Most available evidence for treatment and outcome prediction in traumatic brain injuries (TBI) is derived from observational studies. Such association studies provide limited evidence for the causality of relationships. While randomized controlled trials are appropriately regarded as the gold standard for causal inference, there are many domains where such experimental approaches are not feasible. During the last decades however, mathematical methods have been developed to infer causal relationships from observational data. This study aims to investigate causal relations of systemic and cerebral physiological parameters, intracranial pressure (ICP)-lowering interventions, and outcome in patients with severe TBI. Patients with severe TBI enrolled in the prospective observational Collaborative European Neurotrauma Effectiveness Research in TBI (CENTER-TBI) High-Resolution Substudy group were included (n = 201). We applied a causal inference algorithm to determine causal relations between the first week post-injury mean of values of ICP, cerebrovascular reactivity (PRx), cerebral perfusion pressure (CPP), heart rate, oxygen saturation, arterial partial pressure of carbon dioxide, ICP-lowering therapies [represented by the therapy intensity level (TIL) score], and 6-month outcome represented by Glasgow Outcome Scale-Extended (GOSE). The median age was 51.5 years [interquartile range (IQR) 31 to 64], 158 were men (77.5

Anomaly detection is an essential component for ensuring the safety and reliability of critical systems. Currently, most machine learning-based anomaly detection approaches rely purely on correlations among sensor signals, rather than causal relations, making them susceptible to spurious associations. This limitation can lead to poor generalization and unreliable anomaly detection in practical scenarios. To address this, we propose an anomaly detection approach which leverages score-based causal discovery, NTS-DAGMA. This causal discovery method advances over prior work by combining the network architecture from NTS-NOTEARS with the acyclicity constraint from DAGMA. Like other prediction-based anomaly detection methods, it can predict future states; however, it does this by learning and utilizing causal relations in the time series data. Through comprehensive experiments, we demonstrate that: (i) on causal discovery tasks NTS-NOTEARS and NTS-DAGMA achieve similar performances; (ii) on anomaly detection tasks NTS-NOTEARS and NTS-DAGMA also perform similar to each other, and have comparable performance to state-of-the-art ML approaches; and (iii) most importantly, our results show that NTS-DAGMA provides causally meaningful models: detects anomalies which propagate through child nodes in agreement with the inferred causal graph. Incorporating causal structure into the model enables improved interpretability and aligns anomaly detection with the physical dynamics of the system.

Predictive maintenance requires reliable remaining useful life (RUL) estimation. Existing methods mainly follow two paradigms: wear-based aging models that capture cumulative degradation and sensor-driven data models that reflect instantaneous health conditions, each providing only partial information. In this work, we propose a probabilistic fusion framework that integrates wear-based and sensor-based prognostic components through failure probability distributions. Based on explicit structural assumptions linking wear, latent health, sensor observations, and failure, we derive a principled combination rule that enables uncertainty-aware integration with adaptive weighting of the components. Experimentally, we assess this combination rule by learning the wear-based component using a parametric survival model and the sensor-based component using a 1D convolutional neural network (1D-CNN) with a post-hoc uncertainty model. Evaluation on multiple N-CMAPSS datasets demonstrates that the fused model improves point accuracy, preserves the C-index, and produces narrower yet well-calibrated prediction intervals compared to either component alone. The results highlight the complementary roles of wear-based survival model and sensor-based deep learning model, and show that their probabilistic integration provides a structured pathway toward more robust and consistent prognostics over the life-time.

In the ever-evolving adversarial machine learning landscape, developing effective defenses against patch attacks has become a critical challenge, necessitating reliable solutions to safeguard real-world AI systems. Although diffusion models have shown remarkable capacity in image synthesis and have been recently utilized to counter $l^{p}$-norm bounded attacks, their potential in mitigating localized patch attacks remains largely underexplored. In this work, we propose DiffPAD, a novel framework that harnesses the power of diffusion models for adversarial patch decontamination. DiffPAD first performs super-resolution restoration on downsampled input images, then adopts binarization, dynamic thresholding scheme and sliding window for effective localization of adversarial patches. Such a design is inspired by the theoretically derived correlation between patch size and diffusion restoration error that is generalized across diverse patch attack scenarios. Finally, DiffPAD applies inpainting techniques to the original input images with the estimated patch region being masked. By integrating closed-form solutions for super-resolution restoration and image inpainting into the conditional reverse sampling process of a pre-trained diffusion model, DiffPAD obviates the need for text guidance or fine-tuning. Through comprehensive experiments, we demonstrate that DiffPAD not only achieves state-of-the-art adversarial robustness against patch attacks but also excels in recovering naturalistic images without patch remnants. The source code is available at https://github.com/JasonFu1998/DiffPAD.

The complexity of modern electro-mechanical systems require the development of sophisticated diagnostic methods like anomaly detection capable of detecting deviations. Conventional anomaly detection approaches like signal processing and statistical modelling often struggle to effectively handle the intricacies of complex systems, particularly when dealing with multi-variate signals. In contrast, neural network-based anomaly detection methods, especially Auto-Encoders, have emerged as a compelling alternative, demonstrating remarkable performance. However, Auto-Encoders exhibit inherent opaqueness in their decision-making processes, hindering their practical implementation at scale. Addressing this opacity is essential for enhancing the interpretability and trustworthiness of anomaly detection models. In this work, we address this challenge by employing a feature selector to select features and counterfactual explanations to give a context to the model output. We tested this approach on the SKAB benchmark dataset and an industrial time-series dataset. The gradient based counterfactual explanation approach was evaluated via validity, sparsity and distance measures. Our experimental findings illustrate that our proposed counterfactual approach can offer meaningful and valuable insights into the model decision-making process, by explaining fewer signals compared to conventional approaches. These insights enhance the trustworthiness and interpretability of anomaly detection models.

Vision Language Models (VLMs) have shown remarkable capabilities in multimodal understanding, yet their susceptibility to adversarial perturbations poses a significant threat to their reliability in real-world applications. Despite often being imperceptible to humans, these perturbations can drastically alter model outputs, leading to erroneous interpretations and decisions. This paper introduces DiffCAP, a novel diffusion-based purification strategy that can effectively neutralize adversarial corruptions in VLMs. We theoretically establish a provable recovery region in the forward diffusion process and meanwhile quantify the convergence rate of semantic variation with respect to VLMs. These findings manifest that adversarial effects monotonically fade as diffusion unfolds. Guided by this principle, DiffCAP leverages noise injection with a similarity threshold of VLM embeddings as an adaptive criterion, before reverse diffusion restores a clean and reliable representation for VLM inference. Through extensive experiments across six datasets with three VLMs under varying attack strengths in three task scenarios, we show that DiffCAP outperforms existing defense techniques by a substantial margin. Notably, DiffCAP significantly reduces both hyperparameter tuning complexity and the required diffusion time, thereby accelerating the denoising process. Equipped with theorems and empirical support, DiffCAP provides a robust and practical solution for securely deploying VLMs in adversarial environments. The source code is available at https://github.com/JasonFu1998/DiffCAP.

BACKGROUND:Patients with traumatic brain injury are a heterogeneous population, and the most severely injured individuals are often treated in an intensive care unit (ICU). The primary injury at impact, and the harmful secondary events that can occur during the first week of the ICU stay, will affect outcome in this vulnerable group of patients. We aimed to identify clinical variables that might distinguish disease trajectories among patients with traumatic brain injury admitted to the ICU.METHODS:We used data from the Collaborative European NeuroTrauma Effectiveness Research in Traumatic Brain Injury (CENTER-TBI) prospective observational cohort study. We included patients aged 18 years or older with traumatic brain injury who were admitted to the ICU at one of the 65 CENTER-TBI participating centres, which range from large academic hospitals to small rural hospitals. For every patient, we obtained pre-injury data and injury features, clinical characteristics on admission, demographics, physiological parameters, laboratory features, brain biomarkers (ubiquitin carboxy-terminal hydrolase L1 [UCH-L1], S100 calcium-binding protein B [S100B], tau, neurofilament light [NFL], glial fibrillary acidic protein [GFAP], and neuron-specific enolase [NSE]), and information about intracranial pressure lowering treatments during the first 7 days of ICU stay. To identify clinical variables that might distinguish disease trajectories, we applied a novel clustering method to these data, which was based on a mixture of probabilistic graph models with a Markov chain extension. The relation of clusters to the extended Glasgow Outcome Scale (GOS-E) was investigated.FINDINGS:Between Dec 19, 2014, and Dec 17, 2017, 4509 patients with traumatic brain injury were recruited into the CENTER-TBI core dataset, of whom 1728 were eligible for this analysis. Glucose variation (defined as the difference between daily maximum and minimum glucose concentrations) and brain biomarkers (S100B, NSE, NFL, tau, UCH-L1, and GFAP) were consistently found to be the main clinical descriptors of disease trajectories (ie, the leading variables contributing to the distinguishing clusters) in patients with traumatic brain injury in the ICU. The disease trajectory cluster to which a patient was assigned in a model was analysed as a predictor together with variables from the IMPACT model, and prediction of both mortality and unfavourable outcome (dichotomised GOS-E ≤4) was improved.INTERPRETATION:First-day ICU admission data are not the only clinical descriptors of disease trajectories in patients with traumatic brain injury. By analysing temporal variables in our study, variation of glucose was identified as the most important clinical descriptor that might distinguish disease trajectories in the ICU, which should direct further research. Biomarkers of brain injury (S100B, NSE, NFL, tau, UCH-L1, and GFAP) were also top clinical descriptors over time, suggesting they might be important in future clinical practice.FUNDING:European Union 7th Framework program, Hannelore Kohl Stiftung, OneMind, Integra LifeSciences Corporation, and NeuroTrauma Sciences.

A core part of maintenance planning is a monitoring system that provides a good prognosis on health and degradation, often expressed as remaining useful life (RUL). Most of the current data-driven approaches for RUL prediction focus on single-point prediction. These point prediction approaches do not include the probabilistic nature of the failure. The fewprobabilistic approaches to date either include the aleatoric uncertainty (which originates from the system), or the epistemic uncertainty (which originates from the model param-eters), or both simultaneously as a total uncertainty. Here, we propose ensemble neural networks for probabilistic RUL predictions which considers both uncertainties and decouples these two uncertainties. These decoupled uncertainties are vital in knowing and interpreting the confidence of the predictions. This method is tested on NASA’s turbofan jet engine CMAPSS data-set. Our results show how these uncertainties can be modeled and how to disentangle the contribution of aleatoric and epistemic uncertainty. Additionally, our approach is evaluated on different metrics and compared against the current state-of-the-art methods.

Numerical models based on the linear potential flow equations are of paramount importance in the design of wave energy converters (WECs). Over the years methods such as wave stretching, nonlinear Froude-Krylov and Morrison drag have been developed to overcome the short-comings of the underlying assumptions of small amplitude wave, small motion and inviscous flow. In this work we present a different approach to enhance the performance of the linear method: a hybrid linear potential flow – machine learning (LPF-ML) model. A hierarchy of high-fidelity models – Reynolds-Averaged Navier-Stokes, Euler and fully nonlinear potential flow – is used to create training data for correction factors targeting nonlinear hydrodynamics, pressure drag and skin friction, respectively. Long short-term memory (LSTM) networks are then trained and added to the LPF model. LSTM networks are heavy to train but fast to evaluate so the computational efficiency of the LPF model is kept high. Simple decay tests of generic bodies (sphere, box, etc) are used to validate the LPF-ML model. Finally, the LPF-ML is applied to a model-scale point-absorber WEC to assess the power production.

Maintenance and services of products as well as processes are pivotal for achieving high availability and avoiding catastrophic and costly failures. At the same time, maintenance is routinely performed more frequently than necessary, replacing possibly functional components, which has negative economic impact on the maintenance. New processes and products need to fulfil increased environmental demands, while customers put increasing demands on customization and coordination. Hence, improved maintenance processes possess very high potentials, economically as well as environmentally. The shifting demands on product development and production processes have led to the emergency of new digital solutions as well as new business models, such as integrated product-service offerings. Still, the general maintenance problem of how to perform the right service at the right time, taking available information and given limitations is valid. The project Future Industrial Services Management (FUSE) project was a step in a long-term effort for catalysing the evolution of maintenance and production in the current digital era. In this paper, several aspects of the general maintenance problem are discussed from a data driven perspective, spanning from technology solutions and organizational requirements to new business opportunities and how to create optimal maintenance plans. One of the main results of the project, in the form of a simulation tool for strategy selection, is also described.

Background Survivors of childhood cancer can develop adverse health events later in life. Infrequent occurrences and scarcity of structured information result in analytical and statistical challenges. Alternative statistical approaches are required to investigate the basis of late effects in smaller data sets. Methods Here we describe sex-specific health care use, mortality and causal associations between primary diagnosis, treatment and outcomes in a small cohort ( n = 2315) of 5-year survivors of childhood cancer ( n = 2129) in southern Sweden and a control group ( n = 11,882; age-, sex- and region-matched from the general population). We developed a constraint-based method for causal inference based on Bayesian estimation of distributions, and used it to investigate health care use and causal associations between diagnoses, treatments and outcomes. Mortality was analyzed by the Kaplan–Meier method. Results Our results confirm a significantly higher health care usage and premature mortality among childhood cancer survivors as compared to controls. The developed method for causal inference identifies 98 significant associations ( p < 0.0001) where most are well known ( n = 73; 74.5%). Hitherto undescribed associations are identified ( n = 5; 5.1%). These were between use of alkylating agents and eye conditions, topoisomerase inhibitors and viral infections; pituitary surgery and intestinal infections; and cervical cancer and endometritis. We discuss study-related biases ( n = 20; 20.4%) and limitations. Conclusions The findings contribute to a broader understanding of the consequences of cancer treatment. The study shows relevance for small data sets and causal inference, and presents the method as a complement to traditional statistical approaches.

Abstract Background While the Glasgow coma scale (GCS) is one of the strongest outcome predictors, the current classification of traumatic brain injury (TBI) as ‘mild’, ‘moderate’ or ‘severe’ based on this fails to capture enormous heterogeneity in pathophysiology and treatment response. We hypothesized that data-driven characterization of TBI could identify distinct endotypes and give mechanistic insights. Methods We developed an unsupervised statistical clustering model based on a mixture of probabilistic graphs for presentation (< 24 h) demographic, clinical, physiological, laboratory and imaging data to identify subgroups of TBI patients admitted to the intensive care unit in the CENTER-TBI dataset (N = 1,728). A cluster similarity index was used for robust determination of optimal cluster number. Mutual information was used to quantify feature importance and for cluster interpretation. Results Six stable endotypes were identified with distinct GCS and composite systemic metabolic stress profiles, distinguished by GCS, blood lactate, oxygen saturation, serum creatinine, glucose, base excess, pH, arterial partial pressure of carbon dioxide, and body temperature. Notably, a cluster with ‘moderate’ TBI (by traditional classification) and deranged metabolic profile, had a worse outcome than a cluster with ‘severe’ GCS and a normal metabolic profile. Addition of cluster labels significantly improved the prognostic precision of the IMPACT (International Mission for Prognosis and Analysis of Clinical trials in TBI) extended model, for prediction of both unfavourable outcome and mortality (both p < 0.001). Conclusions Six stable and clinically distinct TBI endotypes were identified by probabilistic unsupervised clustering. In addition to presenting neurology, a profile of biochemical derangement was found to be an important distinguishing feature that was both biologically plausible and associated with outcome. Our work motivates refining current TBI classifications with factors describing metabolic stress. Such data-driven clusters suggest TBI endotypes that merit investigation to identify bespoke treatment strategies to improve care. Trial registration The core study was registered with ClinicalTrials.gov, number NCT02210221 , registered on August 06, 2014, with Resource Identification Portal (RRID: SCR_015582).

Magnitude of intracranial pressure (ICP) elevations and their duration have been associated with worse outcomes in patients with traumatic brain injuries (TBI), however published thresholds for injury vary and uncertainty about these levels has received relatively little attention. In this study, we have analyzed high-resolution ICP monitoring data in 227 adult patients in the CENTER-TBI dataset. Our aim was to identify thresholds of ICP intensity and duration associated with worse outcome, and to evaluate the uncertainty in any such thresholds. We present ICP intensity and duration plots to visualize the relationship between ICP events and outcome. We also introduced a novel bootstrap technique to evaluate uncertainty of the equipoise line. We found that an intensity threshold of 18 ± 4 mmHg (2 standard deviations) was associated with worse outcomes in this cohort. In contrast, the uncertainty in what duration is associated with harm was larger, and safe durations were found to be population dependent. The pressure and time dose (PTD) was also calculated as area under the curve above thresholds of ICP. A relationship between PTD and mortality could be established, as well as for unfavourable outcome. This relationship remained valid for mortality but not unfavourable outcome after adjusting for IMPACT core variables and maximum therapy intensity level. Importantly, during periods of impaired autoregulation (defined as pressure reactivity index (PRx)>0.3) ICP events were associated with worse outcomes for nearly all durations and ICP levels in this cohort and there was a stronger relationship between outcome and PTD. Whilst caution should be exercised in ascribing causation in observational analyses, these results suggest intracranial hypertension is poorly tolerated in the presence of impaired autoregulation. ICP level guidelines may need to be revised in the future taking into account cerebrovascular autoregulation status considered jointly with ICP levels.

We approach the problem of identifying and interpreting clusters over different time scales and granularity in multivariate time series data. We extract statistical features over a sliding window of each time series, and then use a Gaussian mixture model to identify clusters which are then projected back on the data streams. The human analyst can then further analyze this projection and adjust the size of the sliding window and the number of clusters in order to capture the different types of clusters over different time scales. We demonstrate the effectiveness of our approach in two different application scenarios: (1) fleet management and (2) district heating, wherein each scenario, several different types of meaningful clusters can be identified when varying over these dimensions.

Many methods have been proposed over the years for distinguishing causes from effects using observational data only, and new ones are continuously being developed – deducing causal relationships is ...

This paper demonstrates how to explore and visualize different types of structure in data, including clusters, anomalies, causal relations, and higher order relations. The methods are developed wit ...

Discovering causal relations from limited amounts of data can be useful for many applications. However, all causal discovery algorithms need huge amounts of data to estimate the underlying causal graph. To alleviate this gap, this paper proposes a novel visualization tool which incrementally discovers causal relations as more data becomes available. That is, we assume that stronger causal links will be detected quickly and weaker links revealed when enough data is available. In addition to causal links, the correlation between variables and the uncertainty of the strength of causal links are visualized in the same graph. The tool is illustrated on three example causal graphs, and results show that incremental discovery works and that the causal structure converges as more data becomes available.

Most existing work in information fusion focuses on combining information with well-defined meaning towards a concrete, pre-specified goal. In contradistinction, we instead aim for autonomous discovery of high-level knowledge from ubiquitous data streams. This paper introduces a method for recognition and tracking of hidden conceptual modes, which are essential to fully understand the operation of complex environments, and an important step towards building truly intelligent aware systems. We consider a scenario of analyzing usage of a fleet of city buses, where the objective is to automatically discover and track modes such as highway route, heavy traffic, or aggressive driver, based on available on-board signals. The method we propose is based on aggregating the data over time, since the high-level modes are only apparent in the longer perspective. We search through different features and subsets of the data, and identify those that lead to good clusterings, interpreting those clusters as initial, rough models of the prospective modes. We utilize Bayesian tracking in order to continuously improve the parameters of those models, based on the new data, while at the same time following how the modes evolve over time. Experiments with artificial data of varying degrees of complexity, as well as on real-world datasets, prove the effectiveness of the proposed method in accurately discovering the modes and in identifying which one best explains the current observations from multiple data streams.

The pylSC is a Python API and extension to the C++ based Incremental Stream Clustering (ISC) anomaly detection and classification framework. The framework is based on parametric Bayesian statistica ...

This paper presents the Gavagai Living Lexicon, which is an online distributional semantic model currently available in 20 different languages. We describe the underlying distributional semantic model, and how we have solved some of the challenges in applying such a model to large amounts of streaming data. We also describe the architecture of our implementation, and discuss how we deal with continuous quality assurance of the lexicon.