Artificial Neural Network Technology Research Articles

The new SUMPOT to predict postoperative complications using an Artificial Neural Network

An accurate assessment of preoperative risk may improve use of hospital resources and reduce morbidity and mortality in high-risk surgical patients. This study aims at implementing an automated surgical risk calculator based on Artificial Neural Network technology to identify patients at risk for postoperative complications. We developed the new SUMPOT based on risk factors previously used in other scoring systems and tested it in a cohort of 560 surgical patients undergoing elective or emergency procedures and subsequently admitted to intensive care units, high-dependency units or standard wards. The whole dataset was divided into a training set, to train the predictive model, and a testing set, to assess generalization performance. The effectiveness of the Artificial Neural Network is a measure of the accuracy in detecting those patients who will develop postoperative complications. A total of 560 surgical patients entered the analysis. Among them, 77 patients (13.7%) suffered from one or more postoperative complications (PoCs), while 483 patients (86.3%) did not. The trained Artificial Neural Network returned an average classification accuracy of 90% in the testing set. Specifically, classification accuracy was 90.2% in the control group (46 patients out of 51 were correctly classified) and 88.9% in the PoC group (8 patients out of 9 were correctly classified). The Artificial Neural Network showed good performance in predicting presence/absence of postoperative complications, suggesting its potential value for perioperative management of surgical patients. Further clinical studies are required to confirm its applicability in routine clinical practice.

Change of Strength of Recycled Concrete with Age

In this paper, a mathematical model of the relationship between the amount of various components of recycled concrete and its compressive strength is established by using a large number of experimental data on the strength performance of recycled concrete and BP artificial neural network technology. In this paper, the influence trend of water binder ratio and aggregate substitution rate on the strength of recycled concrete is studied by this model. Taking recycled concrete with different recycled aggregate as the research object, a nonlinear structural model reflecting the mapping relationship between mix proportion and strength of recycled concrete is established in this paper. In this paper, the predicted values of the model are compared with the experimental data. The research shows that the strength model of recycled concrete based on BP neural network established in this paper can predict the compressive strength of recycled concrete at the corresponding age according to the mix proportion of recycled concrete, and the prediction accuracy is high. The application of BP neural network effectively reduces the times of a large number of repeated mix proportion test when preparing recycled concrete in practical engineering, reduces the waste of human and material resources, and has good economic benefits.

Optimization of Technological Processes in Horticulture

The issues of the development of horticulture through the use of modern technologies, including digital ones, are discussed. The results of the analysis of the effectiveness of the intensive type of gardens are presented. It has been found that the technology of artificial neural networks is used to optimize processes in horticulture. Information about smart technologies in agriculture, which can be used in intensive cultivation, is provided.

Формализация базовых процессов и математическая модель системы мониторинга и анализа публикаций электронных СМИ

The article describes an approach to formalizing basic processes and building a mathematical model for a system for collecting and analyzing data from electronic media. The authors, as part of a scientific study, are creating a system, including the development of new algorithms, methods and approaches for collecting and analyzing textual information from Internet news sources. The main direction of the study is the application of methods for the mining of text data based on the technology of artificial neural networks, methods of natural language processing, text mining, machine learning and big data processing. Purpose of the study. To develop a formalized description of the model of the system for monitoring and analyzing the text information of electronic news media using the methods of mathematical modeling. Research methods and tools. The use of the toolkit of the methodology of mathematical modeling, with the methods of system analysis is proposed. To study the system, such methods of system analysis as abstraction, formalization, composition and decomposition, structuring and restructuring, modeling, recognition and identification were used. The system is considered as a formalized model of an automatic classifier and clusterizer for a set of text documents in a natural language in the form of an algebraic system. To solve the problems of classification and clustering of texts, it is proposed to apply machine learning methods based on neural network approaches. The structure of the system and its constituent processes, as well as processes interacting with the system from outside, are presented in the form of a formalized mathematical description. Results. The developed formalized mathematical description of the system model clearly shows the interconnection of the system components with each other, as well as internal processes. The applied approach makes it possible to detail the representation of the system based on its decomposition into subsystems and modules. All this makes it possible to streamline the sequence of stages of creating a system and decompose them into separate stages of work. Conclusion. The results obtained in the course of the study allow us to move on to the next stage of the life cycle of the information system being developed - its software development.

Organizing Interactions Between a Robotic Manipulator and a Technological Equipment Control Panel

Algorithms for the organization of standalone operation of a robotic manipulator have been considered in this Article. The controls on the control panel of a man-made equipment piece have been the manipulated object. A robotic manipulator fitted with a control system, and a machine vision system, have been the subsystems under study. The robotic manipulator interacts with the objects to switch on and off a toggle switch, turn a rotary switch, press on a pushbutton, etc. Manipulating the objects in question involves assessing of their positions and orientations, which is achieved through the machine vision system. Coordinated operation of the subsystems is required to plan and to implement control of the manipulator, while taking into account positions of the objects relative to each other. A configuration of interactions between the manipulator and the control panel, a method for organizing coordinated functioning of the machine vision system when manipulating controls, which includes assessing positions of the object of interest relative to the robotic manipulator, and an algorithm for planning control based on artificial neural network technology have been presented in this Article.

Controllable SiOx Nanorod Memristive Neuron for Probabilistic Bayesian Inference.

Modern artificial neural network technology using a deterministic computing framework is faced with a critical challenge in dealing with massive data that are largely unstructured and ambiguous. This challenge demands the advances of an elementary physical device for tackling these uncertainties. Here, wedesigned and fabricated a SiOx nanorod memristive device by employing the glancing angle deposition (GLAD) technique, suggesting a controllable stochastic artificial neuron that can mimic the fundamental integrate-and-fire signaling and stochastic dynamics of a biological neuron. The nanorod structure provides the random distribution of multiple nanopores all across the active area, capable of forming a multitude of Si filaments at many SiOx nanorod edges after the electromigration process, leading to a stochastic switching event with very high dynamic range (≈5.15 × 1010 ) and low energy (≈4.06 pJ). Different probabilistic activation (ProbAct) functions in a sigmoid form are implemented, showing its controllability with low variation by manufacturing and electrical programming schemes. Furthermore, as an application prospect, based on the suggested memristive neuron, wedemonstrated the self-resting neural operation with the local circuit configuration and revealed probabilistic Bayesian inferences for genetic regulatory networks with low normalized mean squared errors (≈2.41 × 10-2 ) and its robustness to the ProbAct variation.

Artificial Intelligence and Digital Technologies in Technical Systems II-2021 (AIDTTS II-2021)

Artificial Intelligence and Digital Technologies in Technical Systems II-2021 (AIDTTS II-2021)

Kohonen’s algorithm in problems of classification of defects in printed circuit assemblies

The article presents a new method for diagnosing the technical condition of radio-electronic components, combining the methods of thermal diagnostics with the technologies of artificial neural networks. The structure of the method is shown, and the composition of the functional blocks is determined. The implementation of the method is a symbiosis of technologies for mathematical and simulation modeling of the technical state of a radio-electronic device with its physical tests and research of characteristics. When developing the method, specialized software tools for design and circuit design were actively used, such as Altium Designer CAD, SolidWorks, NI Multisim, the FloTHERM PCB thermal analysis module, as well as the MATLAB mathematical modeling and calculation package. With the help of these tools, a number of studies were carried out, including sets of numerical values of the power of circuit elements and temperature indicators of the printing unit, both for the correct state of the device and in states with artificially introduced defects. They, in turn, became the basis of the database of electronic node failures. To implement diagnostic procedures and identify the technical condition, an artificial neural network based on selforganizing Kohonen maps was created, its structure, parameters and algorithms of functioning were determined. The diagnostic procedure is based on the analysis of information from the fault database and its comparison with experimental data obtained as a result of a physical experiment. The results of the study showed that the network automatically classifies the characteristic defects of electronic components using the algorithms embedded in it. The list of characteristic defects in the proposed diagnostic method is limited to a discrete set of the most common faults, because, as their number increases, the use of the self-organizing Kohonen network for automatic classification becomes much more complicated and ineffective in terms of performance and reliability of identification. Among the advantages of this technology, it should be noted that the Kohonen network has the ability to convert largedimensional input data into a two-dimensional array. So, the results are easy to visualize and convenient to use when generating reports and recommendations for subsequent decision-making about the possibility of using an electronic device.

Optimization in vitro conditions for plum × apricot embryo rescue and modeling some critical factors by using artificial neural networks technology

The aim of this research was to overcome abortion postzygote incompatibility, and rescuing of hybrid embryos of early and mid-ripening plum cultivars, obtained from interspecific crossing between two plum cultivars (P. salicina L.) as female parents with four apricot cultivars (P. armeniaca L.) as male parents. The effects of cultivar, embryo developmental stage, plant growth regulators (PGRs), cold treatment, embryo size and removing seed coats were investigated on embryo germination at in vitro conditions. Results showed that the best conditions for embryo rescue were: harvesting embryos at 65 d after pollination (DAP) (91.33%), using completed MS medium with 0.5 mgL−1 6-benzyladenine (BA) and 1 mgL−1 indole-3-butyric acid (IBA), and embryo Stratification for 65 and 75 DAP- embryos at 4 °C for 30 d. Larger embryos testa removing treatment showed higher germination rates. Additionally, artificial neural networks (ANNs) was used to model two outputs which are the embryo generation percentage (GP) and complete plant percentage (CFP) based on three inputs including BA, IBA and embryo developmental stage (EDS). According to Multilayer 29 Perceptron (MLP), the best germination rate (100%) and the highest percentage of complete plant (100%) can be obtained by culturing the embryos at 65 DAP on MS medium containing 0.69 mgL−1 BA and 0.95 mgL−1 IBA, or at 75 DAP on MS medium containing 0.94 mgL−1 BA and 0.98 mgL−1 IBA. The MLP results showed a high correlation between the expected and the experimental values, which was 91.99%, 89.33% for GP and CFP, respectively. The results of the traditional statistical analysis by using Two Way ANOVA method were consistent with the results of the model obtained using MLP. Taking as a whole, this research developed an optimal protocol that may be useful in rescuing plum embryos in breeding programs.

Temperature‐Field Sparse‐Reconstruction of Lithium‐Ion Battery Pack Based on Artificial Neural Network and Virtual Thermal Sensor Technology

To monitor the temperature of lithium‐ion battery packs more accurately with as few sensors as possible, a temperature‐field sparse‐reconstruction technique based on an artificial neural network (ANN) and a virtual thermal sensor (VTS) is proposed herein. 64 uniformly distributed temperature points of lithium‐ion battery packs in seven discharge cycles are measured by a thermometer, and the 64 sensors are further divided into real thermal sensors (RTS) and VTSs according to a certain number and spatial position relationship. In addition, the sensor compression rate (SCR) is defined, herein, to quantitatively measure the impact of the RTS number on temperature‐field sparse‐reconstruction. ANN is built and compared with linear regression (LR). The results show that the temperature‐field sparse‐reconstruction based on ANN and VTS can provide accurate and robust prediction; the maximum mean absolute error (MAE) of ANN is less than 0.1873 °C (SCR = 1.56%) in the experiment. ANN obtains better accuracy with fewer RTS compared with LR. In addition, the proposed principle of sensor layout design is effective. Herein, the temperature‐field sparse‐reconstruction of battery pack is realized without any knowledge of battery thermal properties, heat generation, or thermal boundary conditions, and the optimal number of RTS under given accuracy requirements are obtained.

The Use of Neural Networks in Distance Education Technologies for the Identification of Students

Purpose of the research.The purpose of this research is to study the problems of the features of teaching technologies of modern artificial neural networks for carrying out the procedure of unambiguous authentication of students according to a pre-formed reference base of digital biometric characteristics of the authorized users in the field of distance educational technologies.In the modern world, artificial neural networks are successfully used in both applied and scientific fields. The problem of authenticating a human personality, implemented using artificial neural networks, finds practical application in solving problems such as the protection of stateandcorporateinformationresources,robotics,accesscontrolsystems,information retrieval, control systems, etc., and is already beginningto find application in the field of distance educational technologies.InMarch2021,theGovernmentoftheRussianFederationdevelopeda decree on the basis of which higher educational institutions areallowed to use distance learning technologies. Conducting remotelyactivitiesofintermediateandfinalcertification,aswellasmonitoringthe current progress of both distance learning students and full-timeandpart-timestudentswitha temporary transition to distance learningin a pandemic, the problem of identifying the student’s personalityarises in order to achieve unambiguous recognition of the authorized users for the purpose of reliable assessment of learning outcomes, which can be solved using modern technologies of artificial neural networks.Materials and methods.Methods of reviewing scientific literature onthe research topic, methods of collecting, structuring and analyzing the information obtained were used as materials and methods.Research results.The results of the study allow us to draw the following conclusions: to solve the problem of authenticating studentsin distance education systems it is first necessary to form the actualbase of biometric characteristics of the authorized users, which willbe compared with the biometric data of the identified users, and forthe recognition procedure, the neural network must be trained in advance on special trainers datasets. The identification procedure must be repeated several times during a session to ensure that the identity of the authorized user is verified.Conclusion.Realizing the set goal to study the problematics oflearningtechnologiesofmodernartificialneuralnetworksforcarryingouttheprocedureofunambiguousauthenticationofstudentsaccordingto a pre-formed reference base of digital biometric characteristicsof authorized users in the field of distance learning technologies,and relying on the results obtained in the course of generalizationandanalysisofexistingexperienceandourownstudies,theauthors identified two independent stages in the algorithm for the implementation of the task of identifying the student’s personality: the formation of a reference base of digital biometric characteristics ofauthorized users and user authentication according to the previouslyformed reference base, and also revealed that when training a neural network, it is necessary to take into account a sufficiently largenumberofdifferent attributesaffectingit. Withaninsufficient numberof training sets (datasets), neural networks begin to perceive errorsas reliable information, which, as a result, will lead to the need toretrain neural networks. With a sufficiently large number of trainingsets (dataset), more versions of dependencies and variability appear, which makes it possible to create rather complex machine learningmodels of neural networks, in which retraining takes the main place.

The Capture and Assessment system of Student Activity-Based State Recognition for Physical Education

In physical education classes, students get bored and distracted at some point in time. The current physical education programs to reach popularity among many universities are massive open online courses (MOOCs). The MOOC for physical education is recognized globally and provides a chance for physical education change as successful online learning. Educating students in physical education develop online instruction and virtual physical education, especially constructing a supplementation of courses and online courses-based learning. The significant drawbacks of teaching physical education with fewer content to cover and inspiring instructor applicants for time use are open-ended schedules. In this paper, MOOC assisted Teaching Framework (MOOCTF) with an artificial neural network (ANN) to analyze the student knowledge, attention level, and student performance in education is proposed. The proposed MOOCTF utilizes ANN and imaging technology to predict students’ activities during physical education online class. The collected image data are processed in ANN layers with a trained set of students’ behaviour. The simulation analysis proved that online courses for general education could be reformed education courses by taking MOOC’s form. The MOOCTF proposed for MOOC shows high performance, scalability, and high probable predictability.

The modification of predictors of course of acute period of craniocerebral trauma under implementation of stream model of medical care support

The specificity of course of acute period of craniocerebral injury and organization of medical care support are the factors determining outcomes for this category of patients. The purpose of the study is to investigate changes in predictors of course of acute period course of craniocerebral injury under implementation of stream model of medical care organization. The sampling included 150 patients with moderate and severe craniocerebral injury based on data obtained in 2013 and 2019, respectively. The clinical characteristics of patients (gender, age, level of consciousness, alcoholic intoxication, type of injury) and the characteristics of organization of medical care (mode of admission, qualification of hospital physician, time prior to surgery intervention) were evaluated. The selection of predictors significant for prognosis of outcomes of acute period of craniocerebral injury was implemented on the basis of logit-regression analysis and artificial neural network technology. The sampling of patients was divided into groups on the basis of outcomes of acute period of craniocerebral injury. The groups with relatively favorable and unfavorable course of acute period of craniocerebral injury were identified. It is demonstrated that prior to implementation of stream model of medical care provision, the most significant factors determining outcomes of the acute period of craniocerebral injury were characteristics of organization of medical care of these patients. After implementation of stream model the leading predictors became clinical characteristics of patients.

Artificial Neural Network for Rainfall Analysis Using Deep Learning Techniques

The estimation of rainfall is one of the most critical and daunting challenges in today’s environment. Weather and rainfall are typically extremely nonlinear and dynamic, needing sophisticated machine models and simulation for forecasting accurately. The economy of India is agriculture and is focused primarily on crop production and precipitation. Predictions of rainfall are important for all farmers to assess crop productivity. Rainfall forecast involves the application of science and technology to determine weather conditions. In order to utilize water supplies efficiently, the crop productivity and the pre-program of water systems, it is necessary to determine the precipitation in detail. The actions of such nonlinear processes can be modeled using an Artificial Neural Network (ANN). Most researchers in this area have been effectively utilizing ANN for the past 25 years. This article offers you an summary of some of the methodologies valid for using ANN for rainfall prediction by numerous researchers.The survey also states that forecasts of rainfall using ANN technologies are more accurate than conventional mathematical and numerical approaches.

Energy management in connected and disconnected mode of a photovoltaic system with a battery storage using an artificial neural network technique

In order to reduce the inconvenience resulting from the use of the traditional energy sources (oil, gas and coal), the integration of renewable energy sources is among the better solutions. With the integration of green energy sources, there are several strategies that can be adopted, including the combination of clean energy sources (solar, wind, and biomass) with each other, or the combination of renewable sources with conventional sources. In this article, we focus on a photovoltaic system allowing the storage of energy in a battery with a coupling to the electrical grid. In order to overcome the problems related to the random operation that accompanies the use of photovoltaic systems, we have developed a control technique based on the use of artificial neural network technology. The complete system was designed and simulated on MATLAB Simulink.

Prediction of yarn strength based on an expert weighted neural network optimized by particle swarm optimization

Aiming at solving the problem that existing artificial neural networks (ANNs) still have low accuracy in predicting yarn strength, this study combines traditional expert experience and an ANN to propose a hybrid network, named the expert weighted neural network. Many studies have shown that it is reliable to predict yarn strength based on ANN technology. However, most ANN training models face with problems of low accuracy and easy trapping into their local minima. The strength prediction of traditional yarns relies on expert experience. Obvious expert experience can help the model perform preliminary learning and help the algorithm model achieve higher accuracy. Therefore, this study proposes a neural network model that combines expert weights and particle swarm optimization (PSO). The model uses PSO to optimize the weights of experts and investigates its effectiveness in yarn strength prediction.

Mathematical Modeling of Technical and Economic Systems in Agriculture III

K E Tokarev 1 1 Volgograd State Agricultural University, 26, Universitetskiy Avenue, Volgograd, 400002, RussiaE-mail: tke.vgsha@mail.ruDear Authors and (Online) Participants of MMTES-III, International Scientific Conference «Mathematical Modeling of Technical and Economic Systems in Agriculture III» (MMTES III-2020) was successfully held online on Dec 10-11, 2020 in at the Department of Mathematical Modeling and Computer Science with organizational and technical support of the Center of Applied Scientific Research (location of organizers - Volgograd, Russian Federation). Due to COVID-2019 and the pandemic-related nationwide lockdowns and other coordinated restrictive measures, the organizers decided to hold a conference in a virtual format with the organization of access for all participants to the presented reports with comprehensive discussion for ensuring the event at a high scientific level. The safety and well-being of all conference participants is our priority. The COVID-19 is unpredictable, so conference postponement met uncertainty, while many scholars and researchers want to attend this long-waited conference and have academic exchanges with their peers. But I want to note that there are no barriers to science, and we continue to work on our research areas remotely, using modern technical means.The conference was held virtually for 2 days (Dec 10-11, 2020) including keynote and invited speeches, authors’ presentation session. The event was held online using Zoom communication platform for synchronous conversation. The conference was organized as a large-scale online meeting of participants in topical sessions with the opportunity for speakers to provide regulated demonstrations of slides and video files according to the approved technical program. Each speaker had 15 min presentation and 5 min Q&A session. There were always 20-25 participants in the network. During the online presentation, participants discussed more than 50 questions on the problems of modeling technical and economic systems in the agro-industrial complex. Participants of the conference were from the leading institutions of Russian Federation, Uzbekistan, Germany, Republic of Belarus (All-Russian Scientific Research Institute of Hydraulic Engineering and Reclamation named after A.N. Kostyakov, Namangan Engineering and Technology Institute, Technical University Of Munich, All-Russian Research Institute of Irrigated Agriculture, Belarusian State Agrarian Technical University, Volgograd State Technical University and others), dealing with problems of increasing agricultural productivity. The outstanding performance of all the presenters made this conference truly spectacular.Main topics of the conference were:1. Mathematical modeling of socio-technical and organizational-economic systems.2. Modeling of natural-technical and agro-ecological processes.3. Artificial intelligence and neural network technologies in agricultural production.4. Modeling of innovative and technological processes in agricultural engineering.5. Modeling of reclamation and environmental technologies in agricultural production.6. Resource and technological support for the production of agricultural products.7. Seed production, plant breeding and biotechnology.8. Innovative technologies in solving economic problems in the agro-industrial complex.9. Modern electrical technologies, electrical equipment and power supply in rural areas.This volume of IOP Conference Series: Earth and Environmental Science (EES) is a compilation of the accepted papers in MMTES-III and represents contributions that were presented in the conference. I would like to thank all of the conference sponsors and partners who made conference possible. My special thanks go to our speakers as well as all the authors for sharing their latest research results. Looking forward to meeting you during MMTES IV-2021! Tokarev Kirill E., scientific editor List of Committee are available in the pdf

Nonlinear analysis and prediction of soybean futures

We use chaotic artificial neural network (CANN) technology to predict the price of the most widely traded agricultural futures – soybean futures. The nonlinear existence test results show that the time series of soybean futures have multifractal dynamics, long-range dependence, self similarity, and chaos characteristics. This also provides a basis for the construction of a CANN model. Compared with the artificial neural network (ANN) structure as our benchmark system, the predictability of CANN is much higher. The ANN is based on Gaussian kernel function and is only suitable for local approximation of nonstationary signals, so it cannot approach the global nonlinear chaotical hidden pattern. Improving the prediction accuracy of soybean futures prices is of great significance for investors, soybean producers, and decision makers.

Development of mounted system for controlling row crop cultivator in automatic mode

Weed control automation appears to be a very promising technology based on the tremendous advances in computer processing, machine vision and robotics. Machine vision systems are based on size differences between crops and weeds and or on the regular structure of crop rows, allowing the system to recognize crop plants and control surrounding weeds. The paper provides description of the mounted system for orienting the row cultivator in rows and its displacement relative to the tractor using vision systems and automatic control. The developed technical vision system is capable of clearly identifying sugar beet leaves based on the deep learning artificial neural networks technology, and a specially developed algorithm for identifying the center of the row spacing to control the moving part of the cultivator in the required direction to level the inaccuracy of the tractor. The use of controlled mounted device with a tractor and an implement based on vision systems, the accuracy of technological operations for the row crops care, will increase the technical level of the machine and tractor unit, and reduce labor costs. Technical vision systems and automatic control of the cultivator will improve the quality of inter-row cultivation of row crops and reduce the pesticide load on the environment. The results of these studies can be used to create machines for cultivation of agricultural crops with an automated control system.

The short-term prognostication of characteristics of course and optimization of tactics of medical care support of patients with epilepsy

In clinical practice the identification of the dynamics of course of focal epilepsies on the basis of available clinical and neurophysiological indices (prognostication) is of great importance. The purpose of the study is the short-term prognostication of the course of focal frontal and temporal epilepsy. The materials and methods. The control (42 patients) and clinical (70 patients) groups were examined. The complex clinical physiological examination was carried out using electroencephalography, cognitive evoked potential, cardiac rhythm variability and the Schulte test. The cluster analysis was applied to allocate the observable patients into groups according to the dynamics of seizures frequency. The artificial neural networks technology based on physiological characteristics was applied to classify patients into groups with different course of disease. The results. The spectral characteristics of electroencephalographic signal had the greatest value for short-term prognostication of course of disease in the group of patients with focal frontal epilepsy. In patients with focal temporal epilepsy, the most significant predictors were the characteristics of cognitive evoked potential and characteristics of function of coherence of electroencephalogram. The conclusions. The developed algorithm of prognostication of unfavorable course of focal frontal epilepsy has high sensitivity, but lower specificity. Contrariwise, in case of temporal epilepsy, high specificity of the proposed algorithm is demonstrative, but its sensitivity is lower. It is recommended to apply these algorithms and to accentuate attention on characteristics of potential parameters at organization of diagnostic process in case of focal epilepsy.