Alma Rahat

Swansea University | SWAN · Department of Computer Science

In many product design and development applications, Computational Fluid Dynamics (CFD) has become a useful tool for analysis. This is particularly because of the accuracy of CFD simulations in predicting the important flow attributes for a given design. On occasions when design optimisation is applied to real-world engineering problems using CFD,...

The performance of acquisition functions for Bayesian optimisation to locate the global optimum of continuous functions is investigated in terms of the Pareto front between exploration and exploitation. We show that Expected Improvement (EI) and the Upper Confidence Bound (UCB) always select solutions to be expensively evaluated on the Pareto front...

We are often interested in identifying the feasible subset of a decision space under multiple constraints to permit effective design exploration. If determining feasibility required computationally expensive simulations, the cost of exploration would be prohibitive. Bayesian search is data-efficient for such problems: starting from a small dataset,...

Many methods for performing multi-objective optimisation of computationally expensive problems have been proposed recently. Typically, a probabilistic surrogate for each objective is constructed from an initial dataset. The surrogates can then be used to produce predictive densities in the objective space for any solution. Using the predictive dens...

Assessment is a crucial part of education. Traditional marking is a source of inconsistencies and unconscious bias, placing a high cognitive load on the assessors. An approach to address these issues is comparative judgement (CJ). In CJ, the assessor is presented with a pair of items and is asked to select the better one. Following a series of comp...

The UK NHS emergency departments (EDs) are the front-line for patient care, with a wide range of patient presentations but limited resources. Using over 1.5 million ED data entries collected during 2015-2023 from a health board in Wales, we explored the application of machine learning models in predicting clinical outcomes. The features in the mode...

The shape of a hydrodynamic particle separator has been optimized using a parallelized and robust formulation of Bayesian optimization, with data from an unsteady Eulerian flow field coupled with Lagrangian particle tracking. The uncertainty due to the mesh, initial conditions, and stochastic dispersion in the Eulerian-Lagrangian simulations was mi...

Numerical modelling in the coastal environment often requires highly skilled users and can be hindered by high computation costs and time requirements. Machine Learning (ML) techniques have the potential to overcome these limitations and complement existing methods. This is an exploratory investigation utilising a Gaussian Process (GP) data-driven...

The shape of a hydrodynamic particle separator has been optimised using unsteady computational fluid dynamics, coupled with Lagrangian particle tracking, combined with a parallelised and robust formulation of Bayesian optimisation. The noise present in the models of the separator required the use of the minimum probability of improvement infill cri...

Two studies of a human-AI collaborative design tool were carried out in order to understand the influence design recommendations have on the design process. Whereas most previous studies of human-AI collaborative design focus on the effect the human has on the algorithm, here we focus on the effect the algorithm has on the human. The tool investiga...

The sudden outbreak of the COVID-19 pandemic presented governments, policy makers and health services with an unprecedented challenge of taking real-time decisions that could keep the disease under control with non-pharmaceutical interventions, while at the same time limit as much as possible severe consequences of a very strict lockdown. Mathemati...

Optimisation problems involving multiple objectives are commonly found in real-world applications. The existence of conflicting objectives produces trade-offs where a solution can be better with respect to one objective but requires a compromise in the other objectives. In many real-world problems the relationship between objectives is unknown or u...

The recent COVID-19 pandemic highlighted a need for tools to help policy-makers make informed decisions on what policies to implement in order to reduce the impact of the pandemic. Several tools have previously been developed to model how non-pharmaceutical interventions (NPIs), such as social distancing, affect the rate of growth of a disease with...

We report on an ongoing collaboration between epidemiological modellers and visualization researchers by documenting and reflecting upon knowledge constructs—a series of ideas, approaches and methods taken from existing visualization research and practice—deployed and developed to support modelling of the COVID-19 pandemic. Structured independent c...

Many methods for performing multi-objective optimisation of computationally expensive problems have been proposed recently. Typically, a probabilistic surrogate for each objective is constructed from an initial dataset. The surrogates can then be used to produce predictive densities in the objective space for any solution. Using the predictive dens...

The draft tube of a hydraulic turbine plays an important role for the efficiency and power characteristics of the overall system. The shape of the draft tube affects its performance, resulting in an increasing need for data-driven optimisation for its design. In this paper, shape optimisation of an elbow-type draft tube is undertaken, combining Com...

We report on an ongoing collaboration between epidemiological modellers and visualization researchers by documenting and reflecting upon knowledge constructs -- a series of ideas, approaches and methods taken from existing visualization research and practice -- deployed and developed to support modelling of the COVID-19 pandemic. Structured indepen...

Marking and feedback are essential features of teaching and learning, across the overwhelming majority of educational settings and contexts. However, it can take a great deal of time and effort for teachers to mark assessments, and to provide useful feedback to the students. Furthermore, it also creates a significant cognitive load on the assessors...

Optimisation problems often have multiple conflicting objectives that can be computationally and/or financially expensive. Mono-surrogate Bayesian optimisation (BO) is a popular model-based approach for optimising such black-box functions. It combines objective values via scalarisation and builds a Gaussian process (GP) surrogate of the scalarised...

Results from a triple-blind mixed-method user study into the effectiveness of mixed-initiative tools for the procedural generation of game levels are presented. A tool which generates levels using interactive evolutionary optimisation was designed for this study which (a) is focused on supporting the designer to explore the design space and (b) onl...

Performing multi-objective Bayesian optimisation by scalarising the objectives avoids the computation of expensive multi-dimensional integral-based acquisition functions, instead of allowing one-dimensional standard acquisition functions\textemdash such as Expected Improvement\textemdash to be applied. Here, two infill criteria based on hypervolume...

In the first of this two-part contribution, a methodology to assess the performance of an elbow-type draft tube is outlined. Using Computational Fluid Dynamics (CFD) to evaluate the pressure recovery and mechanical energy losses along a draft tube design, while using open-source and commercial software to parameterise and regenerate the geometry an...

Results from a triple-blind mixed-method user study into the effectiveness of mixed-initiative tools for the procedural generation of game levels are presented. A tool which generates levels using interactive evolutionary optimisation was designed for this study which (a) is focused on supporting the designer to explore the design space and (b) onl...

Bayesian optimisation is a popular, surrogate model-based approach for optimising expensive black-box functions. Given a surrogate model, the next location to expensively evaluate is chosen via maximisation of a cheap-to-query acquisition function. We present an ε-greedy procedure for Bayesian optimisation in batch settings in which the black-box f...

We are often interested in identifying the feasible subset of a decision space under multiple constraints to permit effective design exploration. If determining feasibility required computationally expensive simulations, the cost of exploration would be prohibitive. Bayesian search is data-efficient for such problems: starting from a small dataset,...

An approach for shape optimisation of the flow through a diffuser is presented in this work. This multi-objective problem focuses on maximising the diffuser performance by simultaneously increasing the static pressure recovery across the geometry and the flow uniformity at the outflow. The hydrodynamic analysis of the geometry was conducted using t...

Gaussian processes (GPs) belong to a class of probabilistic techniques that have been successfully used in different domains of machine learning and optimization. They are popular because they provide uncertainties in predictions, which sets them apart from other modelling methods providing only point predictions. The uncertainty is particularly us...

The first and last mile problem describes the difficulty of starting and completing a journey when using public transport, where there are limited options once away from centralised transport infrastructure such as train stations. It is particularly an issue for commuter journeys where time lost on regular repeated trips becomes a barrier to the us...

Many expensive black-box optimisation problems are sensitive to their inputs. In these problems it makes more sense to locate a region of good designs, than a single, possible fragile, optimal design. Expensive black-box functions can be optimised effectively with Bayesian optimisation, where a Gaussian process is a popular choice as a prior over t...

Overexpression and secretion of the enzymes cathepsin D (CathD) and cathepsin L (CathL) is associated with metastasis in several human cancers. As a superfamily, extracellularly, these proteins may act within the tumor microenvironment to drive cancer progression, proliferation, invasion and metastasis. Therefore, it is important to discover novel...

Parametrisation of the geometry is one of the essential requirements in shape optimisation, and is a challenging subject when carrying out a automated procedure. It is critically important to maintain the consistency of the shape and grid quality between each evaluation, while providing flexibility for a wide range of shapes using the same paramete...

Gaussian processes (GPs) belong to a class of probabilistic techniques that have been successfully used in different domains of machine learning and optimization. They are popular because they provide uncertainties in predictions, which sets them apart from other modelling methods providing only point predictions. The uncertainty is particularly us...

In many product design and development applications, Computational Fluid Dynamics (CFD) has become a useful tool for analysis. This is particularly because of the accuracy of CFD simulations in predicting the important flow attributes for a given design. On occasions when design optimisation is applied to real-world engineering problems using CFD,...

Coal remains an important energy source. Nonetheless, pollutant emissions – in particular Oxides of Nitrogen (NOx) – as a result of the combustion process in a boiler, are subject to strict legislation due to their damaging effects on the environment. Optimising combustion parameters to achieve a lower NOx emission often results in combustion ineff...

Surrogate-Assisted Evolutionary Algorithms (SAEAs) have been proven to be very effective in solving (synthetic and real-world) computationally expensive optimization problems with a limited number of function evaluations. The two main components of SAEAs are: the surrogate model and the evolutionary optimizer, both of which use parameters to contro...

The intriguing properties of reduced graphene oxide (rGO) have paved the way for a number of potential biomedical applications such as drug delivery, tissue engineering, gene delivery and bio-sensing. Over the last decade, there have been escalating concerns regarding the possible toxic effects, behaviour and fate of rGO in living systems and envir...

Many multi-objective optimisation problems incorporate computationally or financially expensive objective functions. State-of-the-art algorithms therefore construct surrogate model(s) of the parameter space to objective functions mapping to guide the choice of the next solution to expensively evaluate. Starting from an initial set of solutions, an...

Recently, Gaussian Process (GP) has attracted generous attention from industry. This article focuses on the application of coal fired boiler combustion and uses GP to design a strategy for reducing Unburned Carbon Content in Fly Ash (UCC-FA) which is the most important indicator of boiler combustion efficiency. With getting rid of the complicated p...

Wireless sensor networks frequently use multi-path routing schemes between nodes and a base station. Multi-path routing confers additional robustness against link failure, but in battery-powered networks it is desirable to choose paths which maximise the overall network lifetime — the time at which a battery is first exhausted. We introduce multi-o...

Battery powered wireless sensors are widely used in industrial and regulatory monitoring applications. This is primarily due to the ease of installation and the ability to monitor areas that are difficult to access. Additionally, they can be left unattended for long periods of time. However, there are many challenges to successful deployments of wi...

Mesh network topologies are becoming increasingly popular in battery powered wireless sensor networks, primarily due to the extension of network range. However, multi-hop mesh networks suffer from higher energy costs, and the routing strategy employed directly affects the lifetime of nodes with limited energy resources. Hence when planning routes t...

Mesh network topologies are becoming increasingly popular in battery powered wireless sensor networks, primarily due to the extension of network range and resilience against routing failures. However, multi-hop mesh networks suffer from higher energy costs, and the routing strategy directly affects the lifetime of nodes with limited energy sources....