Wyniki wyszukiwania - BazTech

1

Selection of the programming environment for neural modelling of the power and electricity demand generation systems in terms of unmanned factories

Tchórzewski Jerzy, Rosochacki Sebastian

Studia Informatica : systems and information technology

|

2023

|

Vol. 2(29)

95--106

EN

The work concerns the selection of the programming language and environment for the needs of neural modeling of the power and electricity demand generation system in terms of uninhabited factories. Therefore, the main goal of the conducted research is to obtain the best possible Artificial Neural Network, i.e. to teach it a model of a real system, which is a system for generating demand for power and electricity based on numerical data on parts of the power system operation in terms of uninhabited factories. The learning capabilities of artificial neural networks were checked by comparing the MSE error and the Regression Index R2. In each of the examined programming languages and related programming environments, i.e. Matlab, Python and Wolfram, an Artificial Neural Network with the same structure and properties was designed and implemented, i.e. with the same number of input and output neurons, the number of hidden layers and the number of neurons in them, the activation function of neurons and the learning method. In addition to the ANN training of the system model, testing and validation as well as comparative studies were carried out.

2

Comparison of selected classification methods based on machine learning as a diagnostic tool for knee joint cartilage damage based on generated vibroacoustic processes

Karpiński Robert, Krakowski Przemysław, Jonak Józef, Machrowska Anna, Maciejewski Marcin

Applied Computer Science

|

2023

|

Vol. 19, no 4

136--150

EN

Osteoarthritis is one of the most common cause of disability among elderly. It can affect every joint in human body, however, it is most prevalent in hip, knee, and hand joints. Early diagnosis of cartilage lesions is essential for fast and accurate treatment, which can prolong joint function. Available diagnostic methods include conventional X-ray, ultrasound and magnetic resonance imaging. However, those diagnostic modalities are not suitable for screening purposes. Vibroarthrography is proposed in literature as a screening method for cartilage lesions. However, exact method of signal acquisition as well as classification method is still not well established in literature. In this study, 84 patients were assessed, of whom 40 were in the control group and 44 in the study group. Cartilage status in the study group was evaluated during surgical treatment. Multilayer perceptron - MLP, radial basis function - RBF, support vector method - SVM and naive classifier – NBC were introduced in this study as classification protocols. Highest accuracy (0.893) was found when MLP was introduced, also RBF classification showed high sensitivity (0.822) and specificity (0.821). On the other hand, NBC showed lowest diagnostic accuracy reaching 0.702. In conclusion vibroarthrography presents a promising diagnostic modality for cartilage evaluation in clinical setting with the use of MLP and RBF classification methods.

3

Application perspective of digitalneural networks in the context of marine technologies

Konon V., Konon N.

TransNav : International Journal on Marine Navigation and Safety of Sea Transportation

|

2022

|

Vol. 16 No. 4

743--747

EN

This study is focused on the issue of digital neural networks’ implementation in the context of maritime industry. Various algorithms of such networks in the terms of the marine technologies have been reviewed in the current study in order to evaluate the effectiveness of the methodology and to propose a new concept of an artificial neural network’s application in this way. Fire-detection system simulation based on the thermal imagers’ data input had been developed to assess the efficiency of the concept suggested with a multi-layer perceptron (MLP) algorithm integrated into the designed 3d-model.

4

The Development of a combined method to quicklyassess ship speed and fuel consumption at different powertrain load and sea conditions

Krata P., Kniat A., Guedes Soares C., Krata H.

TransNav : International Journal on Marine Navigation and Safety of Sea Transportation

|

2021

|

Vol. 15 No. 2

437--445

EN

Decision support systems (DSS) recently have been increasingly in use during ships operation. They require realistic input data regarding different aspects of navigation. To address the optimal weather routing of a ship, which is one of the most promising field of DSS application, it is necessary to accurately predict an actually attainable speed of a ship and corresponding fuel consumption at given loading conditions and predicted weather conditions. In this paper, authors present a combined calculation method to predict those values. First, a deterministic modeling is applied and then an artificial neural network (ANN) is structured and trained to quickly mimic the calculations. The sensitivity of the ANN to adopted settings is analyzed as well. The research results confirm a more than satisfactory quality of reproduction of speed and fuel consumption data as the ANN response meet the calculation results with high accuracy. The ANN-based approach, however, requires a significantly shorter time of execution. The directions of future research are outlined.

5

An Integration of Neural Network and Shuffled Frog-Leaping Algorithm for CNC Machining Monitoring

Goli Alireza, Tirkolaee Erfan Babaee, Weber Gerhard-Wilhelm

Foundations of Computing and Decision Sciences

|

2021

|

Vol. 46, No. 1

28--42

EN

This paper addresses Acoustic Emission (AE) from Computer Numerical Control (CNC) machining operations. Experimental measurements are performed on the CNC lathe sensors to provide the power consumption data. To this end, a hybrid methodology based on the integration of an Artificial Neural Network (ANN) and a Shuffled Frog-Leaping Algorithm (SFLA) is applied to the data resulting from these measurements for data fusion from the sensors which is called SFLA-ANN. The initial weights of ANN are selected using SFLA. The goal is to assess the potency of the signal periodic component among these sensors. The efficiency of the proposed SFLA-ANN method is analyzed compared to hybrid methodologies of Simulated Annealing (SA) algorithm and ANN (SA-ANN) and Genetic Algorithm (GA) and ANN (GA-ANN).

6

Internet of Things (IoT) and Artificial Neural Networks Towards Water Pollution Forecasting

Ibrahim Thaer, Mishra Alok

Rocznik Ochrona Środowiska

|

2020

|

Tom 22, cz. 1

117--129

EN

Water could be some-times a source of danger on people's lives and property. Although it is one of the most important elements of life on this planet. This article define the threat of water pollution in Tigris River in Iraq. by collecting a data that generated by sensors that installed in a water pollution sensing project in Baghdad city, also this article aimed to detect and analyze the behavior of water environment. It is an effort to predict the threat of pollution by using advanced scientific methods like the technology of Internet of Things (IoT) and Machine learning in order to avoid the threat and/or minimize the possible damages. This can be used as a proactive service provided by E-governments towards their own citizens.

7

Investigating the Role of Atmospheric Variables on Sea Level Variations in the Eastern Central Red Sea Using an Artificial Neural Network Approach

Zubier Khalid M., Eyouni Lina S.

Oceanologia

|

2020

|

No. 62 (3)

267--290

EN

Atmospheric variables play a major role in sea level variations in the eastern central Red Sea, where the role of tides is limited to 20% or less. Extensive analysis of daily-averaged residual sea level and atmospheric variables (atmospheric pressure, air temperature, wind stress components, and evaporation rate) indicated that sea level variations in the eastern central Red Sea are mainly contributed to by the seasonal and weather-band variations in the utilized atmospheric variables. The Non-linear Auto-Regressive Network with eXogenous inputs (NARX), a type of Artificial Neural Network (ANN), was applied to investigate the role of the atmospheric variables on the sea level variations at the eastern central Red Sea. Forced by time-delayed daily-averaged observations of atmospheric variables and residual sea level, the constructed NARX-based model showed high performance in predicting the one-step-ahead residual sea level. The high performance indicated that the constructed model was able to efficiently recognize the role played by the atmospheric variables on the residual sea level variations. Further investigations, using the constructed NARX-based model, revealed the seasonal variation in the role of the atmospheric variables. The study also revealed that the role played by some of the atmospheric variables, on sea level variations, could be masked by the role of one or more of the other atmospheric variables. The obtained results clearly demonstrated that this neurocomputing (NARX) approach is effective in investigating the individual and combined role of the atmospheric variables on residual sea level variations.

8

Evolutionary algorithm inspired by the methods of quantum computer sciences for the improvement of a neural model of the electric power exchange

Tchórzewski J., Ruciński D.

Information Systems in Management

|

2017

|

Vol. 6, No. 4

343--355

EN

The work contains results of research on the possibility to improve the neural model of the Electric Power Exchange (polish: Towarowa Giełda Energii Elektrycznej – TGEE) in MATLAB and Simulink environment using evolutionary algorithm inspired by quantum computer science. The developed artificial neural network was trained using data for the Day Ahead Market, assuming the joint volume of supplied and sold electrical energy [MWh] as the input quantities in each hour of the 24-hour day, and average prices [PLN/MWh] as output quantities. The obtained model of the exchange system was improved using the evolutionary algorithm, and further improvement in the accuracy of the model by supplementing the evolutionary algorithm using quantum solutions, related to the initial population, crossover and mutation operators, selection, etc. were proposed.

9

Forecasting Stock Price using Wavelet Neural Network Optimized by Directed Artificial Bee Colony Algorithm

Khuat T. T., Le Q. C., Nguyen B. L., Le M. H.

Journal of Telecommunications and Information Technology

|

2016

|

nr 2

43--52

EN

Stock prediction with data mining techniques is one of the most important issues in finance. This field has attracted great scientific interest and has become a crucial research area to provide a more precise prediction process. This study proposes an integrated approach where Haar wavelet transform and Artificial Neural Network optimized by Directed Artificial Bee Colony algorithm are combined for the stock price prediction. The proposed approach was tested on the historical price data collected from Yahoo Finance with different companies. Furthermore, the prediction result was found satisfactorily enough as a guide for traders and investors in making qualitative decisions.

10

Rozwiązanie problemu odwrotnego w turbidymetrii z wykorzystaniem sieci neuronowej

Guszkowski T., Mroczka J.

Pomiary Automatyka Kontrola

|

2007

|

R. 53, nr 9 bis

239--241

PL

Praca prezentuje metodę rozwiązania problemu odwrotnego w turbidymetrii z wykorzystaniem sieci neuronowej. Problem odwrotny jest często problemem źle postawionym i/lub źle uwarunkowanym numerycznie, a jego rozwiązanie przeważnie możliwe jest po nałożeniu na możliwy wynik dodatkowych warunków. Jako przykład zaprezentowano rozwiązanie problemu pomiaru wielkości cząstek na podstawie pomiarów turbidymetrycznych wykonanych dla kilku długości fali świetlnej.

EN

The paper presents a proposed solution to an inverse problem in turbidimetry with Artificial Neural Network (ANN). The inverse problem is mostly ill-posed and/or ill-conditioned, and its solution is usually possible after introduction of additional constrain to the proposed result. As an example inversion a determination of water particle size distribution based on multispectral turbidity measurements was shown.