articles
|
№ 6(102)
30 november 2022 year
Rubric: Researching of processes and systems Authors: Klyshnikov K., Danilov V., Ganyukov V., Onishchenko P., Ovcharenko E. |
Significant interest in the field of application of machine learning for the analysis of medical images stimulates the search for promising algorithms for solving routine diagnostic problems in cardiology. In relation to cardiovascular diseases, such a procedure is coronary angiography, which assesses the state of the vascular network and the presence of stenotic areas. This paper demonstrates an example of using modern models of neural networks: SSD MobileNet V2, SSD ResNet-50, Faster-RCNN Inception ResNet for localizing a single-vessel coronary artery lesion on a set of clinical data (3200 images). It is shown that the Faster-RCNN Inception ResNet V2 model was the most accurate in terms of the chosen metric mAP[0.5:0.95], reaching 0.9434 and 0.95 for the validation and test sets, respectively. However, the data processing speed was 0.363 seconds per frame, which corresponds to a speed of 2.8 frames/sec, which does not correspond to the speed of coronary angiography (15 frames/sec). Neural networks with a more “simple” architecture demonstrated an unsatisfactory quality of stenosis localization, expressed in a low characteristic mAP[0.5:0.95]. The results of this study demonstrate a key problem in the application of machine learning algorithms on graphic data – high accuracy, which may be acceptable for medical diagnostic procedures, is “decompensated” by long-term image analysis, as a result, the use of unmodified neural network architectures does not provide real-time data processing. Continue... |
|---|---|
|
№ 6(102)
30 november 2022 year
Rubric: Researching of processes and systems The author: Shchetinin E. |
Anomaly detection is an important task in various applications and areas of technology and production, such as structural defects, malicious intrusions into management and control systems, financial supervision and risk management, digital health screening, etc. The ever-increasing flows of diverse data and their structural complexity require the development of advanced approaches to their solution. In recent years, deep learning methods have achieved significant success in detecting anomalies, and unsupervised deep learning methods have become especially popular. Methods of anomaly detection by methods of deep learning without a teacher are investigated in the work on the example of a set of electrocardiograms containing normal ECG signals and ECG signals of people with various cardiovascular diseases (anomalies). To detect abnormal electrocardiograms, an autoencoder model has been developed in the form of a deep neural network with several fully connected layers. Also, to solve this problem, a method is proposed for selecting the threshold for separating abnormal ECG signals from normal ones, consisting in optimizing the ratio of performance indicators of the autoencoder model by methods. The paper presents a comparative analysis of the effectiveness of applying various machine learning models, such as the one class Support Vector Method, Isolation Forest, Random Forest and the presented autoencoder model to solving the problem of detecting abnormal ECG signals. For this purpose, metrics such as accuracy, recall, completeness, and f-score were used. His results showed that the proposed model surpassed the other models in solving the problem with accuracy = 98.8% precision = 95.75%, recall = 99.12%, f1-score = 98.75%. Continue... |
|
№ 6(102)
30 november 2022 year
Rubric: Algorithmic efficiency Authors: Bobkov V., Bulygina O. V., Vereikina E. |
The problem of rational energy resource use is especially acute for energy- intensive industries, which include high-temperature processing of mining chemical raw materials (for example, the production of phosphorite pellets from apatite-nepheline ore waste by drying and roasting). In this regard, the temperature modes of roasting conveyor machine should ensure not only the completion of the ongoing chemical-technological processes and the required product quality, but also energy and resource saving. Thus, there is an urgent scientific and practical task of optimizing charge heating modes based on the results of modeling heat and mass transfer processes occurring in various zones of the roasting conveyor machine. The impossibility of carrying out expensive full-scale experiments leads to the need to use computer simulation methods. Nonlinearity, large dimension of the search space, high computational complexity make it difficult to use traditional deterministic search methods. Under these conditions, the stochastic methods that deliberately introduce an element of randomness into the search algorithm show good results. Today, population algorithms based on modeling the collective behavior of living organisms and characterized by the ability to simultaneously process several options have become widespread. To solve the optimization problem, it is proposed to use a modified Cuckoo search algorithm (by introducing fuzzy elements), which provides a comprehensive account of a huge number of parameters set for each vacuum chamber of the roasting conveyor machine. The control of the chemical-energy-technological system for the processing of apatite-nepheline ores waste, taking into account the obtained data and based on the existing neural network model of the high-temperature process, will make it possible to minimize the amount of return and provide energy-saving conditions for the operation of roasting units. Continue... |
|
№ 6(102)
30 november 2022 year
Rubric: Algorithmic efficiency Authors: Puchkov A., Dli M. I., Prokimnov N., Shutova D. |
The results of studies aimed at developing multi-level decision-making algorithms for management of energy and resource efficiency, technogenic and environmental safety of a complex multi-stage system for processing fine ore raw materials are presented (MSPFORM). A distinctive feature of such a system is its multidimensionality and multiscale, which manifests itself in the presence of two options for implementing technological processes for processing finely dispersed ore raw materials, the need to take into account the interaction of the aggregates included in the system, as well as the hierarchy of describing the processes occurring in them - mechanical, thermophysical, hydrodynamic, physical and chemical. Such a variety of processes characterizes the interdisciplinarity of research and the complexity of obtaining analytical, interconnected mathematical models. This situation inspired the analyze use of artificial intelligence methods, such as deep machine learning and fuzzy logic, to describe and analyze processes. The scientific component of the research results consists in the developed generalized structure of the MSPFORM, the conceptual basis of multilevel algorithms for evaluating and making decisions on the optimal control of this system, the proposed composition of the parameters and the form of the optimization criterion. The task of the study was to analyze possible options for the processing of ore raw materials, to develop a concept for the construction of the MSPFORM allowing the possibility of optimizing its functioning according to the criterion of energy and resource efficiency while meeting the requirements of environmental safety. The application of evolutionary algorithms for solving the problem of optimizing the MSPFORM according to the criterion of minimum energy consumption is announced and its stages are specified. The structure of the block of neuro-fuzzy analysis of information about the parameters of processes in MSPFORM is presented, which is based on the use of deep recurrent and convolutional neural networks, as well as a fuzzy inference system. The results of a simulation experiment on approbation of the software implementation of this block in the MatLab environment are presented. Continue... |
| The article presents the results of a study of the problem of structural synthesis of a vision system and its parametric identification using a new method based on the mathematical apparatus of the theory of modified descriptive image algebras. The theory of modified descriptive image algebras is a mathematical apparatus that allows one to formally describe the processing and analysis of images. In this mathematical apparatus, it is possible to describe the mathematical model of the measurement function of the technical vision system for the selected attribute of the observed object. To develop mathematical models, procedural and parametric transformations of images are used. Any mathematical model in the theory of modified descriptive image algebras has at least one variational parameter. In the course of parametric identification, it is required to calculate their values. This problem is multimodal and always has at least one solution. Numerical methods are usually used to solve the optimization problem. The article describes the algorithm for constructing a mathematical model for measuring the area using procedural and parametric transformations. The parametric identification problem is solved in the form of a nonlinear optimization problem. The visualization of the objective function has been carried out and recommendations for choosing the values of its variational parameters have been formulated. The collection of statistical data was carried out and a histogram was constructed, on the basis of which the distribution law for the measured value is selected. The statistical task of testing the hypothesis with the selected law of distribution of the general population according to the Pearson criterion is solved for a given level of significance. For the unknown parameters of the chosen distribution law, the estimation of confidence intervals was carried out. The materials of the article are applied in nature and have practical value. Using the proposed approach, it is possible to develop a measurement function for any feature of the observed object on a series of images. Continue... | |
|
№ 1(103)
10 january 2023 year
Rubric: Algorithmic efficiency Authors: Kalashnikov V., Soloviev V. I. |
In the last decade, there has been an active digitalization of industrial production based on rapidly developing information technologies, including artificial intelligence technologies. This is largely due to the development of deep learning methods and their applications in computer vision. Since the mid 2010s convolutional neural networks demonstrate exceptional efficiency in solving problems such as the detection, classification and segmentation of various objects. As a result, computer vision methods are beginning to be actively used in the problems of quality control of raw materials and finished products. All this applies to the mining industry. However, in the Russian scientific literature there are practically no systematic reviews of computer vision applications in this area. The present study aims to fill this gap. The paper provides a systematic review of the history of development and the current state of the methods and technologies of machine vision used in the mining industry for the analysis of solid materials, demonstrates the latest achievements in this area and examples of their application in the mining industry. The authors have analyzed 29 research papers in the field of application of computer vision in the mining industry and classified the stages of technology development from the mid-1980s, when computer vision was used without the use of machine learning, and ending with modern research based on the use of deep convolutional neural networks for solving problems of classification and segmentation. The effectiveness of the methods used is compared, their advantages and disadvantages are discussed, and forecasts are made for the development of computer vision methods in the mining industry in the near future. Examples are given showing that the use of convolutional neural networks made it possible to move to a qualitatively higher level of quality in solving problems of classification and segmentation as applied to the analysis of output volume, particle size distribution, including flakiness, angularity and roughness, dust and clay content, bulk density and emptiness, etc. Continue... |
