A5066340205- Semantic Web and Ontologies
- Advanced Database Systems and Queries
- AI-based Problem Solving and Planning
- Data Mining Algorithms and Applications
- Logic, Reasoning, and Knowledge
- Text and Document Classification Technologies
- Topic Modeling
- Service-Oriented Architecture and Web Services
- Reinforcement Learning in Robotics
- Chronic Lymphocytic Leukemia Research
- Natural Language Processing Techniques
- Data Management and Algorithms
- Advanced Text Analysis Techniques
- Machine Learning and Data Classification
- Constraint Satisfaction and Optimization
- Lymphoma Diagnosis and Treatment
- Machine Learning in Bioinformatics
- Biomedical Text Mining and Ontologies
- Immunodeficiency and Autoimmune Disorders
- Image Retrieval and Classification Techniques
- Time Series Analysis and Forecasting
- Data Stream Mining Techniques
- Advanced Image and Video Retrieval Techniques
- Spam and Phishing Detection
- Logic, programming, and type systems
Aristotle University of Thessaloniki
2016-2025
Marymount University
2022
International Hellenic University
2011-2017
Atypon (United States)
2016
Wageningen University & Research
2015
University Ecclesiastical Academy of Thessaloniki
2015
Purdue University West Lafayette
1997
A simple yet effective multilabel learning method, called label powerset (LP), considers each distinct combination of labels that exist in the training set as a different class value single-label classification task. The computational efficiency and predictive performance LP is challenged by application domains with large number examples. In these cases, classes may become very at same time many are associated few To deal problems, this paper proposes breaking initial into small random...
This paper deals with content-based large-scale image retrieval using the state-of-the-art framework of VLAD and Product Quantization proposed by Jegou as a starting point. Demonstrating an excellent accuracy-efficiency trade-off, this has attracted increased attention from community numerous extensions have been proposed. In work, we make in-depth analysis that aims at increasing our understanding its different processing steps boosting overall performance. Our involves evaluation (both...
This work studies the task of automatic emotion detection in music. Music may evoke more than one different at same time. Single-label classification and regression cannot model this multiplicity. Therefore, focuses on multi-label approaches, where a piece music simultaneously belong to class. Seven algorithms are experimentally compared for task. Furthermore, predictive power several audio features is evaluated using new feature selection method. Experiments conducted set 593 songs with six...
This study proposes a modular water monitoring IoT system that enables quantitative and qualitative measuring of in terms an upgraded version the infrastructure to sustain operational reliability. The proposed method could be used urban rural areas for consumption quality monitoring, or eventually scaled up contemporary enabling providers and/or decision makers (i.e., governmental authorities, global organization, etc.) supervise drive optimal decisions challenging times. inherent resilience...
Defeasible reasoning is a rule-based approach for efficient with incomplete and inconsistent information. Such is, among others, useful ontology integration, where conflicting information arises naturally; the modeling of business rules policies, exceptions are often used. This paper describes these scenarios reports on implementation system defeasible Web. The system, DR-DEVICE, capable about RDF metadata over multiple Web sources using logic rules. It implemented top CLIPS production rule...
The paper presents an integrated approach for automated semantic web service composition using AI planning techniques. An important advantage of this is that the process, as well discovery atomic services take part in composition, are significantly facilitated by incorporation information. OWL-S descriptions transformed into a problem described standardized fashion PDDL, while information used enhancement process approximating optimal composite when exact solutions not found. Solving,...
Streams of objects that are associated with one or more labels at the same time appear in many applications. However, stream classification multi-label data is largely unexplored. Existing approaches try to tackle problem by transferring traditional single-label practices domain. Nevertheless, they fail consider some unique properties such as within and between class imbalance multiple concept drift. To deal these challenges, this paper proposes a novel multilabel approach employs two...
This article introduces a teacher–student framework for reinforcement learning, synthesising and extending material that appeared in conference proceedings [Torrey, L., & Taylor, M. E. (2013)]. Teaching on budget: Agents advising agents learning. {Proceedings of the international autonomous multiagent systems}] non-archival workshop paper [Carboni, N., &Taylor, (2013, May)]. Preliminary results 1 vs. tactics StarCraft. adaptive learning (at AAMAS-13)}]. In this framework, teacher agent...