Publications
186 results found
Mace M, Abdullah-Al-Mamun K, Wang S, et al., 2011, Ensemble classification for robust discrimination of multi-channel, multi-class tongue-movement ear pressure signals., Pages: 1733-1736
In this paper we introduce a robust classification framework for tongue-movement ear pressure signals based around an ensemble voting methodology. The ensemble members are comprised of different combinations of sensor inputs i.e. two in-ear microphones and an acoustic gel sensor positioned under the chin of the individual and classification using three different base models. It is shown that by using all nine ensemble members when compared to the individual (base) models, the average misclassification rate can be reduced from 23% to 2.8% when using the majority voting strategy. The correct classification rate is improved from 76% to 92.4% when utilizing either the borda count or condorcet methods. This is achieved through a combination of rejection based on ambiguity in the ensemble and diversity in the misclassified instances across the ensemble members.
Mace M, Mamun KA, Wang S, et al., 2011, Ensemble classification for robust discrimination of multi-channel , multi-class tongue-movement ear pressure signals, Boston, Proc. of the 33rd IEEE Int. Conf. of Engineering in Medicine and Biology Society, Publisher: IEEE
Buckley M, Vaidyanathan R, Mayol-Cuevas W, 2011, Sensor Suites For Assistive Arm Prosthetics, 24th International Symposium on Computer-Based Medical Systems (CBMS), Publisher: IEEE, ISSN: 2372-9198
- Author Web Link
- Cite
- Citations: 2
Carberry J, Hinchly G, Buckerfield J, et al., 2011, Parametric Design of an Active Ankle Foot Orthosis with Passive Compliance, 24th International Symposium on Computer-Based Medical Systems (CBMS), Publisher: IEEE, ISSN: 2372-9198
- Author Web Link
- Cite
- Citations: 5
Burton TMW, Vaidyanathan R, Burgess SC, et al., 2011, Development of a Parametric Kinematic Model of the Human Hand and a Novel Robotic Exoskeleton, IEEE International Conference on Rehabilitation Robotics (ICORR)/International Neurorehabilitation Symposium (INRS)/International Conference on Virtual Rehabilitation (ICVR), Publisher: IEEE, ISSN: 1945-7898
- Author Web Link
- Cite
- Citations: 6
Craig R, Vaidyanathan R, James C, et al., 2010, Assessment of human response to robot facial expressions through visual evoked potentials, Pages: 647-652
The focus of this work is to investigate and quantify the ability of a humanoid 'hybrid face' robot to effectively convey emotion to a human observer by mapping their physiological (EEG) response to perceived emotional information. Specifically, we examine the event related response during two implicit emotion recognition experiments to determine the modulation of the face-specific N170 brain response component to robot facial expressions. EEG recordings were taken from a range of test subjects observing the BERT2 robot cycle through a range of facial emotions in each emotion recognition experiment. Results from both experiments demonstrate that the stimuli evoke the N170 component and that digital facial expressions with high correlations can be discriminated. Emotional expressions evoke a larger response relative to neutral stimuli, with negative evoking an increased amplitude and latency to positive emotions, and demonstrate that the response to robot facial expressions evoke similar brain activity to that of a human emotions. This study is the first of its nature to investigate and quantify the human physiological response to digital facial expressions as conveyed in real-time by a humanoid robot. ©2010 IEEE.
Lock RJ, Vaidyanathan R, Burgess SC, et al., 2010, Development of a biologically inspired multi-modal wing model for aerial-aquatic robotic vehicles through empirical and numerical modelling of the common guillemot, <i>Uria aalge</i>, BIOINSPIRATION & BIOMIMETICS, Vol: 5, ISSN: 1748-3182
- Author Web Link
- Cite
- Citations: 30
Evins R, Pointer P, Vaidyanathan R, 2010, Configuration of a genetic algorithm for multi-objective optimisation of solar gain to buildings, Pages: 1327-1328
We report the formulation and implementation of a genetic algorithm to address multi-objective optimisation of solar gain to buildings with the goal of minimising energy consumption and hence limiting carbon emissions. Heuristic optimisation approaches hold significant promise to balance complex tradeoffs in building design; however the unique nature of each building optimization problem limits broader implementation. Parameter selection is very challenging with little or no correlation between different architectural configurations. We address this issue through 'calibration' on smaller scale problems with derivable optimal solutions. Various seeding, selection and fitness options were trialled, as well as different parameter values. The Pareto front of the global solution set was successfully reproduced for the calibration case. Varying climate produced no major change in the nature of the solution; however, building orientation forced reparameterization for an optimal solution. Future work will establish when calibration is useful, and aim to quantify the nature of the solution space.
Gupta L, Kota S, Murali S, et al., 2010, A Feature Ranking Strategy to Facilitate Multivariate Signal Classification, IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART C-APPLICATIONS AND REVIEWS, Vol: 40, Pages: 98-108, ISSN: 1094-6977
- Author Web Link
- Open Access Link
- Cite
- Citations: 13
Araromi OA, Conn AT, Ling CS, et al., 2010, A novel fabrication set-up for the flexible production of silicone based EAP "artificial muscle" actuators, 5th International Conference on Comparing Design in Nature with Science and Engineering, Publisher: WIT PRESS, Pages: 289-+, ISSN: 1743-3541
- Author Web Link
- Cite
- Citations: 1
Mace M, Mamun KA, Vaidyanathan R, et al., 2010, Real-time Implementation of a Non-invasive Tongue-based Human-Robot Interface, Taipei, Proc. of the 2010 IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS 2010), Publisher: IEEE, Pages: 5486-5491
Lock RJ, Vaidyanathan R, Burgess SC, 2010, Development of a Biologically Inspired Multi-Modal Wing Model for Aerial-Aquatic Robotic Vehicles, IEEE/RSJ International Conference on Intelligent Robots and Systems, Publisher: IEEE, Pages: 3404-3409, ISSN: 2153-0858
- Author Web Link
- Cite
- Citations: 8
Gupta L, Kota S, Molfese DL, et al., 2010, Diversity-Based Selection of Components for Fusion Classifiers, 32nd Annual International Conference of the IEEE Engineering-in-Medicine-and-Biology-Society (EMBC 10), Publisher: IEEE, Pages: 6304-6307, ISSN: 1557-170X
- Author Web Link
- Cite
- Citations: 2
Bazo D, Vaidyanathan R, Lentz A, et al., 2010, Design and Testing of a Hybrid Expressive Face for a Humanoid Robot, IEEE/RSJ International Conference on Intelligent Robots and Systems, Publisher: IEEE, Pages: 5317-5322, ISSN: 2153-0858
- Author Web Link
- Cite
- Citations: 21
Kota S, Gupta L, Molfese DL, et al., 2009, A Dynamic Channel Selection Strategy for Dense-Array ERP Classification, IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, Vol: 56, Pages: 1040-1051, ISSN: 0018-9294
- Author Web Link
- Open Access Link
- Cite
- Citations: 9
Bachmann RJ, Boria FJ, Vaidyanathan R, et al., 2009, A biologically inspired micro-vehicle capable of aerial and terrestrial locomotion, MECHANISM AND MACHINE THEORY, Vol: 44, Pages: 513-526, ISSN: 0094-114X
- Author Web Link
- Open Access Link
- Cite
- Citations: 71
Boxerbaum AS, Bachmann RJ, Quinn RD, et al., 2009, Design and testing of a highly mobile insect-inspired autonomous robot in a beach environment, International Journal of Design and Nature and Ecodynamics, Vol: 4, Pages: 319-336, ISSN: 1755-7437
The capability of autonomous platforms to function on beaches and in the ocean surf-zone is critical for a wide range of military and civilian operations. Of particular importance is the ability to navigate autonomously through the rocky terrain, hard-packed moist sand, and loose dry sand characterizing this environment. The study of animal locomotion mechanisms can elucidate specific movement principles that can be applied to address these demands. In this work, we report the design, fabrication, control system development, simulation, and field testing of a biologically inspired autonomous robot for deployment and operation in an ocean beach environment. The robot successfully fuses a range of insect-inspired passive mechanisms with active autonomous control architectures to seamlessly adapt to and traverse through a range of challenging substrates.Field testing establishes the performance of the robot to navigate semi-rugged terrain in the surf-zone environment including soft to hard-packed sand, mild to medium inclines, and rocky terrain. Platform autonomy is shown to be effective for navigation and communication. The fusion of passive mechanisms and active control algorithms results in a robot with mobility comparable to a legged vehicle with a control system of comparable simplicity to a wheeled robot. Based on the success of this platform, we further introduce the design of a fully amphibious robot designed to extend its performance to completely undersea surroundings. © 2009 WIT Press.
Bachmann RJ, Vaidyanathan R, Quinn RD, 2009, Drive Train Design Enabling Locomotion Transition of a Small Hybrid Air-Land Vehicle, IEEE RSJ International Conference on Intelligent Robots and Systems, Publisher: IEEE, Pages: 5647-+
- Author Web Link
- Cite
- Citations: 7
Mace M, Vaidyanathan R, Wang S, et al., 2009, Tongue in cheek: A novel concept in assistive human-machine interface, Journal of Assistive Technologies, Vol: 3, Pages: 14-26
Bachmann RJ, Vaidyanathan R, Boria FJ, et al., 2009, A Miniature Vehicle with Extended Aerial and Terrestrial Mobility, FLYING INSECTS AND ROBOTS, Editors: Floreano, Zufferey, Srinivasan, Ellington, Publisher: SPRINGER-VERLAG BERLIN, Pages: 247-270, ISBN: 978-3-540-89392-9
- Author Web Link
- Cite
- Citations: 3
Harkins RH, Dunbar T, Boxerbaum AS, et al., 2009, Confluence of Active and Passive Control Mechanisms Enabling Autonomy and Terrain Adaptability for Robots in Variable Environments, International Conference on Advances in Electrical and Electronics Engineering held at the World Congress on Engineering and Computer Sciences, Publisher: IEEE COMPUTER SOC, Pages: 138-+
- Author Web Link
- Cite
- Citations: 3
Burgess SC, Ling CS, Conn A, et al., 2009, Development of a novel Electro Active Polymer (EAP) actuator for driving the wings of flapping micro air vehicle, 11th International Conference on Computer Aided Optimum Design of Structures, Publisher: WIT PRESS, Pages: 207-217, ISSN: 1746-4498
- Author Web Link
- Cite
- Citations: 8
Lock RJ, Vaidyanathan R, Burgess SC, et al., 2009, Impact of Passive Stiffness Variation on Stability and Mobility of a Hexapod Robot, IEEE/ASME International Conference on Advanced Intelligent Mechatronics, Publisher: IEEE, Pages: 980-+, ISSN: 2159-6255
- Author Web Link
- Cite
- Citations: 2
Boxerbaum AS, Klein MA, Quinn RBRD, et al., 2009, Design of a Semi-Autonomous Hybrid Mobility Surf-Zone Robot, IEEE/ASME International Conference on Advanced Intelligent Mechatronics, Publisher: IEEE, Pages: 974-+, ISSN: 2159-6255
- Author Web Link
- Cite
- Citations: 14
Kota S, Mace M, Gupta LA, et al., 2009, A DCT-Gaussian Classification Scheme for Human-Robot Interface, St. Louis, Proc. of the IEEE 2009 Int. Conf. on Intelligent Robots and Systems (IROS 2009), Publisher: IEEE, Pages: 5503-5508
Gupta L, Kota S, Murali S, et al., 2008, Dimensionality reduction strategies for the design of human machine interface signal classifiers, Pages: 2432-2436, ISSN: 1062-922X
The goal in this paper is to overcome the dimensionality problem related to designing human-machineinterface (HMI) signal classifiers. The dimension is decreased by selecting a small set of linear combination of the input space features using the principal components transform (PCT) and the discrete cosine transform (DCT). Issues dealing with the selection of the basis vectors of the PCT and DCT for multi-class classification problems are addressed and four different classdependant ranking criteria are introduced to select basis vectors from the transformed training vectors in the PCT and DCT domains. The application and evaluation of the resulting PCT and DCT based multivariate classification strategies are demonstrated by classifying ear-pressure signals and event related potentials. The signals in these experiments are typical of control signals used in HMI applications and are also typical of those in which the dimensionality problem occurs. Based on the evaluations and comparisons, it is concluded that the PCT and the DCT based strategies developed in this paper offer viable solutions to overcome the dimensionality problem that frequently plagues the design of practical HMI signal classifiers. © 2008 IEEE.
Kirshenbaum M, Palmer D, McCullick P, et al., 2008, Explaining swarm design concepts using an interactive, bottom-up simulation tool, Pages: 298-303
When promoting emergent behavior as a viable problem-solving option to a community unfamiliar with the concept but nevertheless key stakeholders in the effort, swarm researchers can find themselves making rudimentary analogies to social insects that provide some familiarity, but offers nothing in the way of real understanding. Yet, if these stakeholders are to adopt such a seemingly radical approach, they need to be somewhat conversant with the concepts, the obstacles and the process of an emergent system. We have built an Emergent Behavior Simulation Tool (EBST) to make issues of emergent systems and bottom-up design quickly accessible to interested neophytes. The contextual scenarios are built by swarm researchers, but provide an interface accessible to all. The tool provides an environment in which the consequences of agent based actions can be observed at the global level, and then quickly changed based on observations. Yet the scenarios are specific, and goal-oriented, so that the swarm-layperson is not left to fend for themselves in a sea of syntax, and open-ended possibilities. The tool is the centerpiece of an online course being developed for military students at the US Naval Postgraduate School. © Springer Science+Business Media B.V. 2008.
Vaidyanathan R, Prince TS, Modarreszadeh M, et al., 2008, Computationally efficient predictive adaptive control for robotic operation in dynamic environments and task domains, PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART B-JOURNAL OF ENGINEERING MANUFACTURE, Vol: 222, Pages: 1695-1713, ISSN: 0954-4054
'Dirk'Bindi V, Strunk J, Baker J, et al., 2008, Littoral undersea warfare: A case study in process modelling for functionality and interoperability of complex systems, International Journal of System of Systems Engineering, Vol: 1, Pages: 18-58, ISSN: 1748-0671
The goal of this investigation is to demonstrate the application of a process modelling approach to architect a System of Systems (SoS) capable of conducting Anti-Suhmarine Warfare (ASW) operations projecting to the year 2025. Process modelling is a methodology for architectural analysis for complex systems whose operation is characterised by 'processes' whose sequential execution may be scaled-up to understand overall system behaviour. It is ideally suited to address complexity and interoperability issues of an ASW SoS. New contributions of this work include the successful implementation of a process modelling approach to architect an ASW SoS and a cohesive set of results analysing its operation with future projections to the year 2025. We believe this work may serve as a foundation for future systems engineering research addressing interoperability and performance of complex systems whose function is closely tied to time-dependent processes, with particular application to military and security systems. Copyright © 2008 Inderscience Enterprises Ltd. littoral undersea warfare, Anti-Submarine Warfare, ASW, process modelling, system architectures, functional analysis. interoperability.
Conn AT, Burgess SC, Ling CS, et al., 2008, The design optimisation of an insect-inspired micro air vehicle, International Journal of Design and Nature and Ecodynamics, Vol: 3, Pages: 12-27, ISSN: 1755-7437
Insect-inspired micro air vehicles (MAVs) have been the subject of extensive research in recent years for a range of novel applications. The current generation of vehicles, however, has yet to match even a fraction of the performance of insect flight, in particular with respect to manoeuvrability and payload capacity. Precise reproduction of insect-like flapping motion on the micro-vehicle scale holds significant potential to address this deficiency. The design and optimisation of this critical aspect of an insect-inspired MAV is the subject of this paper. The actuated flapping mechanism must deliver a high power output via complex wing kinematics, which should be dynamically adjustable for controlled flight without the need for traditional control surfaces. This paper first addresses several key flapping MAV design criteria that greatly influence the power requirements and aerodynamic forces for flight, through an assessment of design parameters such as wing length and wingbeat frequency. Two solutions are then proposed that meet these requirements while satisfying the current limitations of miniature actuation technologies and issues related to mechanism constraint. The first of these, the development of an artificial muscle actuator is crucial to the feasibility of a highly adjustable, lightweight under-constrained flapping mechanism. A prototype artificial muscle based on a silicone dielectric elastomer was tested and found to produce a strain output comparable to muscle. We also report the development of an alternative flapping mechanism solution utilising conventional rotary DC motors. The novel parallel crankrocker (PCR) mechanism produces similar wing kinematics to insects and, unlike previously developed DC motor-driven MAV flapping mechanisms, it allows dynamically adjustable control of the wing angle of attack. Aerodynamic testing of a PCR prototype found that it produced a maximum lift force of 6.4 g per wing pair at a wingbeat frequency of 13.2 Hz. Wind
This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.