A. Susaiyah, A. Härmä, E. Reiter, M. PetkoviĆ, “Iterative neural scoring of validated insight candidates,” in ECAI workshop on Intelligent Information Processing and Natural Language Generation, Santiago de Compostela, Spain, Sep 2020.