In order to ensure reliable opening of the productive reservoir without complications and at high mechanical drilling speeds, to obtain objective field-geophysical material in the productivity intervals, much attention is paid to the cleanliness of the bottom of the well, i.e., the absence of foreign metal objects. The development of a device for extracting large and small foreign objects from the bottom of wells with high efficiency, reliability and low cost of work is a very urgent task. Devices based on the hydrodynamic principle of operation fully meet the requirements. The paper proposes a design of a hydrodynamic device that allows to clean the bottom of the well from small particles.

The article discusses the results of studying the processing of washed potash ore from the Chelkar deposit to obtain ballastless potash fertilizer. The efficiency of ore double and triple washing from sodium salts has been studied to determine the optimal mode of ore enrichment on potassium. It has been established that it is expedient to carry out ore double washing with washing water, which ensures the maximum potassium content in the ore and the minimum content of sodium salts. The washing effectiveness is confirmed by the results of the X-ray analysis of the ore after double washing. Ore calcination leads to dehydration of crystalline hydrates of minerals and to increasing content of main components in its composition. Dissolution of the calcined ore at temperatures of 50 and 90°C results in only a partial transition of potassium and magnesium salts into the solution with the complete dissolution of residual amounts of sodium salts. To reach complete dissolution of potassium and magnesium sulfates, which are the target components for obtaining mineral fertilizers, it is necessary to study methods of chemical conversion.

This article studies the main physical and chemical properties of magnetic clays. Structural changes in magnetic clay composite suspensions were evaluated by measuring the permittivity through direct measurement of the sensor capacitance and through computer measurement of the frequency of the electric signal inversely proportional to the sensor capacitance. Natural bentonite clay of the Tagan field (East Kazakhstan region) was used in this study. Magnetite synthesized by the method of co-precipitation of iron salts with magnetite-clay composites. Different compositions of clay-magnetite compounds were investigated to study the magnetic properties of the samples. According to the study, with the increasing of magnetite in the composition the magnetic properties increase. However, increasing the magnetite in the composition leads to lose the stability of the suspension. The stability of the suspension also investigated by measuring of the size of the particles. Depending on the findings of the study 20% magnetite-clay composition was the optimal value for the magnetic solution.

Retail trade or retail is a sale of certain goods to the end consumer or intermediary for further sale, which is implemented through trade in specially equipped premises, through personal sales, etc. Also, retail trade is a commodity exchange process aimed at meeting the demand of customers.

In addition, the retail sector currently occupies a leading position in terms of the intensity of development of the CIS countries economy. Excellent indicators have been achieved and many companies have reached a new level of trading. By about 2005, more than a dozen major retail chains had passed the billion-dollar milestone in terms of annual net revenue, and this is in dollars. The turnover of individual stores and retail facilities competed with some industrial enterprises with solid turnover and production bases.

Thus, we can claim that the sphere of trade affects the growth and development of related industries. The product promotion chain involves the participation of customers and their demand, as well as other participants in the process. Moreover, the development of trade requires sellers to pay more and more attention to working with the product range and inventory balances. Working with inventory and product balances is a main issue for many retailers. And the many companies needed to make sure that there is a sufficient quantity of goods in the warehouse. Another point is that, exclude overstocking, because this is also one of the problems of retailers with a high degree of accuracy is required to make decisions.

To sum up, making decisions in inventory management directly affects sales volumes, logistics costs, revenue, profit, and profitability. Inventory prediction is a necessary task to maintain an optimal level of inventory. I would like to note that the goal of the project / dissertation is to solve this problem using modern prediction methods based on machine learning technologies. The result is that in this way it is quite possible to analyze the dynamics of sales(consumer demand) thousands or even more products.

Restaurant owners must reliably assess restaurant customers in order to function effectively and productively to enhance the restaurant's service. It is important to have a successful forecast in order to prevent losses and boost service and market optimization. There are a variety of machine learning (ML) approaches that can be used to make these predictions, but each visitor is unique and will act in a unique way. As a result, we want to estimate how many guests a restaurant may expect in the future using big data and supervised training in this study. We used three different machine learning methods in a real dataset from supervised training to predict how many visitors a restaurant dataset "Recruit restaurant visitor forecasting" will receive: Neural Network, XGBoost and Random Forest regressor. The predicted values were compared to the real data after the simulation. Basically, algorithms used had mean errors of less than 9.5278, but the Random Forest regressor exceeded, with mean errors of 9.2902.

This article describes image based personality type prediction. With the help of the Instagram API, photos of respondents who previously passed the MBTI test were collected. As a result, 60 percent of accuracy was achieved. This work represents one of the solutions to determine what personality type a person belongs to without passing any tests, but simply uploading an image.

Residual recoverable reserves of high-viscosity and heavy oils in the Republic of Kazakhstan amount to about 340 million tons. The main oil fields containing high-viscosity and heavy oil are Karazhanbas, Kenkiyak, Zhetybai, North Buzachi, Kenbai, etc. Improving the system for the development of high-viscosity oil fields and the selection of rational EOR is relevant for Kazakhstan, as this will increase the efficiency of their development. Given the high resource potential of such fields, it is necessary to develop and introduce new technologies in the development of high-viscous oil fields using enhanced oil recovery methods. To ensure high oil recovery factors, it is necessary to carefully select the EOR applicable to high-viscosity oil fields at an early stage of their development. This work is devoted to the problem of EOR selection in the development of high-viscosity oil fields. For the research polymer injection was selected. Evaluation of the efficiency of the proposed EOR was carried out based on the results of numerical experiments to displace high-viscosity oil with the creation of reservoir conditions. As a result, the aqueous polymer solution with the concentration of 0.05 % yielded 51% of oil recovery, whereas water injection recovered only 10% of oil. However, the interaction of the polymer with high-viscosity oil has not been deeply studied, which is relevant to the fields of Kazakhstan.

An experimental version of the psychological testing system with fixing the psychophysiological parameters of the test person in real time is developed. As sources of physiological data, the data of the electrocardiogram (ECG), skin-galvanic reaction (SGR) are determined. The hardware-software complex of psychophysiological testing allows, when answering each question of the test, to record and evaluate the psychophysiological state of the test person, which provides additional information for psychologists and personnel services.

As a questionnaire, the “Big Five” test was chosen - it is a five-factor personality model designed in such a way that a structured and fairly complete portrait of a personality can be drawn from a set of features included in it. The test was conducted among students of the 3rd and 4th year of the University of Turan. The total number of participants is 60 people.

With the help of the software developed in the article, it is clear that the pivot structure at many production facilities or strategic sites is an indispensable tool for the engineer to predict the thermo-mechanical state of elements under the influence of temperature. 

The article shows that strategic devices arise in the main structural elements under the influence of various complex heat sources. It was considered by a universal numerical method that allows one to study its thermomechanical state. In addition, a computational algorithm was developed. It is shown that the long-term operation of these devices depends on the thermal strength of the main structural elements.

The use of machine learning in the medical field is one of the most difficult and thoroughly unsolved problems. Currently, there are many different algorithms for solving problems in the field of diagnostics and segmentation of biomedical images. Researchers are often faced with the challenge of choosing the best method to apply towards their data. We conducted the empirical research and compared 5 algorithms that able to detect anomalies in the medical images: RCNN, Fast-RCNN, Faster-RCNN, Mask R CNN, U-Net, and Residual Neural Network. The advantages of automatic processing of the medical images are apparent: doctors get a convenient software tool that allows them to diagnose the disease faster and reduce possible errors. The task is to study and then select algorithms for further testing on the actual data. The selection and study of algorithms were based on articles describing the architecture and application of computer vision algorithms.

Computer Vision is the area of Machine Learning that is responsible for machine perception of visual information. Image segmentation is a subfield of Computer Vision that solves the task of dividing a digital image into segments by their class label. One of the main problems in the subfield is the scarcity of data and the restoration of spatial information for the classified image. This article is a brief survey of current Biomedical Image Segmentation approaches, specifically Convolutional Neural Networks architectures and the morphological transformation for data augmentation.

Segmentation is a process of dividing a speech signal into the basic units of language. Segmentation of the speech signals is one of the most important tasks in automatic speech processing systems. This paper proposes a review of methods of automatic speech segmentation. Moreover, methods of wavelet and Hilbert-Huang transformations and techniques based on hidden Markov models are considered.

Market Basket Analysis (MBA) is an approach that finds the strength of association between pairs of products that customers buy and can determine patterns of co-occurrence. The main aim of MBA is to determine customer buying behavior and predict next purchase. It can help companies to increase cross-selling.

To generate association rules, the Apriori algorithm employs frequently purchased item-sets. It is based on the idea that a frequently purchased item’s subset is also a frequently purchased item. If the support value of a frequently purchased item-set exceeds a minimum threshold, the item-set is chosen. This paper observes the advantages of implementing MBA, algorithms that applies in this technique and ways to identify customer buying patterns.