Search
Search Results
-
Generalized attention-based deep multi-instance learning
Attention-based deep multi-instance learning (MIL) is an effective and interpretable model. Its interpretability is attributed to the learnability of...
-
Modeling of anticipation using instance-based learning: application to automation surprise in aviation using passive BCI and eye-tracking data
Human-centered artificial intelligence (HCAI) needs to be able to adapt to anticipated user behavior. We argue that the anticipation capabilities...
-
Improving search and rescue planning and resource allocation through case-based and concept-based retrieval
The need for effective and efficient search and rescue operations is more important than ever as the frequency and severity of disasters increase due...
-
Adaptive Cognitive Agents: Updating Action Descriptions and Plans
In this paper we present an extension of Belief-Desire-Intention agents which can adapt their performance in response to changes in their... -
Map** natural language procedures descriptions to linear temporal logic templates: an application in the surgical robotic domain
Natural language annotations and manuals can provide useful procedural information and relations for the highly specialized scenario of autonomous...
-
On using CPSV-AP to publish public service descriptions as linked open data
Public authorities worldwide provide a large number of Public Services (PS) to citizens, businesses and other authorities. In this context, they...
-
Medical Concept Normalization
Medical concept normalization, which maps clinical entities to concepts in standard terminology, is essential for supporting downstream computational... -
Are These Descriptions Referring to the Same Entity or Just to Similar Ones?
The Knowledge Graph matching task is to identify nodes in the two graphs that refer to the same concept. In this paper, we focus on the analysis of... -
Lcp-mixer: a lightweight model based on concept-level perception for NLP
Transformer-based models excel in natural language processing tasks but demand extensive computational resources and memory. To address this...
-
Extending Boolean Variability Relationship Extraction to Multi-valued Software Descriptions
Extracting variability information from software product descriptions is crucial when reverse engineering a software product line, e.g., for... -
A multi-model framework for semantically enhancing detection of quality-related bug report descriptions
Maintaining and delivering a high-quality software system is a delicate process. One way to ensure that a software system achieves the desired...
-
Pattern Recognition and Concept Analysis
AbstractA number of meaningful problems commonly associated with pattern recognition is considered. A link between these problems and the branch of...
-
AdaDeepStream: streaming adaptation to concept evolution in deep neural networks
Typically, Deep Neural Networks (DNNs) are not responsive to changing data. Novel classes will be incorrectly labelled as a class on which the...
-
LifeSeeker: an interactive concept-based retrieval system for lifelog data
Lifelogging was introduced as the process of passively capturing personal daily events via wearable devices. It ultimately creates a visual diary...
-
Verification of Quantitative Temporal Compliance Requirements in Process Descriptions Over Event Logs
Process compliance verification ensures that processes adhere to a set of given regulatory requirements which are typically assumed to be available... -
Neural Multi-hop Logical Query Answering with Concept-Level Answers
Neural multi-hop logical query answering (LQA) is a fundamental task to explore relational data such as knowledge graphs, which aims at answering... -
Unleashing textual descriptions of business processes
Textual descriptions of processes are ubiquitous in organizations, so that documentation of the important processes can be accessible to anyone...
-
Online concept evolution detection based on active learning
Concept evolution detection is an important and difficult problem in streaming data mining. When the labeled samples in streaming data insufficient...
-
Same film, different audio descriptions: describing foreign films from a functional perspective
The article discusses a functional approach to audio describing foreign films. First, a functional model of audio description (AD) is outlined, aimed...
-
A concept map-based community of inquiry framework for virtual learning contexts to enhance students’ earth science learning achievement and reflection tendency
With the growing popularity of Virtual Reality (VR), the integration of the Community of Inquiry (CoI) framework provides insights into its role in...