Stephan K. Chalup

Khalil Mathieu Hannouch, Stephan Chalup

The topological analysis of four-dimensional (4D) image-type data is challenged by the immense size that these datasets can reach. This can render the direct application of methods, like persistent homology and convolutional neural networks (CNNs), impractical due to computational constraints. This study aims to estimate the topology type of 4D image-type data cubes that exhibit topological intricateness and size above our current processing capacity. The experiments using synthesised 4D data and a real-world 3D data set demonstrate that it is possible to circumvent computational complexity issues by applying downscaling methods to the data before training a CNN. This is achievable even when persistent homology software indicates that downscaling can significantly alter the homology of the training data. When provided with downscaled test data, the CNN can still estimate the Betti numbers of the original sample cubes with over 80\% accuracy, which outperforms the persistent homology approach, whose accuracy deteriorates under the same conditions. The accuracy of the CNNs can be further increased by moving from a mathematically-guided approach to a more vision-based approach where cavity types replace the Betti numbers as training targets.

Dylan Peek, Matthew P. Skerritt, Siddharth Pritam et al.

Topological Data Analysis (TDA) involves techniques of analyzing the underlying structure and connectivity of data. However, traditional methods like persistent homology can be computationally demanding, motivating the development of neural network-based estimators capable of reducing computational overhead and inference time. A key barrier to advancing these methods is the lack of labeled 3D data with class distributions and diversity tailored specifically for supervised learning in TDA tasks. To address this, we introduce a novel approach for systematically generating labeled 3D datasets using the Repulsive Surface algorithm, allowing control over topological invariants, such as hole count. The resulting dataset offers varied geometry with topological labeling, making it suitable for training and benchmarking neural network estimators. This paper uses a synthetic 3D dataset to train a genus estimator network, created using a 3D convolutional transformer architecture. An observed decrease in accuracy as deformations increase highlights the role of not just topological complexity, but also geometric complexity, when training generalized estimators. This dataset fills a gap in labeled 3D datasets and generation for training and evaluating models and techniques for TDA.

Dylan Peek, Matt P. Skerritt, Stephan Chalup

This research uses deep learning to estimate the topology of manifolds represented by sparse, unordered point cloud scenes in 3D. A new labelled dataset was synthesised to train neural networks and evaluate their ability to estimate the genus of these manifolds. This data used random homeomorphic deformations to provoke the learning of visual topological features. We demonstrate that deep learning models could extract these features and discuss some advantages over existing topological data analysis tools that are based on persistent homology. Semantic segmentation was used to provide additional geometric information in conjunction with topological labels. Common point cloud multi-layer perceptron and transformer networks were both used to compare the viability of these methods. The experimental results of this pilot study support the hypothesis that, with the aid of sophisticated synthetic data generation, neural networks can perform segmentation-based topological data analysis. While our study focused on simulated data, the accuracy achieved suggests a potential for future applications using real data.

Khalil Mathieu Hannouch, Stephan Chalup

Understanding the topological characteristics of data is important to many areas of research. Recent work has demonstrated that synthetic 4D image-type data can be useful to train 4D convolutional neural network models to see topological features in these data. These models also appear to tolerate the use of image preprocessing techniques where existing topological data analysis techniques such as persistent homology do not. This paper investigates how methods from algebraic topology, combined with image processing techniques such as morphology, can be used to generate topologically sophisticated and diverse-looking 2-, 3-, and 4D image-type data with topological labels in simulation. These approaches are illustrated in 2D and 3D with the aim of providing a roadmap towards achieving this in 4D.

Dylan Peek, Matthew P. Skerritt, Stephan Chalup

Persistent Homology (PH) and Artificial Neural Networks (ANNs) offer contrasting approaches to inferring topological structure from data. In this study, we examine the noise robustness of a supervised neural network trained to predict Betti numbers in 2D binary images. We compare an ANN approach against a PH pipeline based on cubical complexes and the Signed Euclidean Distance Transform (SEDT), which is a widely adopted strategy for noise-robust topological analysis. Using one synthetic and two real-world datasets, we show that ANNs can outperform this PH approach under noise, likely due to their capacity to learn contextual and geometric priors from training data. Though still emerging, the use of ANNs for topology estimation offers a compelling alternative to PH under structural noise.

Ysobel Sims, Alexandre Mendes, Stephan Chalup

Zero-shot learning enables models to generalise to unseen classes by leveraging semantic information, bridging the gap between training and testing sets with non-overlapping classes. While much research has focused on zero-shot learning in computer vision, the application of these methods to environmental audio remains underexplored, with poor performance in existing studies. Generative methods, which have demonstrated success in computer vision, are notably absent from zero-shot environmental sound classification studies. To address this gap, this work investigates generative methods for zero-shot learning in environmental audio. Two successful generative models from computer vision are adapted: a cross-aligned and distribution-aligned variational autoencoder (CADA-VAE) and a leveraging invariant side generative adversarial network (LisGAN). Additionally, we introduced a novel diffusion model conditioned on class auxiliary data. Synthetic embeddings generated by the diffusion model are combined with seen class embeddings to train a classifier. Experiments are conducted on five environmental audio datasets, ESC-50, ARCA23K-FSD, FSC22, UrbanSound8k and TAU Urban Acoustics 2019, and one music classification dataset, GTZAN. Results show that the diffusion model outperforms all baseline methods on average across six audio datasets. This work establishes the diffusion model as a promising approach for zero-shot learning and introduces the first benchmark of generative methods for zero-shot environmental sound classification, providing a foundation for future research.

Aaron S. W. Wong, Ryan Jeffery, Peter Turner et al.

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 and Built Environment at the University of Newcastle in Australia has hosted and organized the Hunter regional tournament since 2012. This paper presents an analysis of data collected from RoboCup Junior in the Hunter Region, New South Wales, Australia, for a period of six years 2012-2017 inclusive. Our study evaluates the effectiveness of the competition in terms of geographical spread, participation numbers, and gender balance. We also present a case study about current university students who have previously participated in RoboCup Junior.

Fayeem Aziz, Aaron S. W. Wong, James S. Welsh et al.

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 using global distance resulted in the most convincing visualisations. However, the semi-supervised feature-level local alignment methods resulted in smaller alignment errors. These local alignment methods were also more robust to noise and faster than the other methods.

Alexander Biddulph, Trent Houlistion, Alexandre Mendes et al.

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 number of benchmarking tasks including pedestrian detection using deep neural networks. Some of the results were unexpected but demonstrate that platforms exhibit both advantages and disadvantages when taking computational performance and electrical power requirements of such a system into account.

Trent Houliston, Stephan K. Chalup

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 compare the Visual Mesh with several other fast convolutional neural networks. The results demonstrate execution times sixteen times quicker than the fastest competitor tested, while achieving outstanding accuracy.

Josiah Walker, Trent Houliston, Brendan Annable et al.

The NUbots are an interdisciplinary RoboCup team from The University of Newcastle, Australia. The team has a history of strong contributions in the areas of machine learning and computer vision. The NUbots have participated in RoboCup leagues since 2002, placing first several times in the past. In 2014 the NUbots also partnered with the University of Newcastle Mechatronics Laboratory to participate in the RobotX Marine Robotics Challenge, which resulted in several new ideas and improvements to the NUbots vision system for RoboCup. This paper summarizes the history of the NUbots team, describes the roles and research of the team members, gives an overview of the NUbots' robots, their software system, and several associated research projects.

Josiah Walker, Trent Houliston, Brendan Annable et al.

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 share code. This paper summarizes the history of the NUbots team, describes the roles and research of the team members, gives an overview of the NUbots' robots and software system, and addresses relevant research projects within the the Newcastle Robotics Laboratory.