Nirmalie Wiratunga

• Robert Gordon University

Explainable AI (XAI) can greatly enhance user trust and satisfaction in AI-assisted decision-making processes. Recent findings suggest that a single explainer may not meet the diverse needs of multiple users in an AI system; indeed, even individual users may require multiple explanations. This highlights the necessity for a “multi-shot” approach, e...

Communication efficiency is a widely recognised research problem in Federated Learning (FL), with recent work focused on developing techniques for efficient compression, distribution and aggregation of model parameters between clients and the server. Particularly within distributed systems, it is important to balance the need for computational cost...

Systematic Review (SR) are foundational to influencing policies and decision-making in healthcare and beyond. SRs thoroughly synthesise primary research on a specific topic while maintaining reproducibility and transparency. However, the rigorous nature of SRs introduces two main challenges: significant time involved and the continuously growing li...

Explainable AI (XAI) can greatly enhance user trust and satisfaction in AI-assisted decision-making processes. Recent findings suggest that a single explainer may not meet the diverse needs of multiple users in an AI system; indeed, even individual users may require multiple explanations. This highlights the necessity for a "multi-shot" approach, e...

This paper presents a comprehensive survey of AI-driven mini-grid solutions aimed at enhancing sustainable energy access. It emphasises the potential of mini-grids, which can operate independently or in conjunction with national power grids, to provide reliable and affordable electricity to remote communities. Given the inherent unpredictability of...

Explainable Artificial Intelligence (XAI) aims to improve the transparency of autonomous decision-making through explanations. Recent literature has emphasised users' need for holistic "multi-shot" explanations and the ability to personalise their engagement with XAI systems. We refer to this user-centred interaction as an XAI Experience. Despite a...

Systematic reviews (SRs) constitute a critical foundation for evidence-based decision-making and policy formulation across various disciplines, particularly in healthcare and beyond. However, the inherently rigorous and structured nature of the SR process renders it laborious for human reviewers. Moreover, the exponential growth in daily published...

The evolution of Explainable Artificial Intelligence (XAI) has emphasised the significance of meeting diverse user needs. The approaches to identifying and addressing these needs must also advance, recognising that explanation experiences are subjective, user-centred processes that interact with users towards a better understanding of AI decision-m...

Centralised machine learning approaches have raised concerns regarding the privacy of client data. To address this issue, privacy-preserving techniques such as Federated Learning (FL) have emerged, where only updated gradients are communicated instead of the raw client data. However, recent advances in security research have revealed vulnerabilitie...

A clinical dialogue is a conversation between a clinician and a patient to share medical information, which is critical in clinical decision-making. The reliance on manual note-taking is highly inefficient and leads to transcription errors when digitising notes. Speech-to-text applications designed using Automatic Speech Recognition (ASR) can poten...

Counterfactual Explanations (cf-XAI) describe the smallest changes in feature values necessary to change an outcome from one class to another. However, many cf-XAI methods neglect the feasibility of those changes. In this paper, we introduce a novel approach for presenting cf-XAI in natural language (Natural-XAI), giving careful consideration to ac...

In this paper, we propose a novel approach to improve problem-solving efficiency through the reuse of case solutions. Specifically, we introduce the concept of failure-driven transformational case reuse of explanation strategies, which involves transforming suboptimal solutions using relevant components from nearest neighbours in sparse case bases....

Explainable AI (XAI) can greatly enhance user trust and satisfaction in AI-assisted decision-making processes. Numerous explanation techniques (explainers) exist in the literature, and recent findings suggest that addressing multiple user needs requires employing a combination of these explainers. We refer to such combinations as explanation strate...

As deep learning models become increasingly complex, practitioners are relying more on post hoc explanation methods to understand the decisions of black-box learners. However, there is growing concern about the reliability of feature attribution explanations, which are key to explaining machine learning models. Studies have shown that some explaina...

Development of a Diabetic Foot Ulcer (DFU) causes a sharp decline in a patient’s health and quality of life. The process of risk stratification is crucial for informing the care that a patient should receive to help manage their Diabetes before an ulcer can form. In existing practice, risk stratification is a manual process where a clinician alloca...

Systematic Review (SR) presents the highest form of evidence in research for decision and policy-making. Nonetheless, the struc- tured steps involved in carrying out SRs make it demanding for reviewers. Many studies have projected the abstract screening stage tured steps involved in carrying out SRs make it demanding for reviewers. Many studies hav...

Due to the unequivocal need for understanding the decision processes of deep learning networks, both modal-dependent and model-agnostic techniques have become very popular. Although both of these ideas provide transparency for automated decision making, most methodologies focus on either using the modal-gradients (model-dependent) or ignoring the m...

Good communication is critical to good healthcare. Clinical dialogue is a conversation between health practitioners and their patients, with the explicit goal of obtaining and sharing medical information. This information contributes to medical decision-making regarding the patient and plays a crucial role in their healthcare journey. The reliance...

Explainable AI (XAI) has the potential to make a significant impact on building trust and improving the satisfaction of users who interact with an AI system for decision-making. There is an abundance of explanation techniques in literature to address this need. Recently, it has been shown that a user is likely to have multiple explanation needs tha...

Clood is a cloud-based CBR framework based on a microservices architecture which facilitates the design and deployment of case-based reasoning applications of various sizes. This paper presents advances to the similarity module of Clood through the inclusion of enhanced similarity metrics such as word embedding and ontology-based similarity measure...

Counterfactual explanations describe how an outcome can be changed to a more desirable one. In XAI, counterfactuals are “actionable” explanations that help users to understand how model decisions can be changed by adapting features of an input. A case-based approach to counterfactual discovery harnesses Nearest-unlike Neighbours as the basis to ide...

Good communication is critical to good healthcare. Clinical dialogue is a conversation between health practitioners and their patients, with the explicit goal of obtaining and sharing medical information. This information contributes to medical decision-making regarding the patient and plays a crucial role in their healthcare journey. The reliance...

Background: The exponential increase in published articles makes a thorough and expedient review of literature increasingly challenging. This review delineated automated tools and platforms that employ artificial intelligence (AI) approaches and evaluated the reported benefits and challenges in using such methods. Methods: A search was conducted...

Despite the technology advances in the field of virtual assistant and activity monitoring devices, older adults are still reluctant to embrace this technology, specially when it comes to employ it to manage health-related issues. This paper presents a work in progress for a virtual caregiver, based on the Internet of Thing paradigm, that employs di...

Federated Learning (FL) is a distributed machine learning approach in which clients contribute to learning a global model in a privacy preserved manner. Effective aggregation of client models is essential to create a generalised global model. To what extent a client is generalisable and contributing to this aggregation can be ascertained by analysi...

Counterfactual explanations focus on "actionable knowledge" to help end-users understand how a machine learning outcome could be changed to a more desirable outcome. For this purpose a counterfactual explainer needs to discover input dependencies that relate to outcome changes. Identifying the minimum subset of feature changes needed to action an o...

Importance: Lower back pain (LBP) is a prevalent and challenging condition in primary care. The effectiveness of an individually tailored self-management support tool delivered via a smartphone app has not been rigorously tested. Objective: To investigate the effectiveness of selfBACK, an evidence-based, individually tailored self-management sup...

Explanation mechanisms for intelligent systems are typically designed to respond to specific user needs, yet in practice these systems tend to have a wide variety of users. This can present a challenge to organisations looking to satisfy the explanation needs of different groups using an individual system. In this paper we present an explainability...

State-of-the-art methods of Human Activity Recognition (HAR) rely on a considerable amount of labelled data to train deep architectures. This becomes prohibitive when tasked with creating models that are sensitive to personal nuances in human movement, explicitly present when performing exercises and when it is infeasible to collect training data t...

Recent advances in meta-learning provides interesting opportunities for CBR research, in similarity learning, case comparison and personalised recommendations. Rather than learning a single model for a specific task, meta-learners adopt a generalist view of learning-to-learn, such that models are rapidly transferable to related but different new ta...

CBR applications have been deployed in a wide range of sectors, from pharmaceuticals; to defence and aerospace to IoT and transportation, to poetry and music generation; for example. However, a majority of these have been built using monolithic architectures which impose size and complexity constraints. As such these applications have a barrier to...

Fracture detection has been a long-standing paradigm on the medical imaging community. Many algorithms and systems have been presented to accurately detect and classify images in terms of the presence and absence of fractures in different parts of the body. While these solutions are capable of obtaining results which even surpass human scores, few...

Human Activity Recognition~(HAR) is the classification of human movement, captured using one or more sensors either as wearables or embedded in the environment~(e.g. depth cameras, pressure mats). State-of-the-art methods of HAR rely on having access to a considerable amount of labelled data to train deep architectures with many train-able paramete...

Exercise Recognition (ExR) is relevant in many high impact domains, from healthcare to recreational activities to sports sciences. Like Human Activity Recognition (HAR), ExR faces many challenges when deployed in the real-world. For instance, typical lab performances of Machine Learning (ML) models, are hard to replicate, due to differences in pers...

Delivery of digital behaviour change interventions which encourage physical activity has been tried in many forms. Most often interventions are delivered as text notifications, but these do not promote interaction. Advances in conversational AI have improved natural language understanding and generation, allowing AI chatbots to provide an engaging...

BACKGROUND Self-management is the key recommendation for managing non-specific low back pain (LBP). However, there are well-documented barriers to self-management, therefore methods of facilitating adherence are required. Smartphone apps are increasingly being used to provide feedback and reinforcement to support self-management of long-term condit...

Background: Self-management is the key recommendation for managing nonspecific low back pain (LBP). However, there are well-documented barriers to self-management; therefore, methods of facilitating adherence are required. Smartphone apps are increasingly being used to support self-management of long-term conditions such as LBP. Objective: The a...

Human Activity Recognition (HAR) is a core component of clinical decision support systems that rely on activity monitoring for self-management of chronic conditions such as Musculoskeletal Disorders. Deployment success of such applications in part depend on their ability to adapt to individual variations in human movement and to facilitate a range...

Purpose Recommender system approaches such as collaborative and content-based filtering rely on user ratings and product descriptions to recommend products. More recently, recommender system research has focussed on exploiting knowledge from user-generated content such as product reviews to enhance recommendation performance. The purpose of this pa...

Organisations face growing legal requirements and ethical responsibilities to ensure that decisions made by their intelligent systems are explainable. However, provisioning of an explanation is often application dependent, causing an extended design phase and delayed deployment. In this paper we present an explainability framework formed of a catal...

Despite the growing prevalence of multimorbidities, current digital self-management approaches still prioritise single conditions. The future of outof- hospital care requires researchers to expand their horizons; integrated assistive technologies should enable people to live their life well regardless of their chronic conditions. Yet, many of the c...

MEx: Multi-modal Exercises Dataset is a multi-sensor, multi-modal dataset, implemented to benchmark Human Activity Recognition(HAR) and Multi-modal Fusion algorithms. Collection of this dataset was inspired by the need for recognising and evaluating quality of exercise performance to support patients with Musculoskeletal Disorders(MSD). We select 7...

Ontology alignment is crucial for integrating heterogeneous data sources and forms an important component of the semantic web. Accordingly, several ontology alignment techniques have been proposed and used for discovering correspondences between the concepts (or entities) of different ontologies. Most alignment techniques depend on string-based sim...

This book constitutes the refereed post-conference proceedings of the First International Workshop on Artificial Intelligence in Health, AIH 2018, in Stockholm, Sweden, in July 2018. This workshop consolidated the workshops CARE, KRH4C and AI4HC into a single event. The 18 revised full papers included in this volume were carefully selected from th...

This paper explores whether a simple grammar-based metric can accurately predict human opinion of machine-generated song lyrics squality. The proposed metric considers the percentage of words written in natural English and the number of grammatical errors to rate the quality of machine-generated lyrics. We use a state-of-the-art Recurrent Neural Ne...

Siamese Neural Networks (SNNs) are deep metric learners that use paired instance comparisons to learn similarity. The neural feature maps learnt in this way provide useful representations for classification tasks. Learning in SNNs is not reliant on explicit class knowledge; instead they require knowledge about the relationship between pairs. Though...

Within any sufficiently expertise-reliant and work-driven domain there is a requirement to understand the similarities between specific work tasks. Though mechanisms to develop similarity models for these areas do exist, in practice they have been criticised within various domains by experts who feel that the output is not indicative of their viewp...

Aspect-level sentiment analysis of customer feedback data when done accurately can be leveraged to understand strong and weak performance points of businesses and services and also formulate critical action steps to improve their performance. In this work we focus on aspect-level sentiment classification studying the role of opinion context extract...

Theoretical frameworks in psychology map the relationships between emotions and sentiments. In this paper, we study the role of such mapping for computational emotion detection from text (e.g., social media) with an aim to understand the usefulness of an emotion‐rich corpus of documents (e.g., tweets) to learn polarity lexicons for sentiment analys...

Human Activity Recognition (HAR) is typically modelled as a classification task where sensor data associated with activity labels are used to train a classifier to recognise future occurrences of these activities. An important consideration when training HAR models is whether to use training data from a general population (subject-independent), or...

Multiple sensor modalities provide more accurate Human Activity Recognition (HAR) compared to using a single modality, yet the latter is preferred by consumers as it is more convenient and less intrusive. This presents a challenge to researchers, as a single modality is likely to pick up movement that is both relevant as well as extraneous to the h...

Sentiment analysis is the computational study of opinionated text and is becoming increasing important to online commercial applications. However, the majority of current approaches determine sentiment by attempting to detect the overall polarity of a sentence, paragraph, or text window, but without any knowledge about the entities mentioned (e.g....

Semantic annotation is an enabling technology which links documents to concepts that unambiguously describe their content. Annotation improves access to document contents for both humans and software agents. However, the annotation process is a challenging task as annotators often have to select from thousands of potentially relevant concepts from...

The automated classification of text documents is an active research challenge in document-oriented information systems, helping users browse massive amounts of data, detecting likely authors of unsigned work, or analyzing large corpora along predefined dimensions of interest such as sentiment or emotion. Existing approaches to text classification...

selfBACK is an mHealth decision support system used by patients for the self-management of Lower Back Pain. It uses Human Activity Recognition from wearable sensors to monitor user activity in order to measure their adherence to prescribed physical activity plans. Different feature representation approaches have been proposed for Human Activity Rec...

The need to adhere to recommended physical activity guidelines for a variety of chronic disorders calls for high precision Human Activity Recognition (HAR) systems. In the SelfBACK system, HAR is used to monitor activity types and intensities to enable self-management of low back pain (LBP). HAR is typically modelled as a classification task where...

Large-scale social media classification faces the following two challenges: algorithms can be hard to adapt to Web-scale data, and the predictions that they provide are difficult for humans to understand. Those two challenges are solved at the cost of some accuracy by lexicon-based classifiers, which offer a white-box approach to text mining by usi...

Online content has shifted from static and document-oriented to dynamic and discussion-oriented, leading users to spend an increasing amount of time navigating online discussions in order to participate in their social network. Recent work on emotional contagion in social networks has shown that information is not neutral and affects its receiver....

General-purpose emotion lexicons (GPELs) that associate words with emotion categories remain a valuable resource for emotion detection. However, the static and formal nature of their vocabularies make them an inadequate resource for detecting emotions in domains that are inherently dynamic in nature. This calls for lexicons that are not only adapti...

General Purpose Emotion Lexicons (GPELs) that associate words with emotion categories remain a valuable resource for emotion analysis of text. However the static and formal nature of their vocabularies make them inadequate for extracting effective features for document representation, in domains that are inherently dynamic in nature (e.g. Social Me...

Low back pain (LBP) is the most significant contributor to years lived with disability in Europe and results in significant financial cost to European economies. Guidelines for the management of LBP have self-management at their cornerstone, where patients are advised against bed rest, and to remain active. In this paper, we introduce SELFBACK, a d...

Conceptual frameworks for emotion to sentiment mapping have been proposed in Psychology research. In this paper we study this mapping from a computational modelling perspective with a view to establish the role of an emotion-rich corpus for lexicon-based sentiment analysis. We propose two different methods which harness an emotion-labelled corpus o...

The lexicon-based approaches to opinion mining involve the extraction of term polarities from sentiment lexicons and the aggregation of such scores to predict the overall sentiment of a piece of text. It is typically preferred where sentiment labelled data is difficult to obtain or algorithm robustness across different domains is essential. A major...

In this paper, we extend our previous work on social recommender systems to harness knowledge from product reviews. By mining product reviews, we can exploit sentiment-rich content to ascertain user opinion expressed over product aspects. Aspect aware sentiment analysis provides a more structured approach to product comparison. However, aspects ext...

The lexicon-based approach to opinion mining is typically preferred where training data is difficult to obtain or cross domain robustness of algorithms is of essence. However, this approach suffers from the semantic gap between the polarity with which a sentiment-bearing term appears in the text (i.e. contextual polarity) and its prior polarity cap...

This volume presents a collection of carefully selected contributions in the area of social media analysis. Each chapter opens up a number of research directions that have the potential to be taken on further in this rapidly growing area of research. The chapters are diverse enough to serve a number of directions of research with Sentiment Analysis...

Sentiment lexicon is a crucial resource for opinion mining from social media content. However, standard off-the-shelve lexicons are static and typically do not adapt, in content and context, to a target domain. This limitation, adversely affects the effectiveness of sentiment analysis algorithms. In this paper, we introduce the idea of distant-supe...

Capturing users’ preference that change over time is a great challenge in recommendation systems. What makes a product feature interesting now may become the accepted standard in the future. Social recommender systems that harness knowledge from user expertise and interactions to provide recommendation have great potential in capturing such trendin...

Indexing of textual cases is commonly affected by the problem of variation in vocabulary. Semantic indexing is commonly used to address this problem by discovering semantic or conceptual relatedness between individual terms and using this to improve textual case representation. However, representations produced using this approach are not optimal f...

Social recommender systems harness knowledge from social experiences, expertise and interactions. In this paper we focus on two such knowledge sources: sentiment-rich user generated reviews; and preferences from purchase summary statistics. We formalise the integration of these knowledge sources by mixing a novel aspect-based sentiment ranking with...

Research in emotion analysis of text suggest that emotion lexicon based features are superior to corpus based n-gram features. However the static nature of the general purpose emotion lexicons make them less suited to social media analysis, where the need to adopt to changes in vocabulary usage and context is crucial. In this paper we propose a set...

General knowledge sentiment lexicons have the advantage of wider term coverage. However, such lexicons typically have inferior performance for sentiment classification compared to using domain focused lexicons or machine learning classifiers. Such poor performance can be attributed to the fact that some domain-specific sentiment-bearing terms may n...

An important application domain for Machine learning is sentiment classification. Here, the traditional approach is to represent documents using a Bag-Of-Words (BOW) model, where individual terms are used as features. However, the BOW model is unable to sufficiently model the variation inherent in natural language text. Term-relatedness metrics are...

Automatically generated sentiment lexicons offer sentiment information for a large number of terms and often at a more granular level than manually generated ones. While such rich information has the potential of enhancing sentiment analysis, it also presents the challenge of finding the best possible strategy to utilising the information. In Senti...

The variation in natural language vocabulary remains a challenge for text representation as the same idea can be expressed in many different ways. Thus document representations often rely on generalisation to map low-level lexical expressions to higher level concepts in order to capture the inherent semantics of the documents. Term-relatedness meas...

It has been proven experimentally, that a combination of textual and visual representations can improve the retrieval performance ([20], [23]). It is due to the fact, that the textual and visual feature spaces often represent complementary yet correlated aspects of the same image, thus forming a composite system. In this paper, we present a model...

In this paper, we propose a model for direct incorporation of image content into a (short-term) user profile based on correlations between visual words and adaptation of the similarity measure. The relationships between visual words at different contextual levels are explored. We introduce and compare various notions of correlation, which in genera...

Textual case-based reasoning (TCBR) solves new problems by reusing previous similar problem-solving experiences documented as text. During reuse, TCBR identifies reusable textual constructs in the retrieved solution content and differentiates from the rest that need revision. However, reuse is heavily influenced by the quality of retrieval since TC...

This paper presents a novel approach to music genre classification. Having represented music tracks in the form of two dimensional images, we apply the “bag of visual words” method from visual IR in order to classify the songs into 19 genres. By switching to visual domain, we can abstract from musical concepts such as melody, timbre and rhythm. We...

We consider the problem of segmenting text documents that have a two-part structure such as a problem part and a solution part. Documents of this genre include incident reports that typically involve description of events relating to a problem followed by those pertaining to the solution that was tried. Segmenting such documents into the component...

Textual Case-Based Reasoning (TCBR) aims at effective reuse of past problem-solving experiences that are predominantly captured in unstructured form. The absence of structure and a well-defined feature space makes comparison of these experiential cases difficult. Since reasoning is primarily dependent on retrieval of similar cases, the acquisition...