Paolo Missier

Matthew McTeer, Robin Henderson, Quentin M Anstee et al.

Overlapping asymmetric datasets are common in data science and pose questions of how they can be incorporated together into a predictive analysis. In healthcare datasets there is often a small amount of information that is available for a larger number of patients such as an electronic health record, however a small number of patients may have had extensive further testing. Common solutions such as missing imputation can often be unwise if the smaller cohort is significantly different in scale to the larger sample, therefore the aim of this research is to develop a new method which can model the smaller cohort against a particular response, whilst considering the larger cohort also. Motivated by non-parametric models, and specifically flexible smoothing techniques via generalized additive models, we model a twice penalized P-Spline approximation method to firstly prevent over/under-fitting of the smaller cohort and secondly to consider the larger cohort. This second penalty is created through discrepancies in the marginal value of covariates that exist in both the smaller and larger cohorts. Through data simulations, parameter tunings and model adaptations to consider a continuous and binary response, we find our twice penalized approach offers an enhanced fit over a linear B-Spline and once penalized P-Spline approximation. Applying to a real-life dataset relating to a person's risk of developing Non-Alcoholic Steatohepatitis, we see an improved model fit performance of over 65%. Areas for future work within this space include adapting our method to not require dimensionality reduction and also consider parametric modelling methods. However, to our knowledge this is the first work to propose additional marginal penalties in a flexible regression of which we can report a vastly improved model fit that is able to consider asymmetric datasets, without the need for missing data imputation.

Philip Darke, Paolo Missier, Jaume Bacardit

The development of models for Electronic Health Record data is an area of active research featuring a small number of public benchmark data sets. Researchers typically write custom data processing code but this hinders reproducibility and can introduce errors. The Python package torchtime provides reproducible implementations of commonly used PhysioNet and UEA & UCR time series classification repository data sets for PyTorch. Features are provided for working with irregularly sampled and partially observed time series of unequal length. It aims to simplify access to PhysioNet data and enable fair comparisons of models in this exciting area of research.

Shuai Shao, Yu Guan, Xin Guan et al.

Human Activity Recognition (HAR) is one of the core research areas in mobile and wearable computing. With the application of deep learning (DL) techniques such as CNN, recognizing periodic or static activities (e.g, walking, lying, cycling, etc.) has become a well studied problem. What remains a major challenge though is the sporadic activity recognition (SAR) problem, where activities of interest tend to be non periodic, and occur less frequently when compared with the often large amount of irrelevant background activities. Recent works suggested that sequential DL models (such as LSTMs) have great potential for modeling nonperiodic behaviours, and in this paper we studied some LSTM training strategies for SAR. Specifically, we proposed two simple yet effective LSTM variants, namely delay model and inverse model, for two SAR scenarios (with and without time critical requirement). For time critical SAR, the delay model can effectively exploit predefined delay intervals (within tolerance) in form of contextual information for improved performance. For regular SAR task, the second proposed, inverse model can learn patterns from the time series in an inverse manner, which can be complementary to the forward model (i.e.,LSTM), and combining both can boost the performance. These two LSTM variants are very practical, and they can be deemed as training strategies without alteration of the LSTM fundamentals. We also studied some additional LSTM training strategies, which can further improve the accuracy. We evaluated our models on two SAR and one non-SAR datasets, and the promising results demonstrated the effectiveness of our approaches in HAR applications.

Shuai Shao, Yu Guan, Bing Zhai et al.

Human activity recognition (HAR) is one of the core research themes in ubiquitous and wearable computing. With the shift to deep learning (DL) based analysis approaches, it has become possible to extract high-level features and perform classification in an end-to-end manner. Despite their promising overall capabilities, DL-based HAR may suffer from overfitting due to the notoriously small, often inadequate, amounts of labeled sample data that are available for typical HAR applications. In response to such challenges, we propose ConvBoost -- a novel, three-layer, structured model architecture and boosting framework for convolutional network based HAR. Our framework generates additional training data from three different perspectives for improved HAR, aiming to alleviate the shortness of labeled training data in the field. Specifically, with the introduction of three conceptual layers--Sampling Layer, Data Augmentation Layer, and Resilient Layer -- we develop three "boosters" -- R-Frame, Mix-up, and C-Drop -- to enrich the per-epoch training data by dense-sampling, synthesizing, and simulating, respectively. These new conceptual layers and boosters, that are universally applicable for any kind of convolutional network, have been designed based on the characteristics of the sensor data and the concept of frame-wise HAR. In our experimental evaluation on three standard benchmarks (Opportunity, PAMAP2, GOTOV) we demonstrate the effectiveness of our ConvBoost framework for HAR applications based on variants of convolutional networks: vanilla CNN, ConvLSTM, and Attention Models. We achieved substantial performance gains for all of them, which suggests that the proposed approach is generic and can serve as a practical solution for boosting the performance of existing ConvNet-based HAR models. This is an open-source project, and the code can be found at https://github.com/sshao2013/ConvBoost

Ehsan Toreini, Mhairi Aitken, Kovila P. L. Coopamootoo et al.

Concerns about the societal impact of AI-based services and systems has encouraged governments and other organisations around the world to propose AI policy frameworks to address fairness, accountability, transparency and related topics. To achieve the objectives of these frameworks, the data and software engineers who build machine-learning systems require knowledge about a variety of relevant supporting tools and techniques. In this paper we provide an overview of technologies that support building trustworthy machine learning systems, i.e., systems whose properties justify that people place trust in them. We argue that four categories of system properties are instrumental in achieving the policy objectives, namely fairness, explainability, auditability and safety & security (FEAS). We discuss how these properties need to be considered across all stages of the machine learning life cycle, from data collection through run-time model inference. As a consequence, we survey in this paper the main technologies with respect to all four of the FEAS properties, for data-centric as well as model-centric stages of the machine learning system life cycle. We conclude with an identification of open research problems, with a particular focus on the connection between trustworthy machine learning technologies and their implications for individuals and society.

Yulong Gu, Yu Guan, Paolo Missier

Many systems have been developed in recent years to mine logical rules from large-scale Knowledge Graphs (KGs), on the grounds that representing regularities as rules enables both the interpretable inference of new facts, and the explanation of known facts. Among these systems, the walk-based methods that generate the instantiated rules containing constants by abstracting sampled paths in KGs demonstrate strong predictive performance and expressivity. However, due to the large volume of possible rules, these systems do not scale well where computational resources are often wasted on generating and evaluating unpromising rules. In this work, we address such scalability issues by proposing new methods for pruning unpromising rules using rule hierarchies. The approach consists of two phases. Firstly, since rule hierarchies are not readily available in walk-based methods, we have built a Rule Hierarchy Framework (RHF), which leverages a collection of subsumption frameworks to build a proper rule hierarchy from a set of learned rules. And secondly, we adapt RHF to an existing rule learner where we design and implement two methods for Hierarchical Pruning (HPMs), which utilize the generated hierarchies to remove irrelevant and redundant rules. Through experiments over four public benchmark datasets, we show that the application of HPMs is effective in removing unpromising rules, which leads to significant reductions in the runtime as well as in the number of learned rules, without compromising the predictive performance.

Yulong Gu, Yu Guan, Paolo Missier

Efficiently inducing high-level interpretable regularities from knowledge graphs (KGs) is an essential yet challenging task that benefits many downstream applications. In this work, we present GPFL, a probabilistic rule learner optimized to mine instantiated first-order logic rules from KGs. Instantiated rules contain constants extracted from KGs. Compared to abstract rules that contain no constants, instantiated rules are capable of explaining and expressing concepts in more details. GPFL utilizes a novel two-stage rule generation mechanism that first generalizes extracted paths into templates that are acyclic abstract rules until a certain degree of template saturation is achieved, then specializes the generated templates into instantiated rules. Unlike existing works that ground every mined instantiated rule for evaluation, GPFL shares groundings between structurally similar rules for collective evaluation. Moreover, we reveal the presence of overfitting rules, their impact on the predictive performance, and the effectiveness of a simple validation method filtering out overfitting rules. Through extensive experiments on public benchmark datasets, we show that GPFL 1.) significantly reduces the runtime on evaluating instantiated rules; 2.) discovers much more quality instantiated rules than existing works; 3.) improves the predictive performance of learned rules by removing overfitting rules via validation; 4.) is competitive on knowledge graph completion task compared to state-of-the-art baselines.

Flavio Primo, Paolo Missier, Alexander Romanovsky et al.

On social media platforms and Twitter in particular, specific classes of users such as influencers have been given satisfactory operational definitions in terms of network and content metrics. Others, for instance online activists, are not less important but their characterisation still requires experimenting. We make the hypothesis that such interesting users can be found within temporally and spatially localised contexts, i.e., small but topical fragments of the network containing interactions about social events or campaigns with a significant footprint on Twitter. To explore this hypothesis, we have designed a continuous user profile discovery pipeline that produces an ever-growing dataset of user profiles by harvesting and analysing contexts from the Twitter stream. The profiles dataset includes key network and content-based users metrics, enabling experimentation with user-defined score functions that characterise specific classes of online users. The paper describes the design and implementation of the pipeline and its empirical evaluation on a case study consisting of healthcare-related campaigns in the UK, showing how it supports the operational definitions of online activism, by comparing three experimental ranking functions. The code is publicly available.

Paolo Missier, Callum McClean, Jonathan Carlton et al.

Tropical diseases like \textit{Chikungunya} and \textit{Zika} have come to prominence in recent years as the cause of serious, long-lasting, population-wide health problems. In large countries like Brasil, traditional disease prevention programs led by health authorities have not been particularly effective. We explore the hypothesis that monitoring and analysis of social media content streams may effectively complement such efforts. Specifically, we aim to identify selected members of the public who are likely to be sensitive to virus combat initiatives that are organised in local communities. Focusing on Twitter and on the topic of Zika, our approach involves (i) training a classifier to select topic-relevant tweets from the Twitter feed, and (ii) discovering the top users who are actively posting relevant content about the topic. We may then recommend these users as the prime candidates for direct engagement within their community. In this short paper we describe our analytical approach and prototype architecture, discuss the challenges of dealing with noisy and sparse signal, and present encouraging preliminary results.

Timothy McPhillips, Tianhong Song, Tyler Kolisnik et al.

Scientific workflow management systems offer features for composing complex computational pipelines from modular building blocks, for executing the resulting automated workflows, and for recording the provenance of data products resulting from workflow runs. Despite the advantages such features provide, many automated workflows continue to be implemented and executed outside of scientific workflow systems due to the convenience and familiarity of scripting languages (such as Perl, Python, R, and MATLAB), and to the high productivity many scientists experience when using these languages. YesWorkflow is a set of software tools that aim to provide such users of scripting languages with many of the benefits of scientific workflow systems. YesWorkflow requires neither the use of a workflow engine nor the overhead of adapting code to run effectively in such a system. Instead, YesWorkflow enables scientists to annotate existing scripts with special comments that reveal the computational modules and dataflows otherwise implicit in these scripts. YesWorkflow tools extract and analyze these comments, represent the scripts in terms of entities based on the typical scientific workflow model, and provide graphical renderings of this workflow-like view of the scripts. Future versions of YesWorkflow also will allow the prospective provenance of the data products of these scripts to be queried in ways similar to those available to users of scientific workflow systems.

Matias Garcia-Constantino, Paolo Missier, Phil Blytheand Amy Weihong Guo

Using current sensing technology, a wealth of data on driving sessions is potentially available through a combination of vehicle sensors and drivers' physiology sensors (heart rate, breathing rate, skin temperature, etc.). Our hypothesis is that it should be possible to exploit the combination of time series produced by such multiple sensors during a driving session, in order to (i) learn models of normal driving behaviour, and (ii) use such models to detect important and potentially dangerous deviations from the norm in real-time, and thus enable the generation of appropriate alerts. Crucially, we believe that such models and interventions should and can be personalised and tailor-made for each individual driver. As an initial step towards this goal, in this paper we present techniques for assessing the impact of cognitive distraction on drivers, based on simple time series analysis. We have tested our method on a rich dataset of driving sessions, carried out in a professional simulator, involving a panel of volunteer drivers. Each session included a different type of cognitive distraction, and resulted in multiple time series from a variety of on-board sensors as well as sensors worn by the driver. Crucially, each driver also recorded an initial session with no distractions. In our model, such initial session provides the baseline times series that make it possible to quantitatively assess driver performance under distraction conditions.