Adversarial attacks pose a significant threat to machine learning models by inducing incorrect predictions through imperceptible perturbations to input data. While these attacks are well studied in unstructured domains such as images, their behaviour on tabular data remains underexplored due to mixed feature types and complex inter-feature dependencies. This study introduces a comprehensive benchmark that evaluates adversarial attacks on tabular datasets with respect to both effectiveness and imperceptibility. We assess five white-box attack algorithms (FGSM, BIM, PGD, DeepFool, and C&W) across four representative models (LR, MLP, TabTransformer and FT-Transformer) using eleven datasets spanning finance, energy, and healthcare domains. The benchmark employs four quantitative imperceptibility metrics (proximity, sparsity, deviation, and sensitivity) to characterise perturbation realism. The analysis quantifies the trade-off between these two aspects and reveals consistent differences between attack types, with ℓ ∞ -based attacks achieving higher success but lower subtlety, and ℓ 2 -based attacks offering more realistic perturbations. The benchmark findings offer actionable insights for designing more imperceptible adversarial attacks, advancing the understanding of adversarial vulnerability in tabular machine learning.

We introduce HeadZoom, a hands-free interaction technique for navigating two-dimensional visual content using head movements. HeadZoom enables fluid zooming and panning using only real-time head tracking. It supports natural control in applications such as map exploration, radiograph inspection, and image browsing, where physical interaction is limited. We evaluated HeadZoom in a withinsubjects study comparing three interaction techniques-Static, Tilt Zoom, and Parallel Zoom-across spatial, error, and subjective metrics. Parallel Zoom significantly reduced total head movement compared to Static and Tilt modes. Users reported significantly lower perceived exertion for Parallel Zoom, confirming its suitability for prolonged or precision-based tasks. By minimizing movement demands while maintaining task effectiveness, HeadZoom advances the design of head-based 2D interaction in VR and creates new opportunities for accessible hands-free systems for image exploration.

The usage of virtual avatars in healthcare applications has become widely popular; however, certain critical aspects, such as social distancing and avatar size, remain insufficiently explored. This research investigates user experience and preferences when interacting with a healthcare application utilizing virtual avatars displayed in different sizes. For our study, we had 23 participants interacting with five different avatars (a human-size avatar followed by four, respectively, smaller avatars in a randomized order) varying in size, projected on a wall in front of them. The avatars were fully integrated with an artificial intelligence chatbot to make them conversational. Users were asked to rate the usability of the system after interacting with each avatar and complete a survey regarding trust and an additional questionnaire on social presence. The results of this study show that avatar size significantly influences the perceived attractiveness and perspicuity with the medium-sized avatars having received the highest ratings. Social presence correlated strongly with stimulation and attractiveness, suggesting that an avatar’s visual appeal and interactivity influenced user engagement more than its physical size. Additionally, we observed a tendency for gender-specific differences on some of the UEQ+ scales, with male participants tending to prefer human-sized representations, while female participants slightly favored smaller avatars. These findings highlight the importance of avatar design and representation in optimizing user experience and trust in virtual healthcare environments.

Explainable Artificial Intelligence (XAI) techniques are used to provide transparency to complex, opaque predictive models. However, these techniques are often designed for image and text data, and it is unclear how fit-for-purpose they are when applied to tabular data. As XAI techniques are rarely evaluated in the context of tabular data, the applicability of existing evaluation criteria and methods are also unclear and needs re-examination. For example, some works suggest that evaluation methods may unduly influence the evaluation results when using tabular data. This lack of clarity on evaluation procedures can lead to reduced transparency and ineffective use of XAI techniques in real world settings. In this study, we examine literature on XAI evaluation to derive guidelines on functionally-grounded assessment of local, post hoc XAI techniques. We identify 20 evaluation criteria and associated evaluation methods, and derive guidelines on when and how each criterion should be evaluated. We also identify key research gaps to be addressed by future work. Our study contributes to the body of knowledge on XAI evaluation through in-depth examination of functionally-grounded XAI evaluation protocols, and has laid the groundwork for future research on XAI evaluation.

Abstract Hyperspectral unmixing (HU) involves separating mixed pixel spectra into pure endmember spectra and their corresponding abundance fractions. However, it faces significant challenges due to outliers in the hyperspectral data, which often appear as pixel and band anomalies. Outliers in pixels could result in incorrect classification and inaccurate quantification of materials, while outliers in bands could alter spectral characteristics, leading to misidentifying endmembers and incorrect estimates of abundance. To tackle these issues, this paper introduces a new approach, named simultaneous outlier detection and elimination via weighted non-negative matrix tri-factorization (SODE-WNMTF), which offers an efficient means of addressing the impact of outliers in the unmixing process. Leveraging the co-clustering property of NMTF, SODE-WNMTF introduces a novel weighting matrix, which involves simultaneous clustering of both pixels and spectral bands to effectively detect and mitigate the negative impact of both pixel and band outliers during the unmixing process. At the same time, the inherent structure of the hyperspectral image (HSI) is utilized through the examination of local and global connections among pixels and spectral bands, consequently improving the co-clustering procedure. In addition, SODE-WNMTF proposes a spatial weighting factor, which utilizes the similarity of adjacent pixels, to promote piecewise smoothness in abundance maps while mitigating the impact of outliers. Moreover, since pixels in regions dominated by a single endmember exhibit spectra closely resembling that endmember, SODE-WNMTF incorporates a sparse estimation technique for endmember signatures. Finally, to verify the performance of SODE-WNMTF, a series of experiments is conducted on both synthetic and real HSIs, with outcomes proving its superiority against other cutting-edge approaches. The source code is also available at https://github.com/yasinhashemi/SODE-WNMTF .

Abstract In image-based medical decision-making, different modalities of medical images of a given organ of a patient are captured. Each of these images will represent a modality that will render the examined organ differently, leading to different observations of a given phenomenon (such as stroke). The accurate analysis of each of these modalities promotes the detection of more appropriate medical decisions. Multimodal medical imaging is a research field that consists in the development of robust algorithms that can enable the fusion of image information acquired by different sets of modalities. In this paper, a novel multimodal medical image fusion algorithm is proposed for a wide range of medical diagnostic problems. It is based on the application of a boundary measured pulse-coupled neural network fusion strategy and an energy attribute fusion strategy in a non-subsampled shearlet transform domain. Our algorithm was validated in dataset with modalities of several diseases, namely glioma, Alzheimer’s, and metastatic bronchogenic carcinoma, which contain more than 100 image pairs. Qualitative and quantitative evaluation verifies that the proposed algorithm outperforms most of the current algorithms, providing important ideas for medical diagnosis.

In recent years, various machine and deep learning architectures have been successfully introduced to the field of predictive process analytics. Nevertheless, the inherent opacity of these algorithms poses a significant challenge for human decision-makers, hindering their ability to understand the reasoning behind the predictions. This growing concern has sparked the introduction of counterfactual explanations, designed as human-understandable ‘what if’ scenarios, to provide clearer insights into the decision-making process behind undesirable predictions. The generation of counterfactual explanations, however, encounters specific challenges when dealing with the sequential nature of the (business) process cases typically used in predictive process analytics. Our paper tackles this challenge by introducing a data-driven approach, REVISED$^{+}$, to generate more feasible and plausible counterfactual explanations. First, we restrict the counterfactual algorithm to generate counterfactuals that lie within a high-density region of the process data, ensuring that the proposed counterfactuals are realistic and feasible within the observed process data distribution. Additionally, we ensure plausibility by learning sequential patterns between the activities in the process cases, utilising Declare language templates. Finally, we evaluate the properties that define the validity of counterfactuals.

Deep learning (DL) in orthopaedics has gained significant attention in recent years. Previous studies have shown that DL can be applied to a wide variety of orthopaedic tasks, including fracture detection, bone tumour diagnosis, implant recognition, and evaluation of osteoarthritis severity. The utilisation of DL is expected to increase, owing to its ability to present accurate diagnoses more efficiently than traditional methods in many scenarios. This reduces the time and cost of diagnosis for patients and orthopaedic surgeons. To our knowledge, no exclusive study has comprehensively reviewed all aspects of DL currently used in orthopaedic practice. This review addresses this knowledge gap using articles from Science Direct, Scopus, IEEE Xplore, and Web of Science between 2017 and 2023. The authors begin with the motivation for using DL in orthopaedics, including its ability to enhance diagnosis and treatment planning. The review then covers various applications of DL in orthopaedics, including fracture detection, detection of supraspinatus tears using MRI, osteoarthritis, prediction of types of arthroplasty implants, bone age assessment, and detection of joint-specific soft tissue disease. We also examine the challenges for implementing DL in orthopaedics, including the scarcity of data to train DL and the lack of interpretability, as well as possible solutions to these common pitfalls. Our work highlights the requirements to achieve trustworthiness in the outcomes generated by DL, including the need for accuracy, explainability, and fairness in the DL models. We pay particular attention to fusion techniques as one of the ways to increase trustworthiness, which have also been used to address the common multimodality in orthopaedics. Finally, we have reviewed the approval requirements set forth by the US Food and Drug Administration to enable the use of DL applications. As such, we aim to have this review function as a guide for researchers to develop a reliable DL application for orthopaedic tasks from scratch for use in the market.

Radiologists are trained professionals who use medical images to obtain clinically relevant information. However, little is known about visual search patterns and strategies radiologists employ during medical image analysis. Thus, there is a current need for guidelines to specify optimal visual search routines commonly used by radiologists. Identifying these features could improve radiologist training and assist radiologists in their work. Our study found that during the moments in which radiologists view chest X-ray images in silence before verbalizing the analysis, they exhibit unique search patterns regardless of the type of disease depicted. Our findings suggest that radiologists’ search behaviors can be identified at this stage. However, when radiologists verbally interpret the X-rays, the gaze patterns appear noisy and arbitrary. Current deep-learning approaches train their systems using this noisy and arbitrary gaze data. This may explain why previous research still needs to show the superiority of deep-learning models that use eye tracking for disease classification. Our paper investigates these patterns and attempts to uncover the eye-gaze configurations during the different analysis phases.

course Share on Approaches and Challenges in XR and AI for Health Applications Authors: Joaquim Jorge INESC-ID & IST, Universidade de Lisboa INESC-ID & IST, Universidade de LisboaView Profile , João Pereira INESC-ID & IST, Universidade de Lisboa INESC-ID & IST, Universidade de LisboaView Profile , Anderson Maciel INESC-ID & IST, Universidade de Lisboa INESC-ID & IST, Universidade de LisboaView Profile , Catarina Moreira Technical University Sydney Technical University SydneyView Profile , Regis Kopper UNC Greensboro UNC GreensboroView Profile Authors Info & Claims SA '23: SIGGRAPH Asia 2023 CoursesDecember 2023Article No.: 2Pages 1–147https://doi.org/10.1145/3610538.3614640Published:06 December 2023Publication History 0citation52DownloadsMetricsTotal Citations0Total Downloads52Last 12 Months52Last 6 weeks15 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteGet Access

Process mining focuses on the analysis of event log data to build various process analytical capabilities. Predictive process analytics has emerged as one of such key capabilities and it uses machine learning techniques to construct process prediction models. In recent years, deep neural networks have gained increasing interest in process prediction since they can handle multi-dimensional sequential inputs with minimal information loss. However, they are considered black-box models and existing studies in explaining deep neural network-based process predictions rely on only event-level features for explanation. In this paper, we propose a new approach for generating explanations for process outcome predictions at multiple levels. The approach is underpinned by three different prediction models: a transparent model for generating global explanations based on case-level features, an attention-based deep neural network for generating local explanations based on event-level features, and a novel eXplainable Dual-learning Deep network (XD2-net) for generating local explanations based on case-level features. Using three publicly available datasets, we have tested the applicability of the approach and further examined the multi-level explanations generated by the approach through an elaborate case study. Unlike others, the design of our approach promotes the idea of leveraging the complementary capabilities of different models and utilizing their strengths, rather than focusing on model performance competition. This will contribute towards generating more comprehensive explanations that meet the needs of different end users and purposes in the future.

Given the tremendous potential and influence of artificial intelligence (AI) and algorithmic decision‐making (DM), these systems have found wide‐ranging applications across diverse fields, including education, business, healthcare industries, government, and justice sectors. While AI and DM offer significant benefits, they also carry the risk of unfavourable outcomes for users and society. As a result, ensuring the safety, reliability, and trustworthiness of these systems becomes crucial. This article aims to provide a comprehensive review of the synergy between AI and DM, focussing on the importance of trustworthiness. The review addresses the following four key questions, guiding readers towards a deeper understanding of this topic: (i) why do we need trustworthy AI? (ii) what are the requirements for trustworthy AI? In line with this second question, the key requirements that establish the trustworthiness of these systems have been explained, including explainability, accountability, robustness, fairness, acceptance of AI, privacy, accuracy, reproducibility, and human agency, and oversight. (iii) how can we have trustworthy data? and (iv) what are the priorities in terms of trustworthy requirements for challenging applications? Regarding this last question, six different applications have been discussed, including trustworthy AI in education, environmental science, 5G‐based IoT networks, robotics for architecture, engineering and construction, financial technology, and healthcare. The review emphasises the need to address trustworthiness in AI systems before their deployment in order to achieve the AI goal for good. An example is provided that demonstrates how trustworthy AI can be employed to eliminate bias in human resources management systems. The insights and recommendations presented in this paper will serve as a valuable guide for AI researchers seeking to achieve trustworthiness in their applications.

Predictive process analytics often apply machine learning to predict the future states of a running business process. However, the internal mechanisms of many existing predictive algorithms are opaque and a human decision-maker is unable to understand why a certain activity was predicted. Recently, counterfactuals have been proposed in the literature to derive human-understandable explanations from predictive models. Current counterfactual approaches consist of finding the minimum feature change that can make a certain prediction flip its outcome. Although many algorithms have been proposed, their application to multi-dimensional sequence data like event logs has not been explored in the literature.In this paper, we explore the use of a recent, popular model-agnostic counterfactual algorithm, DiCE, in the context of predictive process analytics. The analysis reveals that DiCE is unable to derive explanations for process predictions, due to (1) process domain knowledge not being taken into account, (2) long traces of process execution that often tend to be less understandable, and (3) difficulties in optimising the counterfactual search with categorical variables. We design an extension of DiCE, namely DiCE4EL (DiCE for Event Logs), that can generate counterfactual explanations for process prediction, and propose an approach that supports deriving milestone-aware counterfactual explanations at key intermediate stages along process execution to promote interpretability. We apply our approach to a publicly available real-life event log and the analysis results demonstrate the effectiveness of the proposed approach.

Abstract Expert finding is an information retrieval task that is concerned with the search for the most knowledgeable people with respect to a specific topic, and the search is based on documents that describe people's activities. The task involves taking a user query as input and returning a list of people who are sorted by their level of expertise with respect to the user query. Despite recent interest in the area, the current state‐of‐the‐art techniques lack in principled approaches for optimally combining different sources of evidence. This article proposes two frameworks for combining multiple estimators of expertise. These estimators are derived from textual contents, from graph‐structure of the citation patterns for the community of experts and from profile information about the experts. More specifically, this article explores the use of supervised learning to rank methods, as well as rank aggregation approaches, for combining all of the estimators of expertise. Several supervised learning algorithms, which are representative of the pointwise, pairwise and listwise approaches, were tested, and various state‐of‐the‐art data fusion techniques were also explored for the rank aggregation framework. Experiments that were performed on a dataset of academic publications from the Computer Science domain attest the adequacy of the proposed approaches.

We investigate exact indexing for high dimensional l p norms based on the 1-Lipschitz property and projection operators. The orthogonal projection that satisfies the 1-Lipschitz property for the l p norm is described. The adaptive projection defined by the first principal component is introduced.