Developing neural network model for predicting cardiac and cardiovascular health using bioelectrical signal processing.

Coronary vascular disease (CHD) is one of the most fatal diseases worldwide. Cardio vascular diseases are not easily diagnosed in early disease stages. Early diagnosis is important for effective treatment, however, medical diagnoses are based on physician's personal experiences of the disease which increase time and testing cost to reach diagnosis. Physicians assess patients' condition based on electrocardiography, sonography and blood test results. In this research we develop classification model of the functional state of the cardiovascular system based on the monitoring of the evolution of the amplitudes of the first and second harmonics of the system rhythm of 0.1 Hz. We separate the signal to three streams; the first stream works with natural electro cardio signal, the other two streams are obtained as a result of frequency analysis of the amplitude- and frequency-detected electro cardio signal. We use sliding window of a demodulated electro cardio signal by means of amplitude and frequency detectors. The developed NN model showed an increase in accuracy of diagnostic efficiency by 11%. The neural network model can be trained to give accurate early detection of disease class.

Cleaning of oil-polluted bottom sediments of the boreal lake, Samotlor oil field, North Russia: case report.

Small lakes in areas of intensive crude oil production may be susceptible to oil pollution arising from accidental spills and leaks, eventually leading to the pollution of bottom sediments. Effective cleaning of aquatic bottom sediments remains a challenge. Flotation is a potentially simple and reliable approach for the cleanup of bottom sediments without their excavation from the water body. Full-scale testing of flotation-based technology using the specially designed airlift plant allowed the cleaning of bottom sediments of an unnamed boreal lake ('the lake') within the Samotlor oil field, North Russia, heavily polluted with crude oil several decades ago. The lake bottom sediments are dominated by peat and unevenly polluted with oil. The average oil content in the lake bottom sediments was 111 g kg-1. During the 1.5 months' field test in July-August 2018, the average total oil concentration in the bottom sediments of the lake was reduced to 1.99 g kg-1. Secondary water contamination was minimal; the content of oil hydrocarbons in the water after completion of work did not exceed 0.09 ± 0.04 mg L-1. This study demonstrates that flotation-based technology can be applied for in situ cleaning of oil-contaminated lake bottom sediments including those in boreal climates.

Two dimensional modeling of elastic wave propagation in solids containing cracks with rough surfaces and friction - Part I: Theoretical background.

Our study aims at the creation of a numerical toolbox that describes wave propagation in samples containing internal contacts (e.g. cracks, delaminations, debondings, imperfect intergranular joints) of known geometry with postulated contact interaction laws including friction. The code consists of two entities: the contact model and the solid mechanics module. Part I of the paper concerns the modeling of internal contacts (called cracks for brevity), while part II is related to the integration of the developed contact model into a solid mechanics module that allows the description of wave propagation processes. The contact model is used to produce normal and tangential load-displacement relationships, which in turn are used by the solid mechanics module as boundary conditions at the internal contacts. Due to friction, the tangential reaction curve is hysteretic and memory-dependent. In addition, it depends on the normal reaction curve. An essential feature of the proposed contact model is that it takes into account the roughness of the contact faces. On one hand, accounting for roughness makes the contact model more complicated since it gives rise to a partial slip regime when some parts on the contact area experience slip and some do not. On the other hand, as we will show, the concept of contact surfaces covered by asperities receding under load makes it possible to formulate a consistent contact model that provides nonlinear load-displacement relationships for any value of the drive displacements and their histories. This is a strong advantage, since this way, the displacement-driven model allows for a simple explicit procedure of data exchange with the solid mechanics module, while more traditional flat-surface contacts driven by loads generate a complex iterative procedure. More specifically, the proposed contact model is based on the previously developed method of memory diagrams that allows one to automatically obtain memory-dependent solutions to frictional contact problems in the particular case of partial slip. Here we extend the solution onto cases of total sliding and contact loss which is possible while using the displacement-driven formulation. The method requires the knowledge of the normal contact response obtained in our case as a result of statistical consideration of roughness of contact faces.