Techn. Fakultät Willkommen am Institut für Informatik FAU-Logo

Matthias Ring M. Sc.

Researcher in the Digital Sports group at the Pattern Recognition Lab of the Friedrich-Alexander-Universität Erlangen-Nürnberg

Temperature-Based Bioimpedance Correction for Water Loss Estimation during Physical Exercise
  • The amount of total body water (TBW) can be estimated based on bioimpedance measurements of the human body. In sports, TBW estimations are of importance because mild water losses can impair muscular strength and aerobic endurance. Severe water losses can even be life threatening. TBW estimations based on bioimpedance, however, fail during physical exercise because the increased body temperature corrupts bioimpedance measurements.

    Therefore, we propose a machine learning method that eliminates the effects of increased temperature on bioimpedance and, consequently, reveals the changes in bioimpedance that are due to TBW loss. This is facilitated by utilizing changes in skin and core temperature. The method was evaluated in a study in which bioimpedance, temperature, and TBW loss were recorded every 15 minutes during a two-hour running workout. The evaluation demonstrated that the proposed method is able to reduce the error of TBW loss estimation by up to 71%, compared to the state of art.

    This approach - in combination with portable bioimpedance devices - could facilitate the development of wearable devices for continuous and noninvasive TBW loss monitoring in the future.

    Journal Articles
    Ring, Matthias; Lohmueller, Clemens; Rauh, Manfred; Mester, Joachim; Eskofier, Björn
    A Temperature-Based Bioimpedance Correction for Water Loss Estimation During Sports
    IEEE Journal of Biomedical and Health Informatics, vol. 20, no. 6, pp. 1477-1484, 2016 (BiBTeX, Who cited this?)
    Articles in Conference Proceedings
    Ring, Matthias; Lohmüller, Clemens; Rauh, Manfred; Eskofier, Björn
    A Two-Stage Regression Using Bioimpedance and Temperature for Hydration Assessment During Sports
    Proceedings of the 2014 22nd International Conference on Pattern Recognition (2014 22nd International Conference on Pattern Recognition), Stockholm, Sweden, August 24-28, 2014, pp. 4519-4524, 2014 (BiBTeX, Who cited this?)
Sweat Analysis for Water Loss Estimation during Physical Exercise
  • Quantitative estimation of water loss during physical exercise is important because dehydrations can impair both muscular strength and aerobic endurance. A physiological indicator for total body water (TBW) loss could be the concentration of electrolytes in sweat. It has been shown that electrolyte concentrations differ after physical exercise, depending on whether water loss was replaced by fluid intake or not. However, this observation has not been explored for its potential to estimate TBW loss quantitatively.

    Therefore, we collected sweat samples during two hours of physical exercise without fluid intake. A statistical analysis of the analyzed measurements showed significant correlations between chloride concentration in sweat and TBW loss (r = 0.41, p < 0.01), and between sweat osmolality and TBW loss (r = 0.43, p < 0.01). The estimation of TBW loss using a Gaussian Process regression resulted in a mean absolute error of 0.49 liter. Although this precision has to be improved for usage in the field, the results suggest that TBW loss estimations could be realized based on sweat analysis.

    Articles in Conference Proceedings
    Ring, Matthias; Lohmüller, Clemens; Rauh, Manfred; Eskofier, Björn
    On Sweat Analysis for Quantitative Estimation of Dehydration during Physical Exercise
    Proceedings of the 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society), Milan, Italy, August, 25-29, pp. 7011-7014, 2015 (BiBTeX, Who cited this?)
Salivary Markers for Water Loss Estimation during Physical Exercise
  • Salivary markers have been proposed as noninvasive and easy-to-collect indicators of dehydrations during physical exercise. It has been demonstrated that threshold-based classifications can distinguish dehydrated from euhydrated subjects. However, considerable challenges were reported simultaneously, for example, high inter-subject variabilities in these markers.

    Therefore, we propose a machine learning approach to handle the inter-subject variabilities and to advance from binary classifications to quantitative estimations of total body water (TBW) loss. For this purpose, salivary samples and reference values of TBW loss were collected from ten subjects during a 2-h running workout without fluid intake. The salivary samples were analyzed for previously investigated markers (osmolality, proteins) as well as additional unexplored markers (amylase, chloride, cortisol, cortisone, potassium). Processing all these markers with a Gaussian process approach showed that quantitative TBW loss estimations are possible within an error of 0.34 l, roughly speaking, a glass of water.

    Furthermore, a data analysis illustrated that the salivary markers grow nonlinearly during progressive dehydration, which is in contrast to previously reported, linear observations. This insight could help to develop more accurate physiological models for salivary markers and TBW loss. Such models, in turn, could facilitate even more precise TBW loss estimations in the future.

    Ring, Matthias; Lohmueller, Clemens; Rauh, Manfred; Mester, Joachim; Eskofier, Bjoern M.
    Salivary Markers for Quantitative Dehydration Estimation during Physical Exercise.
    IEEE Journal of Biomedical and Health Informatics, forthcoming, DOI: 10.1109/JBHI.2016.2598854.

Optimal Feature Selection for Nonlinear Data using Branch-and-Bound in Kernel Space
  • Branch-and-bound (B&B) feature selection finds optimal feature subsets without performing an exhaustive search. The classification accuracy achievable with optimal B&B feature subsets, however, is often inferior compared to the accuracy achievable with other algorithms that guarantee optimality.

    We argue this is due to the currently used criterion functions that define the optimal feature subset but may not conceive inherent nonlinear data structures. Therefore, we propose B&B feature selection in Reproducing Kernel Hilbert Space (B&B-RKHS). B&B-RKHS employs two currently used criterion functions (Bhattacharyya distance, Kullback-Leibler divergence) and one new criterion function (mean class distance), however, all computed in RKHS. This enables B&B-RKHS to conceive inherent nonlinear data structures.

    B&B-RKHS was experimentally compared to the popular wrapper approach for feature selection, which requires an exhaustive search to guarantee optimality. The classification accuracy achieved with both methods was comparable. However, runtime of B&B-RKHS was superior using the two existing criterion functions and even completely out of reach using the new criterion function (about 1,500 times faster on average).

    Opens internal link in current windowImplementation available in the ECST

    Journal Articles
    Optimal feature selection for nonlinear data using branch-and-bound in kernel space
    Pattern Recognition Letters, vol. 68, pp. 56-62, 2015 (BiBTeX, Who cited this?)
Approximation of the Gaussian RBF Kernel for Efficient Classification with SVMs
  • In theory, kernel support vector machines (SVMs) can be reformulated to linear SVMs. This reformulation can speed up SVM classifications considerably, in particular, if the number of support vectors is high. For the widely-used Gaussian radial basis function (RBF) kernel, however, this theoretical fact is impracticable because the reproducing kernel Hilbert space (RKHS) of this kernel has infinite dimensionality.

    Therefore, we derive a finite-dimensional approximative feature map, based on an orthonormal basis of the kernel’s RKHS, to enable the reformulation of Gaussian RBF SVMs to linear SVMs. We show that the error of this approximative feature map decreases with factorial growth if the approximation quality is linearly increased. Experimental evaluations demonstrated that the approximative feature map achieves considerable speed-ups (about 18-fold on average), mostly without loosing classification accuracy. Therefore, the proposed approximative feature map provides an efficient SVM evaluation method with minimal loss of precision.

    Initiates file downloadDownload Matlab source code

    Journal Articles
    An approximation of the Gaussian RBF kernel for efficient classification with SVMs
    Pattern Recognition Letters, vol. 84, pp. 107–113, 2016 (BiBTeX, Who cited this?)
Classification on Embedded Systems
  • Embedded microcontrollers are employed in an increasing number of applications as a target for the implementation of classification systems. This is true, for example, for the fields of sports, automotive, and medical engineering. However, important challenges arise when implementing classification systems on embedded microcontrollers, which is mainly due to limited hardware resources.

    With the Embedded Classification Software Toolbox (ECST), we present a solution to the two main challenges, namely obtaining a classification system with low computational complexity and, at the same time, high classification accuracy. For the first challenge, we propose complexity measures on the mathematical operation and parameter level, because the abstraction level of the commonly used Landau notation is too high in the context of embedded system implementation. For the second challenge, we present a software toolbox that trains different classification systems, compares their classification accuracy, and finally analyzes the complexity of the trained system. 

    Opens internal link in current windowVisit project page

    Journal Articles
    Approaching the accuracy-cost conflict in embedded classification system design
    Pattern Analysis and Applications, vol. -, pp. 1-17, 2015 (BiBTeX, Who cited this?)
    Articles in Conference Proceedings
    Pattern Recognition (ICPR), 2012 21st International Conference on (21st International Conference on Pattern Recognition), Tsukuba, Japan, November 11-15, 2012, pp. 2266-2269, 2012, ISBN 978-4-9906441-1-6 (BiBTeX, Who cited this?)
Data Mining in the U.S. National Toxicology Program (NTP) Database
  • Long-term studies in rodents are the benchmark method to assess carcinogenicity of single substances, mixtures, and multi-compounds. In such a study, mice and rats are exposed to a test agent at different dose levels for a period of two years and the incidence of neoplastic lesions is observed. However, this two-year study is also expensive, time-consuming, and burdensome to the experimental animals. Consequently, various alternatives have been proposed in the literature to assess carcinogenicity on basis of short-term studies.

    In this project, we investigated if effects on the rodents' liver weight in short-term studies can be exploited to predict the incidence of liver tumors in long-term studies. A set of 138 paired short- and long-term studies was compiled from the database of the U.S. National Toxicology Program (NTP), more precisely, from (long-term) two-year carcinogenicity studies and their preceding (short-term) dose finding studies. In this set, data mining methods revealed patterns that can predict the incidence of liver tumors with accuracies of over 80%.  However, the results simultaneously indicated a potential bias regarding liver tumors in two-year NTP studies. The incidence of liver tumors does not only depend on the test agent but also on other confounding factors in the study design, e.g., species, sex, type of substance.

    We recommend considering this bias if the hazard or risk of a test agent is assessed on basis of a NTP carcinogenicity study.