Centre for Intelligent Systems Research

CISR Research Seminar Series - 2014

  CISR presentation
blue star Professional development
yellow star Keynote lecture
purple star External presentation
red star No presentation

Seminars will be held at 12pm in the CISR Breakout Area (except where otherwise indicated)

Date Presenter Presentation/topic
Wednesday 23rd July

9:30am
(na1.418)
Prof. Dan Koditschek External presentation  Composition of Attractor Basins for Dexterous Robotic Tasks 

 Biography

Daniel E. Koditschek is the Alfred Fitler Moore Professor of Electrical and Systems Engineering. Dr. Koditschek received his bachelor's degree in Engineering and Applied Science and his M.S. and Ph.D. degrees in Electrical Engineering in 1981 and 1983, all from Yale University. He served on the Yale Faculty in Electrical Engineering until moving to the University of Michigan a decade later. In January 2005, he moved to the University of Pennsylvania to assume the post of Chair of the Electrical and Systems Engineering Department, within the School of Engineering and Applied Science.

Koditschek's research interests include robotics and, more generally, the application of dynamical systems theory to intelligent mechanisms. His archival journal and refereed conference publications, numbering well over 100, have appeared in a broad spectrum of venues ranging from the Transactions of the American Mathematical Society through The Journal of Experimental Biology, with a concentration in several of the IEEE journals and related transactions. Various aspects of this work have received mention in general scientific publications such as Scientific American and Science as well as in the popular and general lay press such as The New York Times and Discover Magazine. Dr. Koditschek is a member of the AMS, ACM, MAA, SIAM, SICB and Sigma Xi and is a Fellow of the IEEE and the AAAS.

Koditschek holds secondary appointments within the School of Engineering and Applied Science in the departments of Computer and Information Science and Mechanical Engineering.

 Abstract

This talk reviews a two decade program of research in the design and implementation of modular controllers for dynamically dexterous robots. We seek to represent tasks by means of "templates:" low dimensional reference dynamics whose specified attractors encode goals and whose repelling boundaries represent obstacles or forbidden behaviors. General purpose machines typically have degrees of freedom unrelated to the needs of specific templates. Hence the most basic control module is an "anchor:" a feedback law that embeds the template as an attracting invariant submanifold in the machine's physical state space. Synthesis of more complicated behaviors from simpler constituents proceeds by sequential and parallel composition of templates. A correct synthesis is one for which the limit set of the anchored composition yields the desired composition of the template limit sets. After reviewing various instances of these ideas applied to the setting of steady state legged locomotion, the talk concludes with a preliminary look at the problem of encoding and implementing transitional tasks such as leaping across gaps and onto ledges.
Monday 21st July Josipa Crnic Professional Development  COS Pivot 

 Abstract

COS Pivot is a powerful tool that provides access to a comprehensive list of global funding and collaboration opportunities

Friday 18th July

12:00pm
(na1.418)
Prof. Toshio Fukuda External presentation  Multi-scale Robotics 

 Biography

Toshio Fukuda received the B.A. degree from Waseda University, Tokyo, Japan, in 1971, and the M.S and Dr. Eng. from the University of Tokyo, Tokyo, Japan, in 1973 and 1977, respectively.

In 1977, he joined the National Mechanical Engineering Laboratory. In 1982, he joined the Science University of Tokyo, Japan, and then joined Nagoya University, Nagoya, Japan, in 1989. He was Director of Center for Micro-Nano Mechatronics and Professor of Department of Micro-Nano Systems Engineering at Nagoya University, where he was mainly involved in the research fields of intelligent robotic and mechatronic system, cellular robotic system, and micro- and nano-robotic system. He was the Russell Springer Chaired Professor at UC Berkeley, Distinguished Professor, Seoul National University, and many other universities. Currently, He is Professor Emeritus Nagoya University, Visiting Professor Institute for Advanced Research Nagoya University, Professor Meijo University, Professor Beijin Institute of Technology.

Dr. Fukuda is IEEE Region 10 Director (2013-2014) and served President of IEEE Robotics and Automation Society (1998-1999), Director of the IEEE Division X, Systems and Control (2001- 2002), and Editor-in-Chief of IEEE / ASME Transactions on Mechatronics (2000-2002). He was President of IEEE Nanotechnology Council (2002-2003, 2005) and President of SOFT (Japan Society for Fuzzy Theory and Intelligent Informatics) (2003-2005). He was elected as a member of Science Council of Japan (2008-). He received the IEEE Eugene Mittelmann Award (1997), IEEE Millennium Medal (2000), Humboldt Research Prize (2002), IEEE Robotics and Automation Pioneer Award (2004), IEEE Robotics and Automation Society Distinguished Service Award (2005), Award from Ministry of Education and Science in Japan (2005). IEEE Nanotechnology Council Distinguished service award (2007). Best Googol Application paper awards from IEEE Trans. Automation Science and Engineering (2007). Best papers awards from RSJ (2004) and SICE (2007), Special Funai Award from JSME (2008), 2009 George Saridis Leadership Award in Robotics and Automation (2009), IEEE Robotics and Automation Technical Field Award (2010), ROBOMECH Award 2010 (2010), The Society of Instrument and Control Engineers Technical Field Award (2010), IROS Harashima Award for Innovative Technologies (2011), Friendship Award of Liaoning Province PR China (2012), Distinguished Service Award, The Robotics Society of Japan (2010), World Automation Congress 2010 (WAC 2010) dedicated to Prof. Toshio Fukuda, Best Paper Award in 2010 International Symposium on Micro-Nano Mechatronics and Human Science (MHS2010), IEEE Fellow (1995), SICE Fellow (1995), JSME Fellow (2001), RSJ Fellow (2004), Honorary Doctor of Aalto University School of Science and Technology (2010).

 Abstract

This talk is an overview of the Multi-scale robotics, based on the Cellular Robotics System, which is the basic concept of the emergence of intelligence in a multi-scale way from Cell Level to the Organizational Level. It consists how the system can be structured from the individual to the group/society levels in analogy with the biological system. It covers a wide range of challenging topics:

  1. Individual robot level, Brachiation Robots and Multi-locomotion robots, medical robotics and simulator
  2. Cooperation and competition of the multiple robotics system
  3. Distributed autonomous robotic system
  4. Micro and nano robotics system
  5. Bio analysis and synthesis: bio-robotics system
Monday 7th July Khawaja Haroon Model Based Spikes Sorting Algorithm for removing overlapping synchronous and near synchronous Correlation Artifacts in Multichannel Multi-Neuron Recordings 

 Abstract

The Primary problem in neurological studies is to get full understanding of the working of large circuits of neurones, especially how they interact and represent information. For decades, Research on neural functions was limited to single electrode single neurone model. It was pre-assumed that study of complex neuronal circuit could be elucidated with such quantification. However with the development of modern MEAs "Multi-electrode Arrays" systems, which have capability to record simultaneous interactions among neurones at multiple electrodes, have uncovered the magnificent interactions among neurones that cannot be observed with single electrode single neurone models. For example, The Neuronal network responsible for correlation activity in retinal ganglion cells "RGCs" is not fully perceived as RGCs exhibit strong stimulus-independent correlated activity. RGC's are located near the inner surface of the retina. Such findings of stimulus independent correlated activity will enable us to better understand the neuronal circuits and will lead towards the cure of different neurological disorder and infections. In addition, a deep understanding of in-vitro electrophysiological studies will also be possible with such discoveries. In this view, any techniques or algorithms which can streamline the problem and make it more tractable is of a great value. When understanding such possibilities of circuit functions, one of the major problems which arise is to detect overlapping spikes. This Research will identify overlapping synchronous or near synchronous spikes which exists in same time bin in that particular identified cluster having overlapping spikes. These are generally neglected by clustering methods. A basic example could be where two spikes are superimposed on each other to produce a third bigger spike with a time shift. Clustering algorithms generally fail to identify such critical data, and hence produce inaccurate results, while much of the critical information is lost as clustering does not even take this problem into account.

Monday 30th June Lei Wei Firearm Training Simulation System through Haptics, Physics Engine and Motion Capture 

 Abstract

Firearm training is of paramount importance in various military and law-enforcement training tasks. Nonetheless, training procedures using actual firearms are dangerous and expensive, and evaluation to such training tasks are difficult. Existing firearm training simulation systems are either visual-only, which lacks the immersion of various forces and torques, or based on modified firearms shooting bullets with CO2 gas, which are still fairly dangerous and expensive. In this presentation, we proposed a firearm training simulation system, which provides dynamic, immersive, accurate and repeatable training experience while imposes virtually no danger to trainees and relatively cost effective. Haptics, physics engine and motion capture were incorporated into different stages of the proposed system, forming a complete pipeline from firearm shooting, to force generation, shooting reactions, as well as result analysis and evaluation. The proposed system is also modularised and extensible, each module can adapt to similar off-the-shelf hardware and software packages. This feature provides great flexibility to the system setup, with reference to scale, budget and other factors. Based on the proposed system, we implemented demonstrations with different configurations and aims and collected corresponding evaluation results to identify the system accuracy, immersion and general usability.

Monday 23rd June Mats Isaksson Analysis of the Inverse Kinematics Problem for 3-DOF Axis-Symmetric Parallel Manipulators with Parasitic Motion 

 Abstract

Determining an analytical solution to the inverse kinematics problem for a parallel manipulator is typically a straightforward problem. However, lower mobility parallel manipulators with 2-5 degrees of freedom "DOFs" often suffer from an unwanted parasitic motion in one or more DOFs. For such manipulators, the inverse kinematics problem can be significantly more difficult. This paper contains an analysis of the inverse kinematics problem for a class of 3-DOF parallel manipulators with axis-symmetric arm systems. All manipulators in the studied class exhibit parasitic motion in one DOF. For manipulators in the studied class, the general solution to the inverse kinematics problem is reduced to solving a univariate equation, while analytical solutions are presented for several important special cases.

Monday 16th June Hailing Zhou Vector Based Image Representation 

 Abstract

We present a subdivision-based vector graphics for image representation and creation. The graphics representation is a subdivision surface defined by a triangular mesh augmented with color attribute at vertices and feature attribute at edges. An automatic algorithm is developed to convert a raster image into such a vector graphics representation. Compared to existing vector-based image representations, the proposed representation and algorithm have the following advantages in addition to the common merits such as editability and scalability: 1. they allow flexible mesh topology and handle images or objects with complicated boundaries or features effectively; 2. they are able to faithfully reconstruct curvilinear features, especially in modeling subtle shading effects around feature curves; and 3. they offer a simple way for the user to create images in a freehand style.

Monday 9th June Abbas Khosravi Optimal design of type reduction algorithms for interval type-2 fuzzy logic systems 

 Abstract

Recent literature shows that interval type-2 fuzzy logic systems "IT2FLSs" possess an excellent approximation capability even better than traditional nonparametric methods such as neural networks "NNs". Type reduction "TR" is one of the key components of IT2FLSs with a huge impact on their performance. This research aims to comprehensively investigate and quantify effects of TR algorithms on the quality of forecasts generated by IT2FLS models. It also proposes a new nonparametric nonlinear TR algorithm that optimally generates the defuzzified model output directly from the firing strengths and consequent lower and upper values of each rule. The NN type reducer is trained through minimization of an error-based cost function using evolutionary optimization algorithms. Once the optimal NN-based type reducer is trained, IT2FLS models can be easily used in prediction and classification problems. Numerical testing using real datasets indicate IT2FLS models equipped with the new optimal TR algorithm outperform IT2FLS models using traditional TR algorithms in terms of forecast accuracy and consistency. This benefit is achieved in no cost, as the computational requirement of the proposed optimal TR algorithm is the same as traditional TR algorithms.

Monday 2nd June

2:00pm
Caroline Ondracek Professional Development  Where to Publish? Quality, Reputation and Impact 
Monday 26th May Bruce Gunn Development of resource based simulation models from process data 

 Abstract

The development of process simulation models often requires significant time investment in the initial stages of the process model formulation. Process Mining (PM) is a methodology that has emerged over the course of the last fifteen years, where a process model of a business enterprise can be discovered from a series of data event logs. Process models, particularly models investigating resource constrained systems, require that the resources utilized in the model be explicitly defined during the model formulation. The process mining methodology, however, fails to take resource utilization into account, despite the potential to extract a resource-based process model from data. This presentation highlights an initial investigation into the development of system resource models from data. To develop such a model the two main challenges are the allocation of resources, both human and equipment, and an estimation of those resource utilization. The resource utilization can be calculated from process activity times and the overall time allocation for each resource. The resource allocation problem is more difficult, and requires the development of associate rules derived from the data-set. A methodology is proposed for the generation of resource-based process models for a range of system complexities, and is highlighted with a case study into a test manufacturing facility.

Monday 19th May

CISR Haptics Lab
John McCormick Applied Research in an Artistic Context 

 Abstract

In this presentation John McCormick and Steph Hutchison will demonstrate the application of current research to the generation of artworks, in particular dance performance. All of the techniques used will be familiar to you; Artificial Neural Networks, Hidden Markov Model, Motion Capture, Movement Tracking and Analysis, Iris ID, Echocardiogram, 3D visualization of data sets, Agent systems, the only difference is the context in which they are applied. Artistic research can provide opportunities for applied research at a high level without the requirement for the creation of a utilitarian product. There is a lot room for experimentation in an artistic setting where both aesthetics and utility inform choices. Considering artistic applications of your research also potentially allows for multiple parallel streams of publishing and presenting. There are many conferences and festivals targeted specifically to the nexus between arts and science, which can profile your work in an engaging manner. It is feasible to publish in both engineering and arts contexts, developing quite different papers from the same body of research. Steph and John will present some short dance performances in the Haptics Lab using the CISR motion capture system. If time allows we will also discuss our desire to apply choreographic principles to robots to create artistic performances. Drawing on dance forms such as Contact Improvisation, SUMO robots can be directed to work collaboratively instead of competitively to create new shared movement capabilities based on their existing abilities. A robot soccer team could work collaboratively to develop complex movement structures with new goals. A drone could give a bird's eye view of Autonomous Ground Vehicle collaborative choreography. The simple transformation from competitive to collaborative engagement could yield many new capabilities within a robotic performance.

Monday 12th May Sara Keretna Named Entity Recognition from informal and unstructured data in the medical domain 

 Abstract

Text mining is a challenging field of research due to the unstructured nature of the data being processed. Increased usage of Electronic Health Records "EHS" in hospitals is making it possible to explore text mining in the medical domain. This talk focuses on drug name extraction, an activity in medical text mining that attempts to extract drug names from raw text. Drug name extraction is a crucial task that is essential for building a complete knowledge base for patients. It is frequently achieved by lexicon-based techniques combined with heuristics. However, these techniques face the difficulty of maintaining an up-to-date and complete lexicon. Methodologies to detect drug names from unstructured medical text that overcome the limitations of the existing techniques are discussed.

Monday 5th May Reza Mohajerpoor Observer Design for Time-Delay Systems 

 Abstract

Time delay is an inherent properties of many systems in various applications including teleoperation, robotics, geographically distributed systems. It can be present in the state, input, measurement output, and any combination of these points of a dynamical system. The system can be Linear Time-Invariant (LTI), Linear Time-Varying (LTV), or Nonlinear. The time delay can be single or multiple; constant or time-varying; known or unknown. This arises almost infinite number of problems regarding to stability analysis, controller and observer design for time-delay systems which has been an active area of research through the past 60 years, and remains active as long as the control science is alive. In this presentation, an overview of the time-delay systems and the complexities they may arise into a control system is addressed. Different modelling approaches, analysis and synthesis of time delay systems are illustrated. Moreover, an introduction to LTV systems and functional observers are briefly described. Our current achievements and future research direction are listed in the end.

Thursday 1st May

9:30am
CISR Haptics Lab
Giovanni Nolli External presentation  XSENS Gyro Motion Capture Suits 

 Biography

Mr Giovanni Nolli, earned his MSc. in Biomedical Engineering. Since the end of 2010 he has been working as Senior Product Specialist at Xsens Movement Science Department. Before joining Xsens, he worked for three years at BTS Bioengineering as Application Specialist and a year At Oklahoma State University as Clinical Biomechanist.

 Abstract

XSENS, a company building gyro-based motion capture suits, will give a presentation about their MVN BIOMECH suit designed specifically for biomechanics and ergonomics projects

Monday 14th April Sahar Araghi Intelligent Traffic Signal Timing Control Using Machine Learning Methods 

 Abstract

The increasing amount of traffic in cities has a significant effect on the road traffic congestion and therefore the time it takes to reach a certain destination, the amount of air pollution and related disease. Extending roads and increasing their capacity is not a sufficient solution, as there will be always an end point, like bottlenecks or intersections. Although bottlenecks cannot be prevented, there is a lot of room for the way intersections are controlled. A common way to control the intersections is using traffic signal light and adjusting the time of each traffic phase. In my research, machine learning methods are applied to control signal timing.

Monday 7th April

5:50pm
(na1.418)
Prof. Bill Moran External presentation  The Ubiquitous Sensor 

 Biography

Professor Bill Moran, from the Department of Electrical and Electronic Engineering, has been appointed as Director of the Defence Science Institute (DSI), a joint venture between the University of Melbourne and the Defence Science and Technology Organisation (DSTO).

Professor Moran is an expert in radar technology, coding and information theory, waveform adaptive sensing, information geometry and compressive sensing, high resolution radar for environmental monitoring, scalable robust video surveillance over constrained networks, mathematics of distributed radar, radar on a chip (ROACH), detection and tracking of targets using distributed antenna, sonar simulation modelling, rapid prototyping, and sensor networks.

Professor Moran is a Fellow of the Australian Academy of Science (FAA), a Member of the Institute of Electrical and Electronic Engineers, and a Member of the London, Australian and American Mathematical Societies.

 Abstract

Sensors are becoming an increasingly important part of our society. Cameras, radars, IR sensors, microphones, are everywhere. If correctly used in disaster management contexts such as bushfires they would be able to assist in deployment of first responders and evacuation of residents.

The aim of this talk is to discuss the theory of sensing, mostly in fairly general terms but with examples taken from disaster management and defence. One aspect of sensing that is being considered in the research community is adaptivity. Sensors can change in many ways: cameras can move, change focal length, change aperture. Radars can change their illumination pattern.

How can we better use this adaptive aspect of sensors to extract the most information from a scene? What is information anyway? And how much does it cost to collect? How can we automate the adaptivity of sensing to optimize the results.

Monday 7th April

5:10pm
(na1.418)
Prof. Laszlo T. Koczy External presentation  Fuzzy signatures 

 Biography

Professor and President of the University Research Council, Szechenyi Istvan University (SZE, Gyor) and Budapest University of Technology and Economics (BME) Hungary

Laszlo Koczy received the M.Sc., M.Phil. and Ph.D. degrees from the Technical University of Budapest (BME) in 1975, 1976 and 1977, respectively; and the (postdoctoral) D.Sc. degree from the Hungarian Academy of Science, all in Electrical/Control Engineering. He spent most of his career at BME until 2001 and from 2002 at SZE. However, he has been a visiting professor at various universities abroad, namely in Australia (ANU, Murdoch and UNSW), Japan (TIT), Korea (POSTECH), Austria (J. Kepler U.), Italy (U. of Trento) and Brazil, China, Finland and Poland for summer schools. He was one of the LIFE Endowed Fuzzy Theory Chair Professors at Tokyo Institute of Technology and advisor to the Laboratory for International Fuzzy Engineering Research in Yokohama. His focus of research interest is fuzzy systems and Computational Intelligence topics (evolutionary algorithms, neural networks), as well as applications. He has published over 370 refereed papers and several textbooks on the subject. He introduced the concept of rule interpolation in sparse fuzzy models, and applied it successfully to the control of an automatic guided vehicle; further hierarchical interpolative fuzzy systems and fuzzy Hough transform. This latter provided the key technology in the winning vehicle in the 2007 Hungarian Mars Rover Competition. His research interests include applications of CI for telecommunication, transportation, vehicles and mobile robots, control, information retrieval, etc.

Among others he had been an Associate Editor of IEEE TFS and he is an Associate Editor of Fuzzy Sets and Systems, Int. J. of Fuzzy Systems, J. of Advanced Computational Intelligence, Mathware and Soft Computing, etc.

He was the General Chair of FUZZ-IEEE 2004 in Budapest, and a number of other conferences, co-chair, PC member, etc. at many other scientific events. He served in the International Fuzzy Systems Association as President, and is now Administrative Committee member of IEEE Computational Intelligence Society.

At SZE he serves his second term as Dean of Engineering, he chairs the Ph.D. School Council and is one of the sponsors of the Szechenyi Alternative Fuel Engine Vehicles Competition, the National Conference of Mechanical Engineering Students, etc.

 Abstract

Fuzzy signatures (FS) are complex structured uncertain descriptors which are suitable for manipulations even when their respective actual structures are not entirely identical. This presentation will give an introduction to the definitions and basic operations in connection with FS.

In many engineering problems there is a series of features which may be grouped into subsets with components related closer to each other, even to sub-subsets within these subsets. Such structures may be represented by either a tree graph, or an iteratively nested vector (with sub-vectors as components).

A very special extension of the idea of FS is given by the Fuzzy Situational Maps (FSM) where the sub-trees represent matrices of two or more dimensions with more or less fixed spatial structure. Zoom in and zoom out operations combined with proper fuzzy aggregations help to increase or decrease the detail view of a given part of the area described by the FSM.

A series of possible applications of FSM will be presented such as description of condition of residential buildings, warehouse layouts and scenarios for intelligent collaborating robots.

Monday 7th April

(na1.417)
Tim Hancock Professional Development  Human Research Ethics at Deakin University 
Monday 31st March Hussein Haggag LGT/VOT Tracking and Performance Evaluation of Depth Images 

 Abstract

This presentation presents object tracking in depth, RGB and normal-maps images using LGT tracker. The depth and RGB images are rendered using depth imaging plugins. A series of experiments were held to evaluate the tracker performance in tracking objects in different image sequences. The experiments conducted were from the Visual Object Tracking (VOT) challenge that was arranged in association with ICCV'13. The accuracy was chosen as the evaluation measure, where the the tracker's bounding box was compared against the ground truth bounding box. Results show that tracking object using depth images gives better results and is more accurate than tracking using either the RGB or normal maps images.

Monday 24th March Fuleah Abdul Razzaq Non-Uniform Sparsity in MRI 

 Abstract

Magnetic Resonance Imaging(MRI) is one of the mostly used imaging techniques in hospitals for capturing images of human body for disease diagnosis and analysis. It differentiates very well between different kinds of tissues which makes it very useful for brain and cancer imaging. Ideally, MRI can be used for capturing live video stream which can be used during surgery, for diagnosis and educational purposes. However, there are some limitations in MR imaging. The imaging process is slow and bound to hardware constraints. It is costly in terms of time as well as motion sensitive which makes it hard for patients. My work contributes towards improving MR imaging process in terms of imaging speed and quality. Enhancing software capabilities can overcome hardware limitations to some extent. This is work is based on the software, signal and image processing module of MRI.

This research explores sparsity distribution MR images. Sparsity of any image can be defined as the information content in that image. MR machines capture Fourier signals which are later converted into images. The first part of my work analyses and identifies sparsity distribution of MR images. Different kinds of Images are used for analysis to understand sparsity distribution in more generic ways rather than making it application specific. Moreover, sparsity is also analysed in different domains other than image and Fourier. The experiments were further extended to localising the sparsity with sub-region of images thus, getting a better understanding of non-uniform nature of MR image sparsity.

The second part presents a novel method to use localise sparsity for MR image de-noising. MR images are corrupted by random Gaussian or Rician Noise. The proposed technique use a simple method to remove this noise based on rules and understanding of localised sparsitywhich was developed earlier. This method analyses and preserves energy contents of imageafter dividing it into a multiple local sections. The simple idea behind this technique is to maximise energy while minimizing the number of non-zero coefficients. Thus, discarding as much noise data as possible and keeping only few carefully chosen coefficients for improved Signal to Noise Ratio (SNR).

The third part uses local sparsity and combines it with Compressive Sensing to achieve Rapid Imaging. The modified proposed approach to Compressive Sensing is named as Locally Sparsified Compressive Sensing. It uses multiple local sparsity constraints and L1 minimisation to reconstruct image from under-sampled data. Measuring fewer samples and reconstructing image from under-sampled data means reducing the image acquisition time and delays caused by MRI hardware. Moreover, a structured framework is presented to define shape, size n number of regions to use Compressive Sensing with local sparsity constraints. Different kinds of MR images were used for experiments and results were compared to simple Compressive Sensing. In comparison to simple Compressive Sensing, this method resulted in reducing sample set up to 30%.

In last part, Locally Sparsified Compressive Sensing was extended for two further applications. Firstly, to improve image quality and decreasing noise occurred due to under-sampled data measurements in simple Compressive Sensing. The basic idea was to use Locally Sparsified Compressive Sensing and exploiting the freedom of using multiple sparsity constraints and sampling levels within an image to improve image quality and reduce noise. Secondly, this developed framework is extended for Dynamic MRI which deals with multiple images captured closely over time to capture some change and motion.

Monday 17th March

2:00pm
CISR Meeting Room
A/Prof. Chee Peng Lim Professional Development  The Craft of Scientific Writing - 3 

 Abstract

Paper writing sessions following the famous Michael Alley's course of "The Craft of Scientific Writing".

Monday 17th March Anwar Hosen Aggregation of PI-based Forecast to Enhance Prediction Accuracy 

 Abstract

In contrast to point forecast, prediction interval-based neural network offers itself as an effective tool to quantify the uncertainty and disturbances that associated with process data. However, single best neural network (NN) does not always guarantee to predict better quality of forecast for different data sets or a whole range of data set. Literature reported that ensemble of NNs using forecast combination produces stable and consistence forecast than single best NN. In this work, a NNs ensemble procedure is introduced to construct better quality of PIs. Weighted averaging forecasts combination mechanism is employed to combine the PI-based forecast. As the key contribution of this paper, a new PI-based cost function is proposed to optimize the individual weights for NN in combination process. An optimization algorithm, named simulated annealing (SA) is used to minimize the PI-based cost function. Finally, the proposed method is examined in two different case studies and compared the results with the individual best NNs and available simple averaging PIs aggregating method. Simulation results demonstrated that the proposed method improved the quality of PIs than individual best NNs and simple averaging ensemble method.

Monday 10th March Mohammed Hossny Video and Image Fusion 

 Abstract

It is not uncommon in many image acquisition applications to resolve a tradeoff between obtaining a high resolution image and a burst of low resolution live images. In this presentation, we introduces a novel framework for imposing the spatial derivative change of low resolution burst sequence to a single high resolution image. The result is a sequence of high resolution warped images. Many application domains such as remote sensing, low radiation live radiology and battlefield automation will benefit from this novel fusion framework.

Monday 3rd March

2:00pm
CISR Meeting Room
A/Prof. Chee Peng Lim Professional Development  The Craft of Scientific Writing - 2 

 Abstract

Paper writing sessions following the famous Michael Alley's course of "The Craft of Scientific Writing".

Monday 24th February Luke Nyhof Non-linear weighted multi-point reference for Adaptive EEG filters: An Application to dynamic motion 

 Abstract

In this presentation, a new method of determining an optimal reference weighting in a two dimensional plane is demonstrated. The focus is on the time-frequency contamination of surface EEG (sEEG) signals by Electromyographic (EMG) noise sources. In particular I propose a new method of minimising the level of signal corruption due to muscle noise based on a cross-correlated multi-point weighted reference system which is then applied to several adaptive filters, focusing on the Weiner Filter and the Least Means Squares adaptive filter. This method has been applied to both simulated EEG and real EEG recorded from healthy subjects. Results show that the proposed method is able to increase the signal-to-noise ratio for EEG signals which are contaminated with muscle noise artefacts; furthermore an application to real biosignal acquisitions recorded during physical movement to a level where analysis has been previously prohibitive.

Monday 17th February

2:00pm
CISR Meeting Room
A/Prof. Chee Peng Lim Professional Development  The Craft of Scientific Writing - 1 

 Abstract

Paper writing sessions following the famous Michael Alley's course of "The Craft of Scientific Writing".

Monday 17th February Houshyar Asadi Human Perception-based Washout Filtering 

 Abstract

Driving simulators are very useful research tools for the governmental institution and research laboratories which are studying in different fields of vehicular and transport design to increase road safety. The aim of this study is to propose the best motion cueing algorithm that can accurately transform vehicle accelerations and angular velocities into simulator platform motions at high fidelity, within the simulator's physical limitations. This is to present the driver with a realistic virtual driving experience and less human sensation error. This presentation will review the various washout filter algorithm architectures, along with the suitable vestibular system models. The review has highlighted the drawbacks and gaps within the different kinds of washout algorithms and vestibular models. Finally, the proposed methodology utilized for the development of an improved optimal motion cueing algorithm is presented.

Monday 10th February Husaini Aza Mohd Adam Colour Identification Based On Haptic Vibrational Frequencies 

 Abstract

The human's visual sensory modality is capable of receiving a large amount of visual information. In today's world, an increasing amount of information is presented visually using digital screen displays. The ability to adequately perceive such visual information has a significant impact on day to day life. An example of such information is 2D visual art, where without adequate vision the information cannot be perceived and the art appreciated. Sensory substitution is one solution to representing visual information to the visually impaired. This paper introduces a haptic system which has been developed to represent colours through haptic vibrations. A new method for mapping colours to vibrations is proposed and evaluated. Vibration representing colour is generated using the Novint Falcon haptic device enabling users to identify colours within a 2D image. A frequency range of 20 Hz to 290Hz is utilised and users are able to differentiate thirteen distinct frequencies corresponding to thirteen colours. The results also show that participants are more successful in differentiating colours towards either end of frequency range than they are in the mid-range which aligns well with observations by other researchers about the frequency response of the human's tactile sensory modality.

Monday 3rd February Sherif Haggag Cepstrum Based Unsupervised Spike Classification 

 Abstract

In this research, we study the effect of feature selection in the spike detection and sorting accuracy. We introduce a new feature representation for neural spikes from multichannel recordings. The features selection plays a significant role in analysing the response of brain neurones. The more precise selection of features leads to a more accurate spike sorting, which can group spikes more precisely into clusters based on the similarity of spikes. Proper spike sorting will enable the association between spikes and neurones. Different with other threshold-based methods, the cepstrum of spike signals is employed in our method to select the candidates of spike features. Simulation results demonstrate that the proposed method not only achieve more accurate clustering results but also reduce computational burden, which implies that it can be applied into real-time spike analysis.

 

Deakin University acknowledges the traditional land owners of present campus sites.

18th July 2014