DHDawid Hanak

Dawid Hanak

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Dawid Hanak has a total of 4 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Variational autoencoder in analysis of motion capture data

    by Marcel Furs, Dawid Hanak, Adam Świtoński

    The aim of this study was to present the applicability of Variational Autoencoders (VAE) in the analysis and generation of human gait data, represented by multivariate sequences containing rotations of skeletal joints or 3D positions of anatomically significant body points. The proposed framework offers two main advantages: it uses data solely from healthy populations for classification (instead of the usual collation of healthy and pathological data) and employs anthropometric measures to determine generated data quality.The paper investigates the semi-supervised classification problem of anomaly detection, in which the VAE is trained based on the selected class called normal for the purpose of discriminating the remaining abnormal ones. Three challenges – the recognition of the gait performed by females and males, the distinction between gait with comfortable and increased paces, as well as the discrimination of walking and running activities – are taken into consideration.To accomplish the tasks, VAE architectures operating on preprocessed motion capture sequences containing single walking and running cycles are proposed. The results achieved are satisfactory. The areas under the receiver operating characteristic curve (ROC-AUC) for the anomaly detection challenges reach 0.862 ± 0.014, 0.843 ± 0.015, and 1.000 ± 0.000, respectively, evaluated through 30 repeated subject-disjoint splits. A robust directional asymmetry pattern was observed: models trained on populations with lower within-group variability achieve consistently higher detection performance, a finding confirmed across multiple anomaly detection methodologies including PCA, One-Class SVM, and Isolation Forest. As regards the generation of gait sequences, they are diverse and contain natural-looking movements.

  • Open Access

    Adaptive Sonification of Mathematical Function Graphs

    by Krzysztof Dobosz, Dawid Hanak, Przemysław Kudłacik

    Graphical representations of mathematical functions remain difficult to access for blind and visually impaired users, particularly in educational contexts where understanding the overall shape and behavior of a function is essential. This paper proposes an adaptive sonification method for mathematical function graphs designed for touchscreen-based exploration supported by continuous auditory feedback and voice interaction. The study focuses on balancing perceptual accessibility and auditory saturation by analyzing the influence of key sonification parameters, including auditory plateau width, slope length, and slope curvature. Two user experiments involving participants with different levels of visual impairment were conducted to evaluate the perceived usability of the proposed approach. The results indicate that usability improves with increasing auditory coverage only up to a certain threshold, beyond which excessive auditory density reduces perceptual clarity. The experimental results suggest that the preferred auditory plateau width is approximately 52 dp (about 9.8 mm), while the optimal slope length is approximately 84 dp (about 15.8 mm). In contrast, slope curvature has relatively little influence on subjective usability. The paper also introduces the Sonification Index (SI) and Auditory Saturation (AS), two quantitative measures that support the analysis and adaptive selection of sonification parameters based on graph complexity and device characteristics.