Wyniki wyszukiwania - BazTech

1

Analiza wybranych metod walidacji krzyżowej w programie RSES

Kołpacki Radosław

Studia i Materiały Informatyki Stosowanej

|

2024

|

T. 16, nr 1

PL

W artykule przeprowadzono analizę zbioru danych za pomocą dwóch metod walidacji krzyżowej. Wykorzystano program RSES do identyfikacji kluczowych właściwości i relacji w zbiorze. Wyniki wykazują wpływ niektórych parametrów na potencjalną dokładność wyników.

EN

This article presents an analysis of a dataset using two cross-validation methods. The RSES program was employed to identify key properties and relationships within the dataset. The results indicate the impact of certain parameters on the potential accuracy of the outcomes.

2

Analiza wybranych metod walidacji krzyżowej w programie RSES

Bethke Beata

Studia i Materiały Informatyki Stosowanej

|

2024

|

T. 16, nr 1

11--14

PL

W artykule przeprowadzono analizę zbioru danych za pomocą dwóch metod walidacji krzyżowej. Wykorzystano program RSES do identyfikacji kluczowych właściwości i relacji w zbiorze. Wyniki wykazują wpływ niektórych parametrów na potencjalną dokładność wyników.

EN

This article presents an analysis of a dataset using two cross-validation methods. The RSES program was employed to identify key properties and relationships within the dataset. The results indicate the impact of certain parameters on the potential accuracy of the outcomes.

3

Genetic algorithm-based decision tree optimization for detection of dementia through MRI analysis

Anuradha Govada, Davu Harini, Karri Muthyalanaidu

Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska

|

2024

|

T. 14, nr 1

83--89

EN

Dementia is a devastating neurological disorder that affects millions of people globally, causing progressive decline in cognitive function and daily living activities. Early and precise detection of dementia is critical for optimal dementia therapy and management however, the diagnosis of dementia is often challenging due to the complexity of the disease and the wide range of symptoms that patients may exhibit. Machine learning approaches are becoming progressively more prevalent in the realm of image processing, particularly for disease prediction. These algorithms can learn to recognize distinctive characteristics and patterns that are suggestive of specific diseases by analyzing images from multiple medical imaging modalities. This paper aims to develop and optimize a decision tree algorithm for dementia detection using the OASIS dataset, which comprises a large collection of MRI images and associated clinical data. This approach involves using a genetic algorithm to optimize the decision tree model for maximum accuracy and effectiveness. The ultimate goal of the paper is to develop an effective, non-invasive diagnostic tool for early and accurate detection of dementia. The GA-based decision tree, as proposed, exhibits strong performance compared to alternative models, boasting an impressive accuracy rate of 96.67% according to experimental results.

PL

Demencja jest wyniszczającym zaburzeniem neurologicznym, które dotyka miliony ludzi na całym świecie, powodując postępujący spadek funkcji poznawczych i codziennych czynności życiowych. Wczesne i precyzyjne wykrywanie demencji ma kluczowe znaczenie dla optymalnej terapii i zarządzania demencją, jednak diagnoza demencji jest często trudna ze względu na złożoność choroby i szeroki zakres objawów, które mogą wykazywać pacjenci. Podejścia oparte na uczeniu maszynowym stają się coraz bardziej powszechne w dziedzinie przetwarzania obrazu, szczególnie w zakresie przewidywania chorób. Algorytmy te mogą nauczyć się rozpoznawać charakterystyczne cechy i wzorce, które sugerują określone choroby, analizując obrazy z wielu modalności obrazowania medycznego. Niniejszy artykuł ma na celu opracowanie i optymalizację algorytmu drzewa decyzyjnego do wykrywania demencji przy użyciu zbioru danych OASIS, który obejmuje duży zbiór obrazów MRI i powiązanych danych klinicznych. Podejście to obejmuje wykorzystanie algorytmu genetycznego do optymalizacji modelu drzewa decyzyjnego w celu uzyskania maksymalnej dokładności i skuteczności. Ostatecznym celem artykułu jest opracowanie skutecznego, nieinwazyjnego narzędzia diagnostycznego do wczesnego i dokładnego wykrywania demencji. Zaproponowane drzewo decyzyjne oparte na GA wykazuje wysoką wydajność w porównaniu z alternatywnymi modelami, szczycąc się imponującym współczynnikiem dokładności wynoszącym 96,67% zgodnie z wynikami eksperymentalnymi.

4

The solution of MRSLP with the use of heuristic algorithms

Kochańska Joanna, Burduk Anna, Łapczyńska Dagmara, Musiał Kamil

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2024

|

Vol. 72, nr 1

art. no. e146407

EN

Improving production processes includes not only activities concerning manufacturing itself, but also all the activities that are necessary to achieve the main objectives. One such activity is transport, which, although a source of waste in terms of adding value to the product, is essential to the realization of the production process. Over the years, many methods have been developed to help manage supply and transport in such a way as to reduce it to the necessary minimum. In the paper, the problem of delivering components to a production area using trains and appropriately laid-out carriages was described. It is a milk run stop locations problem (MRSLP), whose proposed solution is based on the use of heuristic algorithms. Intelligent solutions are getting more and more popular in the industry because of the possible advantages they offer, especially those that include the possibility of finding an optimum local solution in a relatively short time and the prevention of human errors. In this paper, the applicability of three algorithms – tabu search, genetic algorithm, and simulated annealing – was explored.

5

Testing algorithms for quick rescheduling flow shop problems with FlexSim based simulation and R engine

Janke Piotr

Zeszyty Naukowe. Organizacja i Zarządzanie / Politechnika Śląska

|

2023

|

z. 168

163--175

EN

Purpose: The aim of this paper is to present a combination of advanced algorithms for finding optimal solutions together with their tests for a permutation flow-shop problem with the possibilities offered by a simulation environment. Four time-constrained algorithms are tested and compared for a specific problem. Design/methodology/approach: Four time-constrained algorithms are tested and compared for a specific problem. The results of the work realisation of the algorithms are transferred to a simulation environment. The entire solution proposed in the work is composed as a parallel environment to the real implementation of the production process. Findings: The genetic algorithm generated the best solution in the same specified short time. By implementing the adopted approach, the correct cooperation of the FlexSim simulation environment with the R language engine was obtained. Research limitations/implications: The genetic algorithm generated the best solution in the same specified short time. By implementing the approach, a correct interaction between the FlexSim simulation environment and the R language engine was achieved. Practical implications: The solution proposed in this paper can be used as an environment to test solutions proposed in production. Simulation methods in the areas of logistics and production have for years attracted the interest of the scientific community and the wider industry. Combining the achievements of science in solving computationally complex problems with increasingly sophisticated algorithms, including artificial intelligence algorithms, with simulation methods that allow a detailed overview of the consequences of changes made seems promising. Originality/value: The original concept of cooperation between the R environment and the FlexSim simulation software for a specific problem was presented.

6

Calculation strength optimum of surgical robot effector for mechanical eigenproblems using FEM and genetic algorithm

Ilewicz Grzegorz

Vibrations in Physical Systems

|

2023

|

Vol. 34, nr 1

art. no. 2023106

EN

It is essential to check whether the surgical robot end effector is safe to use due to phenomena such as linear buckling and mechanical resonance. The aim of this research is to build an multi criteria optimization model based on such criteria as the first natural frequency, buckling factor and mass, with the assumption of the basic constraint in the form of a safety factor. The calculations are performed for a serial structure of surgical robot end effector with six degrees of freedom ended with a scalpel. The calculation model is obtained using the finite element method. The issue of multi-criteria optimization is solved based on the response surface method, Pareto fronts and the genetic algorithm. The results section illustrates deformations of a surgical robot end effector occurring during the resonance phenomenon and the buckling deformations for subsequent values of the buckling coefficients. The dependencies of the geometrical dimensions on the criteria are illustrated with the continuous functions of the response surface, i.e. metamodels. Pareto fronts are illustrated, based on which the genetic algorithm finds the optimal quantities of the vector function. The conducted analyzes provide a basis for selecting surgical robot end effector drive systems from the point of view of their generated inputs.

7

Performances improvement of fractional order systems using the fractional order adaptive PID controller

Asradj Zahir, Bensafia Bouira, Merzouk Imad

Przegląd Elektrotechniczny

|

2023

|

R. 99, nr 8

257--260

EN

Fractional order systems are widely used in industrial application for its different advantage such us high efficiency, and flexibilities. The applications of fractional order systems in a range of scientific fields have caught the attention of researchers especially in control strategy. The current research work presents the use the fractional adaptive PID controller approach, optimized by genetic algorithm, to improve the performances (rise time, setting time and overshoot) for fractional systems by introducing fractional order integrator and differentiator in the classical feedback adaptive PID controller. To validate the arguments, effectiveness and performances analysis of the proposed approach optimized by genetic algorithm have been studied in comparison to the classical adaptive PID controller. Numerical simulation and analysis are presented to verify the best controller. The Fractional order PID gives the best result in terms of settling time, rise time, overshoot and mean absolute error.

PL

Systemy ułamkowego rzędu są szeroko stosowane w zastosowaniach przemysłowych ze względu na różne zalety, takie jak wysoka wydajność i elastyczność. Zastosowania systemów rzędu ułamkowego w wielu dziedzinach nauki przykuły uwagę badaczy, zwłaszcza w dziedzinie strategii sterowania. Obecna praca badawcza przedstawia wykorzystanie podejścia ułamkowego regulatora adaptacyjnego PID, zoptymalizowanego przez algorytm genetyczny, do poprawy osiągów (czas narastania, czas ustawiania i przeregulowanie) układów ułamkowych poprzez wprowadzenie integratora i układu różniczkowego ułamkowego rzędu do klasycznego regulatora PID z adaptacyjnym sprzężeniem zwrotnym. Aby zweryfikować argumenty, przeprowadzono analizę skuteczności i wydajności proponowanego podejścia zoptymalizowanego za pomocą algorytmu genetycznego w porównaniu z klasycznym adaptacyjnym regulatorem PID. Przedstawiono symulację i analizę numeryczną w celu weryfikacji najlepszego sterownika. PID rzędu ułamkowego daje najlepsze wyniki pod względem czasu ustalania, czasu narastania, przeregulowania i średniego błędu bezwzględnego.

8

Conditions for increasing the recognition of degradation in thermal-flow diagnostics, taking into account environmental legal aspects

Drosińska-Komor Marta, Głuch Jerzy, Brzezińska-Gołębiewska Katarzyna, Piotrowicz Michał, Ziółkowski Paweł

Journal of Power Technologies

|

2023

|

Vol. 103, nr 1

33--48

EN

The ever-increasing demand for electricity and the need for conventional sources to cooperate with renewable ones generates the need to increase the efficiency and safety of the generation sources. Therefore, it is necessary to find a way to operate existing facilities more efficiently with full detection of emerging faults. These are the requirements of Polish, European and International law, which demands that energy facilities operate with the highest efficiency and meet a number of restrictive requirements. In order to improve the operation of steam power plants of electric generating stations, thermal-fluid diagnostics have been traditionally used, and in this paper a three-hull steam turbine, having a high-pressure, a medium-pressure and a low-pressure part, has been selected for analysis. The turbine class is of the order of 200 MW electric. Genetic algorithms (GA) were used in the process of creating the diagnostic model. So far, they have been used for diagnostic purposes in gas turbines, and no work has been found in the literature using GA for the diagnostic process of such complex objects as steam turbines located in professional manufacturing facilities. The use of genetic algorithms allowed rapid acquisition of global extremes, that is efficiency and power of the unit. The result of the work undertaken is the possibility to carry out a full diagnostic process, meaning detection, localization and identification of single and double degradations. In this way 100 % of the main faults are found, but there are sometimes additional ones, and these are not perfectly identified especially for single time detection. Thus, the results showed that with a very high success rate the simulated damage to the geometrical elements of the steam turbine under study is found.

9

FSPL: A meta-learning approach for a filter and embedded feature selection pipeline

Lazebnik Teddy, Rosenfeld Avi

International Journal of Applied Mathematics and Computer Science

|

2023

|

Vol. 33, no. 1

103--115

EN

There are two main approaches to tackle the challenge of finding the best filter or embedded feature selection (FS) algorithm: searching for the one best FS algorithm and creating an ensemble of all available FS algorithms. However, in practice, these two processes usually occur as part of a larger machine learning pipeline and not separately. We posit that, due to the influence of the filter FS on the embedded FS, one should aim to optimize both of them as a single FS pipeline rather than separately. We propose a meta-learning approach that automatically finds the best filter and embedded FS pipeline for a given dataset called FSPL. We demonstrate the performance of FSPL on n = 90 datasets, obtaining 0.496 accuracy for the optimal FS pipeline, revealing an improvement of up to 5.98 percent in the model’s accuracy compared to the second-best meta-learning method.

10

A genetic algorithm based optimized convolutional neural network for face recognition

Karlupia Namrata, Mahajan Palak, Abrol Pawanesh, Lehana Parveen K.

International Journal of Applied Mathematics and Computer Science

|

2023

|

Vol. 33, no. 1

21--31

EN

Face recognition (FR) is one of the most active research areas in the field of computer vision. Convolutional neural networks (CNNs) have been extensively used in this field due to their good efficiency. Thus, it is important to find the best CNN parameters for its best performance. Hyperparameter optimization is one of the various techniques for increasing the performance of CNN models. Since manual tuning of hyperparameters is a tedious and time-consuming task, population based metaheuristic techniques can be used for the automatic hyperparameter optimization of CNNs. Automatic tuning of parameters reduces manual efforts and improves the efficiency of the CNN model. In the proposed work, genetic algorithm (GA) based hyperparameter optimization of CNNs is applied for face recognition. GAs are used for the optimization of various hyperparameters like filter size as well as the number of filters and of hidden layers. For analysis, a benchmark dataset for FR with ninety subjects is used. The experimental results indicate that the proposed GA-CNN model generates an improved model accuracy in comparison with existing CNN models. In each iteration, the GA minimizes the objective function by selecting the best combination set of CNN hyperparameters. An improved accuracy of 94.5% is obtained for FR.

11

Brain tumor classification in MRI imagesusing genetic algorithm appended CNN

Balamurugan Thiyagu, Gnanamanoharan E.

Computer Assisted Methods in Engineering and Science

|

2023

|

Vol. 30, no. 3

305--321

EN

Brain tumors are fatal for majority of the patients, the different nature of the tumorcells requires the use of combined medical measures, and categorizing such tumors isa difficult task for radiologists. The diagnostic structures based on PCs have been offeredas an aid in diagnosing a brain tumor using magnetic resonance imaging (MRI). Generalfunctions are retrieved from the lowest layers of the neural network, and these lowestlayers are responsible for capturing low-level features and patterns in the raw input data,which can be particularly unique to the raw image. To validate this, the EfficientNetB3pre-trained model is utilized to classify three types of brain tumors: glioma, meningioma,and pituitary tumor. Initially, the characteristics of several EfficientNet modules are takenfrom the pre-trained EfficientNetB3 version to locate the brain tumor. Three types of braintumor datasets are used to assess each approach. Compared to the existing deep learningmodels, the concatenated functions of EfficientNetB3 and genetic algorithms give betteraccuracy. Tensor flow 2 and Nesterov-accelerated adaptive moment estimation (Nadam)are also employed to improve the model training process by making it quicker and better.The proposed technique using CNN attains an accuracy of 99.56%, a sensitivity of 98.9%,a specificity of 98.6%, an F-score of 98.9%, a precision of 98.9%, and a recall of 99.54%.

12

Hybrid EEG-fNIRS brain-computer interface based on the non-linear features extraction and stacking ensemble learning

Maher Asmaa, Mian Qaisar Saeed, Salankar N., Jiang Feng, Tadeusiewicz Ryszard, Pławiak Paweł, Abd El-Latif Ahmed A., Hammad Mohamed

Biocybernetics and Biomedical Engineering

|

2023

|

Vol. 43, no. 2

463--475

EN

The Brain-computer interface (BCI) is used to enhance the human capabilities. The hybridBCI (hBCI) is a novel concept for subtly hybridizing multiple monitoring schemes to maximize the advantages of each while minimizing the drawbacks of individual methods. Recently, researchers have started focusing on the Electroencephalogram (EEG) and ‘‘Functional Near-Infrared Spectroscopy” (fNIRS) based hBCI. The main reason is due to the development of artificial intelligence (AI) algorithms such as machine learning approaches to better process the brain signals. An original EEG-fNIRS based hBCI system is devised by using the non-linear features mining and ensemble learning (EL) approach. We first diminish the noise and artifacts from the input EEG-fNIRS signals using digital filtering. After that, we use the signals for non-linear features mining. These features are ‘‘Fractal Dimension” (FD), ‘‘Higher Order Spectra” (HOS), ‘‘Recurrence Quantification Analysis” (RQA) features, and Entropy features. Onward, the Genetic Algorithm (GA) is employed for Features Selection (FS). Lastly, we employ a novel Machine Learning (ML) technique using several algorithms namely, the ‘‘Naïve Bayes” (NB), ‘‘Support Vector Machine” (SVM), ‘‘Random Forest” (RF), and ‘‘K-Nearest Neighbor” (KNN). These classifiers are combined as an ensemble for recognizing the intended brain activities. The applicability is tested by using a publicly available multi-subject and multiclass EEG-fNIRS dataset. Our method has reached the highest accuracy, F1-score, and sensitivity of 95.48%, 97.67% and 97.83% respectively.

13

TOD mode: study on land planning and land use optimization for urban rail transit station area

Shen Hongtian, Ma Guimin

Archives of Transport

|

2023

|

Vol. 66, iss. 2

33--43

EN

The rational planning of land around rail transit stations in cities can effectively improve the convenience of transportation and economic development of cities. This paper briefly introduced the transit-oriented development (TOD) mode of urban planning. We constructed a hierarchical structure for evaluating the quality of land planning of urban rail transit stations through the analytic hierarchy process (AHP) method. The structure started from three large aspects, i.e., traffic volume, regional environmental quality, and regional economic efficiency, and every large aspect was divided into three small aspects. Then, an optimization model was established for land planning of rail transit stations. The land planning scheme was optimized by a genetic algorithm (GA). To enhance the optimization performance of the GA, it was improved by coevolution, i.e., plural populations iterated independently, and every population replaced the poor chromosomes in the other populations with its excellent chromosomes in the previous process. Finally, the Jinzhonghe street station in Hebei District, Tianjin city, was taken as a subject for analysis. The results suggested that the improved GA obtained a set of non-inferior Pareto solutions when solving a multi-objective optimization problem. The distribution of solutions in the set also indicated that any two objectives among traffic volume, environmental quality, and economic efficiency was improved at the cost of the remaining objectives. The land planning schemes optimized by the particle swarm optimization (PSO) algorithm, the traditional GA, and the improved GA, respectively, were superior than the initial scheme, and the optimized scheme of the improved GA was more in line with the characteristics of the TOD mode than the traditional one and the PSO algorithm, and the fitness value was also higher. In conclusion, the GA can be used to optimize the planning design of land in rail transit areas under the TOD mode, and the optimization performance of the GA can be improved by means of coevolution.

14

Finite element model updating of steel-concrete composite bridge: A study case of the Ruri bridge in Vietnam

Nguyen Duc Cong, Salamak Marek, Katunin Andrzej, Gerges Michael, Abdel-Maguid Mohamed

Archives of Civil Engineering

|

2023

|

Vol. 69, nr 3

425--443

EN

The study presents the finite element (FE) model update of the existing simple-spans steel-concrete composite bridge structure using a particle swarm optimisation (PSO) and genetic algorithm (GA) approaches. The Wireless Structural Testing System (STS-WiFi) of Bridge Diagnostic, Inc. from the USA, implemented various types of sensors including: LVDT displacement sensors, intelligent strain transducers, and accelerometers that the static and dynamic historical behaviors of the bridge structure have been recorded in the field testing. One part of all field data sets has been used to calibrate the cross-sectional stiffness properties of steel girders and material of steel beams and concrete deck in the structural members including 16 master and slave variables, and that the PSO and GA optimisation methods in the MATLAB software have been developed with the new innovative tools to interface with the analytical results of the FE model in the ANSYS APDL software automatically. The vibration analysis from the dynamic responses of the structure have been conducted to extract four natural frequencies from experimental data that have been compared with the numerical natural frequencies in the FE model of the bridge through the minimum objective function of percent error to be less than 10%. In order to identify the experimental mode shapes of the structure more accurately and reliably, the discrete-time state-space model using the subspace method (N4SID) and fast Fourier transform (FFT) in MATLAB software have been applied to determine the experimental natural frequencies in which were compared with the computed natural frequencies. The main goal of the innovative approach is to determine the representative FE model of the actual bridge in which it is applied to various truck load configurations according to bridge design codes and standards. The improved methods in this document have been successfully applied to the Vietnamese steel-concrete composite bridge in which the load rating factors (RF) of the AASHTO design standards have been calculated to predict load limits, so the final updated FE model of the existing bridge is well rated with all RF values greater than 1.0. The presented approaches show great performance and the potential to implement them in industrial conditions.

15

Application of genetic algorithm for double-lap adhesive joint design

Kurennov Sergei, Barakhov Konstantin, Polyakov Olexander, Taranenko Igor

Archive of Mechanical Engineering

|

2023

|

LXX, nr 1

27--42

EN

The problem of optimal design of symmetrical double-lap adhesive joint is considered. It is assumed that the main plate has constant thickness, while the thickness of the doublers can vary along the joint length. The optimization problem consists in finding optimal length of the joint and an optimal cross-section of the doublers, which provide minimum structural mass at given strength constraints. The classical Goland-Reissner model was used to describe the joint stress state. A corresponding system of differential equations with variable coefficients was solved using the finite difference method. Genetic optimization algorithm was used for numerical solution of the optimization problem. In this case, Fourier series were used to describe doubler thickness variation along the joint length. This solution ensures smoothness of the desired function. Two model problems were solved. It is shown that the length and optimal shape of the doubler depend on the design load.

16

Developing numerical equality to regional intensity-duration-frequency curves using evolutionary algorithms and multi-gene genetic programming

Citakoglu Hatice, Demir Vahdettin

Acta Geophysica

|

2023

|

Vol. 71, no. 1

469--488

EN

This study aims to carry out regional intensity−duration−frequency (IDF) equality using the relationship with IDF obtained from point frequency analysis. Eleven empirical equations used in the literature for seven climate regions of Turkey were calibrated using particle swarm optimization (PSO) and genetic algorithm (GA) optimization techniques and the obtained results were compared. In addition, in this study, new regional IDF equations were obtained for each region utilizing Multi-Gene Genetic Programming (MGGP) method. Finally, Kruskal–Wallis (KW) test was applied to the IDF values obtained from the methods and the observed values. As a result of the study, it was observed that the coefficients of 11 empirical equations calibrated with PSO, and GA techniques were different from each other. The mean absolute error (MAE), root mean square error (RMSE), mean absolute relative error (MARE), coefficient of determination (R2 ), and Taylor diagram were used to evaluate the performances of PSO, GA, and MGGP techniques. According to the performance criteria, it has been determined that the IDF equations obtained by the MGGP method for the Eastern Anatolia, Aegean, Southeastern Anatolia, and Central Anatolia regions are more successful than the empirical equations calibrated with the PSO and GA method. The empirical IDF equations produced with PSO and the IDF equations acquired with MGGP have similar findings in the Mediterranean, Black Sea, and Marmara. In addition, the KW test results showed that the data of all models were from the same population.

17

Genetic algorithms in active vibration reduction problem

Grochowina Marcin, Tyburski Krzysztof

Vibrations in Physical Systems

|

2022

|

Vol. 33, nr 2

art. no. 2022219

EN

The design of active vibration reduction systems usually consists in selecting a control algorithm and determining the value of its settings. This article presents the results of research on the concept of using genetic algorithms to induce the settings of control systems. To test the concept, a simple pulse-excited flat bar model was selected. The vibrations were suppressed by the PID controller. Genetic algorithms with two types of crossover were tested - arithmetic and uniform. As a result, the settings for the PID controller were obtained, enabling effective reduction of vibrations in a short time.

18

Genetic algorithm application for optimizing traffic signal timing reflecting vehicle emission intensity

Hai Dinh Tuan, Manh Do Van, Nhat Nguyen Minh

Transport Problems

|

2022

|

T. 17, z. 1

5--16

EN

Urbanization has created continuous growth in transportation demand, leading to serious issues, including infrastructure overload, disrupted traffic flow, and associated vehicular emissions. As a result, resolving these problems has become one of the primary missions of governments worldwide. The optimization of the traffic signal timing system is considered a promising approach to overcoming the negative consequences of increasing vehicle volume. In metropolises, oversaturated intersections, where the traffic density and vehicle exhaust emission levels are significant, have been considered as the priority to target. Several scientists have attempted to design traffic lights with the most appropriate timing. However, the majority of previous studies have not formed a comprehensive evaluation of essential factors, especially regarding the appropriate weighting of vehicle emission parameters. By assessing the all-inclusive relationship of critical elements with an emphasis on vehicle exhaust emissions, a performance index model using a genetic algorithm (GA) is established in this paper, demonstrated by data from a case study in Taiwan.

19

Comparison of genetic algorithm and neural network approaches for the prognosis of mechanical idle running losses in agriculture tractor transmission

Ivanov Rosen, Ivanova Donka

Transport Problems

|

2022

|

T. 17, z. 3

51--59

EN

An experimental investigation of mechanical idle running losses in an agriculture tractor transmission was used to collect a wide range of data. The influence of the engine rotation speed, the number of switched-on gears, and the oil level in the transmission gearbox on the idle running losses was determined. Adequate regression models in cases of switched-on and switched-off PTO were received. A genetic algorithm was used to optimize mathematical models obtained using regression analysis. A feedforward artificial neural network was also developed to estimate the same experimental data for mechanical idle running losses in transmission. A back-propagation algorithm was used when training and testing the network. A comparison of the correlation coefficient, reduced chi-square, mean bias error, and root mean square error between the experimental data and fit values of the obtained models was made. It was concluded that the neural network represented the mechanical idle running losses in tractor transmission more accurately than other models.

20

Zastosowanie algorytmu genetycznego w procesie estymacji parametrów modeli przyrządów półprzewodnikowych

Bisewski Damian

Przegląd Elektrotechniczny

|

2022

|

R. 98, nr 9

103--106

PL

Praca dotyczy zastosowania algorytmu genetycznego w procesie estymacji wartości parametrów arbitralnie wybranego modelu tranzystora MOS. Przedstawiono budowę oraz zasadę działania algorytmu genetycznego. Pokazano wpływ wybranych parametrów sterujących działaniem algorytmu na obliczone wartości funkcji celu. Zaproponowano modyfikację operatora krzyżowania wpływającą na uzyskiwanie wyników obliczeń z większą dokładnością.

EN

The paper concerns the application of the genetic algorithm in the process of parameter estimation of an arbitrarily selected MOSFET model. The structure and the principle of operation of the genetic algorithm have been presented. The influence of selected parameters controlling the algorithm operation on the calculated values of the objective function has been shown. A modification of the crossing operator providing calculation results of greater accuracy has been proposed.