Stephan Chalup

Stephan Chalup
The University of Newcastle, Callaghan, Australia · Discipline of Computing and Information Technology

Ph.D. (Machine Learning), Dipl.-Math.

About

165
Publications
45,828
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
1,338
Citations
Introduction
Current work is on machine learning applications with focus on deep learning, manifold learning, computational topology and kernel methods. The application domains are computer vision, big data, visualisations, robot systems as well as aspects of related software engineering.
Additional affiliations
February 2001 - present
The University of Newcastle, Australia
Position
  • Course Coordinator
Description
  • Subjects including: Machine Intelligence, Computer Vision and Deep Learning, Big Data Analytics, Computer Graphics, Advanced Machine Learning
January 2001 - present
The University of Newcastle, Australia
Position
  • Professor (Associate)
June 1997 - September 2000
Queensland University of Technology
Position
  • PhD Student

Publications

Publications (165)
Article
Time series clustering is an important data mining topic and a challenging task due to the sequences’ potentially very complex structures. In the present study we experimentally investigate the combination of support vector clustering with a triangular alignment kernel by evaluating it on an artificial time series benchmark dataset. The experiments...
Article
Full-text available
This study is founded on the idea that an analysis of the visual gaze dynamics of pedestrians can increase our understanding of how important architectural features in urban environments are perceived by pedestrians. The results of such an analysis can lead to improvements in urban design. However, a technical challenge arises when trying to determ...
Conference Paper
Full-text available
Emotions are generated and modulated by many factors in the ever-changing surrounding environment. A new and challenging task is to emulate emotional responses on a robot that are caused by visual stimuli, such that the robot's responses mirror that of the human user. This paper presents the initial stage of an affective system that has been traine...
Conference Paper
Full-text available
This study is part of a project which investigates computational principles which underlie perception and representation of architectural streetscape character. Some of the principles can be associated with fundamental concepts in brain theory and Gestalt psychology. For the experimental analysis streetscapes were represented by sequences of digita...
Article
Full-text available
Robot learning is a growing area of research at the intersection of robotics and machine learning. The main contributions of this paper include a review of how machine learning has been used on Sony AIBO robots and at RoboCup, with a focus on the four-legged league during the years 1998-2004. The review shows that the application-oriented use of ma...
Article
Speech emotion recognition is an important aspect of emotional state recognition in human-machine interaction. Approaches using speech-to-image transforms have become popular in recent years because they can utilise deep neural network models that have proven to be successful in the image processing domain. In this paper, we propose a new speech-to...
Article
Full-text available
The world’s largest coal export operation is located in New South Wales, Australia. The state has more than 87% of the coal transportation done through railways, and one of the strategies to increase throughput is the use of sophisticated computational techniques for rail traffic optimisation. The current state of the art shows a lack of practical...
Chapter
A suitable combination of data in a multimodal emotion recognition model allows conveying and combining each channel’s information to achieve a better recognition of the encoded emotion than would be possible using only a single modality and channel. In this paper, we focus on combining speech and physiological signals to predict the arousal and va...
Article
This study presents a new computer vision approach to perform affective analysis of a scene or object. The approach utilises a simulation of the phenomenon of face pareidolia that can be described as the perception of non-existent faces, for example, in random textures, clouds or rock formations. The emergence of face pareidolia in product designs...
Article
Full-text available
An optimal representation of acoustic features is an ongoing challenge in automatic speech emotion recognition research. In this study, we proposed Cepstral coefficients based on evolutionary filterbanks as emotional features. It is difficult to guarantee that an individual optimized filterbank provides the best representation for emotion classific...
Article
Full-text available
Purpose: The aim of this study was to develop and assess the performance of supervised machine learning technique to classify magnetic resonance imaging (MRI) voxels as cancerous or noncancerous using noncontrast multiparametric MRI (mp-MRI), comprised of T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), and advanced diffusion tensor i...
Article
Full-text available
Wavelet neural networks (WNN) combine the strength of artificial neural networks and the multiresolution ability of wavelets. Determining the structure and, more specifically, the appropriate number of neurons in a WNN is a time-consuming process. We propose a type of multidimensional evolutionary WNN and, using an acrobot, evaluate this approach w...
Chapter
The performance improvement of Convolutional Neural Network (CNN) in image classification and other applications has become a yearly event. Generally, two factors are contributing to achieving this envious success: stacking of more layers resulting in gigantic networks and use of more sophisticated network architectures, e.g. modules, skip connecti...
Article
Full-text available
In this paper, we develop an optimised state-of-the-art 2D U-Net model by studying the effects of the individual deep learning model components in performing prostate segmentation. We found that for upsampling, the combination of interpolation and convolution is better than the use of transposed convolution. For combining feature maps in each convo...
Chapter
Full-text available
Particle swarm optimisation (PSO), oneMirjalili, Seyedehzahra ofZhang, Hongyu theMirjalili, Seyedali most elegant algorithms in the field of nature-inspired optimisation, has many variants for solving different types of problems. One of these variantsChalup, Stephan isNoman, Nasimul binary particle swarm optimisation (BPSO), which is suitable for s...
Chapter
This work describes the optimization of two robot movements in the context of the Humanoid league competition at RoboCup. A multi-objective genetic algorithm (MOGA) was used in conjunction with the real-time physics simulator Gazebo. The motivation for this work was that the NUbots team, from the University of Newcastle, lacked a simulation platfor...
Chapter
This study compares a deep learning approach with the traditional computer vision method of ellipse detection on the task of detecting semi-transparent drinking glasses filled with water in images. Deep neural networks can, in principle, be trained until they exhibit excellent performance in terms of detection accuracy. However, their ability to ge...
Article
Full-text available
Prostate cancer treatment planning can be performed using magnetic resonance imaging (MRI) only with sCT scans. However, sCT scans are computer generated from MRI data and therefore robust, efficient, and accurate patient-specific quality assurance methods for dosimetric verification are required. Bulk anatomical density (BAD) maps can be generated...
Article
Full-text available
The aim of manifold learning is to extract low-dimensional manifolds from high-dimensional data. Manifold alignment is a variant of manifold learning that uses two or more datasets that are assumed to represent different high-dimensional representations of the same underlying manifold. Manifold alignment can be successful in detecting latent manifo...
Article
In the field of robust optimization, the robustness of a solution is confirmed using a robustness indicator. In the literature, such an indicator uses explicit or implicit averaging techniques. One of the main drawbacks of the implicit averaging techniques is unreliability since they only use the sampled points generated by an optimization algorith...
Chapter
This paper proposes an enhancement of convolutional neural networks for object detection in resource-constrained robotics through a geometric input transformation called Visual Mesh. It uses object geometry to create a graph in vision space, reducing computational complexity by normalizing the pixel and feature density of objects. The experiments c...
Chapter
RoboCup Junior is a project-oriented educational initiative that sponsors regional, national and international robotic events for young students in primary and secondary school. It leads children to the fundamentals of teamwork and complex problem solving through step-by-step logical thinking using computers and robots. The Faculty of Engineering a...
Preprint
Full-text available
Big Data in IoT is a large and fast-developing area where many different methods and techniques can play a role. Due to rapid progress in Machine Learning and new hardware developments, a dynamic turnaround of methods and technologies can be observed. This overview therefore tries to be broad and highlevel without claiming to be comprehensive. Its...
Article
HyLogger profile scanning is commonly utilised for drill-core logging but the limited scanning area may not detect all important geological features. The study presented in this paper aims to develop a mineral mapping solution for this core-logging process by leveraging the colour image captured during the scanning process. A machine learning-based...
Chapter
With the introduction of communication infrastructure into the traditional power grids, smart power grids are emerging to meet the future electricity demands. In smart grid, advanced metering infrastructure (AMI) is one of the main components that enables bi-directional communication between home area networks and utility providers. In an AMI netwo...
Conference Paper
This work presents an application of ORB-SLAM in an iGus bipedal humanoid robotic platform. The method was adapted from its original implementation into the framework used by the NUbots robotic soccer team and used for localization purposes. The paper presents a description of the challenges to implement the adaptation, as well as several tests whe...
Preprint
Full-text available
RoboCup Junior is a project-oriented educational initiative that sponsors regional, national and international robotic events for young students in primary and secondary school. It leads children to the fundamentals of teamwork and complex problem solving through step-by-step logical thinking using computers and robots. The Faculty of Engineering a...
Preprint
Full-text available
This study presents the results of a series of simulation experiments that evaluate and compare four different manifold alignment methods under the influence of noise. The data was created by simulating the dynamics of two slightly different double pendulums in three-dimensional space. The method of semi-supervised feature-level manifold alignment...
Article
Measuring the performance of an aeromagnetic compensation system is usually difficult. The standard deviation of the signal has been used as an index in the industry. While the standard deviation is drawn from frequency statistics, it cannot represent the performance on a single sampling point. On the other hand, as the true geomagnetic intensity i...
Preprint
The goal of this study is to test two different computing platforms with respect to their suitability for running deep networks as part of a humanoid robot software system. One of the platforms is the CPU-centered Intel NUC7i7BNH and the other is a NVIDIA Jetson TX2 system that puts more emphasis on GPU processing. The experiments addressed a numbe...
Preprint
Full-text available
This paper proposes an enhancement of convolutional neural networks for object detection in resource-constrained robotics through a geometric input transformation called Visual Mesh. It uses object geometry to create a graph in vision space, reducing computational complexity by normalizing the pixel and feature density of objects. The experiments c...
Article
Full-text available
Wavelet Neural Networks are a combination of neural networks and wavelets and have been mostly used in the area of time-series prediction and control. Recently, Evolutionary Wavelet Neural Networks have been employed to develop cancer prediction models. The present study proposes to use ensembles of Evolutionary Wavelet Neural Networks. The search...
Chapter
Being able to detect anomalies for predicting machine breakdown is of critical importance in the mining industry. These anomalies are usually found in unlabelled sensor data, and therefore unsupervised models represent the preferred choice for the task. In this chapter, we propose the use of a bio-inspired clustering model based on the Self-Organis...
Conference Paper
Context: Nowadays most businesses in Australia maintain a website to advertise their products and services and some to also conduct online sales and payments. Many have an additional Facebook page or utilise other on-line tools and phone apps. Data is now considered to be one of the most valuable assets of companies, and many are using Cloud servic...
Conference Paper
This paper presents the implementation details of a proposed solution to the Emotion Recognition in the Wild 2017 Challenge, in the category of group-level emotion recognition. The objective of this sub-challenge is to classify a group's emotion as Positive, Neutral or Negative. Our proposed approach incorporates both image context and facial infor...
Conference Paper
This study presents an approach of using synthetically rendered images for training deep neural networks on object detection. A new plug-in for the computer graphics modelling software Blender was developed that can generate large numbers of photo-realistic ray-traced images and include meta information as training labels. The performance of the de...
Article
During the process of non-linear dimensionality reduction, manifolds represented by point clouds are at risk of changing their topology. We review techniques for quality assessment of manifold learning and propose to use persistent homology to evaluate the topological impact of manifold learning by comparing the Betti numbers of test manifolds befo...
Article
Wavelet Neural Networks (WNNs) are complex artificial neural systems and their training can be a challenge. In the past, most common training schemes for WNNs, such as gradient descent, have been restricted to training only a subset of differentiable parameters. In this paper, we propose an evolutionary method to train both differentiable and non-d...
Conference Paper
Full-text available
The aim of this pilot study was to compare the performance of four manifold alignment methods on an elementary pendulum task. The methods included Manifold Alignment using Procrustes Analysis, Manifold Alignment Preserving Local Geometry, Manifold Alignment using Graph Embedding and Manifold Alignment Preserving Global Geometry. Experimental data w...
Presentation
Full-text available
RoboCup Junior is a project-oriented educational initiative that sponsors regional, national and international robotic events for young students. It is designed to introduce primary and secondary school children to the fundamentals of teamwork and complex problem solving through step-by-step logical thinking using computers (robots) as a tool to co...
Article
Full-text available
This paper discusses the design and interface of NUClear, a new hybrid message-passing architecture for embodied humanoid robotics. NUClear is modular, low latency and promotes functional and expandable software design. It greatly reduces the latency for messages passed between modules as the messages routes are established at compile time. It also...
Conference Paper
Many recent approaches to ball detection in robot soccer reduce the task to edge-based circle detection, or training a classifier to detect specific balls with known colour or surface texture. In the present work, a more general approach to ball detection is investigated, where spherical 3D objects must be detected under unknown lighting, colouring...
Conference Paper
Current web applications rely on a client-server architecture. Web browsers contact a server to retrieve content which is displayed to the user. With this approach the server responds to all requests which can result in a performance bottleneck. Peer-to-peer systems allow clients to retrieve content from other connected clients, thus reducing the l...
Conference Paper
Parkinson's Disease is the second most common neurological condition in Australia. This paper develops and compares a new type of Wavelet Neural Network that is evolved via Cartesian Genetic Programming for classifying Parkinson's Disease data based on speech signals. The classifier is trained using 10-fold and leave-one-subject-out cross validatio...
Article
Full-text available
Cooperative reinforcement learning algorithms such as BEST-Q, AVE-Q, PSO-Q, and WSS use Q-value sharing strategies between reinforcement learners to accelerate the learning process. This paper presents a comparison study of the performance of these cooperative algorithms as well as an algorithm that aggregates their results. In addition, this paper...
Article
Full-text available
The hierarchical organisation of distributed systems can provide an efficient decomposition for machine learning. This paper proposes an algorithm for cooperative policy construction for independent learners, named Q-learning with aggregation (QA-learning). The algorithm is based on a distributed hierarchical learning model and utilises three speci...
Article
Full-text available
The hierarchical organisation of distributed systems can provide an efficient decomposition for machine learning. This paper proposes an algorithm for cooperative policy construction for independent learners, named Q-learning with aggregation (QA-learning). The algorithm is based on a distributed hierarchical learning model and utilises three speci...
Research
Full-text available
Doxygen Generated document of Source Code: NUbots System Architecture 2010
Conference Paper
This paper proposes a simple and fast method for adapting colour lookup tables to lighting changes in real-time. The method adjusts the classified colour space regions keeping both their surface area and volume constant. Two variations of the method were compared and tested in a RoboCup soccer setting. Detection success rate was measured as a funct...
Conference Paper
Full-text available
A new method is proposed for utilising scene information for stereo eye tracking in stereoscopic 3D virtual environments. The ap-proach aims to improve gaze tracking accuracy and reduce the required user engagement with eye tracking calibration procedures. The approach derives absolute Point of Regard (POR) from the angular velocity of the eyes wit...
Conference Paper
Full-text available
In this study on music learning, we develop an average reward based adaptive parameterisation for reinforcement learning meta-parameters. These are tested using an approximation of user feedback based on the goal of learning the nursery rhymes Twinkle Twinkle Little Star and Mary Had a Little Lamb. We show that a large reduction in learning times c...
Book
This book constitutes the refereed proceedings of the First Australasian Conference on Artificial Life and Computational Intelligence, ACALCI 2015, held in Newcastle, NSW, Australia, in February 2015. The 34 revised full papers presented were carefully reviewed and selected from 63 submissions. The papers are organized in the following topical sect...
Conference Paper
The goal of the City Evolutions Project is to establish interactive systems and games to entertain users. Because of the existing variabilities in the system and potential reuse for similar systems in this domain, the software system is designed and developed in a reuse-based way, i.e. Software Product Line Engineering (SPLE). SPLE is a reuse-based...
Article
Full-text available
http://hdl.handle.net/1959.13/1060047 (link to full text) This article presents a computer vision approach that can detect and classify abstract face-like patterns, including subliminal faces within a scene. This can be regarded as a way of simulating the phenomenon of pareidolia, that is, the tendency of humans to ‘see faces’ in random structures...
Article
Full-text available
The NUbots team, from The University of Newcastle, Australia, has had a strong record of success in the RoboCup Standard Platform League since first entering in 2002. The team has also competed within the RoboCup Humanoid Kid-Size League since 2012. The 2014 team brings a renewed focus on software architecture, modularity, and the ability to easily...