A5045599982- Advanced Software Engineering Methodologies
- Software System Performance and Reliability
- Evolutionary Algorithms and Applications
- Auction Theory and Applications
- Metaheuristic Optimization Algorithms Research
- Distributed systems and fault tolerance
- Game Theory and Applications
- Service-Oriented Architecture and Web Services
- Reinforcement Learning in Robotics
- Cloud Computing and Resource Management
- Video Surveillance and Tracking Methods
- Advanced Multi-Objective Optimization Algorithms
- IoT and Edge/Fog Computing
- Distributed and Parallel Computing Systems
- Evolutionary Game Theory and Cooperation
- Modular Robots and Swarm Intelligence
- Scientific Computing and Data Management
- Data Visualization and Analytics
- Library Science and Administration
- Ethics and Social Impacts of AI
- Multi-Agent Systems and Negotiation
- Innovative Human-Technology Interaction
- Peer-to-Peer Network Technologies
- Context-Aware Activity Recognition Systems
- Catalytic Cross-Coupling Reactions
University of Ontario Institute of Technology
2020-2025
First Technical University
2021-2024
North Wales Hospital
2023
York University
2023
Aston University
2014-2021
Cancer Institute (WIA)
2007-2017
Pennsylvania State University
2007-2017
University of Birmingham
2008-2014
The Open University
2012
Lehigh University
2003
Intelligent machines have reached capabilities that go beyond a level human being can fully comprehend without sufficiently detailed understanding of the underlying mechanisms. The choice moves in game Go (generated by Deep Mind?s Alpha Zero [1]) are an impressive example artificial intelligence system calculating results even expert for hardly retrace [2]. But this is, quite literally, toy example. In reality, intelligent algorithms encroaching more and into our everyday lives, be it...
Novel computing systems are increasingly being composed of large numbers heterogeneous components, each with potentially different goals or local perspectives, and connected in networks which change over time. Management such quickly becomes infeasible for humans. As such, future should be able to achieve advanced levels autonomous behaviour. In this context, the system's ability self-aware self-express important. This paper surveys definitions current understanding self-awareness...
Abstract As artificial intelligence (AI) technology advances, we increasingly delegate mental tasks to machines. However, today’s AI systems usually do these with an unusual imbalance of insight and understanding: new, deeper insights are present, yet many important qualities that a human mind would have previously brought the activity utterly absent. Therefore, it is crucial ask which features minds replicated, missing, if matters. One core feature humans bring tasks, when dealing...
In this article we present an approach to object tracking handover in a network of smart cameras, based on self-interested autonomous agents, which exchange responsibility for objects market mechanism, order maximise their own utility. A novel ant-colony inspired mechanism is used learn the vision graph, that is, camera neighbourhood relations, during runtime, may then be optimise communication between cameras. The key benefits our completely decentralised are one hand generating graph...
The trustworthiness (or otherwise) of AI has been much in discussion late, not least because the recent publication EU Guidelines for Trustworthy AI. Discussions range from how we might make people trust to being possible trust, with many points inbetween. In this article, question whether or these discussions somewhat miss point, which is that are going ahead and basically doing their own thing anyway, should probably help them. Acknowledging a heuristic widely used by humans situations,...
Work on human self-awareness is the basis for a framework to develop computational systems that can adaptively manage complex dynamic tradeoffs at runtime. An architectural case study in cloud computing illustrates framework's potential benefits.
Video surveillance involves watching an area for significant events. Perimeter security generally requires areas that afford trespassers reasonable cover and concealment. By definition, such "interesting" have limited visibility. Furthermore, targets of interest attempt to conceal themselves within the sometimes adding camouflage further reduce their Such are only visible "while in motion". The combined result visibility distance target severely reduces usefulness any panning-based approach....
Contemporary software systems are becoming increasingly large, heterogeneous, and decentralised. They operate in dynamic environments their architectures exhibit complex trade-offs across dimensions of goals, time, interaction, which emerges internally from the externally environment. This gives rise to vision self-aware architecture, where design decisions execution strategies for these concerns dynamically analysed seamlessly managed at run-time. Drawing on concept self-awareness...
The self-improving system integration (SISSY) initiative has emerged in recent years response to a systems engineering trend towards the organisation of open, interconnected integrating large set heterogeneous and autonomous subsystems. Based on idea equip subsystems with capabilities assess maintain their own status within overall composition, variety concepts, techniques, contributions have been proposed fruitfully discussed at particular events underlying workshop series. In this article,...
In this article, we make the case for new class of Self-aware Cyber-physical Systems. By bringing together two established fields cyber-physical systems and self-aware computing, aim at creating with strongly increased yet managed autonomy, which is a main requirement many emerging future applications technologies. are situated in physical environment constrained their resources, they understand own state and, based on that understanding, able to decisions autonomously runtime...
g ReseaRcheRs who have worked in computer science or artificial intelligence for more than a few years will experienced profound shift the public perception of their field from being something that people rarely cared about outside sci-fi niche academic "geek" interest to is suddenly everywhere all over world and seems be permeating every product.How should we respond this?This challenge was raised recently by inclusion (AI) into debate around concept place, triggered an invitation...
Modern compute systems continue to evolve towards increasingly complex, heterogeneous and distributed architectures. At the same time, functionality performance are no longer only aspects when developing applications for such systems, additional concerns as flexibility, power efficiency, resource usage, reliability cost becoming important. This does not raise question of how efficiently develop but also cope with dynamic changes in application behaviour or system environment. The EPiCS...
In this paper we propose an approach based on self-interested autonomous cameras, which exchange responsibility for tracking objects in a market mechanism, order to maximise their own utility. A novel ant-colony inspired mechanism is used grow the vision graph during runtime, may then be optimise communication between cameras. The key benefits of our completely decentralised are one hand generating online permits addition and removal cameras network runtime other relying only local...
Smart cameras perform on-board image analysis, adapt their algorithms to changes in environment, and collaborate with other networked analyze the dynamic behavior of objects. A proposed computational framework adopts concepts self-awareness self-expression more efficiently manage complex tradeoffs among performance, flexibility, resources, reliability. The Web extra at http://youtu.be/NKe31_OKLz4 is a video demonstrating CamSim, smart camera simulation tool, enables users test self-adaptive...
To solve multi-objective problems, multiple reward signals are often scalarized into a single value and further processed using established single-objective problem solving techniques. While the field of optimization has made many advances in applying scalarization techniques to obtain good solution trade-offs, utility these multi-agent learning domain not yet been thoroughly investigated. Agents learn their decisions by linearly scalarizing at local level, while acceptable system wide...
We study heterogeneity among nodes in self-organizing smart camera networks, which use strategies based on social and economic knowledge to target communication activity efficiently. compare homogeneous configurations, when cameras the same strategy, with heterogeneous different strategies. Our first contribution is establish that static leads new outcomes are more efficient than those possible homogeneity. Next, two forms of dynamic investigated: nonadaptive mixed adaptive strategies, learn...