|
|
Blood pressure estimation using smartphone
Šíma, Jan ; Němcová, Andrea
This paper presents an experimental cuff-less measurementof systolic (SBP) and diastolic blood pressure (DBP)using smartphone. A photoplethysmographic signal (PPG) measuredby a smartphone camera is used to estimate blood pressure(BP). This paper contains comparison of several machinelearning (ML) methods for BP estimation. Filtering the PPGsignal with a band-pass filter (0.5-12 Hz) followed by featureextraction and using Random Forest (RF) methods separatelyor as a weak regressor in adaptive boosting (AdaBoost) or bootstrapaggregating (Boosting) reached the best results accordingto Association for the Advancement of Medical Instrumentation(AAMI) and British Hypertension Society (BHS) standardsamong all regression ML models. The mean absolute error(MAE) and standard deviation (SD) of Bagging model were4.532±3.760 mmHg for SBP and 2.738±3.032 mmHg for DBP(AAMI). This result meets the criteria of the AAMI standard.
|
|
|
Influence of selected types of food on changes in the composition of the intestinal microbiome
Šantavý, Tomáš ; Němcová, Andrea (referee) ; Ryšávka, Petr (advisor)
The master's thesis focuses on determining the influence of selected types of food on changes in the intestinal microbiome composition. Dietary composition plays an important role in controlling intestinal microbial populations, including the prevention and treatment of certain diseases. In order to evaluate the effect of daily consumption of fruit-vegetable smoothie on the human intestinal microbiome, changes in the intestinal microbiome at the beginning and after 14 days of intervention were compared. The experimental part was attended by 10 men and 10 women aged 35-45 years, who were evenly divided into 2 groups. The first group of participants consumed a combination of orange, dried turmeric and ginger. The second group consumed a combination of apple, carrot and lemon juice. DNA isolation from stool samples followed by a quantitative PCR method was used to detect differences in the intestinal microbiome. After 14 days of consumption of the fruit-vegetable smoothie, specific changes in the phylum Firmicutes, Bacteroidetes and the genus Lactobacillus, Bifidobacterium were observed. After statistical evaluation of the obtained results, the differences were not detectable at a statistically significant level (p-value > 0.05).
|
|
|
Determination of nutritional values and antioxidant capacity of different edible roots
Ciffrová, Karolína ; Bendová, Agáta (referee) ; Němcová, Andrea (advisor)
This bachelor thesis deals with selected edible roots, their nutritional composition, antioxidant capacity and use in healthy eating. Eight selected edible roots were analyzed: type A, B and C potatoes, red potatoes, sweet potatoes, and purple potatoes were selected as representatives of potatoes. Jerusalem artichoke and cassava represent the other two root crops. The theoretical section of the thesis describes the basic characteristics of root crops, as well as the description and composition of the nutritional substances they contain, i.e. proteins, carbohydrates, fats, vitamins and antioxidant properties. The general characteristics of the methods used for analysis are also described here. The experimental part is based on specific analyses, procedures, results, chemicals and laboratory equipment used to determine the basic nutritional values and antioxidant capacity of these selected root vegetables. First, the total dry matter content was established to be about 23 % in the selected root crops. Higher dry matter content was determined for the cassava at 35 %. Crude protein content determined by the Kjeldahl method ranges from 6.5-9.9 %. The gravimetrically determined fiber in the given root crops was in the range of 0.27–0.91 %. The starch content is significantly higher in the cassava (46 %) than in other root crops. The inulin content was determined in sweet potatoes and Jerusalem artichokes instead of starch content; this value is significant for the Jerusalem artichoke (258.58 g/kg). Fat content in grams per 100 grams of dry matter was determined by Soxhlet extraction. Significant fat content was determined for sweet potatoes (12.6 g/100 g). From the extracted fats, the fatty acid profile was determined for individual root vegetables, such as the content of saturated (SFA), monounsaturated (MUFA) and polyunsaturated fatty acids (PUFA). Total and reducing carbohydrates, determined by the spectrophotometric method, were measured separately in the peel and pulp of the root crops. Antioxidant capacity was determined using antioxidant activity values, polyphenol and flavonoid concentrations. Of the vitamins, vitamin C was determined, vitamin E only in type B, C and purple potatoes. For sweet potatoes, beta-carotene was determined to be 540.56 g/g. The measured and calculated results are plotted in graphs. Finally, there is a discussion of the conclusions of the individual methods.
|
|
|
Effect of addition of microbial or vegetable oil on the efficiency of cosmetic products
Kovářová, Karolína ; Hoová, Julie (referee) ; Němcová, Andrea (advisor)
This thesis focuses on the influence of the fatty acid profile and the concentration of active substances on the abilities to hydrate and to absorb into the skin of cosmetic emulsions. Coconut and macadamia oil, which are common cosmetic ingredients, were used as vegetable active ingredients. The last active ingredient used was the microbial oil, which was prepared as part of this work. Four strains of oleaginous yeast Metschnikowia were tested for the overproduction of microbial lipids in various culture media. Based on the results of gas chromatography, the yeast strain Metschnikowia pulcherrima (149) was selected. The chosen culture medium contained apple cider as a carbon source and had a 10 % sodium chloride content, inducing osmotic stress. Cosmetic emulsions with different concentrations of active ingredients were prepared. These emulsions were tested by sensory analysis. After application, the skin was analyzed with a skin camera that measured desquamation and sebum. The degree of desquamation is directly related to skin hydration and the level of sebum reflects the ability of the emulsion to be absorbed into the skin. It was found that if the user is not used to applying hydrating cosmetic emulsions regularly, but only solves the immediate problem of dry skin, it is advantageous to use an emulsion with an active ingredient content of 5.0 % or more. However, commercially available hydrating creams typically contain effective vegetable oils in lower concentrations. Furthermore, it was found that microbial oil could be a very interesting cosmetic ingredient.
|
|
|
Microbial production of lipids and their applications
Kročianová, Natália ; Szotkowski, Martin (referee) ; Němcová, Andrea (advisor)
The aim of this bachelor's thesis was the production of lipids by selected strains of yeasts of the Metschnikowia genus using food production substrates. Produced microbial lipids are nowadays highly valued and sought after mainly in the biotechnology industry as a substitute for carbon in the industrial process of biofuel production. Plant, ecological, and cost-effective substrates were used for cultivation ; the influence of cultivation conditions on the growth of yeast was monitored at laboratory and reduced temperature. Four types of yeast were investigated, namely M. pulcherrima 147, M. pulcherrima 149, M. sinensis 1144, and M. zizyphicola 1147. The produced biomasses were analyzed using gas chromatography; in analyses, individual fatty acid composition was determined. Visible changes could be observed at different cultivation temperatures and used substrates. The best results were achieved by substrates that contained Metschnikowia sinensis 1144, while all selected yeasts were capable of lipid production. The highest representation of polyunsaturated fatty acids was demonstrated in each analyzed yeast.
|
|
|
Photoplethysmography using a smartphone
Dräxler, Vladislav ; Němcová, Andrea (referee) ; Janoušek, Oto (advisor)
This work is focused on the PPG technology using a smartphone, from the acquisition of the photoplethysmographic curve, through the preprocessing of the PPG signal, the calculation of the parameters to the quality assessment. The practical part contains a measurement protocol under different experimental conditions, an algorithm for obtaining a photoplethysmographic curve from video recordings obtained by measurement, and further deals with determining various parameters and evaluating the quality of the obtained PPG signal. The output of the work is an optimal acquisition protocol for scanning the PPG curve.
|
|
|
Validation of commercially available smartwatches as a human health/activity monitoring tool
Běhunčíková, Vendula ; Janoušek, Oto (referee) ; Němcová, Andrea (advisor)
This master's thesis deals with the topic of health and activity monitoring of individuals using smartwatches. The aim of the thesis was to collect a set of data according to a measurement protocol using various types of smartwatches, along with reference data from the Faros 180 device. The collected data from a total of nine smartwatches was synchronized, and the synchronized heart rate courses were evaluated using the mean absolute error (MAE) metric. The oxygen saturation and blood pressure parameters were statistically evaluated. In the final part of the thesis, the quality of ECG records obtained from the smartwatches and their diagnostic utility were assessed.
|
|
|
Health assessment using smart devices
Vargová, Enikö ; Filipenská, Marina (referee) ; Němcová, Andrea (advisor)
This thesis deals with the possibilities of non-invasive determination of blood glucose from photoplethysmographic signals. Elevated blood sugar is often associated with disease called diabetes mellitus. Diabetes is one of the world’s major chronic diseases. Untreated diabetes is often a cause of death. The aim of the work is to propose methods for glycemic classification and prediction. Two datasets have been created by recording the PPG signals using two smart devices (a smart wristband and a smartphone), along with their blood glucose levels measured in an invasive way. The PPG signals were preprocessed, and suitable features were extracted from them. Various machine-learning models for glycemic classification and prediction were created.
|
|
|
Blood pressure estimation using smartphone
Šíma, Jan ; Vítek, Martin (referee) ; Němcová, Andrea (advisor)
This diploma thesis describes an experimental cuffless measurement of systolic and diastolic blood pressure (SBP and DBP) using only a smartphone. Photoplethysmographic signal (PPG), which was measured by the smartphone camera and phonocardiographic signal (PCG), which was captured by an external microphone in the mitral valve area, were used to estimate blood pressure (BP). The BP estimate was divided into 2 parts. The first was the regression estimation of BP and comparison of several machine learning (MLR) and convolutional neural network (CNN) methods according to the use of the color channel to extract PPG from the video. The second objective was the classification of BP into the category of normotension or hypertension. The PPG signal was filtered for extraction using a bandpass filter with finite impulse response (FIR) (0,5–5 Hz) followed by feature extraction. For estimation of vascular transit time (VTT) and cardiac ejection time (ET), two main cardiac echoes S1 and S2 were detected in the PCG signal. Furthermore, raw sections of PPG signals (RGB video channels) and PCG signals of different time lengths were used for the CNN models. Among the regression approaches, the most accurate algorithm was the support vector regression (SVR) method, which achieved acceptable error according to the standards of the Association for the Advancement of Medical Instrumentation (AAMI) and the British Hypertension Society (BHS) in experimental work. The mean absolute error (MAE) was determined to be 7.64±6.87 mmHg for SBP and 5.07±4.88 mmHg for DBP. The red channel was evaluated as the most appropriate color channel for extracting PPG from the video recordings for regression estimation. For classification, the AdaBoost algorithm with weak random forest (RF) classifiers proved to be the most reliable. It achieved an F1 score of almost 80 % on the PPG features extracted from the combination of red and green color channels of the video.
|
|
|
Production of enriched mixed biomass by co-cultivation of selected strains of yeast and microalgae
Langer, Marek ; Němcová, Andrea (referee) ; Szotkowski, Martin (advisor)
The use of yeast and microalgae in industry is constantly increasing. These microorganisms are able to produce significant amounts of lipids, which can be used, for example, for the production of biodiesel. Like their other metabolites, such as carotenoids, chlorophylls, ubiquinone and ergosterol, they can be used in the food industry. Since these chemical substances also have biological effects on the human organism, they are used in food supplements, but are also being investigated as possible medicines. The presented work deals with the possibilities of making the cultivation of these microorganisms cheaper. One of these options is co-cultivation, or mixed cultivation, which aims to increase biomass and metabolite yields. Another investigated possibility is the replacement of financially expensive substrates for the nutrition of microorganisms with cheap waste from the food industry. The algae Scenedesmus ecornis, Desmodesmus communis, Chlamydomonas reinhardtii and Coccomyxa sp. were used in the experimental work. The yeast strains used were Rhodotorula kratochvilovae and Rhodotorula toruloides. Added waste products were oils (hemp, frying and coffee), molasses, whey and waste glycerol. Analysis of the obtained biomass revealed that the highest lipid yields were achieved when coffee and frying oil were used. The experiment was completed by pilot cultivation in a bioreactor, to which cultures of Scenedesmus ecornis and Rhodotorula kratochvilovae were added. Coffee oil and glycerol were added as a source of nutrients.
|
guest ::
RSS feed.