Abstract
Artificial Intelligence (AI) systems are increasingly dependent on machine learning models which lack interpretability and algorithmic transparency, and hence may not be trusted by its users. The fear of failure in these systems is driving many governments to demand more explanation and accountability. Take, for example, the “Right of Explanation” rule proposed in the European Union in 2019, which gives citizens the right to demand an explanation from AI-based predictions. Explainable Artificial Intelligence (XAI) is an attempt to open up the “black box” and create more explainable systems which create predictive models whose results are easily understandable to humans. This paper describes an explanation model called ExplainEx which automatically generates natural language explanation for predictive models by consuming REST API provided by ExpliClas open-source web service. The classification model consists of four main decision tree algorithms including J48, Random Tree, RepTree and FURIA. The user interface was designed based on Microsoft.Net Framework programming platform. At the background is a software engine automating a seamless interaction between Expliclas API and the trained datasets, to provide natural language explanation to users. Unlike other studies, our proposed model is both a stand-alone and client-server based system capable of providing global explanations for any decision tree classifier. It supports multiple concurrent users in a client-server environment and can apply all four algorithms concurrently on a single dataset, returning both precision score and explanation. It is a ready tool for researchers who have datasets and classifiers prepared for explanation. This work bridges the gap between prediction and explanation, thereby allowing researchers to concentrate on data analysis and building state-of-the-art predictive models.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Alexander, A., Jiang, A., Ferreira, C., Zurkiya, D.: An intelligent future for medical imaging: a market outlook on artificial intelligence for medical imaging. J. Am. Coll. Radiol. 17(1), 165–170 (2019). https://doi.org/10.1016/j.jacr.2019.07.019
Alirio, R., Escobar, R., Liberona, D.: Government and governance in intelligent cities, smart transportation study case in Bogotá Colombia. Ain Shams Eng. J. 11(1), 25–34 (2020). https://doi.org/10.1016/j.asej.2019.05.002
Alonso, J.M.: Explainable Artificial Intelligence for Human-Centric Data Analysis in Virtual Learning Environments Explainable Artificial Intelligence for Human-Centric Data Analysis in Virtual Learning Environments, September 2019. https://doi.org/10.1007/978-3-030-31284-8
Alonso, J.M.: Explainable artificial intelligence for kids. In: EUSFLAT, pp. 134–141 (2019)
Adebayo, V., Sowunmi, O.Y., Misra, S., Ahuja, R., Damaševičius, R., Oluranti, J.: The role of ICTs in sex education: the need for a SexEd app. In: International Conference on Innovations in Bio-Inspired Computing and Applications, pp. 343–351. Springer, Cham, December 2019
Amodei, D., Olah, C., Steinhardt, J., Christiano, P., Schulman, J., Mané, D.: Concrete problems in AI safety. 277(2003), 1–21 (2016). https://arxiv.org/abs/1606.06565
Ikedinachi, A.P., Misra, S., Assibong, P.A., Olu-Owolabi, E.F., Maskeliūnas, R., Damasevicius, R.: Artificial intelligence, smart classrooms and online education in the 21st century: implications for human development. J. Cases Inf. Technol. (JCIT) 21(3), 66–79 (2019)
Cahour, B., Forzy, J., Cahour, B., Does, J.F.: Does projection into use improve trust and exploration? An example with a cruise control system. To cite this version: HAL Id: hal-00471270 (2010)
Calvaresi, D., Främling, K.: Explainable agents and robots: results from a systematic literature review. In: AAMAS, pp. 1078–1088 (2019)
Chen, L., Yang, X., Sun, C., Wang, Y.: Feed intake prediction model for group fish using the MEA-BP neural network in intensive aquaculture. Inf. Process. Agric. 7, 1–11 (2019). https://doi.org/10.1016/j.inpa.2019.09.001
Ogwueleka, F.N., Misra, S., Ogwueleka, T.C., Fernandez-Sanz, L.: An artificial neural network model for road accident prediction: a case study of a developing country. Acta Polytechnica Hungarica 11(5), 177–197 (2014)
Wogu, I.A., Misra, S., Assibong, P., Adewumi, A., Damasevicius, R., Maskeliunas, R.: A critical review of the politics of artificial intelligent machines, alienation and the existential risk threat to America’s labour force. In: International Conference on Computational Science and Its Applications, pp. 217–232. Springer, Cham, May 2018
Duval, A.: Explainable Artificial Intelligence (XAI ) Explainable Artificial Intelligence (XAI) by Alexandre Duval MA4K9 Scholarly Report Submitted to The University of Warwick Mathematics Institute, April 2019. https://doi.org/10.13140/RG.2.2.24722.09929
Dymitruk, M.: The right to a fair trial, pp. 27–44 (2019). https://doi.org/10.5817/MUJLT2019-1-2
Eberle, W., Bundy, S.: Infusing domain knowledge in AI-based “black box” models for better explainability with application in bankruptcy prediction (2019)
Eoin, M., Mark, T., Kenny, E.M., Keane, M.T.: Twin-Systems to Explain Artificial Neural Networks using Case-Based Reasoning: Comparative Tests of Feature-Weighting Methods in ANN-CBR Twins for XAI (2019)
Falade, A., Azeta, A., Oni, A., Odun-ayo, I.: Systematic literature review of crime prediction and data mining. Rev. Comput. Eng. Stud. 6(3), 56–63 (2019). https://doi.org/10.18280/rces.060302
Assibong, P.A., Wogu, I.A.P., Misra, S., Makplang, D.: The utilization of the biometric technology in the 2013 Manyu division legislative and municipal elections in Cameroon: an appraisal. In: Advances in Electrical and Computer Technologies, pp. 347–360. Springer, Singapore (2020)
Gunning, D.: Explainable Artificial Intelligence (XAI). The Need for Explainable AI (2017)
Hekler, A., Utikal, J.S., Enk, A.H., Hauschild, A., Weichenthal, M., Maron, R.C., Berking, C., Haferkamp, S., Klode, J., Schadendorf, D., Schilling, B., Holland-letz, T., Izar, B., Von Kalle, C., Fro, S., Brinker, T.J.: Superior skin cancer classification by the combination of human and artificial intelligence. Eur. J. Cancer 120, 114–121 (2019). https://doi.org/10.1016/j.ejca.2019.07.019
Hoffman, R.R., Mueller, S.T., Klein, G., Litman, J.: Metrics for Explainable AI: Challenges and Prospects, pp. 1–50 (2018). https://arxiv.org/abs/1812.04608
Ibrahim, A., Gamble, P., Jaroensri, R., Abdelsamea, M.M., Mermel, C.H., Chen, P.C., Rakha, E.A.: Artificial intelligence in digital breast pathology: techniques and applications. The Breast 49, 267–273 (2020). https://doi.org/10.1016/j.breast.2019.12.007
Jia, Z., Zeng, X., Duan, H., Lu, X., Li, H.: A patient-similarity-based model for diagnostic prediction. Int. J. Med. Inform. 135, 104073 (2019). https://doi.org/10.1016/j.ijmedinf.2019.104073
Jian, J.-Y.: Foundations for Empirically Determined Scale of Trust in Automated Systems (1998)
Jiao, P., Alavi, A.H.: Geoscience frontiers artificial intelligence in seismology: advent, performance and future trends. Geoscience Frontiers (2019). https://doi.org/10.1016/j.gsf.2019.10.004
Krigsholm, P., Ståhle, P.: Land use policy pathways for a future cadastral system: a socio-technical approach. Land Use Policy 94, 104504 (2020). https://doi.org/10.1016/j.landusepol.2020.104504
Lamy, J., Sekar, B., Guezennec, G., Bouaud, J., Séroussi, B.: Artificial intelligence in medicine explainable artificial intelligence for breast cancer: a visual case-based reasoning approach. Artif. Intell. Med. 94, 42–53 (2019). https://doi.org/10.1016/j.artmed.2019.01.001
Lim, M., Abdullah, A., Jhanjhi, N.Z.: Performance optimization of criminal network hidden link prediction model with deep reinforcement learning. J. King Saud Univ. Comput. Inf. Sci. (2019). https://doi.org/10.1016/j.jksuci.2019.07.010
Łosiewicz, Z., Nikończuk, P., Pielka, D.: Application of artificial intelligence in the process of supporting the ship owner’s decision in the management of ship machinery crew in the aspect of shipping safety. Procedia Comput. Sci. 159, 2197–2205 (2019). https://doi.org/10.1016/j.procs.2019.09.394
Luijken, K., Wynants, L., Van Smeden, M., Van Calster, B.: Changing predictor measurement procedures affected the performance of prediction models in clinical examples. J. Clin. Epidemiol. 119, 7–18 (2020). https://doi.org/10.1016/j.jclinepi.2019.11.001
Malgieri, G.: Automated decision-making in the EU Member States: the right to explanation and other “suitable safeguards” in the national legislations. Comput. Law Secur. Rev. 35(5), 105327 (2019). https://doi.org/10.1016/j.clsr.2019.05.002
Mehta, R., Rice, S., Deaton, J., Winter, S.R.: Transportation research interdisciplinary perspectives creating a prediction model of passenger preference between low cost and legacy airlines ☆. Transp. Res. Interdisc. Perspect. 3, 100075 (2019). https://doi.org/10.1016/j.trip.2019.100075
Wogu, I.A.P., Misra, S., Roland-Otaru, C.O., Udoh, O.D., Awogu-Maduagwu, E., Damasevicius, R.: Human rights’ issues and media/communication theories in the wake of artificial intelligence technologies: the fate of electorates in twenty-first-century American politics. In: Advances in Electrical and Computer Technologies, pp. 319–333. Springer, Singapore (2020)
Siems-anderson, A.R., Walker, C.L., Wiener, G., Iii, W.P.M., Haupt, S.E.: Transportation research interdisciplinary perspectives an adaptive big data weather system for surface transportation ☆. Transp. Res. Interdisc. Perspect. 3, 100071 (2019). https://doi.org/10.1016/j.trip.2019.100071
Silva, J., Palma, H.H., Núñez, W.N., Ruiz-lazaro, A.: Natural Language Explanation Model for Decision Trees (2020). https://doi.org/10.1088/1742-6596/1432/1/012074
Stoel, B.C.: Artificial intelligence in detecting early RA, vol. 49, pp. 25–28 (2019). https://doi.org/10.1016/j.semarthrit.2019.09.020
Osamor, V.C., Azeta, A.A., Ajulo, O.O.: Tuberculosis–diagnostic expert system: an architecture for translating patients information from the web for use in tuberculosis diagnosis. SAGE J. Health Inform. J. 19(3) (2013)
Yang, J., Sophia, Q., Corscadden, K., Niu, H., Lin, J., Astatkie, T.: Advanced models for the prediction of product yield in hydrothermal liquefaction via a mixture design of biomass model components coupled with process variables. Appl. Energy 233–234, 906–915 (2019). https://doi.org/10.1016/j.apenergy.2018.10.035
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Udenwagu, N.E., Azeta, A.A., Misra, S., Nwaocha, V.O., Enosegbe, D.L., Sharma, M.M. (2021). ExplainEx: An Explainable Artificial Intelligence Framework for Interpreting Predictive Models. In: Abraham, A., Hanne, T., Castillo, O., Gandhi, N., Nogueira Rios, T., Hong, TP. (eds) Hybrid Intelligent Systems. HIS 2020. Advances in Intelligent Systems and Computing, vol 1375. Springer, Cham. https://doi.org/10.1007/978-3-030-73050-5_51
Download citation
DOI: https://doi.org/10.1007/978-3-030-73050-5_51
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-73049-9
Online ISBN: 978-3-030-73050-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)