Multifractional Brownian motion characterization based on Hurst exponent estimation and statistical learning.

This paper proposes an approach for the estimation of a time-varying Hurst exponent to allow accurate identification of multifractional Brownian motion (MFBM). The contribution provides a prescription for how to deal with the MFBM measurement data to solve regression and classification problems. Theoretical studies are supplemented with computer simulations and real-world examples. Those prove that the procedure proposed in this paper outperforms the best-in-class algorithm.

Stress Inference from Abdominal Sounds using Machine Learning.

Stress is often considered the 21st century's epidemic, affecting more than a third of the globe's population. Long-term exposure to stress has significant side effects on physical and mental health. In this work we propose a methodology for detecting stress using abdominal sounds. For this study, eight participants were either exposed to a stressful (Stroop test) or a relaxing (guided meditation) stimulus for ten days. In total, we collected 104 hours of abdominal sounds using a custom wearable device in a belt form-factor. We explored the effect of various features on the binary stress classification accuracy using traditional machine learning methods. Namely, we observed the impact of using acoustic features on their own, as well as in combination with features representing current mood state, and hand-crafted domain-specific features. After feature extraction and reduction, by utilising a multilayer perceptron classifier model we achieved 77% accuracy in detecting abdominal sounds under stress exposure. Clinical relevance- This feasibility study confirms the link between the gastrointestinal system and stress and uncovers a novel approach for stress inference via abdominal sounds using machine learning.

Fractional Dynamics Identification via Intelligent Unpacking of the Sample Autocovariance Function by Neural Networks.

Many single-particle tracking data related to the motion in crowded environments exhibit anomalous diffusion behavior. This phenomenon can be described by different theoretical models. In this paper, fractional Brownian motion (FBM) was examined as the exemplary Gaussian process with fractional dynamics. The autocovariance function (ACVF) is a function that determines completely the Gaussian process. In the case of experimental data with anomalous dynamics, the main problem is first to recognize the type of anomaly and then to reconstruct properly the physical rules governing such a phenomenon. The challenge is to identify the process from short trajectory inputs. Various approaches to address this problem can be found in the literature, e.g., theoretical properties of the sample ACVF for a given process. This method is effective; however, it does not utilize all of the information contained in the sample ACVF for a given trajectory, i.e., only values of statistics for selected lags are used for identification. An evolution of this approach is proposed in this paper, where the process is determined based on the knowledge extracted from the ACVF. The designed method is intuitive and it uses information directly available in a new fashion. Moreover, the knowledge retrieval from the sample ACVF vector is enhanced with a learning-based scheme operating on the most informative subset of available lags, which is proven to be an effective encoder of the properties inherited in complex data. Finally, the robustness of the proposed algorithm for FBM is demonstrated with the use of Monte Carlo simulations.

Computer assessment of indirect insight during an airflow interrupter maneuver of breathing.

The paper answers the questions if it is possible to conclude in objective way on more (than one -Rint - in a classical IT) number of parameters from the time domain post-interrupter signals during the occlusional measurement of respiratory mechanics and also verifies what accuracy can be achieved in such attempt. To obtain reported results, the time-domain enhanced interrupter technique (TD-EIT) was developed in this paper using computer simulations. Three-stage scheme of work was assumed in the project. First, the quality of the model identification was assessed for various combinations of pressure and flow signals recorded during the interruption. Then, the correlation between the working characteristics of the interrupter valve and the precision of the parameter estimation were assessed for the TD-EIT algorithm. Finally, a verification experiment by forward-inverse modeling was organized, in which the mechanical characteristics of a complex model were mapped with reduced analogs and with the use of neural networks for three typical modes: 'Normal state', 'Airway constriction' and 'Cheeks supported'. Obtained results show that to became effective in time-domain post-interrupter data exploration, both pressure and flow signals should be used in assessment of respiratory mechanics, taken in a range of at least 100ms and when both slopes (valve closing and opening) of quasi-step excitation are included. What is more, the faster the valve the smaller error of parameter estimation in proposed TD-EIT was observed, and this uncertainty importantly falls down for the length of time window exceeding the limit of 100ms. The pioneering use of neural network for mapping the mechanical properties of lungs with the use of interrupter experiment methodology proves that it is possible to conclude about more (than one) number of parameters characterizing the complex system and that this insight is biased with the error not exceeding of 10%; only peripheral properties are estimated worse. Such observation has a potential to change the experimental protocol, which was used in interrupter measurements up to date and to make this technique more attractive in comparison to other method, i.e. forced oscillation technique or impulse oscillometry. As regards the practical meaning of reported results for engineers and end-users (physicians and patients), proposed solution can be applied in simple portable devices with a feature of easy operation (important for e-monitoring).

Preliminary study on the accuracy of respiratory input impedance measurement using the interrupter technique.

Respiratory input impedance contains information about the state of pulmonary mechanics in the frequency domain. In this paper the possibility of respiratory impedance measurement by interrupter technique as well as the accuracy of this approach are assessed. Transient states of flow and pressure recorded during expiratory flow interruption are simulated with a complex, linear model for the respiratory system and then used to calculate the impedance, including three states of respiratory mechanics and the influence of the measurement noise. The results of computations are compared to the known, theoretical impedance of the model. At 1 kHz sampling rate, the optimal time window lays between 100 and 200 ms and is centred around the pressure jump caused by the flow interruption. The proposed algorithm yields satisfactory accuracy in the range from 10 to 400 Hz, particularly to 150 Hz. Depending on the simulated respiratory system state, the error of calculated impedance (relative Euclidean distance between the vectors of computed and theoretical values), for the window of 190 ms, varies between 5.0% and 7.1%.

Wearable interrupter module for home-based applications in a telemedical system dedicated to respiratory mechanics measurements.

The mobile interrupter module, dedicated to the enhanced interrupter (EIT) measurement of respiratory mechanics in a home environment and capable of cooperation with a telemedical system, is presented. Characterized by noninvasiveness and minimal requirements regarding patient cooperation, the EIT algorithm is especially suitable for newborns, preschool children, and patients suffering from respiratory muscle impairment. Furthermore, this device enables access to raw data--without initial preprocessing--in a fully flexible measurement protocol (which is not available in any commercial apparatus), and the EIT procedure improves insight (the number and precision of assessed parameters) into the physiological system with respect to the classical occlusive methods.

Airway and tissue loading in postinterrupter response of the respiratory system - an identification algorithm construction.

The paper offers an enhancement of the classical interrupter technique algorithm dedicated to respiratory mechanics measurements. Idea consists in exploitation of information contained in postocclusional transient states during indirect measurement of parameter characteristics by model identification. It needs the adequacy of an inverse analogue to general behavior of the real system and a reliable algorithm of parameter estimation. The second one was a subject of reported works, which finally showed the potential of the approach to separation of airway and tissue response in a case of short-term excitation by interrupter valve operation. Investigations were conducted in a regime of forward-inverse computer experiment.

Reduction of a linear complex model for respiratory system during Airflow Interruption.

The paper presents methodology of a complex model reduction to its simpler version - an identifiable inverse model. Its main tool is a numerical procedure of sensitivity analysis (structural and parametric) applied to the forward linear equivalent designed for the conditions of interrupter experiment. Final result - the reduced analog for the interrupter technique is especially worth of notice as it fills a major gap in occlusional measurements, which typically use simple, one- or two-element physical representations. Proposed electrical reduced circuit, being structural combination of resistive, inertial and elastic properties, can be perceived as a candidate for reliable reconstruction and quantification (in the time and frequency domain) of dynamical behavior of the respiratory system in response to a quasi-step excitation by valve closure.