arXiv subjects

Maria Maleshkova

Publications and source records attributed to Maria Maleshkova.

At least 19 recordsLinked to original sources

arXiv2026

Evaluating Different Modalities of Behavioral Approach Tests for Spider Phobia in Virtual Reality

Behavioral approach tests are a common means of assessing specific phobias. In these tests, participants move towards an anxiety-inducing stimulus as close as they are willing to, with the final distance indicating the severity of the anxiety. In this work, we aim to evaluate a virtual reality implementation of the BAT. For this purpose, four different BATs were designed, consisting of two approach methods, both replicated in vivo and in virtuo. Evaluation of these BATs is done by using a standardised presence questionnaire, application-specific questions, as well as the physiological reactions of the participants. The study focuses on the fear of spiders and uses a real and virtual spider as an anxiety-inducing stimulus. Our results show that the developed VR BAT perform within established presence norms, while the different modalities influenced participants' subjective impressions. Furthermore, the standardized structure of the VR environment ensured a consistent experience regarding the anxiety-inducing stimulus. This differs from the observation in the real-world setting, where the behavior of the spider might differ between individuals and also between sessions. This highlights one of the key advantages of virtual reality: complete control over the stimulus and environment. Correlations between presence and physiological signals were found. Particularly, tonic electrodermal activity levels are more stable with increased presence. However, more research into this is required, as the effects of anxiety on the physiological signals make the correlations difficult to interpret. The evaluation has revealed, which design choices are particularly promising for increasing presence in VR applications, and some which should be avoided. Overall, these results indicates that our VR-based implementation is a promising tool for assessing avoidance behavior for individuals with spider phobia.

cs.HC↗

arXiv2026

Impact of Age Specialized Models for Hypoglycemia Classification

Disease progression varies with age and is influenced by underlying genetic, biochemical, and hormonal etiologies, suggesting the need for tailored monitoring, care, and medication beyond standard clinical guidelines. Specifically, in autoimmune diseases like type 1 diabetes (T1D), where patients depend on exogenous insulin to compensate for insulin deficiency, medication dosing and the physiological response reflected in vital signs can differ. Insulin therapy can lead to hypoglycemia, a dangerous condition characterized by decreased blood glucose levels ($\leq$70). This risk can be mitigated through improved diabetes management supported by data analytics. Notably, leveraging data from continuous glucose monitoring (CGM) devices, hypoglycemia onset can be predicted. However, while glucose variability, auto-antibody levels, and hypoglycemia occurrence differ across age groups, hypoglycemia classification most often only relies on population-based models specialized in specific age ranges. In this work, we classify hypoglycemia 0, 5-15, 20-45, and 50-120 minutes before onset using DiaData, a large CGM dataset of patients with T1D ranging from children to seniors. In particular, we investigate: 1) the generalizability of a population-based model including all age groups, 2) the impact of age-segmented models trained separately per age group, and 3) the effect of model individualization through transfer learning. The results show that a global population-based model yields similar or superior performance compared to age-segmented models. These findings suggest that data from children, teenagers, and adults can be combined for training models on hypoglycemia classification. While glucose variation differs across age groups, short-term hypoglycemic patterns are similar. However, data of children obtain their best recall with age specialized model.

cs.LG↗

arXiv2026

Presenting DiaData for Research on Type 1 Diabetes

Type 1 diabetes (T1D) is an autoimmune disorder that leads to the destruction of insulin-producing cells, resulting in insulin deficiency, as to why the affected individuals depend on external insulin injections. However, insulin can decrease blood glucose levels and can cause hypoglycemia. Hypoglycemia is a severe event of low blood glucose levels ($\le$70 mg/dL) with dangerous side effects of dizziness, coma, or death. Data analysis can significantly enhance diabetes care by identifying personal patterns and trends leading to adverse events. Especially, machine learning (ML) models can predict glucose levels and provide early alarms. However, diabetes and hypoglycemia research is limited by the unavailability of large datasets. Thus, this work systematically integrates 15 datasets to provide a large database of 2510 subjects with glucose measurements recorded every 5 minutes. In total, 149 million measurements are included, of which 4% represent values in the hypoglycemic range. Moreover, two sub-databases are extracted. Sub-database I includes demographics, and sub-database II includes heart rate data. The integrated dataset provides an equal distribution of sex and different age levels. As a further contribution, data quality is assessed, revealing that data imbalance and missing values present a significant challenge. Moreover, a correlation study on glucose levels and heart rate data is conducted, showing a relation between 15 and 55 minutes before hypoglycemia.

cs.LG↗

arXiv2026

Benchmarking ResNet for Short-Term Hypoglycemia Classification with DiaData

Individualized therapy is driven forward by medical data analysis, which provides insight into the patient's context. In particular, for Type 1 Diabetes (T1D), which is an autoimmune disease, relationships between demographics, sensor data, and context can be analyzed. However, outliers, noisy data, and small data volumes cannot provide a reliable analysis. Hence, the research domain requires large volumes of high-quality data. Moreover, missing values can lead to information loss. To address this limitation, this study improves the data quality of DiaData, an integration of 15 separate datasets containing glucose values from 2510 subjects with T1D. Notably, we make the following contributions: 1) Outliers are identified with the interquartile range (IQR) approach and treated by replacing them with missing values. 2) Small gaps ($\le$ 25 min) are imputed with linear interpolation and larger gaps ($\ge$ 30 and $<$ 120 min) with Stineman interpolation. Based on a visual comparison, Stineman interpolation provides more realistic glucose estimates than linear interpolation for larger gaps. 3) After data cleaning, the correlation between glucose and heart rate is analyzed, yielding a moderate relation between 15 and 60 minutes before hypoglycemia ($\le$ 70 mg/dL). 4) Finally, a benchmark for hypoglycemia classification is provided with a state-of-the-art ResNet model. The model is trained with the Maindatabase and Subdatabase II of DiaData to classify hypoglycemia onset up to 2 hours in advance. Training with more data improves performance by 7% while using quality-refined data yields a 2-3% gain compared to raw data.

eess.SP↗

arXiv2026

Towards Improved Short-term Hypoglycemia Prediction and Diabetes Management based on Refined Heart Rate Data

Hypoglycemia is a severe condition of decreased blood glucose, specifically below 70 mg/dL (3.9 mmol/L). This condition can often be asymptomatic and challenging to predict in individuals with type 1 diabetes (T1D). Research on hypoglycemic prediction typically uses a combination of blood glucose readings and heart rate data to predict hypoglycemic events. Given that these features are collected through wearable sensors, they can sometimes have missing values, necessitating efficient imputation methods. This work makes significant contributions to the current state of the art by introducing two novel imputation techniques for imputing heart rate values over short-term horizons: Controlled Weighted Rational Bézier Curves (CRBC) and Controlled Piecewise Cubic Hermite Interpolating Polynomial with mapped peaks and valleys of Control Points (CMPV). In addition to these imputation methods, we employ two metrics to capture data patterns, alongside a combined metric that integrates the strengths of both individual metrics with RMSE scores for a comprehensive evaluation of the imputation techniques. According to our combined metric assessment, CMPV outperforms the alternatives with an average score of 0.33 across all time gaps, while CRBC follows with a score of 0.48. These findings clearly demonstrate the effectiveness of the proposed imputation methods in accurately filling in missing heart rate values. Moreover, this study facilitates the detection of abnormal physiological signals, enabling the implementation of early preventive measures for more accurate diagnosis.

q-bio.QM↗

arXiv2026

A Review on Machine Learning Approaches for the Prediction of Glucose Levels and Hypogylcemia

Type 1 Diabetes (T1D) is an autoimmune disease leading to insulin insufficiency. Thus, patients require lifelong insulin therapy, which has a side effect of hypoglycemia. Hypoglycemia is a critical state of decreased blood glucose levels (BGL) below 70 mg/dL and is associated with increased risk of mortality. Machine learning (ML) models can improve diabetes management by predicting hypoglycemia and providing optimal prevention methods. ML models are classified into regression and classification based, that forecast glucose levels and identify events based on defined labels, respectively. This review investigates state-of-the-art models trained on data of continuous glucose monitoring (CGM) devices from patients with T1D. We compare the models' performance across short-term (15 to 120 min) and long term (3 to more than 24 hours) prediction horizons (PHs). Particularly, we explore: 1) How much in advance can glucose values or a hypoglycemic event be accurately predicted? 2) Which models have the best performance? 3) Which factors impact the performance? and 4) Does personalization increase performance? The results show that 1) a PH of up to 1 hour provides the best results. 2) Conventional ML methods yield the best results for classification and DL for regression. A single model cannot adequately classify across multiple PHs. 3) The model performance is influenced by multivariate datasets and the input sequence length (ISL). 4) Personal data enhances performance but due to limited data quality population-based models are preferred.

cs.LG↗

arXiv2026

A Proposed Paradigm for Imputing Missing Multi-Sensor Data in the Healthcare Domain

Chronic diseases such as diabetes pose significant management challenges, particularly due to the risk of complications like hypoglycemia, which require timely detection and intervention. Continuous health monitoring through wearable sensors offers a promising solution for early prediction of glycemic events. However, effective use of multisensor data is hindered by issues such as signal noise and frequent missing values. This study examines the limitations of existing datasets and emphasizes the temporal characteristics of key features relevant to hypoglycemia prediction. A comprehensive analysis of imputation techniques is conducted, focusing on those employed in state-of-the-art studies. Furthermore, imputation methods derived from machine learning and deep learning applications in other healthcare contexts are evaluated for their potential to address longer gaps in time-series data. Based on this analysis, a systematic paradigm is proposed, wherein imputation strategies are tailored to the nature of specific features and the duration of missing intervals. The review concludes by emphasizing the importance of investigating the temporal dynamics of individual features and the implementation of multiple, feature-specific imputation techniques to effectively address heterogeneous temporal patterns inherent in the data.

cs.LG↗

arXiv2025

Breaking Free: Decoupling Forced Systems with Laplace Neural Networks

Modelling forced dynamical systems - where an external input drives the system state - is critical across diverse domains such as engineering, finance, and the natural sciences. In this work, we propose Laplace-Net, a decoupled, solver-free neural framework for learning forced and delay-aware systems. It leverages a Laplace transform-based approach to decompose internal dynamics, external inputs, and initial values into established theoretical concepts, enhancing interpretability. Laplace-Net promotes transferability since the system can be rapidly re-trained or fine-tuned for new forcing signals, providing flexibility in applications ranging from controller adaptation to long-horizon forecasting. Experimental results on eight benchmark datasets - including linear, non-linear, and delayed systems - demonstrate the method's improved accuracy and robustness compared to state-of-the-art approaches, particularly in handling complex and previously unseen inputs.

cs.LG↗

arXiv2025

MicroLabVR: Interactive 3D Visualization of Simulated Spatiotemporal Microbiome Data in Virtual Reality

Microbiomes are a vital part of the human body, engaging in tasks like food digestion and immune defense. Their structure and function must be understood in order to promote host health and facilitate swift recovery during disease. Due to the difficulties in experimentally studying these systems in situ, more research is being conducted in the field of mathematical modeling. Visualizing spatiotemporal data is challenging, and current tools that simulate microbial communities' spatial and temporal development often only provide limited functionalities, often requiring expert knowledge to generate useful results. To overcome these limitations, we provide a user-friendly tool to interactively explore spatiotemporal simulation data, called MicroLabVR, which transfers spatial data into virtual reality (VR) while following guidelines to enhance user experience (UX). With MicroLabVR, users can import CSV datasets containing population growth, substance concentration development, and metabolic flux distribution data. The implemented visualization methods allow users to evaluate the dataset in a VR environment interactively. MicroLabVR aims to improve data analysis for the user by allowing the exploration of microbiome data in their spatial context.

cs.HC↗

arXiv2025

Stress Detection from Multimodal Wearable Sensor Data

Human-Computer Interaction (HCI) is a multi-modal, interdisciplinary field focused on designing, studying, and improving the interactions between people and computer systems. This involves the design of systems that can recognize, interpret, and respond to human emotions or stress. Developing systems to monitor and react to stressful events can help prevent severe health implications caused by long-term stress exposure. Currently, the publicly available datasets and standardized protocols for data collection in this domain are limited. Therefore, we introduce a multi-modal dataset intended for wearable affective computing research, specifically the development of automated stress recognition systems. We systematically review the publicly available datasets recorded in controlled laboratory settings. Based on a proposed framework for the standardization of stress experiments and data collection, we collect physiological and motion signals from wearable devices (e.g., electrodermal activity, photoplethysmography, three-axis accelerometer). During the experimental protocol, we differentiate between the following four affective/activity states: neutral, physical, cognitive stress, and socio-evaluative stress. These different phases are meticulously labeled, allowing for detailed analysis and reconstruction of each experiment. Meta-data such as body positions, locations, and rest phases are included as further annotations. In addition, we collect psychological self-assessments after each stressor to evaluate subjects' affective states. The contributions of this paper are twofold: 1) a novel multi-modal, publicly available dataset for automated stress recognition, and 2) a benchmark for stress detection with 89\% in a binary classification (baseline vs. stress) and 82\% in a multi-class classification (baseline vs. stress vs. physical exercise).

cs.HC↗

arXiv2025

Evaluating Imputation Techniques for Short-Term Gaps in Heart Rate Data

Recent advances in wearable technology have enabled the continuous monitoring of vital physiological signals, essential for predictive modeling and early detection of extreme physiological events. Among these physiological signals, heart rate (HR) plays a central role, as it is widely used in monitoring and managing cardiovascular conditions and detecting extreme physiological events such as hypoglycemia. However, data from wearable devices often suffer from missing values. To address this issue, recent studies have employed various imputation techniques. Traditionally, the effectiveness of these methods has been evaluated using predictive accuracy metrics such as RMSE, MAPE, and MAE, which assess numerical proximity to the original data. While informative, these metrics fail to capture the complex statistical structure inherent in physiological signals. This study bridges this gap by presenting a comprehensive evaluation of four statistical imputation methods, linear interpolation, K Nearest Neighbors (KNN), Piecewise Cubic Hermite Interpolating Polynomial (PCHIP), and B splines, for short term HR data gaps. We assess their performance using both predictive accuracy metrics and statistical distance measures, including the Cohen Distance Test (CDT) and Jensen Shannon Distance (JS Distance), applied to HR data from the D1NAMO dataset and the BIG IDEAs Lab Glycemic Variability and Wearable Device dataset. The analysis reveals limitations in existing imputation approaches and the absence of a robust framework for evaluating imputation quality in physiological signals. Finally, this study proposes a foundational framework to develop a composite evaluation metric to assess imputation performance.

stat.AP↗

arXiv2025

Regression-Based Approach to Anxiety Estimation of Spider Phobics During Behavioural Avoidance Tasks

Phobias significantly impact the quality of life of affected persons. Two methods of assessing anxiety responses are questionnaires and behavioural avoidance tests (BAT). While these can be used in a clinical environment they only record momentary insights into anxiety measures. In this study, we estimate the intensity of anxiety during these BATs, using physiological data collected from unobtrusive, wrist-worn sensors. Twenty-five participants performed four different BATs in a single session, while periodically being asked how anxious they currently are. Using heart rate, heart rate variability, electrodermal activity, and skin temperature, we trained regression models to predict anxiety ratings from three types of input data: (1) using only physiological signals, (2) adding computed features (e.g., min, max, range, variability), and (3) computed features combined with contextual task information. Adding contextual information increased the effectiveness of the model, leading to a root mean squared error (RMSE) of 0.197 and a mean absolute error (MAE) of 0.041. Overall, this study shows, that data obtained from wearables can continuously provide meaningful estimations of anxiety, which can assist in therapy planning and enable more personalised treatment.

cs.HC↗

arXiv2025

Deep Learning-Based Hypoglycemia Classification Across Multiple Prediction Horizons

Type 1 diabetes (T1D) management can be significantly enhanced through the use of predictive machine learning (ML) algorithms, which can mitigate the risk of adverse events like hypoglycemia. Hypoglycemia, characterized by blood glucose levels below 70 mg/dL, is a life-threatening condition typically caused by excessive insulin administration, missed meals, or physical activity. Its asymptomatic nature impedes timely intervention, making ML models crucial for early detection. This study integrates short- (up to 2h) and long-term (up to 24h) prediction horizons (PHs) within a single classification model to enhance decision support. The predicted times are 5-15 min, 15-30 min, 30 min-1h, 1-2h, 2-4h, 4-8h, 8-12h, and 12-24h before hypoglycemia. In addition, a simplified model classifying up to 4h before hypoglycemia is compared. We trained ResNet and LSTM models on glucose levels, insulin doses, and acceleration data. The results demonstrate the superiority of the LSTM models when classifying nine classes. In particular, subject-specific models yielded better performance but achieved high recall only for classes 0, 1, and 2 with 98%, 72%, and 50%, respectively. A population-based six-class model improved the results with at least 60% of events detected. In contrast, longer PHs remain challenging with the current approach and may be considered with different models.

q-bio.QM↗

arXiv2022

Contrastive Representation Learning for Conversational Question Answering over Knowledge Graphs

This paper addresses the task of conversational question answering (ConvQA) over knowledge graphs (KGs). The majority of existing ConvQA methods rely on full supervision signals with a strict assumption of the availability of gold logical forms of queries to extract answers from the KG. However, creating such a gold logical form is not viable for each potential question in a real-world scenario. Hence, in the case of missing gold logical forms, the existing information retrieval-based approaches use weak supervision via heuristics or reinforcement learning, formulating ConvQA as a KG path ranking problem. Despite missing gold logical forms, an abundance of conversational contexts, such as entire dialog history with fluent responses and domain information, can be incorporated to effectively reach the correct KG path. This work proposes a contrastive representation learning-based approach to rank KG paths effectively. Our approach solves two key challenges. Firstly, it allows weak supervision-based learning that omits the necessity of gold annotations. Second, it incorporates the conversational context (entire dialog history and domain information) to jointly learn its homogeneous representation with KG paths to improve contrastive representations for effective path ranking. We evaluate our approach on standard datasets for ConvQA, on which it significantly outperforms existing baselines on all domains and overall. Specifically, in some cases, the Mean Reciprocal Rank (MRR) and Hit@5 ranking metrics improve by absolute 10 and 18 points, respectively, compared to the state-of-the-art performance.

cs.CL↗

arXiv2022

An Answer Verbalization Dataset for Conversational Question Answerings over Knowledge Graphs

We introduce a new dataset for conversational question answering over Knowledge Graphs (KGs) with verbalized answers. Question answering over KGs is currently focused on answer generation for single-turn questions (KGQA) or multiple-tun conversational question answering (ConvQA). However, in a real-world scenario (e.g., voice assistants such as Siri, Alexa, and Google Assistant), users prefer verbalized answers. This paper contributes to the state-of-the-art by extending an existing ConvQA dataset with multiple paraphrased verbalized answers. We perform experiments with five sequence-to-sequence models on generating answer responses while maintaining grammatical correctness. We additionally perform an error analysis that details the rates of models' mispredictions in specified categories. Our proposed dataset extended with answer verbalization is publicly available with detailed documentation on its usage for wider utility.

cs.CL↗

arXiv2021

VOGUE: Answer Verbalization through Multi-Task Learning

In recent years, there have been significant developments in Question Answering over Knowledge Graphs (KGQA). Despite all the notable advancements, current KGQA systems only focus on answer generation techniques and not on answer verbalization. However, in real-world scenarios (e.g., voice assistants such as Alexa, Siri, etc.), users prefer verbalized answers instead of a generated response. This paper addresses the task of answer verbalization for (complex) question answering over knowledge graphs. In this context, we propose a multi-task-based answer verbalization framework: VOGUE (Verbalization thrOuGh mUlti-task lEarning). The VOGUE framework attempts to generate a verbalized answer using a hybrid approach through a multi-task learning paradigm. Our framework can generate results based on using questions and queries as inputs concurrently. VOGUE comprises four modules that are trained simultaneously through multi-task learning. We evaluate our framework on existing datasets for answer verbalization, and it outperforms all current baselines on both BLEU and METEOR scores.

cs.CL↗

arXiv2021

Conversational Question Answering over Knowledge Graphs with Transformer and Graph Attention Networks

This paper addresses the task of (complex) conversational question answering over a knowledge graph. For this task, we propose LASAGNE (muLti-task semAntic parSing with trAnsformer and Graph atteNtion nEtworks). It is the first approach, which employs a transformer architecture extended with Graph Attention Networks for multi-task neural semantic parsing. LASAGNE uses a transformer model for generating the base logical forms, while the Graph Attention model is used to exploit correlations between (entity) types and predicates to produce node representations. LASAGNE also includes a novel entity recognition module which detects, links, and ranks all relevant entities in the question context. We evaluate LASAGNE on a standard dataset for complex sequential question answering, on which it outperforms existing baseline averages on all question types. Specifically, we show that LASAGNE improves the F1-score on eight out of ten question types; in some cases, the increase in F1-score is more than 20% compared to the state of the art.

cs.CL↗

arXiv2021

Demographic Aware Probabilistic Medical Knowledge Graph Embeddings of Electronic Medical Records

Medical knowledge graphs (KGs) constructed from Electronic Medical Records (EMR) contain abundant information about patients and medical entities. The utilization of KG embedding models on these data has proven to be efficient for different medical tasks. However, existing models do not properly incorporate patient demographics and most of them ignore the probabilistic features of the medical KG. In this paper, we propose DARLING (Demographic Aware pRobabiListic medIcal kNowledge embeddinG), a demographic-aware medical KG embedding framework that explicitly incorporates demographics in the medical entities space by associating patient demographics with a corresponding hyperplane. Our framework leverages the probabilistic features within the medical entities for learning their representations through demographic guidance. We evaluate DARLING through link prediction for treatments and medicines, on a medical KG constructed from EMR data, and illustrate its superior performance compared to existing KG embedding models.

cs.IR↗