SciTePress - Affiliation Profile

Research.Publish.Connect.

Title:
ISBN:
Year:
Acronym:
Subject:

Advanced Search Proceedings Search

If you're looking for an exact phrase use quotation marks on text fields.

Title:
Author:
Affiliation:
Subject:

Advanced Search Papers Search

If you're looking for an exact phrase use quotation marks on text fields.

Name:
Affiliation:
Country:
Conference:
Subject:

Advanced Search Authors Search

If you're looking for an exact phrase use quotation marks on text fields.

Name:
Country:
Subject:

Advanced Search Affiliations Search

If you're looking for an exact phrase use quotation marks on text fields.

Proceedings

Proceedings Search

Title:
ISBN:
Year:
Acronym:
Subject:

Advanced Search Proceedings Search

If you're looking for an exact phrase use quotation marks on text fields.

Papers

Papers Search

Title:
Author:
Affiliation:
Subject:

Advanced Search Papers Search

If you're looking for an exact phrase use quotation marks on text fields.

Authors

Authors Search

Name:
Affiliation:
Country:
Conference:
Subject:

Advanced Search Authors Search

If you're looking for an exact phrase use quotation marks on text fields.

Advanced Search

Affiliation

Select a Subject
Refine Ontology Subject

The University of Edinburgh, United Kingdom

Context (please use complete words only)

Field

Sort by

19 Papers

Extracting Accurate Long-term Behavior Changes from a Large Pig Dataset

Topics: Machine Learning Technologies for Vision; Object Detection and Localization; Deep Learning for Visual Understanding ; Deep Learning for Tracking

Authors: Luca Bergamini ¹ , Stefano Pini ¹ , Alessandro Simoni ¹ , Roberto Vezzani ¹ , Simone Calderara ¹ , Rick D’Eath ² and Robert Fisher ³

Affiliations: ¹ University of Modena and Reggio Emilia, Italy , ² SRUC, Edinburgh, U.K. , ³ University of Edinburgh, U.K.

Digital Object Identifier: 10.5220/0010288405240533

Proceedings of VISAPP 2021, ISBN: 978-989-758-488-6

Quick Abstract

Visual observation of uncontrolled real-world behavior leads to noisy observations, complicated by occlusions, ambiguity, variable motion rates, detection and tracking errors, slow transitions between behaviors, etc. We show in this paper that reliable estimates of long-term trends can be extracted given enough data, even though estimates from individual frames may be noisy. We validate this concept using a new public dataset of approximately 20+ million daytime pig observations over 6 weeks of their main growth stage, and we provide annotations for various tasks including 5 individual behaviors. Our pipeline chains detection, tracking and behavior classification combining deep and shallow computer vision techniques. While individual detections may be noisy, we show that long-term behavior changes can still be extracted reliably, and we validate these results qualitatively on the full dataset. Eventually, starting from raw RGB video data we are able to both tell what pigs main daily activities are, and how these change through time.

ABC Repair System for Datalog-like Theories

Topics: Knowledge Representation; Domain Analysis and Modeling; Knowledge Engineering

Authors: Xue Li , Alan Bundy and Alan Smaill

Affiliation: CISA, School of Informatics, University of Edinburgh, 10 Crichton St, Edinburgh and U.K.

Digital Object Identifier: 10.5220/0006959703350342

Proceedings of KEOD 2018, ISBN: 978-989-758-330-8

Quick Abstract

This paper aims to develop a domain-independent system for repairing faulty Datalog-like theories by combining three existing techniques: abduction, belief revision and conceptual change. From the three repair technique candidates, the proposed system is named the ABC repair system. Given an observed assertion and a current theory, abduction adds axioms which represent the simplest and most likely explanation. Belief revision incorporates a new piece of information which conflicts with input theory by deleting old axioms from the input theory. Conceptual change uses the reformation algorithm for blocking unwanted proofs or unblocking wanted proofs. The former two techniques change an axiom as a whole, while reformation changes the language in which the theory is written. These three techniques are complementary: abduction adds new axioms, belief revision deletes conflicting axioms, while reformation changes the language of the theory. But they have not previously been combined into one system. We are working on aligning these three techniques in the ABC repair system, which is capable of repairing logical theories with better quality than individual techniques. Datalog is used as the underlying logic of theories in this paper, but the proposed system has the potential to be adapted to theories in other logics.

Related Ontology Subjects/Areas/Topics (6)

Artificial Intelligence		Knowledge Engineering and Ontology Development		Knowledge-Based Systems
Domain Analysis and Modeling		Knowledge Representation		Symbolic Systems

3D Plane Labeling Stereo Matching with Content Aware Adaptive Windows

Topic: Stereo Vision and Structure from Motion

Authors: Luis Horna and Robert B. Fisher

Affiliation: The University of Edinburgh, United Kingdom

Digital Object Identifier: 10.5220/0006105401620171

Proceedings of VISAPP 2017/VISIGRAPP, ISBN: 978-989-758-227-1

Quick Abstract

In this paper, we present an algorithm that exploits both the underlying 3D structure and image entropy to generate an adaptive matching window. The presented algorithm estimates real valued disparity maps by smartly exploring a 3D search space using a novel hypothesis generation approach that acts like a propagation scheduler. The proposed approach is among the top performing results when evaluated in the Middlebury, KITTI 2015 benchmarks.

Related Ontology Subjects/Areas/Topics (3)

Computer Vision, Visualization and Computer Graphics

Motion, Tracking and Stereo Vision

Stereo Vision and Structure from Motion

Designing a Social Machine for the Heart Manual Service

Topics: e-Health; Medical Informatics; Design and Development of Methodologies for Healthcare IT

Authors: Vanessa Hanschke ¹ , Areti Manataki ² , Cristina Adriana Alexandru ² , Petros Papapanagiotou ² , Carolyn Deighan ³ , Louise Taylor ³ and Dave Robertson ²

Affiliations: ¹ Microsoft, Italy , ² The University of Edinburgh, United Kingdom , ³ NHS Lothian, United Kingdom

Digital Object Identifier: 10.5220/0006249004350440

Proceedings of HEALTHINF 2017/BIOSTEC, ISBN: 978-989-758-213-4

Quick Abstract

Social machines are emerging as a focus of research within the field of informatics as they begin to become the central administrator of our everyday communications. The difficulty of applying such systems to specialised contexts, such as healthcare, calls for guidelines on how to design them, so that they become truly useful. In collaboration with the Heart Manual Department, this project is an attempt at finding suitable methods for designing social machines in a healthcare context. It suggests that adopting a participatory approach where stakeholders are active, equal participants throughout the design process leads to a more usable, likeable, and thus more successful social machine. We describe the process of designing a social machine for the Heart Manual service, in which requirements were elicited through various participatory design methods and a proof of concept evaluation was carried out with a prototype. The prototype was received largely positively and scored highly on the System Usability Scale, indicating the success of the proposed methodology.

Related Ontology Subjects/Areas/Topics (5)

Biomedical Engineering		e-Health		Platforms and Applications
Cloud Computing		Health Information Systems

Distributionally Robust Games with Risk-averse Players

Topics: Optimization; Game Theory

Author: Nicolas Loizou

Affiliation: University of Edinburgh, United Kingdom

Digital Object Identifier: 10.5220/0005753301860196

Proceedings of ICORES 2016, ISBN: 978-989-758-171-7

Quick Abstract

We present a new model of incomplete information games without private information in which the players use a distributionally robust optimization approach to cope with the payoff uncertainty. With some specific restrictions, we show that our “Distributionally Robust Game” constitutes a true generalization of three popular finite games. These are the Complete Information Games, Bayesian Games and Robust Games. Subsequently, we prove that the set of equilibria of an arbitrary distributionally robust game with specified ambiguity set can be computed as the component-wise projection of the solution set of a multi-linear system of equations and inequalities. For special cases of such games we show equivalence to complete information finite games (Nash Games) with the same number of players and same action spaces. Thus, when our game falls within these special cases one can simply solve the corresponding Nash Game. Finally, we demonstrate the applicability of our new model of games and highlight its importance.

Related Ontology Subjects/Areas/Topics (8)

Artificial Intelligence	Knowledge-Based Systems	Optimization
Game Theory	Methodologies and Technologies	Symbolic Systems
Knowledge Discovery and Information Retrieval	Operational Research

LS2C – A Platform to Design, Implement and Execute Social Computations

Topics: Industrial Applications of AI; Distributed Problem Solving; Cooperation and Coordination; Negotiation and Interaction Protocols; Knowledge-Based Systems

Authors: Flavio S. Correa Da Silva ¹ , Dave Robertson ² and Wamberto Vasconcelos ³

Affiliations: ¹ University of Sao Paulo, Brazil , ² University of Edinburgh, United Kingdom , ³ University of Aberdeen, United Kingdom

Digital Object Identifier: 10.5220/0005237101960203

Proceedings of ICAART 2015, ISBN: 978-989-758-074-1

Quick Abstract

Social computers have been characterised as goal oriented complex systems comprised of humans as well as computational devices. Such systems can be found in natura in a variety of scenarios, as well as designed to tackle specific issues of social and economic relevance. In the present article we introduce the Lightweight Situated Social Calculus (LS2C) as a language to design executable specifications of interaction protocols for social computations. Additionally, we describe a platform to process these specifications, giving them a computational realisation. We argue that LS2C can be used to design, implement and execute social computations.

Related Ontology Subjects/Areas/Topics (9)

Agents	Distributed Problem Solving	Negotiation and Interaction Protocols
Artificial Intelligence	Industrial Applications of AI	Soft Computing
Cooperation and Coordination	Knowledge-Based Systems	Symbolic Systems

Event-driven Dynamic Platform Selection for Power-aware Real-time Anomaly Detection in Video

Topics: Camera Networks and Vision; Video Surveillance and Event Detection; Pervasive Smart Cameras; Mobile Imaging

Authors: Calum G Blair ¹ and Neil M Robertson ²

Affiliations: ¹ University of Edinburgh, United Kingdom , ² Heriot-Watt University, United Kingdom

Digital Object Identifier: 10.5220/0004737400540063

Proceedings of VISAPP 2014/VISIGRAPP, ISBN: 978-989-758-009-3

Quick Abstract

In surveillance and scene awareness applications using power-constrained or battery-powered equipment, performance characteristics of processing hardware must be considered. We describe a novel framework for moving processing platform selection from a single design-time choice to a continuous run-time one, greatly increasing flexibility and responsiveness. Using Histogram of Oriented Gradients (HOG) object detectors and Mixture of Gaussians (MoG) motion detectors running on 3 platforms (FPGA, GPU, CPU), we characterise processing time, power consumption and accuracy of each task. Using a dynamic anomaly measure based on contextual object behaviour, we reallocate these tasks between processors to provide faster, more accurate detections when an increased anomaly level is seen, and reduced power consumption in routine or static scenes. We compare power- and speed- optimised processing arrangements with automatic event-driven platform selection, showing the power and accuracy tradeoffs between each. Real-time performance is evaluated on a parked vehicle detection scenario using the i-LIDS dataset. Automatic selection is 10% more accurate than power-optimised selection, at the cost of 12W higher average power consumption in a desktop system.

Related Ontology Subjects/Areas/Topics (7)

Applications and Services	Mobile Imaging	Pervasive Smart Cameras
Camera Networks and Vision	Motion, Tracking and Stereo Vision	Video Surveillance and Event Detection
Computer Vision, Visualization and Computer Graphics

KEWI - A Knowledge Engineering Tool for Modelling AI Planning Tasks

Topics: Intelligent Problem Solving; Knowledge Representation; Domain Analysis and Modeling

Authors: Gerhard Wickler ¹ , Lukáš Chrpa ² and Thomas Leo McCluskey ²

Affiliations: ¹ University of Edinburgh, United Kingdom , ² University of Huddersfield, United Kingdom

Digital Object Identifier: 10.5220/0005034400360047

Proceedings of KEOD 2014/IC3K, ISBN: 978-989-758-049-9

Quick Abstract

This paper introduces the Knowledge Engineering Web Interface (KEWI) which primarily aims to be used for modelling automated planning tasks in a semi-formal framework. The conceptual model used to represent the declarative and procedural knowledge in KEWI is described formally. The model consists of three layers: a rich ontology, a model of basic actions, and more complex methods. It is this structured conceptual model based on the rich ontology that facilitates knowledge engineering. The focus of this paper is to show how the central knowledge model used in KEWI differs from a model directly encoded in PDDL, the language accepted by most existing planning engines. Specifically, the rich ontology enables a more concise and natural style of representation. For operational use, KEWI automatically generates PDDL. Initial experiments show that the generated PDDL can be processed by a planner without incurring significant drawbacks.

Related Ontology Subjects/Areas/Topics (9)

Artificial Intelligence	Intelligent Problem Solving	Knowledge-Based Systems
Domain Analysis and Modeling	Knowledge Engineering and Ontology Development	Software Engineering
Enterprise Software Technologies	Knowledge Representation	Symbolic Systems

Multiple Ontologies Enhanced with Performance Capabilities to Define Interacting Domains within a Workflow Framework for Analysing Large Undersea Videos

Topics: Ontology Engineering; Intelligent Problem Solving; Process Knowledge and Semantic Services; Applications and Case-Studies; Domain Analysis and Modeling

Authors: Nadarajan Gayathri , Cheng-Lin Yang and Yun-Heh Chen-Burger

Affiliation: University of Edinburgh, United Kingdom

Digital Object Identifier: 10.5220/0004643304190426

Proceedings of KEOD 2013/IC3K, ISBN: 978-989-8565-81-5

Quick Abstract

In this paper, we describe our efforts in using ontological engineering as a backbone technology to define multi-disciplinary knowledge that interact with one another in a complex domain. Multiple ontologies were developed to define these interacting domains. Combined with planning technology, they are used in a three-layered framework that enables the definition, creation and execution of a workflow management system based on dynamic user requirements. We report on how such ontologies play a central role in enabling the workflow system to work consistently and systematically while communicating and collaborating with other project partner systems. We also extend the capability elements of the ontologies with hardware and software performance measures. These metrics are valuable factors in improving the overall system’s performance.

Related Ontology Subjects/Areas/Topics (15)

Applications and Case-studies	Enterprise Software Technologies	Ontologies and the Semantic Web
Artificial Intelligence	Information Systems Analysis and Specification	Ontology Engineering
Data Engineering	Intelligent Problem Solving	Process Knowledge and Semantic Services
Domain Analysis and Modeling	Knowledge Engineering and Ontology Development	Software Engineering
Enterprise Information Systems	Knowledge-Based Systems	Symbolic Systems

Managing Data in Help4Mood

Authors: Maria K. Wolters ¹ , Juan Martínez-Miranda ² , Helen F. Hastie ³ and Colin Matheson ¹

Affiliations: ¹ University of Edinburgh, United Kingdom , ² Universitat Politécnica de Valencia, Spain , ³ Heriot-Watt University, United Kingdom

Digital Object Identifier: 10.5220/0003879400170024

Proceedings of MindCare 2012/BIOSTEC, ISBN: 978-989-8425-92-8

Quick Abstract

Help4Mood is a system that supports the treatment of people with major depression through collecting a wealth of cognitive, psychomotor, and motor data, which can then be summarised and analysed further. Data is stored in functional units that correspond to treatment relevant entities using a custom XML DTD. As far as possible, observations and findings are coded using SNOMED CT to ensure interoperability with other applications such as Electronic Health Records.