Depicting Decision-Making: A Type-2 Fuzzy Logic Based Explainable Artificial Intelligence System for Goal-Driven Simulation in the Workforce Allocation Domain

The recent years have witnessed a growing anticipation for the positive transformation of industries which adopt Artificial Intelligence (AI) for the core areas of their business activities. However, the effectiveness and reliability of such AI systems must comprise the ability to explain their data acquisition, the underlying algorithms operations and the final decisions to stakeholders, including regulators, risk managers, supervisors and end-users among others. There are plenty of areas where Explainable AI (XAI) holds the promise to be a major disruptor. Particularly, in Telecommunication Service Providers (TSPs) which is a core business activity relating to the workforce allocation domain, which, involves costly and time-consuming scheduling processes. This paper focuses on the construction of an XAI framework to assist workforce allocation based on a big bang- big crunch interval type-2 fuzzy logic system (BB-BC IT2FLS) for modelling and scaling goal-driven simulation (GDS) problems, specifically within the telecommunications industry. The obtained results reported the proposed XAI system produces similar results to opaque box models like Neural Networks (NNs) and LSTM Recurrent NNs while being able to explain the decision and operation of the employed system.

[1]  Filip Karlo Dosilovic,et al.  Explainable artificial intelligence: A survey , 2018, 2018 41st International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO).

[2]  Shimei Pan,et al.  Interpreting Social Media-Based Substance Use Prediction Models with Knowledge Distillation , 2018, 2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI).

[3]  Hani Hagras,et al.  Toward Human-Understandable, Explainable AI , 2018, Computer.

[4]  Carlos Guestrin,et al.  "Why Should I Trust You?": Explaining the Predictions of Any Classifier , 2016, ArXiv.

[5]  Song-Chun Zhu,et al.  Learning AND-OR Templates for Object Recognition and Detection , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Hani Hagras,et al.  A multi-objective genetic type-2 fuzzy logic based system for mobile field workforce area optimization , 2016, Inf. Sci..

[7]  Huamin Qu,et al.  RuleMatrix: Visualizing and Understanding Classifiers with Rules , 2018, IEEE Transactions on Visualization and Computer Graphics.

[8]  James C. Bezdek,et al.  On cluster validity for the fuzzy c-means model , 1995, IEEE Trans. Fuzzy Syst..

[9]  Trevor Darrell,et al.  Generating Visual Explanations , 2016, ECCV.

[10]  Stéphane Ayache,et al.  Design of an explainable machine learning challenge for video interviews , 2017, 2017 International Joint Conference on Neural Networks (IJCNN).

[11]  Hani Hagras,et al.  Enabling Field Force Operational Sustainability: A Big Bang-Big Crunch Type-2 Fuzzy Logic System for Goal-Driven Simulation , 2018, 2018 IEEE Symposium Series on Computational Intelligence (SSCI).

[12]  Hani Hagras,et al.  A hierarchical type-2 fuzzy logic control architecture for autonomous mobile robots , 2004, IEEE Transactions on Fuzzy Systems.

[13]  Scott Lundberg,et al.  A Unified Approach to Interpreting Model Predictions , 2017, NIPS.

[14]  Sergey Levine,et al.  Goal-driven dynamics learning via Bayesian optimization , 2017, 2017 IEEE 56th Annual Conference on Decision and Control (CDC).

[15]  Joshua B. Tenenbaum,et al.  Human-level concept learning through probabilistic program induction , 2015, Science.

[16]  Hani Hagras,et al.  A Fuzzy Logic-Based System for Indoor Localization Using WiFi in Ambient Intelligent Environments , 2013, IEEE Transactions on Fuzzy Systems.

[17]  Cynthia Rudin,et al.  Interpretable classifiers using rules and Bayesian analysis: Building a better stroke prediction model , 2015, ArXiv.

[18]  Seth Flaxman,et al.  European Union Regulations on Algorithmic Decision-Making and a "Right to Explanation" , 2016, AI Mag..

[19]  Zachary Chase Lipton.  The mythos of model interpretability , 2016, ACM Queue.

[20]  Céline Hudelot,et al.  Learning Fuzzy Relations and Properties for Explainable Artificial Intelligence , 2018, 2018 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE).

[21]  Scott M. Lundberg,et al.  Consistent Individualized Feature Attribution for Tree Ensembles , 2018, ArXiv.

[22]  Lalana Kagal,et al.  J un 2 01 8 Explaining Explanations : An Approach to Evaluating Interpretability of Machine Learning , 2018 .

[23]  Luis Magdalena,et al.  Designing interpretable Hierarchical Fuzzy Systems , 2018, 2018 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE).

[24]  P Surekha,et al.  A methodology to schedule and optimize job shop scheduling using computational intelligence paradigms , 2010, 2010 International Conference on Intelligent Control and Information Processing.

[25]  Siobhán Clarke,et al.  Goal-Driven Service Composition in Mobile and Pervasive Computing , 2018, IEEE Transactions on Services Computing.

[26]  Hani Hagras,et al.  Online Learning and Adaptation of Autonomous Mobile Robots for Sustainable Agriculture , 2002, Auton. Robots.

[27]  Daniel A. Ashlock,et al.  Evolutionary computation for modeling and optimization , 2005 .

[28]  Ibrahim Eksin,et al.  A new optimization method: Big Bang-Big Crunch , 2006, Adv. Eng. Softw..

[29]  Hani Hagras,et al.  A type-2 fuzzy logic system for engineers estimation in the workforce allocation domain , 2017, 2017 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE).

[30]  Theresa-Marie Rhyne,et al.  Visual Analytics for Explainable Deep Learning , 2018, IEEE Computer Graphics and Applications.