A. Stephen McGough

Cameron Trotter, Nick Wright, A. Stephen McGough et al.

Photo-identification (photo-id) is one of the main non-invasive capture-recapture methods utilised by marine researchers for monitoring cetacean (dolphin, whale, and porpoise) populations. This method has historically been performed manually resulting in high workload and cost due to the vast number of images collected. Recently automated aids have been developed to help speed-up photo-id, although they are often disjoint in their processing and do not utilise all available identifying information. Work presented in this paper aims to create a fully automatic photo-id aid capable of providing most likely matches based on all available information without the need for data pre-processing such as cropping. This is achieved through a pipeline of computer vision models and post-processing techniques aimed at detecting cetaceans in unedited field imagery before passing them downstream for individual level catalogue matching. The system is capable of handling previously uncatalogued individuals and flagging these for investigation thanks to catalogue similarity comparison. We evaluate the system against multiple real-life photo-id catalogues, achieving mAP@IOU[0.5] = 0.91, 0.96 for the task of dorsal fin detection on catalogues from Tanzania and the UK respectively and 83.1, 97.5% top-10 accuracy for the task of individual classification on catalogues from the UK and USA.

Ayse Betul Cengiz, A. Stephen McGough

The collection of data to train a Deep Learning network is costly in terms of effort and resources. In many cases, especially in a medical context, it may have detrimental impacts. Such as requiring invasive medical procedures or processes which could in themselves cause medical harm. However, Deep Learning is seen as a data hungry method. Here, we look at two commonly held adages i) more data gives better results and ii) transfer learning will aid you when you don't have enough data. These are widely assumed to be true and used as evidence for choosing how to solve a problem when Deep Learning is involved. We evaluate six medical datasets and six general datasets. Training a ResNet18 network on varying subsets of these datasets to evaluate `more data gives better results'. We take eleven of these datasets as the sources for Transfer Learning on subsets of the twelfth dataset -- Chest -- in order to determine whether Transfer Learning is universally beneficial. We go further to see whether multi-stage Transfer Learning provides a consistent benefit. Our analysis shows that the real situation is more complex than these simple adages -- more data could lead to a case of diminishing returns and an incorrect choice of dataset for transfer learning can lead to worse performance, with datasets which we would consider highly similar to the Chest dataset giving worse results than datasets which are more dissimilar. Multi-stage transfer learning likewise reveals complex relationships between datasets.

Mohamad Khalil, A. Stephen McGough, Hussain Kazmi et al.

Forecasting building energy consumption has become a promising solution in Building Energy Management Systems for energy saving and optimization. Furthermore, it can play an important role in the efficient management of the operation of a smart grid. Different data-driven approaches to forecast the future energy demand of buildings at different scale, and over various time horizons, can be found in the scientific literature, including extensive Machine Learning and Deep Learning approaches. However, the identification of the most accurate forecaster model which can be utilized to predict the energy demand of such a building is still challenging.In this paper, the design and implementation of a data-driven approach to predict how forecastable the future energy demand of a building is, without first utilizing a data-driven forecasting model, is presented. The investigation utilizes a historical electricity consumption time series data set with a half-hour interval that has been collected from a group of residential buildings located in the City of London, United Kingdom

Atif Khan, Conor Lawless, Amy Vincent et al.

Single cell analysis of human skeletal muscle (SM) tissue cross-sections is a fundamental tool for understanding many neuromuscular disorders. For this analysis to be reliable and reproducible, identification of individual fibres within microscopy images (segmentation) of SM tissue should be automatic and precise. Biomedical scientists in this field currently rely on custom tools and general machine learning (ML) models, both followed by labour intensive and subjective manual interventions to fine-tune segmentation. We believe that fully automated, precise, reproducible segmentation is possible by training ML models. However, in this important biomedical domain, there are currently no good quality, publicly available annotated imaging datasets available for ML model training. In this paper we release NCL-SM: a high quality bioimaging dataset of 46 human SM tissue cross-sections from both healthy control subjects and from patients with genetically diagnosed muscle pathology. These images include $>$ 50k manually segmented muscle fibres (myofibres). In addition we also curated high quality myofibre segmentations, annotating reasons for rejecting low quality myofibres and low quality regions in SM tissue images, making these annotations completely ready for downstream analysis. This, we believe, will pave the way for development of a fully automatic pipeline that identifies individual myofibres within images of tissue sections and, in particular, also classifies individual myofibres that are fit for further analysis.

Atif Khan, Conor Lawless, Amy E Vincent et al.

Mitochondrial diseases are currently untreatable due to our limited understanding of their pathology. We study the expression of various mitochondrial proteins in skeletal myofibres (SM) in order to discover processes involved in mitochondrial pathology using Imaging Mass Cytometry (IMC). IMC produces high dimensional multichannel pseudo-images representing spatial variation in the expression of a panel of proteins within a tissue, including subcellular variation. Statistical analysis of these images requires semi-automated annotation of thousands of SMs in IMC images of patient muscle biopsies. In this paper we investigate the use of deep learning (DL) on raw IMC data to analyse it without any manual pre-processing steps, statistical summaries or statistical models. For this we first train state-of-art computer vision DL models on all available image channels, both combined and individually. We observed better than expected accuracy for many of these models. We then apply state-of-the-art explainable techniques relevant to computer vision DL to find the basis of the predictions of these models. Some of the resulting visual explainable maps highlight features in the images that appear consistent with the latest hypotheses about mitochondrial disease progression within myofibres.

Atif Khan, Conor Lawless, Amy Vincent et al.

Single cell analysis of skeletal muscle (SM) tissue is a fundamental tool for understanding many neuromuscular disorders. For this analysis to be reliable and reproducible, identification of individual fibres within microscopy images (segmentation) of SM tissue should be precise. There is currently no tool or pipeline that makes automatic and precise segmentation and curation of images of SM tissue cross-sections possible. Biomedical scientists in this field rely on custom tools and general machine learning (ML) models, both followed by labour intensive and subjective manual interventions to get the segmentation right. We believe that automated, precise, reproducible segmentation is possible by training ML models. However, there are currently no good quality, publicly available annotated imaging datasets available for ML model training. In this paper we release NCL-SM: a high quality bioimaging dataset of 46 human tissue sections from healthy control subjects and from patients with genetically diagnosed muscle pathology. These images include $>$ 50k manually segmented muscle fibres (myofibres). In addition we also curated high quality myofibres and annotated reasons for rejecting low quality myofibres and regions in SM tissue images, making this data completely ready for downstream analysis. This, we believe, will pave the way for development of a fully automatic pipeline that identifies individual myofibres within images of tissue sections and, in particular, also classifies individual myofibres that are fit for further analysis.

Cameron Trotter, Georgia Atkinson, Matt Sharpe et al.

We introduce the Northumberland Dolphin Dataset 2020 (NDD20), a challenging image dataset annotated for both coarse and fine-grained instance segmentation and categorisation. This dataset, the first release of the NDD, was created in response to the rapid expansion of computer vision into conservation research and the production of field-deployable systems suited to extreme environmental conditions -- an area with few open source datasets. NDD20 contains a large collection of above and below water images of two different dolphin species for traditional coarse and fine-grained segmentation. All data contained in NDD20 was obtained via manual collection in the North Sea around the Northumberland coastline, UK. We present experimentation using standard deep learning network architecture trained using NDD20 and report baselines results.

Rob Geada, David Towers, Matthew Forshaw et al.

The boundless possibility of neural networks which can be used to solve a problem -- each with different performance -- leads to a situation where a Deep Learning expert is required to identify the best neural network. This goes against the hope of removing the need for experts. Neural Architecture Search (NAS) offers a solution to this by automatically identifying the best architecture. However, to date, NAS work has focused on a small set of datasets which we argue are not representative of real-world problems. We introduce eight new datasets created for a series of NAS Challenges: AddNIST, Language, MultNIST, CIFARTile, Gutenberg, Isabella, GeoClassing, and Chesseract. These datasets and challenges are developed to direct attention to issues in NAS development and to encourage authors to consider how their models will perform on datasets unknown to them at development time. We present experimentation using standard Deep Learning methods as well as the best results from challenge participants.

Matthew Kent Myers, Nick Wright, A. Stephen McGough et al.

Online temporal action segmentation shows a strong potential to facilitate many HRI tasks where extended human action sequences must be tracked and understood in real time. Traditional action segmentation approaches, however, operate in an offline two stage approach, relying on computationally expensive video wide features for segmentation, rendering them unsuitable for online HRI applications. In order to facilitate online action segmentation on a stream of incoming video data, we introduce two methods for improved training and inference of backbone action recognition models, allowing them to be deployed directly for online frame level classification. Firstly, we introduce surround dense sampling whilst training to facilitate training vs. inference clip matching and improve segment boundary predictions. Secondly, we introduce an Online Temporally Aware Label Cleaning (O-TALC) strategy to explicitly reduce oversegmentation during online inference. As our methods are backbone invariant, they can be deployed with computationally efficient spatio-temporal action recognition models capable of operating in real time with a small segmentation latency. We show our method outperforms similar online action segmentation work as well as matches the performance of many offline models with access to full temporal resolution when operating on challenging fine-grained datasets.

Georgia Atkinson, Nick Wright, A. Stephen McGough et al.

In recent years generative adversarial networks (GANs) have been used to supplement datasets within the field of marine bioacoustics. This is driven by factors such as the cost to collect data, data sparsity and aid preprocessing. One notable challenge with marine bioacoustic data is the low signal-to-noise ratio (SNR) posing difficulty when applying deep learning techniques such as GANs. This work investigates the effect SNR has on the audio-based GAN performance and examines three different evaluation methodologies for GAN performance, yielding interesting results on the effects of SNR on GANs, specifically WaveGAN.

Alexander J. M. Kell, A. Stephen McGough, Matthew Forshaw

A lowering in the cost of batteries and solar PV systems has led to a high uptake of solar battery home systems. In this work, we use the deep deterministic policy gradient algorithm to optimise the charging and discharging behaviour of a battery within such a system. Our approach outputs a continuous action space when it charges and discharges the battery, and can function well in a stochastic environment. We show good performance of this algorithm by lowering the expenditure of a single household on electricity to almost \$1AUD for large batteries across selected weeks within a year.

Alexander J. M. Kell, A. Stephen McGough, Matthew Forshaw

Electricity supply must be matched with demand at all times. This helps reduce the chances of issues such as load frequency control and the chances of electricity blackouts. To gain a better understanding of the load that is likely to be required over the next 24h, estimations under uncertainty are needed. This is especially difficult in a decentralized electricity market with many micro-producers which are not under central control. In this paper, we investigate the impact of eleven offline learning and five online learning algorithms to predict the electricity demand profile over the next 24h. We achieve this through integration within the long-term agent-based model, ElecSim. Through the prediction of electricity demand profile over the next 24h, we can simulate the predictions made for a day-ahead market. Once we have made these predictions, we sample from the residual distributions and perturb the electricity market demand using the simulation, ElecSim. This enables us to understand the impact of errors on the long-term dynamics of a decentralized electricity market. We show we can reduce the mean absolute error by 30% using an online algorithm when compared to the best offline algorithm, whilst reducing the required tendered national grid reserve required. This reduction in national grid reserves leads to savings in costs and emissions. We also show that large errors in prediction accuracy have a disproportionate error on investments made over a 17-year time frame, as well as electricity mix.

Alexander J. M. Kell, Matthew Forshaw, A. Stephen McGough

Decentralized electricity markets are often dominated by a small set of generator companies who control the majority of the capacity. In this paper, we explore the effect of the total controlled electricity capacity by a single, or group, of generator companies can have on the average electricity price. We demonstrate this through the use of ElecSim, a simulation of a country-wide energy market. We develop a strategic agent, representing a generation company, which uses a deep deterministic policy gradient reinforcement learning algorithm to bid in a uniform pricing electricity market. A uniform pricing market is one where all players are paid the highest accepted price. ElecSim is parameterized to the United Kingdom for the year 2018. This work can help inform policy on how to best regulate a market to ensure that the price of electricity remains competitive. We find that capacity has an impact on the average electricity price in a single year. If any single generator company, or a collaborating group of generator companies, control more than ${\sim}$11$\%$ of generation capacity and bid strategically, prices begin to increase by ${\sim}$25$\%$. The value of ${\sim}$25\% and ${\sim}$11\% may vary between market structures and countries. For instance, different load profiles may favour a particular type of generator or a different distribution of generation capacity. Once the capacity controlled by a generator company, which bids strategically, is higher than ${\sim}$35\%, prices increase exponentially. We observe that the use of a market cap of approximately double the average market price has the effect of significantly decreasing this effect and maintaining a competitive market. A fair and competitive electricity market provides value to consumers and enables a more competitive economy through the utilisation of electricity by both industry and consumers.

Alexander J. M. Kell, A. Stephen McGough, Matthew Forshaw

Averting the effects of anthropogenic climate change requires a transition from fossil fuels to low-carbon technology. A way to achieve this is to decarbonize the electricity grid. However, further efforts must be made in other fields such as transport and heating for full decarbonization. This would reduce carbon emissions due to electricity generation, and also help to decarbonize other sources such as automotive and heating by enabling a low-carbon alternative. Carbon taxes have been shown to be an efficient way to aid in this transition. In this paper, we demonstrate how to to find optimal carbon tax policies through a genetic algorithm approach, using the electricity market agent-based model ElecSim. To achieve this, we use the NSGA-II genetic algorithm to minimize average electricity price and relative carbon intensity of the electricity mix. We demonstrate that it is possible to find a range of carbon taxes to suit differing objectives. Our results show that we are able to minimize electricity cost to below \textsterling10/MWh as well as carbon intensity to zero in every case. In terms of the optimal carbon tax strategy, we found that an increasing strategy between 2020 and 2035 was preferable. Each of the Pareto-front optimal tax strategies are at least above \textsterling81/tCO2 for every year. The mean carbon tax strategy was \textsterling240/tCO2.

Alexander J. M. Kell, Matthew Forshaw, A. Stephen McGough

Many systems require optimisation over multiple objectives, where objectives are characteristics of the system such as energy consumed or increase in time to perform the work. Optimisation is performed by selecting the `best' set of input parameters to elicit the desired objectives. However, the parameter search space can often be far larger than can be searched in a reasonable time. Additionally, the objectives are often mutually exclusive -- leading to a decision being made as to which objective is more important or optimising over a combination of the objectives. This work is an application of a Genetic Algorithm to identify the Pareto frontier for finding the optimal parameter sets for all combinations of objectives. A Pareto frontier can be used to identify the sets of optimal parameters for which each is the `best' for a given combination of objectives -- thus allowing decisions to be made with full knowledge. We demonstrate this approach for the HTC-Sim simulation system in the case where a Reinforcement Learning scheduler is tuned for the two objectives of energy consumption and task overhead. Demonstrating that this approach can reduce the energy consumed by ~36% over previously published work without significantly increasing the overhead.

Cameron Trotter, Georgia Atkinson, Matthew Sharpe et al.

Methods for cetacean research include photo-identification (photo-id) and passive acoustic monitoring (PAM) which generate thousands of images per expedition that are currently hand categorised by researchers into the individual dolphins sighted. With the vast amount of data obtained it is crucially important to develop a system that is able to categorise this quickly. The Northumberland Dolphin Dataset (NDD) is an on-going novel dataset project made up of above and below water images of, and spectrograms of whistles from, white-beaked dolphins. These are produced by photo-id and PAM data collection methods applied off the coast of Northumberland, UK. This dataset will aid in building cetacean identification models, reducing the number of human-hours required to categorise images. Example use cases and areas identified for speed up are examined.

Tom Ryder, Andrew Golighty, A. Stephen McGough et al.

State-space models (SSMs) provide a flexible framework for modelling time-series data. Consequently, SSMs are ubiquitously applied in areas such as engineering, econometrics and epidemiology. In this paper we provide a fast approach for approximate Bayesian inference in SSMs using the tools of deep learning and variational inference.

Amit Gajbhiye, Sardar Jaf, Noura Al Moubayed et al.

Dropout is a crucial regularization technique for the Recurrent Neural Network (RNN) models of Natural Language Inference (NLI). However, dropout has not been evaluated for the effectiveness at different layers and dropout rates in NLI models. In this paper, we propose a novel RNN model for NLI and empirically evaluate the effect of applying dropout at different layers in the model. We also investigate the impact of varying dropout rates at these layers. Our empirical evaluation on a large (Stanford Natural Language Inference (SNLI)) and a small (SciTail) dataset suggest that dropout at each feed-forward connection severely affects the model accuracy at increasing dropout rates. We also show that regularizing the embedding layer is efficient for SNLI whereas regularizing the recurrent layer improves the accuracy for SciTail. Our model achieved an accuracy 86.14% on the SNLI dataset and 77.05% on SciTail.

A. Stephen McGough, Matthew Forshaw, John Brennan et al.

High Throughput Computing (HTC) provides a convenient mechanism for running thousands of tasks. Many HTC systems exploit computers which are provisioned for other purposes by utilising their idle time - volunteer computing. This has great advantages as it gives access to vast quantities of computational power for little or no cost. The downside is that running tasks are sacrificed if the computer is needed for its primary use. Normally terminating the task which must be restarted on a different computer - leading to wasted energy and an increase in task completion time. We demonstrate, through the use of simulation, how we can reduce this wasted energy by targeting tasks at computers less likely to be needed for primary use, predicting this idle time through machine learning. By combining two machine learning approaches, namely Random Forest and MultiLayer Perceptron, we save 51.4% of the energy without significantly affecting the time to complete tasks.

Thomas Ryder, Andrew Golightly, A. Stephen McGough et al.

Parameter inference for stochastic differential equations is challenging due to the presence of a latent diffusion process. Working with an Euler-Maruyama discretisation for the diffusion, we use variational inference to jointly learn the parameters and the diffusion paths. We use a standard mean-field variational approximation of the parameter posterior, and introduce a recurrent neural network to approximate the posterior for the diffusion paths conditional on the parameters. This neural network learns how to provide Gaussian state transitions which bridge between observations in a very similar way to the conditioned diffusion process. The resulting black-box inference method can be applied to any SDE system with light tuning requirements. We illustrate the method on a Lotka-Volterra system and an epidemic model, producing accurate parameter estimates in a few hours.

Noura Al Moubayed, Toby Breckon, Peter Matthews et al.

In This paper we present a novel approach to spam filtering and demonstrate its applicability with respect to SMS messages. Our approach requires minimum features engineering and a small set of la- belled data samples. Features are extracted using topic modelling based on latent Dirichlet allocation, and then a comprehensive data model is created using a Stacked Denoising Autoencoder (SDA). Topic modelling summarises the data providing ease of use and high interpretability by visualising the topics using word clouds. Given that the SMS messages can be regarded as either spam (unwanted) or ham (wanted), the SDA is able to model the messages and accurately discriminate between the two classes without the need for a pre-labelled training set. The results are compared against the state-of-the-art spam detection algorithms with our proposed approach achieving over 97% accuracy which compares favourably to the best reported algorithms presented in the literature.