Transformation Algorithm Research Articles

Impact of beam-coupling impedance on the Schottky spectrum of bunched beam

The Schottky monitors of the Large Hadron Collider (LHC) can be used for non-invasive beam diagnostics to estimate various bunch characteristics, such as tune, chromaticity, bunch profile or synchrotron frequency distribution. However, collective effects, in particular beam-coupling impedance, can significantly affect Schottky spectra when large bunch charges are involved. In such conditions, the available interpretation methods are difficult to apply directly to the measured spectra, thus preventing the extraction of beam and machine parameters, which is possible for lower bunch charges. To study the impact of impedance on such spectra, we introduce a method for building Schottky spectra from macro-particle simulations performed with the PyHEADTAIL code, applied to LHC beam conditions. In this case, the use of a standard Fast Fourier Transform (FFT) algorithm to recover the spectral content of the beam becomes computationally intractable memory-wise, because of the relatively short bunch length compared to the large revolution period. To circumvent this difficulty, a semi-analytical method was developed to efficiently compute the Fourier transform. The simulated Schottky spectrum is then compared against theoretical formulas and measurements of Schottky signals previously obtained with lead ion beams in the LHC where impedance effects are expected to be limited. Furthermore, this study provides preliminary interpretations of the impact of beam-coupling impedance on proton Schottky spectra by incorporating longitudinal and transverse resonator-like impedance models into the simulations. A theoretical framework is also introduced for the case of the longitudinal impedance, allowing the extension of the existing theoretical formalism.

Neuromorphic Camera Denoising Using Graph Neural Network-Driven Transformers.

Neuromorphic vision is a bio-inspired technology that has triggered a paradigm shift in the computer vision community and is serving as a key enabler for a wide range of applications. This technology has offered significant advantages, including reduced power consumption, reduced processing needs, and communication speedups. However, neuromorphic cameras suffer from significant amounts of measurement noise. This noise deteriorates the performance of neuromorphic event-based perception and navigation algorithms. In this article, we propose a novel noise filtration algorithm to eliminate events that do not represent real log-intensity variations in the observed scene. We employ a graph neural network (GNN)-driven transformer algorithm, called GNN-Transformer, to classify every active event pixel in the raw stream into real log-intensity variation or noise. Within the GNN, a message-passing framework, referred to as EventConv, is carried out to reflect the spatiotemporal correlation among the events while preserving their asynchronous nature. We also introduce the known-object ground-truth labeling (KoGTL) approach for generating approximate ground-truth labels of event streams under various illumination conditions. KoGTL is used to generate labeled datasets, from experiments recorded in challenging lighting conditions, including moon light. These datasets are used to train and extensively test our proposed algorithm. When tested on unseen datasets, the proposed algorithm outperforms state-of-the-art methods by at least 8.8% in terms of filtration accuracy. Additional tests are also conducted on publicly available datasets (ETH Zürich Color-DAVIS346 datasets) to demonstrate the generalization capabilities of the proposed algorithm in the presence of illumination variations and different motion dynamics. Compared to state-of-the-art solutions, qualitative results verified the superior capability of the proposed algorithm to eliminate noise while preserving meaningful events in the scene.

Biomedical Applications of Wavelet Transform Algorithm on Deep Learning Ultrasonic Image Optimization as a Prognosis Model for Acute Myocarditis

We aimed to investigate the biomedical methods of wavelet transform algorithm on ultrasonic image denoising algorithm and the risk factors for the adverse prognostic events of patients with myocarditis and analyse its correlation with free triiodothyronine (FT3) level. A retrospective study was performed to include 68 patients diagnosed with acute myocarditis (AM). The included patients were enrolled into adverse event (AE) group (n = 7) and non-adverse event (NAE) group (n = 61). The clinical data, laboratory examination indicators, echocardiographic parameters, and thyroid functions between the patients in the two groups at admission were compared. Besides, wavelet transform (WT) algorithm was employed to process ultrasonic images containing noises. Univariate and multivariate analysis were performed using Logistic regression model. It was demonstrated that peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) (35.279, 0.847) of wavelet transform algorithm were higher than those of denoising convolutional neural network (DnCNN) algorithm (30.673, 0.582) and Red-Net algorithm (28.489, 0.638). In the AE group, the QRS interval was longer ([102 (93, 135) ms] versus [86 (79, 102) ms]), the proportion of prolonged QRS period was higher (28.57%, 9.83%), and the creatine kinase isoenzyme, a marker of myocardial injury, was higher [32.87 (13.64, 78.62) U/L] versus 12.02 (9.89, 27.65) U/L], and the level of FT3 was lower [1.87 (1.23, 2.36) pg/mL versus 2.83 (1.83, 3.45) pg/mL] compared to the NAE group. The left ventricular ejection fraction (LVEF) in the adverse event group was lower than that in the non-adverse event group [45.78 (36.18, 54.32) % versus 63.72 (54.82, 64.68)]. Multivariate Logistic regression analysis showed that the risk factors for adverse events in patients with acute myocarditis included QRS interval > 120 ms (OR = 1.021), creatine kinase isoenzyme > 24 U/L (OR = 1.024), FT3 (OR = 0.067), and LVEF < 50% (OR = 0.973). This work confirmed that the wavelet transform algorithm can optimize the image quality of echocardiography, improve the clarity, and provide a feasible idea for improving the prognosis of patients with acute myocarditis.

Qin Seal Script Character Recognition with Fuzzy and Incomplete Information

The dependable and efficient identification of Qin seal script characters is pivotal in the discovery, preservation, and inheritance of the distinctive cultural values embodied by these artifacts. This paper uses image histograms of oriented gradients (HOG) features and an SVM model to discuss a character recognition model for identifying partial and blurred Qin seal script characters. The model achieves accurate recognition on a small, imbalanced dataset. Firstly, a dataset of Qin seal script image samples is established, and Gaussian filtering is employed to remove image noise. Subsequently, the gamma transformation algorithm adjusts the image brightness and enhances the contrast between font structures and image backgrounds. After a series of preprocessing operations, the oriented gradient histograms (HOG) features are extracted from the images. During model training, different weights are assigned to classes with varying sample quantities to address the issue of class imbalance and improve the model's classification accuracy. Results show that the model achieves an accuracy of 95.30%. This research can help historians quickly identify and extract the text content on newly discovered Qin slip cultural relics, shortening the cycle of building a historical database.

Analytical method of determining conditions for full compensation of reactive power in the power supply system

Goal. The purpose of the article is the development of an analytical method for determining the conditions for achieving full compensation in the generalized power supply system based on the use of substitute circuits, which are obtained using equivalent transformations of the topology of the original circuit. Methodology. The article proposes a methodology for replacing series reactive power compensation in high-voltage paths of the power supply system with parallel reactive power compensation in a low-voltage load node. Results. An algorithm for successive transformations of the power supply circuit has been developed, which makes it possible to estimate the values of the capacitances of compensating capacitors, at which full compensation of reactive power in the system is achieved. Originality. The proposed analytical method for calculating the parameters of the compensation unit makes it possible to dispense with complex optimization computer methods and makes it possible to estimate the compensation capacities that fall on the share of the load and the network. Practical value. The proposed technique allows, using a simple algorithm, to determine with high accuracy the necessary parameters of the compensating device, which provide the optimal mode in the power supply system. The proposed algorithm can easily be implemented in a microcontroller system for automatic control of the modes of the power supply system.

LiDAR Dynamic Target Detection Based on Multidimensional Features.

To address the limitations of LiDAR dynamic target detection methods, which often require heuristic thresholding, indirect computational assistance, supplementary sensor data, or postdetection, we propose an innovative method based on multidimensional features. Using the differences between the positions and geometric structures of point cloud clusters scanned by the same target in adjacent frame point clouds, the motion states of the point cloud clusters are comprehensively evaluated. To enable the automatic precision pairing of point cloud clusters from adjacent frames of the same target, a double registration algorithm is proposed for point cloud cluster centroids. The iterative closest point (ICP) algorithm is employed for approximate interframe pose estimation during coarse registration. The random sample consensus (RANSAC) and four-parameter transformation algorithms are employed to obtain precise interframe pose relations during fine registration. These processes standardize the coordinate systems of adjacent point clouds and facilitate the association of point cloud clusters from the same target. Based on the paired point cloud cluster, a classification feature system is used to construct the XGBoost decision tree. To enhance the XGBoost training efficiency, a Spearman's rank correlation coefficient-bidirectional search for a dimensionality reduction algorithm is proposed to expedite the optimal classification feature subset construction. After preliminary outcomes are generated by XGBoost, a double Boyer-Moore voting-sliding window algorithm is proposed to refine the final LiDAR dynamic target detection accuracy. To validate the efficacy and efficiency of our method in LiDAR dynamic target detection, an experimental platform is established. Real-world data are collected and pertinent experiments are designed. The experimental results illustrate the soundness of our method. The LiDAR dynamic target correct detection rate is 92.41%, the static target error detection rate is 1.43%, and the detection efficiency is 0.0299 s. Our method exhibits notable advantages over open-source comparative methods, achieving highly efficient and precise LiDAR dynamic target detection.

Physical Reservoir Computing Enabled by Solitary Waves and Biologically Inspired Nonlinear Transformation of Input Data

Reservoir computing (RC) systems can efficiently forecast chaotic time series using the nonlinear dynamical properties of an artificial neural network of random connections. The versatility of RC systems has motivated further research on both hardware counterparts of traditional RC algorithms and more-efficient RC-like schemes. Inspired by the nonlinear processes in a living biological brain and using solitary waves excited on the surface of a flowing liquid film, in this paper, we experimentally validated a physical RC system that substitutes the effect of randomness that underpins the operation of the traditional RC algorithm for a nonlinear transformation of input data. Carrying out all operations using a microcontroller with minimal computational power, we demonstrate that the so-designed RC system serves as a technically simple hardware counterpart to the ‘next-generation’ improvement of the traditional RC algorithm.

A spectral and spatial transformer for hyperspectral remote sensing image super-resolution

ABSTRACT Due to the generally low spatial resolution of hyperspectral images (HSIs), early multispectral images lacked corresponding panchromatic bands, and as a result, fusion methods could not be used to enhance resolution. Many researchers have proposed various image super-resolution methods to address these limitations. However, these methods still suffered from issues, such as inadequate feature representation, lack of spectral feature representation, and high computational cost and inefficiency. To address these challenges, a spectral and spatial transformer (SST) algorithm for hyperspectral remote sensing image super-resolution is introduced. This algorithm uses a spatial transformer structure to extract the spatial features between the image pixels and a spectral transformer structure to extract the spectral features within the image pixels. The integration of these two components is applied to HSI super-resolution. After comparative experiments with currently advanced methods on three publicly available hyperspectral datasets, the results consistently show that our algorithm has better performance in both spectral fidelity and spatial restoration. Furthermore, our proposed algorithm was applied to real-world super-resolution experiments in the region of China's Ruoergai National Park, and subsequently, pixel-based classification was conducted on the super-resolution images, the results indicate that our algorithm could also be applied to future remote sensing interpretation tasks.

Individual recognition of Eurasian beavers (Castor fiber) by their tail patterns using a computer-assisted pattern-identification algorithm.

Individual recognition of animals is an important aspect of ecological sciences. Photograph-based individual recognition options are of particular importance since these represent a non-invasive method to distinguish and identify individual animals. Recent developments and improvements in computer-based approaches make possible a faster semi-automated evaluation of large image databases than was previously possible. We tested the Scale Invariant Feature Transform (SIFT) algorithm, which extracts distinctive invariant features of images robust to illumination, rotation or scaling of images. We applied this algorithm to a dataset of 800 tail pattern images from 100 individual Eurasian beavers (Castor fiber) collected as part of the Norwegian Beaver Project (NBP). Images were taken using a single-lens reflex camera and the pattern of scales on the tail, similar to a human fingerprint, was extracted using freely accessible image processing programs. The focus for individual recognition was not on the shape or the scarring of the tail, but purely on the individual scale pattern on the upper (dorsal) surface of the tail. The images were taken from two different heights above ground, and the largest possible area of the tail was extracted. The available data set was split in a ratio of 80% for training and 20% for testing. Overall, our study achieved an accuracy of 95.7%. We show that it is possible to distinguish individual beavers from their tail scale pattern images using the SIFT algorithm.

Propagation of uncertainty for an epipole-dependent model for convergent stereovision structure computation

An analytic model incorporating stereo epipoles is proposed for structure computation using a convergent stereovision setup. The developed model is predicated on the image parameters of both CCD camera sensors, together with two extrinsic parameters, namely the stereo baseline distance and the stereo projection angle of the scene point of interest. In the model, the points on the image planes are measured relative to the principal points, stereo epipoles are featured, and only focal length-normalized camera sensor coordinates are required for structure computation. The reconstruction model could be employed in active vision-based metrology in which the stereo imaging cameras are systematically rotated about their vertical axes relative to each other. The performance of the model is studied, and its accuracy tested by comparing the 3-space coordinates it predicted to the those obtained by a gold standard triangulation and to the ground truth results. In terms of execution speed the proposed reconstruction model exhibited a computation time of 0.6 ms compared to 6.2 ms and 9.9 ms recorded for the direct linear transformation and gold standard triangulation algorithms respectively. The coordinate measurement uncertainties determined by experimental methods are subsequently compared with those obtained by a theoretical approach based on the analytic reconstruction model. Strong correlations were found to exist between the two sets of uncertainty values obtained.

Dual-quaternion-based iterative algorithm of the three dimensional coordinate transformation

Nowadays a unit quaternion is widely employed to represent the three-dimensional (3D) rotation matrix and then applied to the 3D similarity coordinate transformation. A unit dual quaternion can describe not only the 3D rotation matrix but also the translation vector meanwhile. Thus it is of great potentiality to the 3D coordinate transformation. The paper constructs the 3D similarity coordinate transformation model based on the unit dual quaternion in the sense of errors-in-variables (EIV). By means of linearization by Taylor's formula, Lagrangian extremum principle with constraints, and iterative numerical technique, the Dual Quaternion Algorithm (DQA) of 3D coordinate transformation in weighted total least squares (WTLS) is proposed. The algorithm is capable to not only compute the transformation parameters but also estimate the full precision information of computed parameters. Two numerical experiments involving an actual geodetic datum transformation case and a simulated case from surface fitting are demonstrated. The results indicate that DQA is not sensitive to the initial values of parameters, and obtains the consistent values of transformation parameters with the quaternion algorithm (QA), regardless of the size of the rotation angles and no matter whether the relative errors of coordinates (pseudo-observations) are small or large. Moreover, the DQA is advantageous to the QA. The key advantage is the improvement of estimated precisions of transformation parameters, i.e. the average decrease percent of standard deviations is 18.28%, and biggest decrease percent is 99.36% for the scaled quaternion and translations in the geodetic datum transformation case. Another advantage is the DQA implements the computation and precision estimation of traditional seven transformation parameters (which still are frequent used yet) from dual quaternion, and even could perform the computation and precision estimation of the scaled quaternion.Graphical

A novel coupled algorithm-based method, and the characteristics and driving mechanism of water shortage in the upper Yellow River

ABSTRACT Gaining a clear understanding of the spatiotemporal characteristics of water shortage and their driving mechanism in the upper Yellow River (UYR) is crucial for the assessment and effective management of water resources in the region. The standardized streamflow index (SSI) and the improved Hilbert-Huang transform (IHHT) algorithm are combined to form a coupled SSI-IHHT method (CSIHM). The streamflow above Lanzhou Station over 1969–2015 is analysed. Results show that summer and autumn are high-risk periods of continuous water shortage. Annual streamflow has inter-annual change cycles of 3.5–9.0 a and inter-decadal change cycles between 16.4 and 28.2 a. The annual streamflow change is mainly affected by climate change. But the seasonal streamflow change is mainly influenced by human activities resulting from the operation of reservoirs. The CSIHM has advantages of mutual verification of the results and wide applicability to the field of water shortage.

Three-dimensional imaging of acoustic pressure by tomography applied to optical feedback interferometry

This paper presents a novel experimental technique for three-dimensional imaging of acoustic pressure waves by means of an optical feedback interferometer associated to standard Radon transformation algorithm for tomography. The imaging system is based on the sensing of the optical refractive index changes induced by the pressure variation in the medium where the acoustic wave propagates. Thanks to the compactness allowed by the laser optical feedback interferometer, this technique allows to image in three dimensions the variations of pressure of any acoustic source without any displacement of the source.

The energy management strategy of a loop microgrid with wind energy prediction and energy storage system day-ahead optimization

Microgrid has been extensively applied in the modern power system as a supplementary mode for the distributed energy resources. The microgrid with wind energy is usually vulnerable to the intermittence and uncertainty of the wind energy. To increase the robustness of the microgrid, the energy storage system (ESS) is necessary to compensate the power imbalance between the power supply and the load. To further maximize the economic efficiency of the system, the system level control for the microgrid is desired to be optimized when it is integrated with the utility grid. Aiming at the aforementioned problem, this paper comprehensively analyzes the power flow of a typical loop microgrid. A transformer-based wind power prediction (WPP) algorithm is proposed and compared with recurrent neural networks algorithm. With the historical weather data, it can accurately predict the 24 h average wind energy. Based on the predicted wind energy and the time-of-use (TOU) electricity price, a day-ahead daily cycling profile of the ESS with particle swarm optimization algorithm is introduced. It comprehensively considers the system capacity constraints and the battery degree of health. The functionality of the proposed energy management strategy is validated from three levels. First, WPP is conducted with the proposed algorithm and the true historical weather data. It has validated the accuracy of the transformer algorithm in prediction of the hourly level wind energy. Second, with the predicted wind energy, a case study is given to validate the day-ahead daily cycling profile. A typical 1 MVA microgrid is utilized as the simulation model to validate performance of the daily cycling optimization algorithm. The case study results show that the ESS daily cycling can effectively reduce the daily energy expense and help to shave the peak power demand in the grid.

An investigation of an athlete injury likelihood monitoring system using the random forest algorithm and DWT.

The main goal of sports science is to monitor sports injuries. Nevertheless, the existing sports injury monitoring projects have many expensive instruments and excessively extended monitoring periods, which makes it difficult to expand sports injury monitoring on a large scale. The advancement of machine learning algorithms opens up new avenues for the tracking of sports injuries. A training set of sports injuries was created using the Discrete Wavelet Transform (DWT) and Random Forest algorithms. Next, a basic analytic framework was created based on the lower-body movement of runners, and an athlete's injury likelihood monitoring system was established. First off, the wearable gyroscope device can efficiently plot the motion displacement curve and monitor the three-dimensional mechanics of the athlete's hips, thighs, and calves. Secondly, the system has a higher computational efficiency and an advantage over other classifier-based systems in terms of testing and training times. The suggested system framework identifies athletes' injury propensity, providing preventive recommendations based on displacement curves, and offering a low total cost and high testing accuracy, making it easy to implement and cost-effective. All things considered, the sports injury monitoring device is very accurate and reasonably priced, making it appropriate for widespread use.

Blockchain-enabled supervised secure data sharing and delegation scheme in Web3.0

Web3.0 represents the ongoing evolution of blockchain technology, placing a strong emphasis on establishing a decentralized and user-controlled Internet. Current data delegation solutions for Web3.0 predominantly rely on attribute-based encryption algorithms (ABE) but lack the essential capabilities for processing ciphertext. Additionally, the attribute-based ciphertext transformation algorithm (ABCT) falls short when it comes to verifying the transformed ciphertext provided by data proxies. The primary objective of this article is to design a fine-grained and supervised attribute-based data delegating solution tailored specifically for Web3.0. This scheme aims to enhance the ciphertext processing capabilities of existing data delegation solutions based on blockchain and ABE. Additionally, it addresses the current limitations of ABCT technology. This includes its inability to verify re-encrypted ciphertext and ensure non-repudiation of transformation results. We leverage smart contracts to ensure the automatic execution of the data delegation process and to store permanent records on the blockchain for auditing and traceability. This approach guarantees a fair distribution of interests among all stakeholders. Furthermore, we employ a commitment mechanism and digital signature to enhance the regulatory compliance of existing ABCT technology. We present a secure access control and supervised data delegation scheme for Web3.0 with blockchain along with its instantiation, emphasizing its fine-grained nature and verifiability. Finally, the evaluation results demonstrate its practicality and effectiveness.

Rhesus monkeys learn to control a directional-key inspired brain machine interface via bio-feedback.

Brain machine interfaces (BMI) connect brains directly to the outside world, bypassing natural neural systems and actuators. Neuronal-activity-to-motion transformation algorithms allow applications such as control of prosthetics or computer cursors. These algorithms lie within a spectrum between bio-mimetic control and bio-feedback control. The bio-mimetic approach relies on increasingly complex algorithms to decode neural activity by mimicking the natural neural system and actuator relationship while focusing on machine learning: the supervised fitting of decoder parameters. On the other hand, the bio-feedback approach uses simple algorithms and relies primarily on user learning, which may take some time, but can facilitate control of novel, non-biological appendages. An increasing amount of work has focused on the arguably more successful bio-mimetic approach. However, as chronic recordings have become more accessible and utilization of novel appendages such as computer cursors have become more universal, users can more easily spend time learning in a bio-feedback control paradigm. We believe a simple approach which leverages user learning and few assumptions will provide users with good control ability. To test the feasibility of this idea, we implemented a simple firing-rate-to-motion correspondence rule, assigned groups of neurons to virtual "directional keys" for control of a 2D cursor. Though not strictly required, to facilitate initial control, we selected neurons with similar preferred directions for each group. The groups of neurons were kept the same across multiple recording sessions to allow learning. Two Rhesus monkeys used this BMI to perform a center-out cursor movement task. After about a week of training, monkeys performed the task better and neuronal signal patterns changed on a group basis, indicating learning. While our experiments did not compare this bio-feedback BMI to bio-mimetic BMIs, the results demonstrate the feasibility of our control paradigm and paves the way for further research in multi-dimensional bio-feedback BMIs.

An efficient hybrid optimization of ETL process in data warehouse of cloud architecture

In big data, analysis data is collected from different sources in various formats, transforming into the aspect of cleansing the data, customization, and loading it into a Data Warehouse. Extracting data in other formats and transforming it to the required format requires transformation algorithms. This transformation stage has redundancy issues and is stored across any location in the data warehouse, which increases computation costs. The main issues in big data ETL are handling high-dimensional data and maintaining similar data for effective data warehouse usage. Therefore, Extract, Transform, Load (ETL) plays a vital role in extracting meaningful information from the data warehouse and trying to retain the users. This paper proposes hybrid optimization of Swarm Intelligence with a tabu search algorithm for handling big data in a cloud-based architecture-based ETL process. This proposed work overcomes many issues related to complex data storage and retrieval in the data warehouse. Swarm Intelligence algorithms can overcome problems like high dimensional data, dynamical change of huge data and cost optimization in the transformation stage. In this work for the swarm intelligence algorithm, a Grey-Wolf Optimizer (GWO) is implemented to reduce the high dimensionality of data. Tabu Search (TS) is used for clustering the relevant data as a group. Clustering means the segregation of relevant data accurately from the data warehouse. The cluster size in the ETL process can be optimized by the proposed work of (GWO-TS). Therefore, the huge data in the warehouse can be processed within an expected latency.

A patient safety knowledge graph supporting vaccine product development

BackgroundKnowledge graphs are well-suited for modeling complex, unstructured, and multi-source data and facilitating their analysis. During the COVID-19 pandemic, adverse event data were integrated into a knowledge graph to support vaccine safety surveillance and nimbly respond to urgent health authority questions. Here, we provide details of this post-marketing safety system using public data sources. In addition to challenges with varied data representations, adverse event reporting on the COVID-19 vaccines generated an unprecedented volume of data; an order of magnitude larger than adverse events for all previous vaccines. The Patient Safety Knowledge Graph (PSKG) is a robust data store to accommodate the volume of adverse event data and harmonize primary surveillance data sources.MethodsWe designed a semantic model to represent key safety concepts. We built an extract-transform-load (ETL) data pipeline to parse and import primary public data sources; align key elements such as vaccine names; integrated the Medical Dictionary for Regulatory Activities (MedDRA); and applied quality metrics. PSKG is deployed in a Neo4J graph database, and made available via a web interface and Application Programming Interfaces (APIs).ResultsWe import and align adverse event data and vaccine exposure data from 250 countries on a weekly basis, producing a graph with 4,340,980 nodes and 30,544,475 edges as of July 1, 2022. PSKG is used for ad-hoc analyses and periodic reporting for several widely available COVID-19 vaccines. Analysis code using the knowledge graph is 80% shorter than an equivalent implementation written entirely in Python, and runs over 200 times faster.ConclusionsOrganizing safety data into a concise model of nodes, properties, and edge relationships has greatly simplified analysis code by removing complex parsing and transformation algorithms from individual analyses and instead managing these centrally. The adoption of the knowledge graph transformed how the team answers key scientific and medical questions. Whereas previously an analysis would involve aggregating and transforming primary datasets from scratch to answer a specific question, the team can now iterate easily and respond as quickly as requests evolve (e.g., “Produce vaccine-X safety profile for adverse event-Y by country instead of age-range”).

ПІДХОДИ ДО РЕАЛІЗАЦІЇ ЦИФРОВОЇ ТРАНСФОРМАЦІЇ БІЗНЕС-ПРОЦЕСІВ ПІДПРИЄМСТВА: УПРАВЛІНСЬКИЙ АСПЕКТ

The article is devoted to the study of approaches to managing the digital transformation of business entities. It presents differences in the interpretation of the essence of the concepts of digitalization, digitization, and digital transformation. Three main areas of the enterprise affected by digital transformation have been identified: work with clients, operational business processes, and business models of the enterprise. Digitalization of enterprise business processes will influence changes in value formation and structural changes, and will also depend on them. It is substantiated that the level of use of digital technologies will be greatly influenced by the financial capabilities of the enterprise. An algorithm for the digital transformation of an enterprise has been developed, which makes it possible to choose priority areas for optimizing business processes through varying degrees of digitalization. This algorithm provides a preparatory stage at which it is recommended to carry out a detailed diagnosis of the external environment and assess the degree of penetration of digital technologies into the industry in which the activity is carried out. It provides for diagnostics of the enterprise taking into account available resources and identification of business processes that require innovative changes and solutions. The developed algorithm provides for partial optimization of individual business processes (installation of ERP-, CRM-, HRM- and other resource management systems, document management, logistics, etc.) and significant changes in several business processes using AI, BigData, IoT, cloud technologies, etc. The algorithm ends with the implementation stage, at which the necessary software and technological solutions are implemented. Transformation of operational processes through automation will provide economies of scale and increase productivity. The elements of digitalization of business processes of the enterprise are characterized. Three variable blocks in the transformation of business models are considered: digital modifications of individual processes, the introduction of new digital business models, and digital globalization. Conclusions about the main advantages of enterprises that have carried out digital transformation are drawn.