Focal Interest
Focal Interest
AI Summary of Peer-Reviewed Research

This page presents an AI-generated summary of a published research paper. The original authors did not write or review this article. [See full disclosure ↓]

Publishing process signals: STRONG — reflects the venue and review process. — venue and review process.

Explainable quantum AI predicted vehicular energy use in smart cities

A woman stands beside a dark-colored electric vehicle parked next to a black wall-mounted EV charging station on a brick building in an urban residential area.
Research area:Artificial intelligenceElectrical and Electronic EngineeringElectric Vehicles and Infrastructure

What the study found

The study found that an Explainable Quantum AI (XQAI) model can predict vehicular energy consumption in smart cities and provide explanations for those predictions. In the abstract, the authors report that the Hybrid Classical–Quantum Regressor achieved an R 2 score of 0.8439 and that LIME produced a confidence score of 0.95.

Why the authors say this matters

The authors say this matters because autonomous electric vehicles create challenges for energy management systems in smart cities, especially for real-time decisions, complex AI, and heavy computing demands. They conclude that a model combining quantum machine learning (QML) with explainable AI (XAI) may support scalable, understandable, and regulated vehicular energy forecasting.

What the researchers tested

The researchers proposed an XQAI model that combines quantum machine learning with explainable AI methods. They used data from real cities with a wide range of features to predict energy consumption across different trip types, and they used LIME and SHAP to help explain the model's decisions.

What worked and what didn't

According to the simulation results reported in the abstract, the Hybrid Classical–Quantum Regressor performed well, with an R 2 score of 0.8439. The abstract also says LIME showed a confidence score of 0.95, which the authors present as evidence of credibility, interpretability, and reliability. The abstract does not describe any specific failed approach or negative result.

What to keep in mind

The available summary reports simulation results, not real-world deployment outcomes. The abstract does not provide detailed limitations beyond noting the challenges of complexity, scalability, and clarity in AI-based energy management.

Key points

  • The study proposes an Explainable Quantum AI model for vehicular energy forecasting.
  • The Hybrid Classical–Quantum Regressor is reported to have an R 2 score of 0.8439.
  • LIME is reported to have produced a confidence score of 0.95.
  • The model was tested on data from real cities across different trip types.
  • The abstract presents the approach as supporting scalable, understandable, and regulated forecasting.

Disclosure

Research title:
Explainable quantum AI predicted vehicular energy use in smart cities
Authors:
Muhammad Saleem, Muhammad Sajid Farooq, Khan Muhammad Adnan, Muhammad Nadeem Ali, Adeel Munawar, Byung-seo Kim
Institutions:
National College of Business Administration and Economics, University of Engineering and Technology Lahore, Gachon University, Hongik University, Karlsruhe Institute of Technology, Thammasat University
Publication date:
2026-04-08
DOI:
10.1016/j.eij.2026.100966
OpenAlex record:
View
AI provenance: This post was generated by OpenAI. The original authors did not write or review this post.

More posts