Search
Search Results
-
Explainable Machine Learning and Visual Knowledge Discovery
The importance of visual methods in machine learning (ML) as tools to increase the interpretability and validity of models, is growing. The visual... -
Explainable AI in drug discovery: self-interpretable graph neural network for molecular property prediction using concept whitening
Molecular property prediction is a fundamental task in the field of drug discovery. Several works use graph neural networks to leverage molecular...
-
Concept-guided multi-level attention network for image emotion recognition
Image emotion recognition aims to predict people’s emotional response toward visual stimuli. Recently, emotional region discovery has become hot...
-
Navigating the landscape of concept-supported XAI: Challenges, innovations, and future directions
This comprehensive review of concept-supported interpretation methods in Explainable Artificial Intelligence (XAI) navigates the multifaceted...
-
MyBioethics: How Ed-Tech Enables Discovery-Driven Empirical Bioethics Research
Digital tools have granted new opportunities to engage people with bioethical discussion and rehearsed decision-making. The ongoing development of...
-
ServiceNet: resource-efficient architecture for topology discovery in large-scale multi-tenant clouds
Modern computing infrastructures are evolving due to virtualisation, especially with the advent of 5G and future technologies. While this transition...
-
Optimizing inquiry-based science education: verifying the learning effectiveness of augmented reality and concept map** in elementary school
As information technologies are introduced into science education, educators face their impact on teaching and learning. On one hand, educators must...
-
Scale-preserving automatic concept extraction (SPACE)
Convolutional Neural Networks (CNN) have become a common choice for industrial quality control, as well as other critical applications in the...
-
ConceptGlassbox: Guided Concept-Based Explanation for Deep Neural Networks
Various industries and fields have utilized machine learning models, particularly those that demand a significant degree of accountability and...
-
Visual link retrieval and knowledge discovery in painting datasets
Visual arts are of inestimable importance for the cultural, historic and economic growth of our society. One of the building blocks of most analysis...
-
Exploring the Relationship Between Visual Information and Language Semantic Concept in the Human Brain
Functional magnetic resonance imaging (fMRI) can be used to map patterns of brain activity and understand how information is expressed in the human... -
Contextual topic discovery using unsupervised keyphrase extraction and hierarchical semantic graph model
Recent technological advancements have led to a significant increase in digital documents. A document’s key information is generally represented by...
-
On Shapley value interpretability in concept-based learning with formal concept analysis
We propose the usage of two power indices from cooperative game theory and public choice theory for ranking attributes of closed sets, namely intents...
-
Medical Concept Normalization
Medical concept normalization, which maps clinical entities to concepts in standard terminology, is essential for supporting downstream computational... -
Hesitant fuzzy three-way concept lattice and its attribute reduction
Formal concept analysis is a widely studied mathematical tool for performing data analysis and processing. Three-way decision is a model of decision...
-
Designing Refreshable Tactile Graphics for Accessing Visual Imagery for the Blind and People with Visual Impairments
The accessibility of digital content is an important aspect in the lives of individuals who are blind, as the visualization of graphs and symbolic... -
Description, discovery, and recommendation of Cloud services: a survey
Cloud computing has become the most popular concept for on-demand delivery of Cloud computing services. Due to its high flexibility, many Cloud...
-
Analyzing Healthcare Processes with Incremental Process Discovery: Practical Insights from a Real-World Application
AbstractMost process mining techniques are primarily automated, meaning that process analysts input information and receive output. As a result,...
-
Product discovery utilizing the semantic data model
Most of the existing techniques to product discovery and recommendations rely on syntactic approaches, thus ignoring valuable and specific semantic...
-
Enhancing knowledge discovery and management through intelligent computing methods: a decisive investigation
Knowledge Discovery and Management (KDM) encompasses a comprehensive process and approach involving the creation, discovery, capture, organization,...