# TwinExplainer: Explaining Predictions of an Automotive Digital Twin

arXiv: https://arxiv.org/abs/2302.00152 · HTML: https://mlsanity.com/paper/2302.00152/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 41 references that are in the map.
- First posted on arXiv 1 Feb 2023.

## Builds on (most cited first, 14 of 14)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://mlsanity.com/paper/1803.01271/) (2018)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Distribution-Free Predictive Inference For Regression](https://mlsanity.com/paper/1604.04173/) (2016)
- [Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models](https://mlsanity.com/paper/1708.08296/) (2017)
- [Explainable Intrusion Detection Systems (X-IDS): A Survey of Current Methods, Challenges, and Opportunities](https://mlsanity.com/paper/2207.06236/) (2022)
- [A Survey of Predictive Maintenance: Systems, Purposes and Approaches](https://mlsanity.com/paper/1912.07383/) (2019)
- [Global Model Interpretation via Recursive Partitioning](https://mlsanity.com/paper/1802.04253/) (2018)
- [Creating an Explainable Intrusion Detection System Using Self Organizing Maps](https://mlsanity.com/paper/2207.07465/) (2022)
- [A Temporal Anomaly Detection System for Vehicles utilizing Functional Working Groups and Sensor Channels](https://mlsanity.com/paper/2209.06828/) (2022)
- [Explainable Human-in-the-loop Dynamic Data-Driven Digital Twins](https://mlsanity.com/paper/2207.09106/) (2022)
- [A White-Box Adversarial Attack Against a Digital Twin](https://mlsanity.com/paper/2210.14018/) (2022)
- [Digital Twin approach to Clinical DSS with Explainable AI](https://mlsanity.com/paper/1910.13520/) (2019)

## Built on by (most cited first, 6 of 6)

- [Security Considerations in AI-Robotics: A Survey of Current Methods, Challenges, and Opportunities](https://mlsanity.com/paper/2310.08565/) (2023)
- [Impacts and Risk of Generative AI Technology on Cyber Defense](https://mlsanity.com/paper/2306.13033/) (2023)
- [Large Language Models for Explainable Decisions in Dynamic Digital Twins](https://mlsanity.com/paper/2405.14411/) (2024)
- [A Survey on Privacy Attacks Against Digital Twin Systems in AI-Robotics](https://mlsanity.com/paper/2406.18812/) (2024)
- [Explainable Interface for Human-Autonomy Teaming: A Survey](https://mlsanity.com/paper/2405.02583/) (2024)
- [Explainable Anomaly Detection: Counterfactual driven What-If Analysis](https://mlsanity.com/paper/2408.11935/) (2024)

## Abstract (arXiv)

Vehicles are complex Cyber Physical Systems (CPS) that operate in a variety of environments, and the likelihood of failure of one or more subsystems, such as the engine, transmission, brakes, and fuel, can result in unscheduled downtime and incur high maintenance or repair costs. In order to prevent these issues, it is crucial to continuously monitor the health of various subsystems and identify abnormal sensor channel behavior. Data-driven Digital Twin (DT) systems are capable of such a task. Current DT technologies utilize various Deep Learning (DL) techniques that are constrained by the lack of justification or explanation for their predictions. This inability of these opaque systems can influence decision-making and raises user trust concerns. This paper presents a solution to this issue, where the TwinExplainer system, with its three-layered architectural pipeline, explains the predictions of an automotive DT. Such a system can assist automotive stakeholders in understanding the global scale of the sensor channels and how they contribute towards generic DT predictions. TwinExplainer can also visualize explanations for both normal and abnormal local predictions computed by the DT.