Will Neil Browne

• BE (Hons), MSc (distinction), EngD. (Doctorate)
• Professor at Queensland University of Technology

Emotion classification plays a crucial role in the domain of human–computer interaction, as it holds substantial significance in effective communication. However, the task of emotion classification presents notable challenges primarily due to the subjective and multifaceted nature of emotions, encompassing varying cultural and individual interpreta...

Evolutionary Computation (EC) often throws away learned knowledge as it is reset for each new problem addressed. Conversely, humans can learn from small-scale problems, retain this knowledge (plus functionality), and then successfully reuse them in larger-scale and/or related problems. Linking solutions to problems has been achieved through layered...

Classification is a supervised machine learning process that categories an instance based on a number of features. The process of classification involves several stages, including data preprocessing (such as feature selection and feature construction), model training and evaluation. Evolutionary computation has been widely applied to all these stag...

Regression and modelling, which identify the relationship between the dependent and independent variables, play an important role in knowledge discovery from data. Symbolic regression goes a step further by learning explicitly symbolic models from data that are potentially interpretable. This chapter provides an overview of evolutionary computation...

Emotions are considered to convey much meaning in communication. Hence, artificial methods for emotion categorization are being developed to meet the increasing demand to introduce intelligent systems, such as robots, into shared workspaces. Deep learning algorithms have demonstrated limited competency in categorizing images from posed datasets wit...

As digital technology continues to evolve rapidly and get integrated into various aspects of our cities and societies, the alignment of technological advancements with societal values becomes paramount. The evolving socio-technical landscape has prompted an increased focus on responsible innovation and technology (RIT) among technology companies, d...

Emotions are considered to convey much meaning in communication. Hence, artificial methods for emotion categorization are being developed to meet the increasing demand to introduce intelligent systems, such as robots, into shared workspaces. Deep learning algorithms have demonstrated limited competency in categorizing images from posed datasets wit...

Compensating for slip and skid is crucial for mobile robots navigating outdoor terrains. In these challenging environments, slipping and skidding introduce uncertainties into trajectory tracking systems, potentially compromising the safety of the vehicle. Despite research in this field, having a real-world feasible online slip and skid compensation...

Skidding is a surface hazard for mobile robots' navigation and traction control systems when operating in outdoor environments and uneven terrains due to the wheel–terrain interaction. It could lead to large trajectory tracking errors, losing the robot's controllability, and mission failure occurring. Despite research in this field, the development...

This article describes a new database (named “EMAP”) of 145 individuals' reactions to emotion‐provoking film clips. It includes electroencephalographic and peripheral physiological data as well as moment‐by‐moment ratings for emotional arousal in addition to overall and categorical ratings. The resulting variation in continuous ratings reflects int...

In an era in which technological advancements have a profound impact on our cities and societies, it is crucial to ensure that digital technology is not only driven by technological progress with economic goals but that it can also fulfill moral and social responsibilities. Hence, it is needed to advocate for ‘Responsible Innovation and Technology’...

Interest in reinforcement learning (RL) has recently surged due to the application of deep learning techniques, but these connectionist approaches are opaque compared with symbolic systems. Learning Classifier Systems (LCSs) are evolutionary machine learning systems that can be categorised as eXplainable AI (XAI) due to their rule-based nature. Mic...

Reinforcement learning (RL) is experiencing a resurgence in research interest, where Learning Classifier Systems (LCSs) have been applied for many years. However, traditional Michigan approaches tend to evolve large rule bases that are difficult to interpret or scale to domains beyond standard mazes. A Pittsburgh Genetic Fuzzy System (dubbed Fuzzy...

Autonomic nervous system (ANS) responses such as heart rate (HR) and galvanic skin responses (GSR) have been linked with cerebral activity in the context of emotion. Although much work has focused on the summative effect of emotions on ANS responses, their interaction in a continuously changing context is less clear. Here, we used a multimodal data...

Lateralization is ubiquitous in vertebrate brains which, as well as its role in locomotion, is considered an important factor in biological intelligence. Lateralization has been associated with both poor and good performance. It has been hypothesized that lateralization has benefits that may counterbalance its costs. Given that lateralization is ub...

The majority of computer vision algorithms fail to find higher-order (abstract) patterns in an image so are not robust against adversarial attacks, unlike human lateralized vision. Deep learning considers each input pixel in a homogeneous manner such that different parts of a ``locality-sensitive hashing table'' are often not connected, meaning hig...

Accounting for wheel–terrain interaction is crucial for navigation and traction control of mobile robots in outdoor environments and rough terrains. Wheel slip is one of the surface hazards that needs to be detected to mitigate against the risk of losing the robot's controllability or mission failure occurring. The open problems in the Terramechani...

Partial face coverings such as sunglasses and face masks unintentionally obscure facial expressions, causing a loss of accuracy when humans and computer systems attempt to categorize emotion. With the rise of soft computing techniques interacting with humans, it is important to know not just their accuracy, but also the confusion errors being made—...

Emotion categorization has become an important area of research due to the increasing number of intelligent systems, such as robots interacting with humans. This includes deep learning models, which have performed remarkably well on many classification-based tasks. However, due to their homogeneous representation of knowledge, the deep learning mod...

Learning Classifier Systems (LCSs) are a group of rule-based evolutionary computation techniques, which have been frequently applied to data mining tasks. The LCSs’ rules are designed to be human-readable to enable the underlying knowledge to be investigated. However, the models for the majority of domains with high feature interaction contain a la...

Modern classifier systems can effectively classify targets that consist of simple patterns. However, they can fail to detect hierarchical patterns of features that exist in many real-world problems, such as understanding speech or recognizing object ontologies. Biological nervous systems have the ability to abstract knowledge from simple and small-...

The parametric uncertainties inherent in the models of renewable and sustainable energy systems (RSESs) make the associated decision-making processes of integrated resource operation, planning, and designing profoundly complex. Accordingly, intelligent energy management strategies are recognised as an effective intervention to efficiently accommoda...

Human intelligence can simultaneously process many tasks with the ability to accumulate and reuse knowledge. Recent advances in artificial intelligence, such as Transfer, Multitask and Layered Learning, seek to replicate these abilities. However, humans must specify the task order, which is often difficult particularly with uncertain domain knowled...

Aggregator-activated demand response (DR) is widely recognised as a viable means for increasing the flexibility of renewable and sustainable energy systems (RSESs) necessary to accommodate a high penetration of variable renewables. To this end, by acting as DR aggregators and offering energy trading capabilities to smaller customers, energy retaile...

Learning Classifier Systems (LCSs) are a paradigm of rule-based evolutionary computation (EC). LCSs excel in data-mining tasks regarding helping humans to understand the explored problem, often through visualizing the discovered patterns linking features to classes. Due to the stochastic nature of EC, LCSs unavoidably produce and keep redundant rul...

Deep neural networks are a powerful model for feature extraction. They produce features that enable state-of-the-art performance on many tasks, including emotion categorization. However, their homogeneous representation of knowledge has made them prone to attacks, i.e. small modification in train or test data to mislead the models. Emotion categori...

Perceptual aliasing challenges reinforcement learning agents. They struggle to learn stable policies through failing to identify and disambiguate perceptually identical states in the environment that require different actions to reach a goal. As the agent often has only a local frame-of-reference it cannot represent the global environment. Frame-of...

Emotion categorization plays an important role in understanding human emotions by artificial intelligence systems such as robots. It is a difficult task as humans express many features, which vary over time when showing an emotion. Thus, existing classification techniques are overwhelmed, and the creation of a subset of appropriate features is need...

Partial face coverings such as sunglasses and face masks unintentionally obscure facial expressions, causing a loss of accuracy when humans and computer systems attempt to categorise emotion. With the rise of soft computing techniques interacting with humans, it is important to know not just their accuracy, but also the confusion errors being made\...

The multipoint dynamic aggregation (MPDA) problem of the multirobot system is of great significance for its real-world applications such as bush fire elimination. The problem is to design the optimal plan for a set of heterogeneous robots to complete some geographically distributed tasks collaboratively. In this article, we consider the dynamic ver...

While industrial demand response programmes have long been valued to support the power grid, recent advances in information and communications technology have enabled new opportunities to leverage the potential of responsive loads in less energy-dense end-use sectors. This brings to light the importance of accurately projecting flexible demand-side...

Deep learning has achieved a high classification accuracy on image classification tasks, including emotion categorization. However, deep learning models are highly vulnerable to adversarial attacks. Even a small change, imperceptible to a human (e.g. one-pixel attack), can decrease the classification accuracy of deep models. One reason could be the...

Emotional information is considered to convey much meaning in communication. Hence, artificial emotion categorization methods are being developed to meet the increasing demand to introduce intelligent systems, such as robots, into shared workspaces. Deep learning algorithms have demonstrated limited competency in categorizing images from posed data...

Bridging the gap between simulation and reality for successful micro-grid (MG) implementation requires accurate mathematical modelling of the underlying energy infrastructure and extensive optimisation of the design space defined by all possible combinations of the size of the equipment. While exact mathematical optimisation approaches to the MG ca...

Multipoint dynamic aggregation is a meaningful optimization problem due to its important real-world applications, such as post-disaster relief, medical resource scheduling, and bushfire elimination. The problem aims to design the optimal plan for a set of robots to execute geographically distributed tasks. Unlike the majority of scheduling and rout...

Emotion categorization can be the process of identifying different emotions in humans based on their facial expressions. It requires time and sometimes it is hard for human classifiers to agree with each other about an emotion category of a facial expression. However, machine learning classifiers have done well in classifying different emotions and...

Emotion recognition has become an increasingly important area of research due to the increasing number of CCTV cameras in the past few years. Deep network-based methods have made impressive progress in performing emotion recognition-based tasks, achieving high performance on many datasets and their related competitions such as the ImageNet challeng...

Learning classifier systems (LCSs) originated from cognitive-science research but migrated such that LCS became powerful classification techniques. Modern LCSs can be used to extract building blocks of knowledge to solve more difficult problems in the same or a related domain. Recent works on LCSs showed that the knowledge reuse through the adoptio...

Evolutionary computation has brought great progress to rule-based learning but this progress is often blind to the optimality of the system design. This work theoretically reveals an optimal learning scheme on the most popular evolutionary rule-based learning approach -the accuracy-based classifier system (or XCS). XCS seeks to form accurate, maxim...

Multitask Learning is a learning paradigm that deals with multiple different tasks in parallel and transfers knowledge among them. XOF, a Learning Classifier System using tree-based programs to encode building blocks (meta-features), constructs and collects features with rich discriminative information for classification tasks in an observed list....

Multitask Learning is a learning paradigm that deals with multiple different tasks in parallel and transfers knowledge among them. XOF, a Learning Classifier System using tree-based programs to encode building blocks (meta-features), constructs and collects features with rich discriminative information for classification tasks in an observed list....

A major goal of machine learning is to create techniques that abstract away irrelevant information. The generalisation property of standard Learning Classifier System (LCS) removes such information at the feature level but not at the feature interaction level. Code Fragments (CFs), a form of tree-based programs, introduced feature manipulation to d...

Learning Classifier Systems (LCSs), a 40-year-old technique, evolve interrogatable production rules. XCSs are the most popular reinforcement learning based LCSs. It is well established that the subsumption method in XCSs removes overly detailed rules. However, the technique still suffers from overly general rules that reduce accuracy and clarity in...

In complex classification problems, constructed features with rich discriminative information can simplify decision boundaries. Code Fragments (CFs) produce GP-tree-like constructed features that can represent decision boundaries effectively in Learning Classifier Systems (LCSs). But the search space for useful CFs is vast due to this richness in b...

On the XCS classifier system, an ideal assumption in the latest XCS learning theory means that it is impossible for XCS to distinguish accurate rules from any other rules with 100% success rate in practical use. This paper presents a preliminary work to remove this assumption. Furthermore, it reveals a dilemma in setting a crucial XCS parameter. Th...

Figure-ground image segmentation is a process of separating regions of interest from a target image. Genetic programming has been employed to evolve segmentors that have the potential to capture high variations of images and conduct accurate segmentation. However, GP-based methods tend to evolve complex segmentors that have large sizes, are computa...

Humans and many animals can selectively sample necessary part of the visual scene to carry out daily activities like foraging and finding prey or mates. Selective attention allows them to efficiently use the limited resources of the brain by deploying sensory apparatus to collect data believed to be pertinent to the organisms current situation. Rob...

http://ecs.victoria.ac.nz/Events/AI2018/WebHome

Most versions of the XCS Classifier System have been designed to evolve only two rules for each rule discovery invocation, which restricts the search capacity. A difficulty behind generating multiple rules each time is the increase in the probability of deleting immature rules, which conflicts with the requirement that parent rules be sufficiently...

Learning Classifier Systems (LCSs) have been widely used to tackle Reinforcement Learning (RL) problems as they have a good generalization ability and provide a simple understandable rule-based solution. The accuracy-based LCS, XCS, has been most popularly used for single-objective RL problems. As many real-world problems exhibit multiple conflicti...

On behalf of the organizing committee, it is our great pleasure to invite you to the annual IEEE Congress on Evolutionary Computation (CEC), which is one of the leading events in the area of evolutionary computation. IEEE CEC provides a forum to bring together researchers and practitioners from all over the world to present and discuss their resear...

Learning Classifier Systems (LCSs) have demonstrated their classification capability by employing a population of polymorphic rules in addressing numerous benchmark problems. However, although the produced solution is often accurate, the alternative ways to represent the data in a single population obscure the underlying patterns of a problem. More...

Figure-ground segmentation is a process of separating regions of interest from unimportant backgrounds. For complex images (e.g. images with high variations), feature construction (FC) is necessary, which can produce high-level features, to help achieve accurate segmentation performance. Genetic programming (GP) is considered as a well-suited FC te...

Learning classifier system (LCSs) have the ability to solve many difficult benchmark problems, but they have to be applied individually to each separate problem. Moreover, the solutions produced, although accurate, are not compact such that important knowledge is obscured. Recently a multi-agent system has been introduced that enables multiple, dif...

This chapter aims to provide an appreciation for core concepts that separate LCSs from other techniques. In particular, we provide insight into why they work, and how they are conceptually unique. It is hoped that the reader will appreciate that LCSs represent a machine learning concept, rather than a single technique. We consider the answers to qu...

LCSs as a concept and framework are suited to a wide range of applications. This chapter describes how the various LCS methods can be chosen and adapted for certain types of problems, such as data mining or robot control. Specifically, this chapter offers a basic setup guide discussing logistics, design considerations, setting run parameters, tunin...

This chapter aims to demonstrate how LCS algorithms have been adapted to different problem domains. This will be accomplished by differentiating major LCS algorithm subtypes, describing specific LCS implementations, and introducing additional variations of LCS components. An understanding of the different options and insight into the performance tr...

This chapter aims to introduce readers to Learning Classifier Systems (LCSs) through the lens of an accessible but non-trivial classification problem. It offers a brief summary of the basic concepts and components of an LCS algorithm, concluding with code exercises that pair with this textbook to offer hands-on experience.

This chapter aims to build upon the brief, simplified description of an LCS functional cycle outlined in Section 1.3. Previously, we discussed how all LCSs include a form of discovery and learning components, and Figure 1.3 specifically illustrated many of the common LCS algorithm components in step-wise order. Here we will discuss these algorithmi...

Figure-ground segmentation is an important image processing task that genetic programming (GP) has been successfully introduced to solve. However, existing GP methods use a homogeneous mixture of preprocessing and postprocessing operators for segmentation. This can result in inappropriate operators being connected, leading to poor performance and u...

XCS is the most popular type of Learning Classifier System, but setting optimum parameter values is more of an art than a science. Early theoretical work required the impractical assumption that classifier parameters had fully converged with infinite update times. The aim of this work is to derive a theoretical condition to mathematically guarantee...

Engineers and architects are now turning to use computational aids in order to analyze and solve complex design problems. Most of these problems can be handled by techniques that exploit Evolutionary Computation (EC). However existing EC techniques are slow [8] and hard to understand, thus disengaging the user. Swarm Intelligence (SI) relies on soc...

Figure-ground segmentation is the process of separating regions of interest from unimportant background. One challenge is to segment images with high variations (e.g. containing a cluttered background), which requires effective feature sets to capture the distinguishing information between objects and backgrounds. Feature selection is necessary to...

For several years great effort has been devoted to the study of Architectural Design Optimization(ADO). However, although in the recent years ADO has attracted much attention from academia, optimization methods and tools have had a limited influence on the architectural profession. The aim of the study is to reveal users’ expectations from the opti...

Figure-ground segmentation is a process of separating regions of interest from unimportant backgrounds. It is challenging to separate objects from target images with high variations (e.g. cluttered backgrounds), which requires effective feature sets to capture the discriminative information between object and background regions. Feature constructio...

This accessible introduction shows the reader how to understand, implement, adapt, and apply Learning Classifier Systems (LCSs) to interesting and difficult problems. The text builds an understanding from basic ideas and concepts. The authors first explore learning through environment interaction, and then walk through the components of LCS that fo...