Wyniki wyszukiwania - BazTech

1

Optimization of a task schedule for teams with members having various skills

Bazan Marek, Smutnicki Czesław, Marchwiany Maciej E.

International Journal of Electronics and Telecommunications

|

2024

|

Vol. 70, No. 1

59--69

EN

We consider the real-life problem of planning tasks for teams in a corporation, in conditions of some restrictions. The problem takes into account various constraints, such as for instance flexible working hours, common meeting periods, time set aside for self-learning, lunchtimes and periodic performance of tasks. Additionally, only a part of the team may participate in meetings, and each team member may have their own periodic tasks such as self-development. We propose an algorithm that is an extension of the algorithm dedicated for scheduling on parallel unrelated processors with the makespan criterion. Our approach assumes that each task can be defined by a subset of employees or an entire team. However, each worker is of a different efficiency, so task completion times may differ. Moreover, the tasks are prioritized. The problem is NP-hard. Numerical experiments cover benchmarks with 10 instances of 100 tasks assigned to a 5-person team. For all instances, various algorithms such as branch-and-bound, genetic and tabu search have been tested.

2

Optimisation of a Nacelle Electro-Thermal Ice Protection System for Icing Wind Tunnel Testing

Gallia Mariachiara, Carnemolla Alessandro, Premazzi Marco, Guardone Alberto

Transactions on Aerospace Research

|

2023

|

Nr 1 (270)

32--44

EN

Aircraft are equipped with ice protection systems (IPS), to avoid, delay or remove ice accretion. Two widely used technologies are the thermo-pneumatic IPS and the electro-thermal IPS (ETIPS). Thermopneumatic IPS requires air extraction from the engine negatively affecting its performances. Moreover, in the context of green aviation, aircraft manufacturers are moving towards hybrid or fully electric aircraft requiring all electric on-board systems. In this work, an ETIPS has been designed and optimised to replace the nacelle pneumatic-thermal system. The aim is to minimise the power consumption while assuring limited or null ice formation and that the surface temperature remains between acceptable bounds to avoid material degradation. The design parameters were the length and heat flux of each heater. Runback ice formations and surface temperature were assessed by means of the in-house developed PoliMIce framework. The optimisation was performed using a genetic algorithm, and the constraints were handled through a linear penalty method. The optimal configuration required 33% less power with respect to the previously installed thermo-pneumatic IPS. Furthermore, engine performance is not affected in the case of the ETIPS. This energy saving resulted in an estimated reduction of specific fuel consumption of 3%, when operating the IPS in anti-icing mode.

3

Optimization of Job Shop Scheduling Problem by Genetic Algorithms: Case Study

Sahar Habbadi, Herrou Brahim, Sekkat Souhail

Management and Production Engineering Review

|

2023

|

Vol. 14, No. 3

44--56

EN

The Job Shop scheduling problem is widely used in industry and has been the subject of study by several researchers with the aim of optimizing work sequences. This case study provides an overview of genetic algorithms, which have great potential for solving this type of combinatorial problem. The method will be applied manually during this study to understand the procedure and process of executing programs based on genetic algorithms. This problem requires strong decision analysis throughout the process due to the numerous choices and allocations of jobs to machines at specific times, in a specific order, and over a given duration. This operation is carried out at the operational level, and research must find an intelligent method to identify the best and most optimal combination. This article presents genetic algorithms in detail to explain their usage and to understand the compilation method of an intelligent program based on genetic algorithms. By the end of the article, the genetic algorithm method will have proven its performance in the search for the optimal solution to achieve the most optimal job sequence scenario.

4

Optimisation of crop rotations : A case study for corn growing practices in forest-steppe of Ukraine

Romashchenko Mykhailo, Bohaienko Vsevolod, Shatkovskyi Andrij, Saidak Roman, Matiash Tetiana, Kovalchuk Volodymyr

Journal of Water and Land Development

|

2023

|

no. 56

194--202

EN

The formation of optimal crop rotations is virtually unsolvable from the standpoint of the classical methodology of experimental research. Here, we deal with a mathematical model based on expert estimates of “predecessor-crop” pairs’ efficiency created for the conditions of irrigation in the forest-steppe of Ukraine. Solving the problem of incorporating uncertainty assessments into this model, we present new models of crop rotations’ economic efficiency taking into account irrigation, application of fertilisers, and the negative environmental effect of nitrogen fertilisers’ introduction into the soil. For the considered models we pose an optimisation problem and present an algorithm for its solution that combines a gradient method and a genetic algorithm. Using the proposed mathematical tools, for several possible scenarios of water, fertilisers, and purchase price variability, the efficiency of growing corn as a monoculture in Ukraine is simulated. The proposed models show a reduction of the profitability of such a practice when the purchase price of corn decreases below 0.81 EUR∙kg-1 and the price of irrigation water increases above 0.32 EUR∙m-3 and propose more flexible crop rotations. Mathematical tools developed in the paper can form a basis for the creation of decision support systems that recommend optimal crop rotation variations to farmers and help to achieve sustainable, profitable, and ecologically safe agricultural production. However, future works on the actualisation of the values of its parameters need to be performed to increase the accuracy.

5

Application of Real-time fan scheduling in exploration-exploitation to optimize minimum function objectives

Larios-Gómez Mariano, Quintero-Flores Perfecto M., Anzures-García Mario, Camacho-Hernandez Miguel

Applied Computer Science

|

2023

|

Vol. 19, no 2

43--54

EN

This paper presents the application of a task scheduling algorithm called Fan based on artificial intelligence technique such as genetic algorithms for the problem of finding minima in objective functions, where equations are predefined to measure the return on investment. This work combines the methodologies of population exploration and exploitation. Results with good aptitudes are obtained until a better learning based on non-termination conditions is found, until the individual provides a better predisposi¬tion, adhering to the established constraints, exhausting all possible options and satisfying the stopping condition. A real-time task planning algorithm was applied based on consensus techniques. A software tool was developed, and the scheduler called FAN was adapted that contemplates the execution of periodic, aperiodic, and sporadic tasks focused on controlled environments, considering that strict time restrictions are met. In the first phase of the work, it is shown how convergence precipitates to an evolution. This is done in a few iterations. In the second stage, exploitation was improved, giving the algorithm a better performance in convergence and feasibility. As a result, a population was used and iterations were applied with a fan algorithm and better predisposition was obtained, which occurs in asynchronous processes while scheduling in real time.

6

Application of genetic algorithms to the traveling salesman problem

Sikora Tomasz, Gryglewicz-Kacerka Wanda

Applied Computer Science

|

2023

|

Vol. 19, no 2

55--62

EN

The purpose of this paper was to investigate in practice the possibility of using evolutionary algorithms to solve the traveling salesman problem on a real example. The goal was achieved by developing an original implementation of the evolutionary algorithm in Python, and by preparing an example of the traveling salesman problem in the form of a directed graph representing Polish voivodship cities. As part of the work an application in Python was written. It provides a user interface which allows to set selected parameters of the evolutionary algorithm and solve the prepared problem. The results are presented in both text and graphical form. The correctness of the evolutionary algorithm's operation and the implementation was confirmed by performed tests. A large number of tested solutions (2500) and the analysis of the obtained results allowed for a conclusion that an optimal (relatively suboptimal) solution was found.

7

ForestTaxator : a tool for detection and approximation of cross-sectional area of trees in a cloud of 3D points

Małaszek Maciej, Zembrzuski Andrzej, Gajowniczek Krzysztof

Machine Graphics and Vision

|

2022

|

Vol. 31, No. 1/4

19--48

EN

In this paper we propose a novel software, named ForestTaxator, supporting terrestrial laser scanning data processing, which for dendrometric tree analysis can be divided into two main processes: tree detection in the point cloud and development of three-dimensional models of individual trees. The usage of genetic algorithms to solve the problem of tree detection in 3D point cloud and its cross-sectional area approximation with ellipse-based model is also presented. The detection and approximation algorithms are proposed and tested using various variants of genetic algorithms. The work proves that the genetic algorithms work very well: the obtained results are consistent with the reference data to a large extent, and the time of genetic calculations is very short. The attractiveness of the presented software is due to the fact that it provides all necessary functionalities used in the forest inventory field. The software is written in C# and runs on the .NET Core platform, which ensures its full portability between Windows, MacOS and Linux. It provides a number of interfaces thus ensuring a high level of modularity. The software and its code are made freely available.

8

AH Method: a Novel Routine for Vicinity Examination of the Optimum Found with a Genetic Algorithm

Piętak Daniel Andrzej, Bilski Piotr, Napiorkowski Paweł Jan

International Journal of Electronics and Telecommunications

|

2022

|

Vol. 68. No. 4

695--708

EN

The paper presents a novel heuristic procedure (further called the AH Method) to investigate function shape in the direct vicinity of the found optimum solution. The survey is conducted using only the space sampling collected during the optimization process with an evolutionary algorithm. For this purpose the finite model of point-set is considered. The statistical analysis of the sampling quality based upon the coverage of the points in question over the entire attraction region is exploited. The tolerance boundaries of the parameters are determined for the user-specified increase of the objective function value above the found minimum. The presented test-case data prove that the proposed approach is comparable to other optimum neighborhood examination algorithms. Also, the AH Method requires noticeably shorter computational time than its counterparts. This is achieved by a repeated, second use of points from optimization without additional objective function calls, as well as significant repository size reduction during preprocessing.

9

Applying optimization techniques on cold-formed C-channel section under bending

El-Lafy Heba F., Elgendi Elbadr O., Morsy Alaa M.

International Journal of Applied Mechanics and Engineering

|

2022

|

Vol. 27, no. 4

52--65

EN

There are no standard dimensions or shapes for cold-formed sections (CFS), making it difficult for a designer to choose the optimal section dimensions in order to obtain the most cost-effective section. A great number of researchers have utilized various optimization strategies in order to obtain the optimal section dimensions. Multi-objective optimization of CFS C-channel beams using a non-dominated sorting genetic algorithm II was performed using a Microsoft Excel macro to determine the optimal cross-section dimensions. The beam was optimized according to its flexural capacity and cross-sectional area. The flexural capacity was computed utilizing the effective width method (EWM) in accordance with the Egyptian code. The constraints were selected so that the optimal dimensions derived from optimization would be production and construction-friendly. A Pareto optimal solution was obtained for 91 sections. The Pareto curve demonstrates that the solution possesses both diversity and convergence in the objective space. The solution demonstrates that there is no optimal solution between 1 and 1.5 millimeters in thickness. The solutions were validated by conducting a comprehensive parametric analysis of the change in section dimensions and the corresponding local buckling capacity. In addition, performing a single-objective optimization based on section flexural capacity at various thicknesses The parametric analysis and single optimization indicate that increasing the dimensions of the elements, excluding the lip depth, will increase the section’s carrying capacity. However, this increase will depend on the coil’s wall thickness. The increase is more rapid in thicker coils than in thinner ones.

10

The simplest option valuation genetic algorithm model – NASDAQ case study

Małecka Joanna, Vila Biglieri Jorge

Zeszyty Naukowe Politechniki Poznańskiej. Organizacja i Zarządzanie

|

2021

|

Nr 83

63--80

EN

The capital market is the meeting place of supply and demand. The profit orientation possible through the stock market stimulates two processes: 1) buying or 2) selling financial instruments – a long or short option. Investing is a process accompanied by fluctuations – often of <1% per day. Hence, individual investors look for alternatives, which include deriv-atives that fluctuate up to 100% per day. Therefore, the need was perceived to develop an instrument – a valuation tool – to help individual investors make investment decisions. The Black-Scholes Model (BSM) uses six independent variables. It was therefore decided to com-pile an alternative valuation model based on the Genetic Algorithm (GA) on the strength of companies listed on NASDAQ: FaceBook, Apple, Amazon, Netflix and Google (so-called FAANG companies), using Eureqa GA software. The purpose of this paper is to present the results of a study that attempts to develop a more efficient option pricing model by comparing the accuracy of the Genetic Algorithm (GA) and the Black-Scholes Model (BSM) and evaluating gaps in underlying price movements. The comparison of the genetic algorithm with the traditional Black-Scholes option pricing model led to the development of a new linear investment model – investors can make predictions using one variable – the share price, which should significantly optimise strategic investment decisions. The presented model is characterised by higher investment efficiency, especially important for individual investors, who usually are not able to achieve the profit scale effect based on the value of a retail investment portfolio.

PL

Rynek kapitałowy jest miejscem spotkania podaży i popytu. Orientacja na zysk, możliwy do osiągnięcia za pośrednictwem giełdy stymuluje dwa procesy: 1) kupno instrumentów finansowych lub 2) ich sprzedaż, czyli długą lub krótką opcję. Inwestowanie to proces, któremu towarzyszą wahania – często na poziomie <1% dziennie. Stąd inwestorzy indywidualni poszukują rozwiązań alternatywnych, do których należą instrumenty pochodne, dziennie oscylujące nawet o 100%. Dlatego dostrzeżono potrzebę opracowania instrumentu – narzędzia wyceny – ułatwiającego inwestorom indywidualnym podejmowanie decyzji inwestycyjnych. Wykorzystywany model Blacka-Scholesa (BSM) stosuje sześć zmiennych niezależnych. Zdecydowano skompilować alternatywny model wyceny bazujący na algorytmie genetycznym (GA) na podstawie indeksów spółek notowanych na NASDAQ: Facebook, Apple, Amazon, Netflix i Google (tzw. spółki FAANG), przy zastosowaniu oprogramowania Eureqa GA. Celem artykułu jest prezentacja wyników badań będących próbą opracowania skuteczniejszego modelu wyceny opcji przez porównanie dokładności algorytmu genetycznego (GA) i Blacka-Scholesa (BSM) oraz ewaluacji luk w ruchach cen instrumentów bazowych. Komparacja algorytmu genetycznego z tradycyjnym modelem wyceny opcji Blacka-Scholesa pozwoliła na opracowanie nowego modelu inwestycyjnego o charakterze liniowym – inwestorzy mogą dokonywać prognoz za pomocą tylko jednej zmiennej – ceny akcji, co znacznie powinno zoptymalizować podejmowanie strategicznych decyzji inwestycyjnych, bowiem presja zakupowa powoduje szybki wzrost cen instrumentów bazowych, co implikuje niechęć właścicieli opcji do sprzedaży instrumentów pochodnych w momentach wzrostów ujemnych. Prezentowany model charakteryzuje większa skuteczność inwestycyjna, szczególnie istotna dla indywidualnych inwestorów, którzy zazwyczaj nie są w stanie osiągnąć efektu skali zysku na podstawie wartości detalicznego portfela inwestycyjnego.

11

Multi-objective optimization of elastomeric bearings to improve seismic performance of old bridges using eigen analysis and genetic algorithms

Abbadi Mohammed S., Lamdouar Nouzha

Przegląd Naukowy Inżynieria i Kształtowanie Środowiska

|

2021

|

Vol. 30, No. 4

511--524

EN

Old bridges present several seismic vulnerabilities and were designed before the emergence of seismic codes. In this context, partial seismic isolation has given a special attention to improve their seismic performance. In particular, elastomeric bearings are the simplest and least expensive mean for this, enabling to resist both non-seismic actions and earthquake loads. In order to assess the initial structural performance and the improvement done by the isolation, this paper attempts to combine multi objective optimization using genetic algorithms with linear and non-linear analysis using FE program OpenSees. A prior screening of the columns states is settled and then a multi objective optimization of a population of standard sized bearings meeting non-seismic and stability requirements is established to optimize the linear and non-linear behavior of the structure, finding the best compromise between displacements and forces at the columns.

12

Optimization of the loading pattern of the PWR core using genetic algorithms and multi-purpose fitness function

Kubiński Wojciech, Darnowski Piotr, Chęć Kamil

Nukleonika

|

2021

|

Vol. 66, No. 4

147--151

EN

The study demonstrates an application of genetic algorithms (GAs) in the optimization of the first core loading pattern. The Massachusetts Institute of Technology (MIT) BEAVRS pressurized water reactor (PWR) model was applied with PARCS nodal-diffusion core simulator coupled with GA numerical tool to perform pattern selection. In principle, GAs have been successfully used in many nuclear engineering problems such as core geometry optimization and fuel confi guration. In many cases, however, these analyses focused on optimizing only a single parameter, such as the effective neutron multiplication factor (keff), and often limited to the simplified core model. On the contrary, the GAs developed in this work are equipped with multiple-purpose fitness function (FF) and allow the optimization of more than one parameter at the same time, and these were applied to a realistic full-core problem. The main parameters of interest in this study were the total power peaking factor (PPF) and the length of the fuel cycle. The basic purpose of this study was to improve the economics by finding longer fuel cycle with more uniform power/flux distribution. Proper FFs were developed, tested, and implemented and their results were compared with the reference BEAVRS first fuel cycle. In the two analysed test scenarios, it was possible to extend the fi rst fuel cycle while maintaining lower or similar PPF, in comparison with the BEAVRS core, but for the price of increased initial reactivity.

13

Application of genetic algorithms in optimization of SFR nuclear reactor design

Żurkowski Wojciech, Sawicki Piotr, Kubiński Wojciech, Darnowski Piotr

Nukleonika

|

2021

|

Vol. 66, No. 4

139--145

EN

This work presents a demonstrational application of genetic algorithms (GAs) to solve sample optimization problems in the generation IV nuclear reactor core design. The new software was developed implementing novel GAs, and it was applied to show their capabilities by presenting an example solution of two selected problems to check whether GAs can be used successfully in reactor engineering as an optimization tool. The 3600 MWth oxide core, which was based on the OECD/NEA sodium-cooled fast reactor (SFR) benchmark, was used a reference design [1]. The first problem was the optimization of the fuel isotopic inventory in terms of minimizing the volume share of long-lived actinides, while maximizing the effective neutron multiplication factor. The second task was the optimization of the boron shield distribution around the reactor core to minimize the sodium void reactivity effect (SVRE). Neutron transport and fuel depletion simulations were performed using Monte Carlo neutron transport code SERPENT2. The simulation resulted in an optimized fuel mixture composition for the selected parameters, which demonstrates the functionality of the algorithm. The results show the efficiency and universality of GAs in multidimensional optimization problems in nuclear engineering.

14

Optimization of material distribution for forged automotive components using hybrid optimization techniques

Sebastjan Przemysław, Kuś Wacław

Computer Methods in Materials Science

|

2021

|

Vol. 21, No. 2

63--74

EN

The paper deals with the problem of optimal material distribution inside the provided design area. Optimization based on deterministic and stochastic algorithms is used to obtain the best result on the basis of the proposed objective function and constraints. The optimization of the shock absorber is used as an example of the described methods. One of the main difficulties addressed is the manufacturability of the optimized part intended for the forging process. Additionally, nonlinear buckling simulation with the use of the finite element method is used to solve the misuse case of shock absorber compression, where the shape of the optimized part has a key role in the total strength of the automotive damper. All of that, together with the required design precision, creates the nontrivial constrained optimization problem solved using the parametric, implicit geometry representation and a combination of stochastic and deterministic algorithms used with parallel design processing. Two methods of optimization are examined and compared in terms of the total amount of function calls, final design mass, and feasibility of the resultant design. Also, the amount of parameters used for the implicit geometry representation is greatly reduced compared to existing schemes presented in the literature. The problem addressed in this article is strongly inspired by the actual industrial example of the mass minimization process, but it is more focused on the actual manufacturability of the resultant component and admissible solving time. Commercially accessible software combined with authors’ procedures is used to resolve the material distribution task, which makes the proposed method universal and easily adapted to other fields of the optimization of mechanical elements.

15

Direct least squares and derivative-free optimisation techniques for determining mine-induced horizontal ground displacement

Rusek Janusz, Tajduś Krzysztof

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2021

|

Vol. 69, nr 1

art. no. e135840

EN

The paper presents the results of analyses concerning a new approach to approximating trajectory of mining-induced horizontal displacements. Analyses aimed at finding the most effective method of fitting data to the trajectory of mining-induced horizontal displacements. Two variants were made. In the first, the direct least square fitting (DLSF) method was applied based on the minimization of the objective function defined in the form of an algebraic distance. In the second, the effectiveness of differential-free optimization methods (DFO) was verified. As part of this study, the following methods were tested: genetic algorithms (GA), differential evolution (DE) and particle swarm optimization (PSO). The data for the analysis were measurements of on the ground surface caused by the mining progressive work at face no. 698 of the German Prospel-Haniel mine. The results obtained were compared in terms of the fitting quality, the stability of the results and the time needed to carry out the calculations. Finally, it was found that the direct least square fitting (DLSF) approach is the most effective for the analyzed registration data base. In the authors’ opinion, this is dictated by the angular range in which the measurements within a given measuring point oscillated.

16

Archipelag sztucznej inteligencji. Część I

Tadeusiewicz Ryszard

Napędy i Sterowanie

|

2020

|

R. 22, nr 12

26--40

PL

Tytuł tego artykułu może budzić wątpliwości Czytelników. Sztuczna inteligencja? Wiadomo! Ale jakiś archipelag? Już wyjaśniam. Otóż sztuczna inteligencja tylko z nazwy jest dziedziną integralną, jak – nawiązując do tytułu miesięcznika – napędy albo sterowanie. W istocie sztuczna inteligencja to zbiór bardzo różnych metod, które ludzie wymyślili w tym celu, żeby maszyny lepiej zaspokajały ich potrzeby. Te metody w większości nie mają ze sobą nawzajem absolutnie nic wspólnego. Są od siebie odległe i nie ma łatwego sposobu przejścia od jednej z nich do innej. Pozwoliłem sobie porównać tę sytuację do archipelagu wysp.

17

Toward the best combination of optimization with fuzzy systems to obtain the best solution for the GA and PSO algorithms using parallel processing

Valdez Fevrier, Kawano Yunkio, Melin Patricia

Journal of Automation Mobile Robotics and Intelligent Systems

|

2020

|

Vol. 14, No. 1

55--64

EN

In general, this paper focuses on finding the best configuration for PSO and GA, using the different migration blocks, as well as the different sets of the fuzzy systems rules. To achieve this goal, two optimization algorithms were configured in parallel to be able to integrate a migration block that allow us to generate diversity within the subpopulations used in each algorithm, which are: the particle swarm optimization (PSO) and the genetic algorithm (GA). Dynamic parameter adjustment was also performed with a fuzzy system for the parameters within the PSO algorithm, which are the following: cognitive, social and inertial weight parameter. In the GA case, only the crossover parameter was modified.

18

A genetic algorithm for the maximum 2-packing set problem

Trejo-Sánchez Joel Antonio, Fajardo-Delgado Daniel, Gutierrez-Garcia J. Octavio

International Journal of Applied Mathematics and Computer Science

|

2020

|

Vol. 30, no. 1

173--184

EN

Given an undirected connected graph G = (V, E), a subset of vertices S is a maximum 2-packing set if the number of edges in the shortest path between any pair of vertices in S is at least 3 and S has the maximum cardinality. In this paper, we present a genetic algorithm for the maximum 2-packing set problem on arbitrary graphs, which is an NP-hard problem. To the best of our knowledge, this work is a pioneering effort to tackle this problem for arbitrary graphs. For comparison, we extended and outperformed a well-known genetic algorithm originally designed for the maximum independent set problem. We also compared our genetic algorithm with a polynomial-time one for the maximum 2-packing set problem on cactus graphs. Empirical results show that our genetic algorithm is capable of finding 2-packing sets with a cardinality relatively close (or equal) to that of the maximum 2-packing sets. Moreover, the cardinality of the 2-packing sets found by our genetic algorithm increases linearly with the number of vertices and with a larger population and a larger number of generations. Furthermore, we provide a theoretical proof demonstrating that our genetic algorithm increases the fitness for each candidate solution when certain conditions are met.

19

A novel feature biometric fusion approach for iris, speech and signature

Garg Mamta, Arora Ajat Shatru, Gupta Savita

Computer Methods in Materials Science

|

2020

|

Vol. 20, No. 2

63--71

EN

With an ever-increasing emphasis on security and the new dimensions in security challenges facing the world today, the need for automated personal identification/verification system based on multimodal biometrics has increased. This paper addresses the issue of multiple biometric fusion to enhance the security of recognition. The paper utilizes iris, speech,and signature for the novel fusion. A segregated classification mechanism for each biometric is also presented. The fusion is done on the base of features extracted at the time of individual classification of biometrics. Different feature extraction algorithms are applied for different biometrics. The paper has utilized 2-Dimensional Principle Component Analysis (2DPCA) for Iris, Scale Invariant Feature Transform (SIFT) for signature and Mel-frequency cepstral coefficients for speech biometric. This paper utilizes Genetic Algorithm for the optimization of the evaluated features. The classification is done using Artificial Neural Network (ANN).

PL

W związku z ciągłym wzrostem wymagań dotyczących bezpieczeństwa i nowymi wyzwaniami stojącymi dzisiaj w tym zakresie przed światem istnieje potrzeba tworzenia ststremów wykorzystujących biometrię multimodalną do automatycznej identyfikacji/weryfikacji osób. Artykuł opisuje problem zastosowania multimodalnej fuzji biometrycznej do poprawy bezpieczeństwa rozpoznawania osób. Do nowej fuzji wykorzystano tęczówkę, mowę i podpis. Zaprezentowano oddzielny mechanism dla każdego czynnika biometrycznego. Fuzję przeprowadzono wykorzystując cechy wybrane w danej chwili czasu indywidualnie dla każdego czynnika. Dla różnych czynników zastosowano różny algorytm wyboru cech biometrycznych. Zastosowano 2- wymiarową analizę podstawowych składników (ang. 2-Dimensional Principle Component Analysis - 2DPCA) dla tęczówki, skaloniezmiennicze przekształcenie cech (ang. Scale Invariant Feature Transform - SIFT) dla podpisu oraz parametry melcepstralne (ang. Mel-Frequency Cepstral Coefficients) dla mowy. W artykule wykorzystano metodę Algorytmów Genetycznych do optymalizacji oceny poszczególnych cech. Klasyfikację przeprowadzono wykorzystując sztuczne sieci neuronowe.

20

Feature selection for classification in Steady state visually evoked potentials (SSVEP)-based brain-computer interfaces with genetic algorithm

Karkosz Stanisław, Jukiewicz Marcin

Bio-Algorithms and Med-Systems

|

2020

|

Vol. 16, no. 2

art. no. 20200013

EN

Objectives: Optimization of Brain-Computer Interface by detecting the minimal number of morphological features of signal that maximize accuracy. Methods: System of signal processing and morphological features extractor was designed, then the genetic algorithm was used to select such characteristics that maximize the accuracy of the signal’s frequency recognition in offline Brain-Computer Interface (BCI). Results: The designed system provides higher accuracy results than a previously developed system that uses the same preprocessing methods, however, different results were achieved for various subjects. Conclusions: It is possible to enhance the previously developed BCI by combining it with morphological features extraction, however, it’s performance is dependent on subject variability.