Search

This paper presents innovative machine-learning solutions to enhance energy efficiency in electrical tomography for industrial reactors. Addressing the key challenge of optimizing the neural model's loss function, a classifier tailored to precisely recommend optimal loss functions based on the measurement data is designed. This classifier recommends which model, equipped with given loss functions, should be used to ensure the best reconstruction quality. The novelty of this study lies in the optimal adjustment of the loss function to a specific measurement vector, which allows for better reconstructions than that by traditional models trained based on a constant loss function. This study presents a methodology enabling the development of an optimal loss function classifier to determine the optimal model and loss function for specific datasets. The approach eliminates the randomness inherent in traditional methods, leading to more accurate and reliable reconstructions. In order to achieve the set goal, four models based on a simple LSTM network structure were first trained, each connected with various loss functions: HMSE (half mean squared error), Huber, l1loss (L1 loss for regression tasks—mean absolute error), and l2loss (L2 loss for regression tasks—mean squared error). The best classifier training results were obtained for support vector machines. The quality of the obtained reconstructions was evaluated using three image quality indicators: PSNR, ICC, and MSE. When applied to simulated cases and real measurements from the Netrix S.A. laboratory, the classifier demonstrated effective performance, consistently recommending models that produced reconstructions that closely resembled the real objects. Such a classifier can significantly optimize the use of EIT in industrial reactors by increasing the accuracy and efficiency of imaging, resulting in improved energy management and efficiency. [ABSTRACT FROM AUTHOR]

The mechanisms by which yeast cells respond to environmental stress include the production of heat shock proteins (HSPs) and the reduction of oxidative stress. The response of yeast exposed to aflatoxins B2+G1 (AFB2+G1), ochratoxin A (OTA), and zearalenone (ZEA) in aerobic conditions was studied. After 72 h of yeast cultivation in media contaminated with mycotoxins, the growth of yeast biomass, the level of malondialdehyde, and the activity of superoxide dismutase, glutathione S-transferase and glutathione peroxidase were examined; the expression profile of the following heat shock proteins was also determined: HSP31, HSP40, HSP60, HSP70, and HSP104. It was demonstrated that at the tested concentrations, both AFB2+G1 and ZEA inhibited yeast biomass growth. OTA at a concentration of 8.4 [µg/L] raised the MDA level. Intensified lipoperoxidation and increased activity of SOD and GPx were observed, regardless of the level of contamination with ZEA (300 µg/L or 900 µg/L). Increased contamination with AFB2+G1 and OTA caused an increase in the production of most HSPs tested (HSP31, HSP40, HSP70, HSP104). ZEA contamination in the used concentration ranges reduced the production of HSP31. The response of yeast cells to the presence of mycotoxin as a stressor resulted in the expression of certain HSPs, but the response was not systematic, which was manifested in different profiles of protein expression depending on the mycotoxin used. The tested mycotoxins influenced the induction of oxidative stress in yeast cells to varying degrees, which resulted in the activation of mainly SOD without GST mobilization or with a small involvement of GPx. [ABSTRACT FROM AUTHOR]

Wet foundations and walls of buildings significantly increase the energy consumption of buildings, and the drying of walls is one of the priority activities as part of thermal modernization, along with the insulation of the facades. This article discusses the research findings of detecting moisture decomposition within building walls utilizing electrical impedance tomography (EIT) and deep learning techniques. In particular, the focus was on algorithmic models whose task is transforming voltage measurements into spatial EIT images. Two homogeneous deep learning networks were used: CNN (Convolutional Neural Network) and LSTM (Long-Short Term Memory). In addition, a new heterogeneous (hybrid) network was built with LSTM and CNN layers. Based on the reference reconstructions' simulation data, three separate neural network algorithmic models: CNN, LSTM, and the hybrid model (CNN+LSTM), were trained. Then, based on popular measures such as mean square error or correlation coefficient, the quality of the models was assessed with the reference images. The obtained research results showed that hybrid deep neural networks have great potential for solving the tomographic inverse problem. Furthermore, it has been proven that the proper joining of CNN and LSTM layers can improve the effect of EIT reconstructions. [ABSTRACT FROM AUTHOR]

Smart buildings are becoming a new standard in construction, which allows for many possibilities to introduce ergonomics and energy savings. These contain simple improvements, such as controlling lights and optimizing heating or air conditioning systems in the building, but also more complex ones, such as indoor movement tracking of building users. One of the necessary components is an indoor localization system, especially without any device worn by the person being located. These types of solutions are important in locating people inside smart buildings, managing hospitals of the future and other similar institutions. The article presents a prototype of an innovative energy-efficient device for radio tomography, in which the hardware and software layers of the solution are presented. The presented example consists of 32 radio sensors based on a Bluetooth 5 protocol controlled by a central unit. The preciseness of the system was verified both visually and quantitatively by the image reconstruction as a result of solving the inverse tomographic problem using three neural networks. [ABSTRACT FROM AUTHOR]

Effective project management has contributed to successful operations and process management. The goal of this article is to look at the link between a project's success (PS) and the amount of intellectual capital (IC) an organization has. Instead of being reactive to measuring the cost, timeliness, and quality (customer requirements), a more predictive indicator of a project's success is needed. Nearly 300 people who work in the field of digital (information and communication) technology took part in the survey research. The survey contains 88 questions. Several statistical techniques are utilized for the data analysis. Based on the comprehensive surveys, the findings show the strong possibility for IC to be adapted as a predictor of the success of investment projects, especially for digital upgrade and improvement. IC plays a key role in assuring the effective (and successful) project management. The study highlights the impacts of effective project management on industrial and organizational operations. This highlight is based on the attempt to determine whether IC contributes to a PS. In this study, in addition to the three traditional factors of cost, timeliness, and quality (or requirements), IC should be considered as a prediction for the project management's success. The survey was addressed to selected companies from the ICT industry (IT projects). The sample selection is based on non-probability sampling. The author's method of converting the respondents' answers into binary form was adopted. [ABSTRACT FROM AUTHOR]

One of the key elements influencing the efficiency of cellulosic ethanol production is the effective pretreatment of lignocellulosic biomass. The aim of the study was to evaluate the effect of microwave-assisted pretreatment of wheat stillage in the presence of sodium cumene sulphonate (NaCS) hydrotrope used for the production of second-generation bioethanol. As a result of microwave pretreatment, the composition of the wheat stillage biomass changed significantly when compared with the raw material used, before treatment. Microwave-assisted pretreatment with NaCS effectively reduced the lignin content and hemicellulose, making cellulose the dominant component of biomass, which accounted for 42.91 ± 0.10%. In post pretreatment, changes in biomass composition were also visible on FTIR spectra. The peaks of functional groups and bonds characteristic of lignins (C–O vibration in the syringyl ring, asymmetric bending in CH3, and aromatic skeleton C–C stretching) decreased. The pretreatment of the analyzed lignocellulosic raw material with NaCS resulted in the complete conversion of glucose to ethanol after 48 h of the process, with yield (in relation to the theoretical one) of above 91%. The highest observed concentration of ethanol, 23.57 ± 0.10 g/L, indicated the high effectiveness of the method used for the pretreatment of wheat stillage that did not require additional nutrient supplementation. [ABSTRACT FROM AUTHOR]

Featured Application: The proposed neural imaging method helps improve the functionality of widely used tomographic methods. The presented method is suitable to monitor the protections of the tailings ponds and flood embankments. This paper presents an innovative system of many artificial neural networks that enables the tomographic reconstruction of the internal structure of a flood embankment. An advantage of the proposed method is that it allows us to obtain high-resolution images, which essentially contributes to early, precise and reliable prediction of operational hazards. The method consists in training a cluster of separate neural networks, each of which generates a single point of the output image. The simultaneous and parallel application of the set of neural networks led to effective reconstruction of the internal structure of a deposition site for floatation tailings. Results obtained from the study allow us to solve the low resolution problem that usually occurs with non-invasive imaging methods. This effect was possible thanks to the design of a new intelligent image reconstruction system. [ABSTRACT FROM AUTHOR]

Pyrazines are organic compounds with a varied, intense aroma of roasted nuts, occasionally with hints of baked potatoes, almonds, and others. As a result, they are used in the food industry as food flavorings. Biosynthesis of pyrazines using microorganisms in environmentally friendly conditions is an alternative to chemical synthesis. However, screening is required to isolate efficient producer strains for efficient biosynthesis of this compound. The study's goal was to assess the ability of Bacillus subtilis cultures isolated from natto (fermented soybeans) to biosynthesize a broad range of alkylpyrazines. B. subtilis isolated cultures were found to be capable of producing 2-methylpyrazine, 2,3-dimethylpyrazine, 2,5-dimethylpyrazine, 2,6-dimethylpyrazine, 2,3,5-trimethylpyrazine, and 2,3,5,6-tetramethylpyrazine. As a result of the screening, two cultures of B. subtilis capable of producing alkylpyrazines were isolated. At a total concentration of 3261 µg/L, the BcP4 strain primarily produced 2-methylpyrazine (690 µg/L), 2,3-dimethylpyrazine (680 µg/L), and 2,6-dimethylpyrazine (1891 µg/L). At a total concentration of 558 mg/L, the BcP21 strain produced 2,5-dimethylpyrazine (4.5 mg/L), 2,3,5-trimethylpyrazine (52.6 mg/L), and 2,3,5,6-tetramethylpyrazine (501.1 mg/L). The results show that different B. subtilis strains are predisposed to produce different alkylpyrazines. [ABSTRACT FROM AUTHOR]

Electrical tomography is a non-invasive method of monitoring the interior of objects, which is used in various industries. In particular, it is possible to monitor industrial processes inside reactors and tanks using tomography. Tomography enables real-time observation of crystals or gas bubbles growing in a liquid. However, obtaining high-resolution tomographic images is problematic because it involves solving the so-called ill-posed inverse problem. Noisy input data cause problems, too. Therefore, the use of appropriate hardware solutions to eliminate this phenomenon is necessary. An important cause of obtaining accurate tomographic images may also be the incorrect selection of algorithmic methods used to convert the measurements into the output images. In a dynamically changing environment of a tank reactor, selecting the optimal algorithmic method used to create a tomographic image becomes an optimization problem. This article presents the machine learning method's original concept of intelligent selection depending on the reconstructed case. The long short-term memory network was used to classify the methods to choose one of the five homogenous methods—elastic net, linear regression with the least-squares learner, linear regression with support vector machine learner, support vector machine model, or artificial neural networks. In the presented research, tomographic images of selected measurement cases, reconstructed using five methods, were compared. Then, the selection methods' accuracy was verified thanks to the long short-term memory network used as a classifier. The results proved that the new concept of long short-term memory classification ensures better tomographic reconstructions efficiency than imaging all measurement cases with single homogeneous methods. [ABSTRACT FROM AUTHOR]

An effective microbial synthesis of surfactin depends on the composition of the culture medium, the culture conditions and the genetic potential of the producer strain. The aim of this study was to evaluate the suitability of various medium components for the surfactin producing strain and to determine the impact of the culture conditions on the biosynthesis of surfactin isoforms by the newly isolated native strain Bacillus subtilis natto BS19. The efficiency of surfactin biosynthesis was determined by measuring the surface tension of the medium before and after submerged culture (SmF) and by qualitative and quantitative analysis of the obtained compound by high performance liquid chromatography. The highest efficiency of surfactin biosynthesis was achieved using starch as the carbon source and yeast extract as the nitrogen source at pH 7.0 and 37 °C. Potato peelings were selected as an effective waste substrate. It was shown that the increase in the percentage of peel extract in the culture medium enhanced the biosynthesis of surfactin (mg/L) (2–30.9%; 4–46.0% and 6–58.2%), while reducing surface tension of the medium by about 50%. The obtained results constitute a promising basis for further research on biosynthesis of surfactin using potato peelings as a cheap alternative to synthetic medium components. [ABSTRACT FROM AUTHOR]

This paper presents the results of research on the use of machine learning algorithms and electrical tomography in detecting humidity inside the walls of old buildings and structures. The object of research was a historical building in Wrocław, Poland, built in the first decade of the 19th century. Using the prototype of an electric tomograph of our own design, a number of voltage measurements were made on selected parts of the building. Many algorithmic methods have been preliminarily analyzed. Ultimately, the three models based on machine learning were selected: linear regression with SVM (support vector machine) learner, linear regression with least squares learner, and a multilayer perceptron neural network. The classical Gauss–Newton model was also used in the comparison. Both the experiments based on real measurements and simulation data showed a higher efficiency of machine learning methods than the Gauss–Newton method. The tomographic methods surpassed the point methods in measuring the dampness in the walls because they show a spatial image of the interior and not separate points of the examined cross-section. Research has shown that the selection of a machine learning model has a large impact on the quality of the results. Machine learning has a greater potential to create correct tomographic reconstructions than traditional mathematical methods. In this research, linear regression models performed slightly worse than neural networks. [ABSTRACT FROM AUTHOR]

The article deals with the problem of detecting moisture in the walls of historical buildings. As part of the presented research, the following four methods based on mathematical modeling and machine learning were compared: total variation, least-angle regression, elastic net, and artificial neural networks. Based on the simulation data, the systems for the reconstruction of "pixel by pixel" tomographic images were trained. In order to test the reconstructive algorithms obtained during the research, images were generated based on real measurements and simulation cases. The method comparison was performed on the basis of three indicators: mean square error, relative image error, and image correlation coefficient. The above indicators were applied to four selected variants that corresponded to various parts of the walls. The variants differed in the dimensions of the tested wall sections, the number of electrodes used, and the resolution of the 3D image meshes. In all analyzed variants, the best results were obtained using the elastic net algorithm. In addition, all machine learning methods generated better tomographic reconstructions than the classic Total Variation method. [ABSTRACT FROM AUTHOR]

Understanding the specific response of yeast cells to environmental stress factors is the starting point for selecting the conditions of adaptive culture in order to obtain a yeast line with increased resistance to a given stress factor. The aim of the study was to evaluate the specific cellular response of Saccharomyces cerevisiae strain Ethanol Red to stress caused by toxic by-products generated during the pretreatment of lignocellulose, such as levulinic acid, 5-hydroxymethylfurfural, furfural, ferulic acid, syringaldehyde and vanillin. The presence of 5-hydroxymethylfurfural at the highest analyzed concentration (5704.8 ± 249.3 mg/L) under aerobic conditions induced the overproduction of ergosterol and trehalose. On the other hand, under anaerobic conditions (during the alcoholic fermentation), a decrease in the biosynthesis of these environmental stress indicators was observed. The tested yeast strain was able to completely metabolize 5-hydroxymethylfurfural, furfural, syringaldehyde and vanillin, both under aerobic and anaerobic conditions. Yeast cells reacted to the presence of furan aldehydes by overproducing Hsp60 involved in the control of intracellular protein folding. The results may be helpful in optimizing the process parameters of second-generation ethanol production, in order to reduce the formation and toxic effects of fermentation inhibitors. [ABSTRACT FROM AUTHOR]

The article presents an original machine-learning-based automated approach for controlling the process of machining of low-rigidity shafts using artificial intelligence methods. Three models of hybrid controllers based on different types of neural networks and genetic algorithms were developed. In this study, an objective function optimized by a genetic algorithm was replaced with a neural network trained on real-life data. The task of the genetic algorithm is to select the optimal values of the input parameters of a neural network to ensure minimum deviation. Both input vector values and the neural network's output values are real numbers, which means the problem under consideration is regressive. The performance of three types of neural networks was analyzed: a classic multilayer perceptron network, a nonlinear autoregressive network with exogenous input (NARX) prediction network, and a deep recurrent long short-term memory (LSTM) network. Algorithmic machine learning methods were used to achieve a high level of automation of the control process. By training the network on data from real measurements, we were able to control the reliability of the turning process, taking into account many factors that are usually overlooked during mathematical modelling. Positive results of the experiments confirm the effectiveness of the proposed method for controlling low-rigidity shaft turning. [ABSTRACT FROM AUTHOR]

This paper refers to the method of using the deep neural long-short-term memory (LSTM) network for the problem of electrocardiogram (ECG) signal classification. ECG signals contain a lot of subtle information analyzed by doctors to determine the type of heart dysfunction. Due to the large number of signal features that are difficult to identify, raw ECG data is usually not suitable for use in machine learning. The article presents how to transform individual ECG time series into spectral images for which two characteristics are determined, which are instantaneous frequency and spectral entropy. Feature extraction consists of converting the ECG signal into a series of spectral images using short-term Fourier transformation. Then the images were converted using Fourier transform again to two signals, which includes instantaneous frequency and spectral entropy. The data set transformed in this way was used to train the LSTM network. During the experiments, the LSTM networks were trained for both raw and spectrally transformed data. Then, the LSTM networks trained in this way were compared with each other. The obtained results prove that the transformation of input signals into images can be an effective method of improving the quality of classifiers based on deep learning. [ABSTRACT FROM AUTHOR]

The aim of the study was to assess the effectiveness of microwave pretreatment combined with acid catalysis in the decomposition of various types of biomass (pine and beech chips and hemp stems). It was clearly demonstrated that sulfuric acid was a catalyst enabling the most effective decomposition of the tested plant biomass, guaranteeing the highest concentrations of simple sugars released. Acid catalysis with 1% v/v sulfuric acid combined with microwave radiation provided high glucose concentrations of 89.8 ± 3.4, 170.4 ± 2.4 and 164.6 ± 4.6 mg/g for pine chips, beech chips and hemp stems, respectively. In turn, the use of nitric acid promoted the degradation of hemicellulose, which resulted in high concentrations of galactose and xylose, i.e., 147.6 ± 0.6, 163.6 ± 0.4 and 134.9 ± 0.8 mg/g of pine chips, beech chips and hemp stems, respectively, while glucose levels remained relatively low. It was also demonstrated that the undesirable dehydration of sugars such as glucose and xylose is more pronounced in sulfuric acid than nitric acid processes. The use of H2SO4 and increased pressure generated 5-hydroxymethylfurfural (5-HMF) and furfural at a concentration of ca. 12 and 6 mg/g, 10 and 45 mg/g and 14 and 30 mg/g, of pine chips, beech chips and hemp shoots, respectively. Our studies confirmed the usefulness of the combined use of microwaves and acid catalysis in the degradation of softwood, hardwood and non-wood plant biomass. It should be emphasized that obtaining high concentrations of released simple sugars (as potential substrates in biosynthesis), while maintaining low levels of toxic by-products (inhibitors), requires precise selection of process parameters such as pressure, exposition time and type of acid catalyst. [ABSTRACT FROM AUTHOR]

The paper presents the results of research on the hybrid industrial tomograph electrical impedance tomography (EIT) and ultrasonic tomography (UST) (EIT-UST), operating on the basis of electrical and ultrasonic data. The emphasis of the research was placed on the algorithmic domain. However, it should be emphasized that all hardware components of the hybrid tomograph, including electronics, sensors and transducers, have been designed and mostly made in the Netrix S.A. laboratory. The test object was a tank filled with water with several dozen percent concentration. As part of the study, the original multiple neural networks system was trained, the characteristic feature of which is the generation of each of the individual pixels of the tomographic image, using an independent artificial neural network (ANN), with the input vector for all ANNs being the same. Despite the same measurement vector, each of the ANNs generates its own independent output value for a given tomogram pixel, because, during training, the networks get their respective weights and biases. During the tests, the results of three tomographic methods were compared: EIT, UST and EIT-UST hybrid. The results confirm that the use of heterogeneous tomographic systems (hybrids) increases the reliability of reconstruction in various measuring cases, which is used to solve quality problems in managing production processes. [ABSTRACT FROM AUTHOR]

This study aimed to evaluate the use of softwood and hardwood waste for the production of levulinic acid by one-stage conversion using microwave radiation combined with acid catalysis. The analysis demonstrated that the type and concentration of the acid used, the concentration of biomass in the reaction mixture and pressure value had the greatest impact on the yield of levulinic acid. The highest efficiency of carbohydrate conversion to levulinic acid, regardless of the type of raw material, was achieved using a pressure of 225 PSI and sulfuric acid as a catalyst. Maximum yield from biomass, ca. 16.5% for cherry wood chips and ca. 25% for pine chips, was obtained using sulfuric acid at a concentration of 1% v/v and 2% v/v, respectively, for the following process parameters: Exposure time 20 min, biomass concentration 3.3%, and the pressure of 225 PSI. The ratio of actual yield to theoretical yield was high: 64.7% ± 4.5% for pine chips and 43.4% ± 1.0% for cherry wood chips. High efficiency of the presented method of biomass conversion to levulinic acid indicates the possibility of its use for waste management in the wood processing industry. High concentration of levulinic acid in the post-reaction mixture allows for cost-effective extraction and purification of the compound. [ABSTRACT FROM AUTHOR]

The main goal of the research presented in this paper was to develop a refined machine learning algorithm for industrial tomography applications. The article presents algorithms based on logistic regression in relation to image reconstruction using electrical impedance tomography (EIT) and ultrasound transmission tomography (UST). The test object was a tank filled with water in which reconstructed objects were placed. For both EIT and UST, a novel approach was used in which each pixel of the output image was reconstructed by a separately trained prediction system. Therefore, it was necessary to use many predictive systems whose number corresponds to the number of pixels of the output image. Thanks to this approach the under-completed problem was changed to an over-completed one. To reduce the number of predictors in logistic regression by removing irrelevant and mutually correlated entries, the elastic net method was used. The developed algorithm that reconstructs images pixel-by-pixel is insensitive to the shape, number and position of the reconstructed objects. In order to assess the quality of mappings obtained thanks to the new algorithm, appropriate metrics were used: compatibility ratio (CR) and relative error (RE). The obtained results enabled the assessment of the usefulness of logistic regression in the reconstruction of EIT and UST images. [ABSTRACT FROM AUTHOR]

The main goal of this work was to compare the selected machine learning methods with the classic deterministic method in the industrial field of electrical impedance tomography. The research focused on the development and comparison of algorithms and models for the analysis and reconstruction of data using electrical tomography. The novelty was the use of original machine learning algorithms. Their characteristic feature is the use of many separately trained subsystems, each of which generates a single pixel of the output image. Artificial Neural Network (ANN), LARS and Elastic net methods were used to solve the inverse problem. These algorithms have been modified by a corresponding increase in equations (multiply) for electrical impedance tomography using the finite element method grid. The Gauss-Newton method was used as a reference to machine learning methods. The algorithms were trained using learning data obtained through computer simulation based on real models. The results of the experiments showed that in the considered cases the best quality of reconstructions was achieved by ANN. At the same time, ANN was the slowest in terms of both the training process and the speed of image generation. Other machine learning methods were comparable with the deterministic Gauss-Newton method and with each other. [ABSTRACT FROM AUTHOR]

This article presents the results of research on a new method of spatial analysis of walls and buildings moisture. Due to the fact that destructive methods are not suitable for historical buildings of great architectural significance, a non-destructive method based on electrical tomography has been adopted. A hybrid tomograph with special sensors was developed for the measurements. This device enables the acquisition of data, which are then reconstructed by appropriately developed methods enabling spatial analysis of wet buildings. Special electrodes that ensure good contact with the surface of porous building materials such as bricks and cement were introduced. During the research, a group of algorithms enabling supervised machine learning was analyzed. They have been used in the process of converting input electrical values into conductance depicted by the output image pixels. The conductance values of individual pixels of the output vector made it possible to obtain images of the interior of building walls as both flat intersections (2D) and spatial (3D) images. The presented group of algorithms has a high application value. The main advantages of the new methods are: high accuracy of imaging, low costs, high processing speed, ease of application to walls of various thickness and irregular surface. By comparing the results of tomographic reconstructions, the most efficient algorithms were identified. [ABSTRACT FROM AUTHOR]

The idea of using microorganisms, especially microalgae, as biosorbents of heavy metals deserves particular attention due to their natural biosorbent properties and the relatively simple and inexpensive methods of obtaining their biomass. The cosmopolitan microscopic green alga of the genus Pseudopediastrum is an example of an organism with the desired biosorption properties. The aim of the study was to assess the potential use the dry biomass of Ps. boryanum var. longicorne in the process of biosorption of chromium(VI) (Cr(VI)) ions from aqueous solutions. Biomass of microalgae was cultivated in the photobioreactor conditions (L-S2T2 medium, light intensity of 4000 lx, photoperiod 12L:12D). The biomass obtained was used for the biosorption of Cr(VI) ions from aqueous solution. The effect of pH (2–6), biosorbent concentration (0.5–2 g/L) and initial chromium concentration (10–100 mg/L) was examined. The highest removal of Cr(VI) ions (70%) was observed at pH 2, initial chromium concentration of 10 mg/L and a biomass concentration of 2 g/L. At this chromium concentration, the sorption capacity of the microalga was the lowest. The results indicated that the biomass of the Ps. boryanum is suitable for the development of efficient biosorbent for the removal of Cr(VI) from wastewater. [ABSTRACT FROM AUTHOR]

One of the key steps in the production of phytases of microbial origin is selection of culture parameters, followed by isolation of the enzyme and evaluation of its catalytic activity. It was found that conditions for S. cerevisiae yeast culture, strain Finarome, giving the reduction in phytic acid concentration of more than 98% within 24 h of incubation were as follows: pH 5.5, 32 °C, continuous stirring at 80 rpm, the use of mannose as a carbon source and aspartic acid as a source of nitrogen. The highest catalytic activity of the isolated phytase was observed at 37 °C, pH 4.0 and using phytate as substrate at concentration of 5.0 mM. The presence of ethanol in the medium at a concentration of 12% v/v reduces the catalytic activity to above 60%. Properties of phytase derived from S. cerevisiae yeast culture, strain Finarome, indicate the possibility of its application in the form of a cell’s free crude protein isolate for the hydrolysis of phytic acid to improve the efficiency of alcoholic fermentation processes. Our results also suggest a possibility to use the strain under study to obtain a fusant derived with specialized distillery strains, capable of carrying out a highly efficient fermentation process combined with the utilization of phytates. [ABSTRACT FROM AUTHOR]