Artificial Neural Network Theory Research Articles

Bayesian neural networks to reduce accidents while tower crane operations

The subject of the article is methods of preventing and reducing the risk of an accident during the operation of a tower crane. The research focuses on the method when the Bayesian approach is integrated with an artificial neural network to determine probability distribution function of tower crane accident. The goal of the study isto provide the rational reasons why using a Bayesian neural network could reduce the level of accident risk while tower crane operating. To achieve the goal of the research were performed: review and analysis of the methods used in modern conditions to assess the level of accident risk when operating a tower crane; identified the reasons why these methods need improvements; proposed and provided justifications why Bayesian neural network could be a powerful method in preventing tower crane accident. During review and analysis were used: Bayes theorem, theory of probability and mathematical statistics, theory of artificial neural networks. The summary from the results of conducted analysis of modern methods which are used to estimate accident risk level for tower crane included that some methods are based on expert judgements only which are not possible to verify so the risk’s estimates obtained from those methods could be biased; other methods are good in estimation of the probability of happening of tower crane accident, however could not be used to prevent the accident to happen. In order to eliminated disadvantages of the used methods it is proposed to use Bayesian neural network to determine probability distribution function and use it to determine threshold value for risk factors which could provoke an accident’s event happens during tower crane operation.

DEVELOPMENT OF AN ONTOLOGICAL MODEL OF DEEP LEARNING NEURAL NETWORKS

This research paper examines the challenges and prospects associated with the integration of artificial neural networks and knowledge bases. The focus is on leveraging this integration to address practical problems. The paper explores the development, training, and integration of artificial neural net- works, emphasizing their adaptation to knowledge bases. This adaptation involves processes such as in- tegration, communication, representation of ontological structures, and interpretation by the knowledge base of the artificial neural network's representation through input and output. The paper also delves into the direction of establishing an intellectual environment conducive to the development, training, and integration of adapted artificial neural networks with knowledge bases. The knowledge base embedded in an artificial neural network is constructed using a homogeneous semantic network, and knowledge processing employs a multi-agent approach. The representation of artificial neural networks and their specifications within a unified semantic model of knowledge representation is detailed, encompassing text-based specifications in the language of knowledge representation with theoretical semantics. The models shared with the knowledge base include dynamic and other types that vary in their capabilities for knowledge representation. Furthermore, the paper conducts an analysis of approaches to creating artificial neural networks across various libraries of the high-level programming language Python. It explores techniques for developing arti- ficial neural networks within the Python development environment, investigating the key features and func- tions of these libraries. A comparative analysis of neural networks created in object-oriented programming languages is provided, along with the development of an ontological model for deep learning neural net- works.

Review of diffractive deep neural networks

In 2018, a UCLA research group published an important paper on optical neural network (ONN) research in the journal Science. It developed the world’s first all-optical diffraction deep neural network (DNN) system, which can perform MNIST dataset classification tasks at near-light-speed. To be specific, the UCLA research group adopted a terahertz light source as the input, established the all-optical diffractive DNN (D2NN) model using the Rayleigh-Sommerfeld diffraction theory, optimized the model parameters using the stochastic gradient descent algorithm, and then used 3D printing technology to make the diffraction grating and built the D2NN system. This research opened a new ONN research direction. Here, we first review and analyze the development history and basic theory of artificial neural networks (ANNs) and ONNs. Second, we elaborate D2NN as holographic optical elements (HOEs) interconnected by free space light and describe the theory of D2NN. Then we cover the nonlinear research and application scenarios for D2NN. Finally, the future directions and challenges of D2NN are briefly discussed. Hopefully, our work can provide support and help to researchers who study the theory and application of D2NN in the future.

Estimation of intelligent-based quality of service in terrestrial FSO links: A case of South Africa propagation paths

Free Space Optical (FSO) communication is one of the popular technologies’ dominants in the optical communication domain. Despite all the advantages, FSO links are grossly affected by severe atmospheric conditions such as fog, rain, snow, smoke, and dust or aerosol particles suspended in the air. Fog is one of the major challenges for free-space optics to achieve carrier-class availability and causes extreme attenuation. A 10-year (2010––2019) visibility data were obtained from the South African Weather Services (SAWS) with a special focus on Cape Town (–33.925° S, 18.424° E). This extracted and processed Cape Town data was used to estimate the needed fog-induced attenuation. The intelligent algorithm is rooted in the theory of Artificial Neural Networks (ANN) systems which intelligently control the sub-tropical climate conditions of the chosen region. The adopted network-based technique is capable to interact with ever-changing weather by generating appropriate improvements to the free space optical communication link quality of service for efficient services to the customers. In this study, an Intelligent Algorithm (IA) based on an Artificial Neural Network (ANN) has been utilized to improve the reliability of QoS that can satisfy customer SLAs and improve received signal over FSO communications. The results obtained by implementing the IA system indicates that the power transmitted range from 8 to 100 dB and the adjusted Signal to Noise Ratio (SNR) between 390–––420 dB at 650 nm optical wavelength, whereas the same trend could be observed when the optical wavelength of 1550 nm was applied. Subsequently, the model effectively estimated the automatic transmit power control for enhancement in SNR and resulting in better QoS at the receiving end, regardless of the related weather changes along with the transmission link.

A Fault Detection Algorithm Based on Artificial Neural Network Threshold Selection in Multi-Terminal DC Grids

The DC fault is one of the critical challenges in the High Voltage Multi-Terminal Direct Current (HV-MTDC) grid. The fixed value threshold used in some implementations may be affected by different grid conditions and thus causes errors in the fault detection procedure. This paper offers a two-stage fault detection algorithm based on the integrated Artificial Neural Network (ANN) and Discrete Wavelet Transform (DWT) theory. The main innovations of the proposed method are: 1) Increasing the reliability of the fault detection operation by solving the fixed value threshold problems; 2) Offering high robustness against the wide range of fault resistances; 3) Providing bus protection capability and 4) Setting relays locally, and avoiding the requirement to high-speed communications links. Also, it offers DC fault detection in a short period of time. The performance of the proposed protection scheme has been ascertained via simulations in the MATLAB/Simulink environment. The results prove the robustness of the proposed method against noise disturbance, high resistance fault, and grid parameters variations.

A Novel Electric Vehicle Battery Management System Using an Artificial Neural Network-Based Adaptive Droop Control Theory

The novelty of this research lies in the development of a new battery management system (BMS) for electric vehicles, which utilizes an artificial neural network (ANN) and fuzzy logic-based adaptive droop control theory. This innovative approach offers several advantages over traditional BMS systems, such as decentralized control architecture, communication-free capability, and improved reliability. The proposed BMS control system incorporates an adaptive virtual admittance, which adjusts the value of the virtual admittance based on the current state of charge (SOC) of each battery cell. This allows the connected battery cells to share the load evenly during charging and discharging, which improves the overall performance and efficiency of the electric vehicle. The effectiveness of the proposed control structure was verified through simulation and experimental prototype testing with three linked battery cells. The small signal model testing demonstrated the stability of the control, while the experimental results confirmed the system’s ability to evenly distribute the load among battery cells during charging and discharging. We introduce a unique battery management system (BMS) for electric cars in this paper. Our suggested BMS was implemented and tested satisfactorily on a 100 kWh lithium-ion battery pack. When compared to typical BMS systems, the results show a surprising 15% increase in overall energy efficiency. Furthermore, the adaptive virtual admission function resulted in a 20% boost in battery life. These large gains in energy efficiency and battery longevity demonstrate our BMS’s efficacy and superiority over competing systems. Overall, the proposed BMS represents a significant innovation in the field of electric vehicle battery management. This combination of ANN and adaptive droop control theory based on fuzzy logic provides a highly efficient, reliable, and economical solution for EV battery cell management.

Survey of Optimization Algorithms in Modern Neural Networks

The main goal of machine learning is the creation of self-learning algorithms in many areas of human activity. It allows a replacement of a person with artificial intelligence in seeking to expand production. The theory of artificial neural networks, which have already replaced humans in many problems, remains the most well-utilized branch of machine learning. Thus, one must select appropriate neural network architectures, data processing, and advanced applied mathematics tools. A common challenge for these networks is achieving the highest accuracy in a short time. This problem is solved by modifying networks and improving data pre-processing, where accuracy increases along with training time. Bt using optimization methods, one can improve the accuracy without increasing the time. In this review, we consider all existing optimization algorithms that meet in neural networks. We present modifications of optimization algorithms of the first, second, and information-geometric order, which are related to information geometry for Fisher–Rao and Bregman metrics. These optimizers have significantly influenced the development of neural networks through geometric and probabilistic tools. We present applications of all the given optimization algorithms, considering the types of neural networks. After that, we show ways to develop optimization algorithms in further research using modern neural networks. Fractional order, bilevel, and gradient-free optimizers can replace classical gradient-based optimizers. Such approaches are induced in graph, spiking, complex-valued, quantum, and wavelet neural networks. Besides pattern recognition, time series prediction, and object detection, there are many other applications in machine learning: quantum computations, partial differential, and integrodifferential equations, and stochastic processes.

Learning Heuristics With Different Representations for Stochastic Routing.

Uncertainty is ubiquitous in real-world routing applications. The automated design of the routing policy by hyperheuristic methods is an effective technique to handle the uncertainty and to achieve online routing for dynamic or stochastic routing problems. Currently, the tree representation routing policy evolved by genetic programming is commonly adopted because of the remarkable flexibility. However, numeric representations have never been used. Considering the practicability of the numeric representations and the capability of the numeric optimization methods, in this article, we investigate two numeric representations on a representative stochastic routing problem and uncertain capacitated arc routing problem. Specifically, a linear representation and an artificial neural-network (ANN) representation are implemented and compared with the tree representation to reveal the potential of the numeric representations and the characteristics of their optimization. Experimental results show that the tree representation is the best choice, but on a majority of the test instances, the numeric representations, especially the ANN representation, can provide competitive performance. Further analyses also show that training a good ANN representation policy requires more training data than the tree representation. Finally, a guideline of representation selection is given.

Two-Module Neural Network Method of Information Processing in Gas Analysis Systems

Purpose of research: reduction of additional errors in measuring gas concentrations in gas analytical systems (GS) caused by the sensitivity of semiconductor sensors to non-target components of gas mixtures, ambient temperature and humidity. To develop and test a two-module neural network method for processing information in a GS, which allows automating the processes of generating training data and searching for the optimal structure of artificial neural networks (ANNs), reducing errors in reproducing the characteristics of sensors by replacing their mathematical models with neural networks.Methods. Theory of artificial neural networks, numerical methods, simulation methods. To evaluate the effectiveness of the proposed solution, the relative error (d), standard deviation (RMS) were calculated, and comparison with analogues was carried out.Results: a two-module neural network method for processing information in a GS has been studied. Numerical modeling was used to carry out experimental studies on the choice of optimal ANN structures, the volume and composition of training data. In the course of experimental studies, the errors of generating training data using ANN (less than 5%) and determining the concentrations of detected gases under conditions of fluctuations in the parameters of the air environment and the composition of the gas mixture (less than 4%) were calculated.Conclusion. A two-module neural network method for information processing is proposed, which is distinguished by the use of two successive modules of multilayer neural networks for generating training data and processing information coming from the GS sensor unit. The use of an auxiliary module makes it possible to compress the initial data, unify and automate the process of their generation, as well as improve the accuracy of reproduction of multiparameter sensor conversion functions, in comparison with alternative methods. Results of experimental studies of the effectiveness of using the information processing method to reduce additional errors in the quantitative determination of the composition of the air environment under conditions of parameter fluctuations are presented.

APPLICATION OF ARTIFICIAL NEURAL NETWORKS AND ACHIEVEMENTS OF TECHNOLOGICAL RE-ENGINEERING OF MODERN INDUSTRIAL PRODUCTION

The article deals with the issue of the justification mechanism for the choice of directions of technological reengineering. It was determined that the effectiveness of the transformations primarily depends on the methods, tools for choosing directions for the radical transformation of the technological basis of the production enterprise and, in general, on the technological policy. The justification of the directions of technological training engineering is connected with a large volume of interdependent variables of innovative transformations and requires a fundamental analysis of their behaviour and impact on production process. Today, neural networks are one of the most famous and effective tools for intelligent data analysis, which is developed thanks to achievements in the field of artificial intelligence theory and computer science. Intelligent systems based on artificial neural networks and fuzzy logic allow solving the tasks of forecasting, optimization, pattern recognition and management. To train the network, it is necessary to have a set of values of input values (factors) and corresponding to each separate set of values of the desired output value. Such an approach completely coincides with the tasks of choosing the directions of technological reengineering at the enterprises of the innovation cluster. For this purpose, significant external and internal factors influencing the effectiveness of the cluster policy have been determined. In contrast to internal, external to the greatest extent allow solving the tasks of forecasting, optimization, pattern recognition and management. In the conditions of an imperfect regional innovation system and taking into account this factor, for the efficiency of solving the tasks of technological reengineering of industrial production, a methodology is proposed that combines foresight forecasting of the prospects of technological reengineering of enterprises with the theory of artificial neural networks. The mechanism of interaction of artificial neural networks and the foresight method in determining directions of technological reengineering based on regional cluster policy are proposed.

Solving the nuclear pairing model with neural network quantum states.

We present a variational Monte Carlo method that solves the nuclear many-body problem in the occupation number formalism exploiting an artificial neural network representation of the ground-state wave function. A memory-efficient version of the stochastic reconfiguration algorithm is developed to train the network by minimizing the expectation value of the Hamiltonian. We benchmark this approach against widely used nuclear many-body methods by solving a model used to describe pairing in nuclei for different types of interaction and different values of the interaction strength. Despite its polynomial computational cost, our method outperforms coupled-cluster and provides energies that are in excellent agreement with the numerically exact full configuration-interaction values.

РАЗРАБОТКА МЕТОДИКИ МОДЕРНИЗАЦИИ МАРШРУТА ТЕХНИЧЕСКОГО ДОКУМЕНТООБОРОТА НАУКОЕМКОГО ПРОИЗВОДСТВА

A method for modernizing the route of technical document flow at an enterprise manufacturing high-tech products proposed using elements of the theory of artificial neural networks. The traditional route of the processes of approval of technical documentation in the environment of an automated enterprise system revised. With analysis using elements of the theory of artificial neural networks, elements of the route that require improvement identified. An improved model of the technical document flow route in the environment of an enterprise automated system is proposed, which made it possible to improve the quality of the processes of approval of the enterprise's technical documentation.

Performance evolution in machining parameter of Al-Si (LM6) alloy using neural network

The global manufacturing age has increased competition in the manufacturing sector as markets become more agile and customer-focused. Because of the fierce rivalry, manufacturers are paying more attention to automation. In the last several decades, computer numerically controlled (CNC) machine tools have been utilized to achieve complete automation in machining. The artificial neural network theories are used in this research to train a solution for the problem of selecting machine setup settings for a turning operation. A collection of input and output values can be mapped out by an artificial neural network. A network may be used to anticipate output values for a certain set of input values once it has been trained. Process inputs like cutting speed, feed, depth of cut, and coolant flow rate can be generated by a trained program, as can their related process outputs like surface finish. Forward mapping of process inputs and outputs is accomplished using back propagation neural networks in this approach. The optimum machine setup parameter may then be selected interactively using these networks. To solve the model, a MATLAB program has been created. The experiment's findings are verified using a neural network.

A universal correlation for predicting two-phase frictional pressure drop in horizontal tubes based on machine learning

Accurate prediction of the two-phase frictional pressure drop (FPD) facilitates designing compact phase-change heat exchangers. This study implements ML methods and develops a new universal correlation for predicting FPDs in adiabatic and diabatic flow. A consolidated database with 8663 experimental samples from 64 published literature covering 25 fluids and broad operating conditions is amassed to serve this purpose. The designed ML models, based on artificial neural network (ANN) and extreme gradient boosting (XGBoost) theory, can predict the unknown data with the best mean absolute relative deviate (MARD) of 8.59% and the coefficient of determination (R2) of 0.988 or higher. With the aid of parametric importance analysis conducted by the trained ML models, the obtained key parameters, including vapor quality, dimensionless vapor velocity, Froude number, Bond number, and convection number, are adopted to formulate a new correlation. The new correlations can provide more reliable predictive performance than existing correlations for the consolidated database with a MARD of 24.84%. An excluded database is collected to verify the generality of the correlation, and a lower MARD of 27.47% than existing models is obtained. It demonstrates that ML methods can help develop the universal correlation with improved accuracy and universality.

Neural network pressure observerfor a turbomechanism electromechanical system powered by a wind generator

Ecological and economic production of electrical energy through the use ofalternative energy sources is an urgent direction due to the trend of increasing prices of energy carriers used in the electrical energy production and as a result of significant damage of the energy system of Ukraine in consequence of the war on the country territory.It is worth noting that in some areas it is possible to use only autonomous power generation systems, since the laying of electrical networks in these districts is impractical and unprofitable. Usually, the mentioned systems are basedon a combination of a wind or hydro turbine -drive motor, and an electric generator. Such systems are characterized by high resource, reliability, low cost,and complexity of maintenance. Sometimes people's lives and the possibility of communication withthe outside world depend on the operation of an autonomous electric power generation system, which is especially important in the conditions of martial law. At the same time, the lack of stabilization of the hydraulic networkpressureof the water supply system can lead to the household conditions aggravation, the emergency situations occurrence, and the technological process disruption.In view of the mentioned factors, there is a need to measure the pressure of the hydraulic network, which is possible byusing technological coordinatesobserversbuilt on the basis of the artificial networks theory. In the paper a modern turbomechanism electromechanical control systempowered by an alternative electrical energy source under the conditions of pressure stabilization of thehydraulic network when using atechnological coordinatesobserver, namely a pressure estimator, is proposed. A mathematical description of the main elements of the investigatedsystem is given. A hydraulic network pressure observerbased onthe artificial neural networks theory isbuilt and studied. Features of design and training of technological coordinate estimators based on neural networks with feedback are described. The operation of the sensorless system during thepressure stabilization at a given level when the resistance of the hydraulic network changes within the typical daily cycle of water consumption is considered on a specific example. The results and analysis of the investigationof the developed observerin standard and sensorless control systems are shown.

Artificial Neural Networks and Its Applications in Chemical Industry

Artificial neural networks, as an important part of artificial intelligence, have a wide scope of development to improve the traditional production technology of chemical processes with its inherent advantages of parallel structure and parallel processing, fault tolerance, full approximation of any complex nonlinear relationships, learnability and self-adaptability, etc. Thus, it has a wide scope of development to improve the problems of lagging diagnosis, difficult to optimize control, large errors in physical property estimation and inability to deal with nonlinear complex situations. This paper summarizes the theory of artificial neural network, including its structure and characteristics, and introduces its applications in different fields, especially in chemical industry.

Jaringan Saraf Tiruan Pengenalan Pola Karakter Kabataku Menggunakan Metode Bidirectional Associative Memory (BAM) Kontinu

Artificial neural network is an information processing paradigm with a working system using biological concepts in processing information so that it has capabilities similar to the human brain, Jst is able to solve problems using uncertainty science such as Kabataku pattern recognition. Kabataku is a character operator used in Mathematics with the concepts of X, :, + and -. Introduction This character operator uses the concept of artificial intelligence, which uses the theory and process of Artificial Neural Networks. The purpose of this study is to determine the effectiveness of the Continuous BAM method in recognizing Kabataku character patterns in arithmetic operations in mathematics. The Bidirectional Associative Memory (BAM) method has the ability in associative memory or content addressable memory can be called by using the part stored in the memory itself. BAM in an artificial neural network has 2 layers, namely the input layer and the output layer that are interconnected between the two, also called bidirectional, with the work process if the matrix weight of the signal sent from the input layer X to the output layer Y is W, then the matrix weight of the signal sent from the output layer Y to the input layer X is WT . Continuous BAM method will change the input to output more finely with a value that lies in the range [0,1]. The activation function used is the sigmoid function. The final result of pattern recognition is x1= [-8 -12], x2 =[ 8 0], x3 [12 8], x4= [16 12] Not all patterns match the target.

Строгие методы преобразования систем координат

Determination of coordinate systems’ parameters transformation has always been and remains the core of surveyors’ practical and theoretical works. However, in most cases, the issue is interpreted under the assumption that the angular rotation of the coordinate axes and the similarity parameter are very small, which enables a significant simplifying of the algorithm. In this paper the strict theory of determining the 7 and 9 parameters of coordinate systems transformation within the framework of nonlinear method of least squares with limitations is considered. Strict algorithm is described and numerical experiments are performed. The connection of the coordinate systems transformation theory with the general one of mathematical statistics, known under the name of Procrust analysis, is specified. However, in general, artificial neural network theory is recommended for conversion of one coordinate system to another. This generally eliminates the need for a prior determination of the transformation’s appropriate parameters, inevitably associated with hypotheses for the transformation model, but quickly and accurately solves the main problem.

Monitoring Technology of Abnormal Displacement of BeiDou Power Line Based on Artificial Neural Network.

In the practice of power line engineering, navigation and positioning technology is often used in the fields of information collection and analysis, optimized line design, and deformation monitoring. Compared with traditional measurement technology, it has the characteristics of high precision and high reliability. In order to realize the measurement of abnormal displacement of power lines, improve the efficiency and quality of monitoring, and reduce the occurrence of faults, firstly, this study introduces the basic theory of artificial neural network (ANN). The core algorithm of the ANN-BP (back propagation) neural network has been improved. The improved algorithm is used to improve the BeiDou Navigation Satellite System (BDS). The improved and the unimproved BDS are used to solve the collected related data. The results show that the geometric dilution of precision (GDOP) values obtained by conventional BDS are small, all within the range of less than 4. After the introduction of the BP neural network into the system, the geometric space distribution of positioning satellites is improved, the GDOP is reduced, the reliability and availability of satellite positioning are enhanced, and the accuracy requirements are met. The accuracy of the measured data positioning results of the two systems has reached the cm level. There is not much difference between the processing results of the two modes. Among them, the Z direction accuracy has the largest difference, which is 2.5 cm. The introduction of the BP neural network has improved the spatial combination structure, and the positioning results in the three directions of X, Y, and Z are all better. From the perspective of root mean square (RMS), the RMS fluctuation of the simulation results obtained by observing the conventional BDS is large. The RMS value of BDS displacement based on the BP neural network is smaller, and the change is gentle. With the increase in the number of epochs and the increase in the number of simulations, its value is also more convergent. These data show that the quality of BDS observations based on the BP neural network is significantly better. These contents will effectively improve the monitoring accuracy and operational reliability of the system and have important practical significance and application value.

Optimizing the Prognostic Model of Cervical Cancer Based on Artificial Intelligence Algorithm and Data Mining Technology

With the accumulation and development of medical multimodal data as well as the breakthrough in the theory and practice of artificial neural network and deep learning algorithm, the deep integration of multimodal data and artificial intelligence based on the Internet has become an important goal of the Internet of Medical Things. The deep application of the latest technologies in the medical field, such as artificial intelligence, machine learning, multimodal data, and advanced sensors, has a profound impact on the development of medical research. Artificial intelligence can achieve low-consumption and high-efficiency screening of specific markers due to its powerful data integration and processing capabilities, and its advantages are fully demonstrated in the construction of disease-related risk prediction models. In this study, multi-type cloud data were used as research objects to explore the potential of alternative CpG sites and establish a high-quality prognosis model of cervical cancer DNA methylation big data. 14,419 strict differentially methylated CpG sites (DMCs) were identified by ChAMP methylation analysis and presented these distributions based on different genomic regions and relation to island. Further, rbsurv and Cox regression analyses were performed to construct a prognostic model integrating these four methylated CpG sites that could adequately predict the survival of patients ( AUC = 0.833 , P < 0.001 ). The low- and high-risk patient groups, divided by risk score, showed significantly different overall survival (OS) in both the training ( P < 0.001 ) and validation datasets ( P < 0.005 ). Moreover, the model has an independent predictive value for FIGO stage and age and is more suitable for predicting survival time in patients with histological type (SCC) and histologic grade (G2/G3). Finally, the model exhibited much higher predictive accuracy compared to other known models and the corresponding expression of genes. The proposed model provides a novel signature to predict the prognosis, which can serve as a useful guide for increasing the accuracy of predicting overall survival of cervical cancer patients.