Using Case-Based Reasoning for Capturing Expert Knowledge on Explanation Methods

Darias, Jesus M.; Caro-Martínez, Marta; Dí­az-Agudo, Belén; Recio-Garcí­a, Juan A.

doi:10.1007/978-3-031-14923-8_1

Cited by 8 publications

(4 citation statements)

References 19 publications

(19 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Developing user profiles and providing tailored explanations to each type of user will facilitate understandability [6]. To customize explanations for each user, Darias et al [75] developed a method using Case-Based Reasoning to select the best explanation method for each situation based on the AI model, domain, and user preferences. Customized explana-tions enable users to learn more from the explanations and gain a better understanding of the CPS.…”

Section: Customizable Output For Different Usersmentioning

confidence: 99%

Explainable AI for Cyber-Physical Systems: Issues and Challenges

Hoenig,

Roy,

Acquaah

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Artificial intelligence and cyber-physical systems (CPS) are two of the key technologies of the future that are enabling major global shifts. However, most of the current implementations of AI in CPS are not explainable, which creates serious problems in ethical, legal, regulatory, and other domains. Therefore, it is necessary for explainable artificial intelligence (XAI) to be integrated with cyber-physical systems to meet the vital needs for control, fairness, accountability, safety, cyber-resilience, and cybersecurity. The goal of this review is to demonstrate the need, benefits, challenges, and implementation of XAI for CPS. We review the existing literature about XAI and CPS, discuss the current state of the art, examine applications in different domains, and make recommendations for future research directions. To the best of our knowledge, this is the first peer-reviewed academic article to provide a comprehensive review of general XAI for CPS. We also contribute new research ideas including development of multisensory explanations and outputs for these systems, application of XAI to CPS to decrease occupational burnout and increase employee engagement, and enumeration of the multidisciplinary goals and benefits of XAI as applied to cyber-physical systems.

show abstract

Section: Customizable Output For Different Usersmentioning

confidence: 99%

Explainable AI for Cyber-Physical Systems: Issues and Challenges

Hoenig,

Roy,

Acquaah

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…These challenges can be overcome by using simple linear models that can provide accuracy with greater transparency and using visualization tools that can help users understand the model and the basis of the AI decisions. With the help of XAI methods such as Local interpretable Model-agnostic Explanations (LIME) that provides human understandable terminology, clinicians can understand how the decision-making process works in the model [7].…”

Section: Challenges and Considerationsmentioning

confidence: 99%

AI and Machine Learning in Healthcare - Applications, Challenges and Ethics

Nadakuditi,

Kumar,

Kumar

2024

IJHS

View full text Add to dashboard Cite

Purpose: This research aims to discuss how AI and machine learning can be used in healthcare, challenges associated with implementation and the ethics around the widespread adoption of AI in the health care ecosystem while understanding the regulations around the technology implementation. Methodology: By conducting qualitative analysis on various applications of AI and machine learning in health care and its impacts on patient care, the analysis summarizes the challenges and ethics associated with the implementation. Findings: Results indicate that in the last few years, the data collected in the healthcare industry has increased manifold. Some studies suggest that structured data is growing by 40% each year, unstructured data is growing by over 80% and global data produced is forty zettabytes (ZB) as of 2020. With the increased regulatory and compliance requirements, effective data governance is a mandate for industries like healthcare where there is greater focus on data privacy, data security and personal information protection. This rapid explosion of data and the need to ensure the data is available at the right time has led to increased adoption of artificial intelligence (AI) and machine learning solutions across healthcare organizations to gain meaningful insights from the data collected. These technologies are proving to transform many aspects of healthcare ecosystem from patient care to administrative functions. Unique contribution to theory, policy, and practice: Currently AI and machine learning are aiding providers and patients by improving the health outcomes, but further research is necessary to validate to ensure these technologies are complying the regulatory guidelines without comprising on the patient care and the ethics involved when it comes to patient security and privacy.

show abstract

“…(3) Interpretation-oriented retrieval: Explaining CBR and justifying recommendations or solutions is often important, especially in the field of medical decision-making, in which explaining the cause and correctness of the search results can provide compelling support (McSherry 2005;Doyle et al 2004;Darias et al 2022).…”

Section: Case Retrievalmentioning

confidence: 99%

A review of the development and future challenges of case-based reasoning

Yan

Cheng

2023

Preprint

View full text Add to dashboard Cite

Case-based reasoning (CBR), which is based on the cognitive assumption that similar problems have similar solutions, is an important problem-solving and learning method in the field of artificial intelligence. In this article, the development of CBR is mainly reviewed, and the major challenges of CBR are summarized. The paper is organized into four parts. First, the basic framework and concepts of CBR are introduced. Then, the developed technology and innovative work that were formed in solving problems by CBR are summarized. Moreover, the application fields of CBR are sorted. Finally, according to the idea of deep learning and interpretable artificial intelligence, the main challenges for the future development of CBR are proposed.

show abstract

Using Case-Based Reasoning for Capturing Expert Knowledge on Explanation Methods

Cited by 8 publications

References 19 publications

Explainable AI for Cyber-Physical Systems: Issues and Challenges

Explainable AI for Cyber-Physical Systems: Issues and Challenges

AI and Machine Learning in Healthcare - Applications, Challenges and Ethics

A review of the development and future challenges of case-based reasoning

Contact Info

Product

Resources

About