Explainable artificial intelligence (XAI) is a collection of techniques and systems that enable human users to grasp and trust the findings produced by artificial intelligence (AI) algorithms. AI has entered various fields, including education, construction, health, manufacturing, law enforcement, and finance. This extends to AI applications used in healthcare, autonomous vehicles, and even drones. XAI provides methods for making decision-making more transparent and efficient. Alternatively, XAI could eliminate the so-called black boxes and thoroughly explain the decision. This book will discuss every aspect of an explainable AI system, covering what it is, what its fundamental premise is, why it is needed, and how it will be developed. This book investigates and seeks to grasp the methods and models that are used to make decisions. The book covers concepts such as black-box models, model transparency, interpretable machine learning and explainable models, various methods for XAI including evaluation methods and metrics related to this, ethical, legal and social issues, and applications and real-life examples in different sectors.

Main Highlights of the Book:

• Book Series: Intelligent Systems Reference Library, Springer
• The books of this series are submitted to ISI Web of Science, SCOPUS, DBLP and Springerlink for indexing
• No publication fees

Submission Guidelines

All papers must be original and not simultaneously submitted to another journal or conference. 

• Please visit  Book Manuscript Guidelines for chapter format (Word & Latex)
• Length of chapter should be between 15 to 40 pages.
• Include figures & tables in the chapter only if necessary. Please do not include them just to complement the text.
• Important Dates:
  • Chapter Submission Deadline: 28th February 2022
  • Acceptance Notification          : 31st March 2022
  • Camera Ready Submission     : 30th April 2022

List of Topics

The topics of interest for this book include, but not limited to:  

• Fundamental concepts of Explainable AI
• Black Box Models
• Significance of Transparency in Machine Learning Models
• XAI Techniques/Frameworks/Tools
• Evaluation Methods and Metrics for XAI
• Ethical, Legal and Social Issues of XAI
• Application of Explainable AI in Real-life Sectors such as Healthcare, Transportation, Finance, Military, Security, Legal Judgement etc.
• Human-Computer Interaction (HCI) and XAI
• Current Challenges and Future Opportunities in XAI

Committees

Program Committee

Editors:

Dr. Mayuri Mehta, Sarvajanik College of Engineering & Technology, Surat, India.

Dr. Vasile Palade, Coventry University, UK

Dr. Indranath Chatterjee, Tongmyong University, South Korea.

Publication

Explainable AI: Foundations, Methodologies and Applications book will be published by Springer Nature

Contact

All questions about submissions should be emailed to profmayurimehta@gmail.com, vpalade453@gmail.com and indranath.cs.du@gmail.com