-
Chapter and Conference Paper
CNN-Based Explanation Ensembling for Dataset, Representation and Explanations Evaluation
Explainable Artificial Intelligence has gained significant attention due to the widespread use of complex deep learning models in high-stake domains such as medicine, finance, and autonomous cars. However, dif...
-
Chapter and Conference Paper
A Comparative Analysis of SHAP, LIME, ANCHORS, and DICE for Interpreting a Dense Neural Network in Credit Card Fraud Detection
Financial institutions heavily rely on advanced Machine Learning algorithms to screen transactions. However, they face increasing pressure from regulators and the public to ensure AI accountability and transpa...
-
Chapter and Conference Paper
SRFAMap: A Method for Map** Integrated Gradients of a CNN Trained with Statistical Radiomic Features to Medical Image Saliency Maps
Many explainable AI methods for generating medical image saliency maps exist, but most are devoted to working on trained neural network-based models. At the same time, many medical image classification neural ...
-
Chapter and Conference Paper
Correction to: Explainable Artificial Intelligence
-
Chapter and Conference Paper
Selecting Textural Characteristics of Chest X-Rays for Pneumonia Lesions Classification with the Integrated Gradients XAI Attribution Method
Global texture characteristics are powerful tools for solving medical image classification tasks. There are many such characteristics like Grey-Level Co-occurrence Matrices, Grey-Level Run-Length Matrices, Gre...
-
Chapter and Conference Paper
Investigating the Effect of Pre-processing Methods on Model Decision-Making in EEG-Based Person Identification
Electroencephalography (EEG) data has emerged as a promising modality for biometric applications, offering unique and secure personal identification and authentication methods. This research comprehensively co...
-
Chapter and Conference Paper
An Exploration of the Latent Space of a Convolutional Variational Autoencoder for the Generation of Musical Instrument Tones
Variational Autoencoders (VAEs) constitute one of the most significant deep generative models for the creation of synthetic samples. In the field of audio synthesis, VAEs have been widely used for the generati...
-
Chapter and Conference Paper
Development of a Human-Centred Psychometric Test for the Evaluation of Explanations Produced by XAI Methods
One goal of Explainable Artificial Intelligence (XAI) is to interpret and explain the inferential process of data-driven machine-learned models to make it comprehensible for humans. To reach it, it is necessar...
-
Chapter and Conference Paper
An Ontological Approach for Recommending a Feature Selection Algorithm
Feature selection plays an important role in machine learning or data mining problems. Removing irrelevant features increases model accuracy and reduces the computational cost. However, selecting important fea...
-
Chapter and Conference Paper
A Survey on the Application of Virtual Reality in Event-Related Potential Research
Virtual reality (VR) is getting traction in many contexts, allowing users to have a real-life experience in a virtual world. However, its application in the field of Neuroscience, and above all probing newer a...
-
Chapter and Conference Paper
Data Quality Assessment of Comma Separated Values Using Linked Data Approach
With an increasing amount of structured data on the web, the need to understand and convert it into linked data is growing. One of the most frequent data formats is Comma Separated Value (CSV). However, it is ...
-
Chapter and Conference Paper
Linked Data Quality Assessment: A Survey
Data is of high quality if it is fit for its intended use in operations, decision-making, and planning. There is a colossal amount of linked data available on the web. However, it is difficult to understand ho...
-
Chapter and Conference Paper
A Novel Human-Centred Evaluation Approach and an Argument-Based Method for Explainable Artificial Intelligence
One of the aim of Explainable Artificial Intelligence (XAI) is to equip data-driven, machine-learned models with a high degree of explainability for humans. Understanding and explaining the inferences of a mod...
-
Chapter and Conference Paper
A Novel Parabolic Model of Instructional Efficiency Grounded on Ideal Mental Workload and Performance
Instructional efficiency within education is a measurable concept and models have been proposed to assess it. The main assumption behind these models is that efficiency is the capacity to achieve established g...
-
Chapter and Conference Paper
Expressing Trust with Temporal Frequency of User Interaction in Online Communities
Reputation systems concern soft security dynamics in diverse areas. Trust dynamics in a reputation system should be stable and adaptable at the same time to serve the purpose. Many reputation mechanisms have b...
-
Chapter and Conference Paper
Explainable Artificial Intelligence: Concepts, Applications, Research Challenges and Visions
The development of theory, frameworks and tools for Explainable AI (XAI) is a very active area of research these days, and articulating any kind of coherence on a vision and challenges is itself a challenge. A...
-
Chapter and Conference Paper
Task Demand Transition Peak Point Effects on Mental Workload Measures Divergence
The capacity to assess and manage mental workload is becoming more and more relevant in the current work environments as it helps to prevent work related accidents and achieve better efficiency and productivit...
-
Chapter and Conference Paper
Empowering Qualitative Research Methods in Education with Artificial Intelligence
Artificial Intelligence is one of the fastest growing disciplines, disrupting many sectors. Originally mainly for computer scientists and engineers, it has been expanding its horizons and empowering many other...
-
Chapter and Conference Paper
Direct and Constructivist Instructional Design: A Comparison of Efficiency Using Mental Workload and Task Performance
Cognitive Load Theory is based upon the assumption that working memory can process only explicit and direct instructions. Therefore, it is believed that inquiries techniques, not employing explicit instruction...
-
Chapter and Conference Paper
The Evolution of Cognitive Load Theory and the Measurement of Its Intrinsic, Extraneous and Germane Loads: A Review
Cognitive Load Theory has been conceived for supporting instructional design through the use of the construct of cognitive load. This is believed to be built upon three types of load: intrinsic, extraneous and...
