Explainable Artificial Intelligence (XAI) for Internet of Things: A Survey
Kok, Ibrahim, Okay, Feyza Yildirim, Muyanli, Ozgecan, Ozdemir, Suat
–arXiv.org Artificial Intelligence
Black-box nature of Artificial Intelligence (AI) models do not allow users to comprehend and sometimes trust the output created by such model. In AI applications, where not only the results but also the decision paths to the results are critical, such black-box AI models are not sufficient. Explainable Artificial Intelligence (XAI) addresses this problem and defines a set of AI models that are interpretable by the users. Recently, several number of XAI models have been to address the issues surrounding by lack of interpretability and explainability of black-box models in various application areas such as healthcare, military, energy, financial and industrial domains. Although the concept of XAI has gained great deal of attention recently, its integration into the IoT domain has not yet been fully defined. In this paper, we provide an in-depth and systematic review of recent studies using XAI models in the scope of IoT domain. We categorize the studies according to their methodology and applications areas. In addition, we aim to focus on the challenging problems and open issues and give future directions to guide the developers and researchers for prospective future investigations.
arXiv.org Artificial Intelligence
Jun-7-2022
- Country:
- North America > United States
- California (0.28)
- Asia > Middle East
- Republic of Türkiye (0.28)
- North America > United States
- Genre:
- Overview (1.00)
- Research Report > New Finding (0.46)
- Industry:
- Banking & Finance (1.00)
- Transportation > Air (0.75)
- Government > Military (0.67)
- Information Technology
- Security & Privacy (1.00)
- Smart Houses & Appliances (0.83)
- Health & Medicine > Therapeutic Area
- Infections and Infectious Diseases (0.46)
- Immunology (0.46)
- Energy
- Power Industry (1.00)
- Oil & Gas (0.67)
- Technology:
- Information Technology
- Data Science > Data Mining (1.00)
- Artificial Intelligence
- Natural Language > Explanation & Argumentation (1.00)
- Issues > Social & Ethical Issues (1.00)
- Representation & Reasoning
- Rule-Based Reasoning (1.00)
- Expert Systems (1.00)
- Agents (1.00)
- Machine Learning > Neural Networks
- Deep Learning (1.00)
- Information Technology