Filters








13,687 Hits in 2.1 sec

Towards ontology driven learning of visual concept detectors [article]

Sanchit Arora, Chuck Cho, Paul Fitzpatrick, Francois Scharffe
2016 arXiv   pre-print
In this paper, we propose a system that combines neural techniques, a large scale visual concepts ontology, and an active learning loop, to provide on the fly model learning of arbitrary concepts.  ...  We give an overview of the system as a whole, and focus on the central role of the ontology for guiding and bootstrapping the learning of new concepts, improving the recall of concept detection, and, on  ...  Ontology Driven Neural Model Learning As Section 2 illustrated, there are multiple areas where the use of a comprehensive ontology can improve the process of incrementally learning a visual concept detection  ... 
arXiv:1605.09757v1 fatcat:pkway76tcrh3xpngzogls4vwqi

Management of dynamic knowledge

Peter Haase, Johanna Völker, York Sure, John Davies
2005 Journal of Knowledge Management  
Our approach for usage-driven and data-driven change discovery not only assures the consistency of ontologies modeling dynamic knowledge, but also reduces the burden of manual ontology engineering.  ...  Originality/value -This paper presents the first approach towards a common framework for ontology evolution based on usage-driven and data-driven change discovery.  ...  Usage-driven hierarchy pruning Our goal is to help an ontology engineer in the continual improvement of the ontology.  ... 
doi:10.1108/13673270510622483 fatcat:ens6irvcwjaw3aqoti5ywz63du

Ontologies and Information Extraction [article]

Claire Nédellec
2006 arXiv   pre-print
This report argues that, even in the simplest cases, IE is an ontology-driven process.  ...  Hierarchies Beyond lists of entities, ontologies are often described as hierarchies of semantic or word classes.  ...  We will argue that even in the simplest cases, IE is an ontology-driven process.  ... 
arXiv:cs/0609137v1 fatcat:s5374ygzwzbnxp2ejzq2wmxw3a

The Dynamic Web Services Adaptation Framework in Context-Aware Mobile Cloud Learning using Semantic-Based Method

2019 International Journal of Engineering and Advanced Technology  
The framework is applied in MCL mobile application that offers basic learning language.  ...  Contextual information are represented using semantic-based approach for high expressiveness and formal representation for reasoning technique.  ...  The Dynamic Web Services Adaptation Framework in Context-Aware Mobile Cloud Learning using Semantic-based Method  ... 
doi:10.35940/ijeat.a2652.109119 fatcat:lgzse6ggqjga3f2giouqzmggwi

The Development of Personality Ontology Based on the Methontology Approach

Zalmiyah Zakaria, Shahreen Kasim, Nur Husna Mohamad Hasbullah, Ayu Alyani Azadin, Ansari Saleh Ahmar, Rahmat Hidayat
2018 International Journal of Engineering & Technology  
There are many ways to express the structured knowledge, Ontology is one of them. In this paper will discuss the development of Fingerprint Ontology based on METHONTOLOGY approach.  ...  The figure below shows the hierarchy of Fingerprint ontology. Protégé-OWL supports graphical representation of a class hierarchy though OWLVIZ plug-in.  ...  Figure 2 show the hierarchy of Fingerprint ontology. The class hierarchy was developed and formalized by means of a combination of top-down and bottom-up classification strategies [8] .  ... 
doi:10.14419/ijet.v7i2.5.13955 fatcat:jdxmfvyuzfdwhnencrpgcc6zcu

A Cognitive Vision System for Nuclear Fusion Device Monitoring [chapter]

Vincent Martin, Victor Moncada, Jean-Marcel Travere, Thierry Loarer, François Brémond, Guillaume Charpiat, Monique Thonnat
2011 Lecture Notes in Computer Science  
Our system is made intelligent by the use of a priori knowledge of both contextual and perceptual information for ontology-driven event modeling and task-oriented event recognition.  ...  Ontology-driven vision task composing. The unification of information and especially visual and contextual data can be achieved with ontologies, as demonstrated in [5] and [4] .  ...  We propose a formal method to infer the vision task hierarchy from prior knowledge described in our ontology.  ... 
doi:10.1007/978-3-642-23968-7_17 fatcat:aqpa7tmcfndm7n4xmjeio6owum

Semantics-Driven Remote Sensing Scene Understanding Framework for Grounded Spatio-Contextual Scene Descriptions

Abhishek V. Potnis, Surya S. Durbha, Rajat C. Shinde
2021 ISPRS International Journal of Geo-Information  
The Sem-RSSU, at its core, constitutes novel Ontology-driven Spatio-Contextual Triple Aggregation and realization algorithms to transform KGs to render grounded natural language scene descriptions.  ...  In that regard, a contextual domain knowledge encompassing Flood Scene Ontology (FSO) has been developed.  ...  Acknowledgments: The authors are grateful to the Google Cloud Research Credits Program for providing the credits that enabled the use of GCP for training and validating the deep-learning models.  ... 
doi:10.3390/ijgi10010032 fatcat:warifoopejaqfglljmkbatjrke

Taxonomy Extraction from Automotive Natural Language Requirements Using Unsupervised Learning

Martin Ringsquand, Mathias Schraps
2014 International Journal on Natural Language Computing  
This work is part of an ontology-driven requirements engineering process, which builds on top of the taxonomy.  ...  In this paper we present a novel approach to semi-automatically learn concept hierarchies from natural language requirements of the automotive industry.  ...  Related Work on Ontology-Driven RE Ontology-driven RE tries to establish a synergy between ontological domain modeling and requirements specification.  ... 
doi:10.5121/ijnlc.2014.3403 fatcat:aukdfc5ibbbatgwxtvn4bldgeu

Ontology-Driven Adaptive and Pervasive Learning Environments – APLEs: An Interdisciplinary Approach [chapter]

Ahmet Soylu, Mieke Vandewaetere, Kelly Wauters, Igor Jacques, Patrick De Causmaecker, Piet Desmet, Geraldine Clarebout, Wim Van den Noortgate
2011 Communications in Computer and Information Science  
Thereafter, we argue for an ontology-driven approach employing ontologies at run-time and development-time where formalized ontologies and rules are considered as main medium of adaptivity, user involvement  ...  Finally, we introduce a prototype domain context ontology for item-based learning environments and demonstrate its run-time and development-time uses.  ...  This paper is based on research funded by the Industrial Research Fund (IOF) and conducted within the IOF Knowledge platform "Harnessing collective intelligence in order to make e-learning environments  ... 
doi:10.1007/978-3-642-20074-8_9 fatcat:mvy5l6iiorfftnp57isn37hucy

Leveraging Machine Learning to Extend Ontology-Driven Geographic Object-Based Image Analysis (O-GEOBIA): A Case Study in Forest-Type Mapping

Sachit Rajbhandari, Jagannath Aryal, Jon Osborn, Arko Lucieer, Robert Musk
2019 Remote Sensing  
Ontology-driven Geographic Object-Based Image Analysis (O-GEOBIA) contributes to the identification of meaningful objects.  ...  Two machine learning algorithms, Random Forest and Boruta, are used to identify important and relevant feature variables. A variogram is used to describe textural and spatial features.  ...  Ontology for Forest-Type Mapping The forest-type mapping in this work is accomplished extending an Ontology-driven GEOBIA (O-GEOBIA) framework [5, 6] .  ... 
doi:10.3390/rs11050503 fatcat:fr5mort43vcblckcgej4psgvni

Towards Ontology Based Cognitive Vision [chapter]

Nicolas Maillot, Monique Thonnat, Alain Boucher
2003 Lecture Notes in Computer Science  
This paper details a visual concept ontology driven knowledge acquisition methodology.  ...  We propose to use a visual concept ontology to guide experts in the visual description of the objects of their domain (e.g. pollen grain).  ...  Then comes the visual concept ontology-driven description phase, which means that the expert uses the vocabulary provided by the ontology to describe the objects of the domain.  ... 
doi:10.1007/3-540-36592-3_5 fatcat:kk2t7laxtrfmni6a7v4vudmowy

Towards ontology-based cognitive vision

Nicolas Maillot, Monique Thonnat, Alain Boucher
2004 Machine Vision and Applications  
This paper details a visual concept ontology driven knowledge acquisition methodology.  ...  We propose to use a visual concept ontology to guide experts in the visual description of the objects of their domain (e.g. pollen grain).  ...  Then comes the visual concept ontology-driven description phase, which means that the expert uses the vocabulary provided by the ontology to describe the objects of the domain.  ... 
doi:10.1007/s00138-004-0142-9 fatcat:p4ppu36gzvayhogndb3uomuija

An intelligent system for semi-automatic evolution of ontologies

Maryam Ramezani, Hans Friedrich Witschel
2010 2010 5th IEEE International Conference Intelligent Systems  
However, the traditional expert-driven development of ontologies is time-consuming and often results in incomplete and inappropriate ontologies.  ...  We use the Wikipedia category hierarchy to evaluate our algorithm and our experimental results show that the proposed algorithm produces high quality recommendations.  ...  [5] use frequent itemset mining for learning ontologies from folksonomies.  ... 
doi:10.1109/is.2010.5548403 dblp:conf/is/RamezaniW10 fatcat:n3heejxbarcfjbqwmkngjpyjfa

Context-aware Human Intent Inference for Improving Human Machine Cooperation [article]

Xiang Zhang
2018 arXiv   pre-print
The ontology provides a rich hierarchy with multilevels of depth in the context of human behavior intents in the specific domain.  ...  Calibrating via Ontological Reasoning for Reliable Intent Inference This task is towards the exploration of using of ontological reasoning to reinforce the performance of learningbased approaches.  ... 
arXiv:1803.04099v1 fatcat:re7jchoffvh4vnkf2svqiqiu5m

Ontology‐based activity recognition in intelligent pervasive environments

Liming Chen, Chris Nugent
2009 International Journal of Web Information Systems  
, i.e., activity ontologies, addressing the lifecycle of activity recognition.  ...  Based on an analysis of existing solutions, the paper then proposes an integrated ontology-based approach to activity recognition.  ...  While ADL ontologies establish links between activities and contextual information through activity properties, context ontologies establish links between contextual information with sensor observations  ... 
doi:10.1108/17440080911006199 fatcat:s56mcxvofzbpncaohnvgwk6o3a
« Previous Showing results 1 — 15 out of 13,687 results