Wyniki wyszukiwania - BazTech

1

Design of Low Power Thinned Smart Antenna for 6G Sky Connection

Khan Anindita, Roy Jibendu Sekhar

Journal of Telecommunications and Information Technology

|

2024

|

nr 1

26--33

EN

To improve radio access capability, sky connectionsrelying on satellites or unmanned aerial vehicles (UAV), as wellas high-altitude platforms (HAP) will be exploited in6G wirelesscommunication systems, complementing terrestrial networks.For long-distance communication, a large smart antenna will beused that is characterized by high amounts of power consumedby digital beamformers. This paper focuses on reducing powerconsumption by relying on a thinned smart antenna (TSA). Theperformance of TSA is investigated in the sub-6GHz band. Thedifferential evolution (DE) algorithm is used to optimize excita-tion weights of the individual dipoles in the antenna array andthese excitation weights are then used in TSA for beamforming,with signal processing algorithms deployed. The DE techniqueis used with the least mean square, recursive least square andsample matrix inversion algorithms. The proposed method of-fers almost the same directivity, simultaneously ensuring lowerside lobes (SLL) and reduced power consumption. For a TSAof20,31, and64dipoles, the power savings are20%,19.4%,and17.2%, respectively. SLL reductions achieved, in turn, varyfrom 5.2 dB to 8.1 dB.

2

An enhanced differential evolution algorithmwith adaptive weight bounds for efficient training ofneural networks

Limtrakul Saithip, Wetweerapong Jeerayut

Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska

|

2023

|

T. 13, nr 1

4--13

EN

Artificial neural networks are essential intelligent tools for various learning tasks. Training them is challenging due to the nature of the data set, many training weights, and their dependency, which gives rise to a complicated high-dimensional error function for minimization. Thus, global optimization methods have become an alternative approach. Many variants of differential evolution (DE) have been applied as training methods to approximate the weights of a neural network. However, empirical studies show that they suffer from generally fixed weight bounds. In this research, we propose an enhanced differential evolution algorithm with adaptive weight bound adjustment (DEAW) for the efficient training of neural networks. The DEAW algorithm uses small initial weight bounds and adaptive adjustment in the mutation process. It gradually extends the bounds when a component of a mutant vector reaches its limits. We also experiment with using several scales of an activation function with the DEAW algorithm. Then, we apply the proposed method with its suitable setting to solve function approximation problems. DEAW can achieve satisfactory results compared to exact solutions.

PL

Sztuczne sieci neuronowe są niezbędnymi inteligentnymi narzędziami do realizacji różnych zadań uczenia się. Ich szkolenie stanowi wyzwanie ze względu na charakter zbioru danych, wiele wag treningowych i ich zależności, co powoduje powstanie skomplikowanej, wielowymiarowej funkcji błędu do minimalizacji. Dlatego alternatywnym podejściem stały się metody optymalizacji globalnej. Wiele wariantów ewolucji różnicowej (DE) zostało zastosowanych jako metody treningowe do aproksymacji wag sieci neuronowej. Jednak badania empiryczne pokazują, że cierpią one z powodu ogólnie ustalonych granic wag. W tym badaniu proponujemy ulepszony algorytm ewolucji różnicowej z adaptacyjnym dopasowaniem granic wag (DEAW) dla efektywnego szkolenia sieci neuronowych. Algorytm DEAW wykorzystuje małe początkowe granice wag i adaptacyjne dostosowanie w procesie mutacji. Stopniowo rozszerza on granice, gdy składowa wektora mutacji osiąga swoje granice. Eksperymentujemy również z wykorzystaniem kilku skal funkcji aktywacji z algorytmem DEAW. Następnie, stosujemy proponowaną metodę z jej odpowiednim ustawieniem do rozwiązywania problemów aproksymacji funkcji. DEAW może osiągnąć zadowalające rezultaty w porównaniu z rozwiązaniami dokładnymi.

3

Shape identification of the jet-grouted column based on the thermal analysis and differential evolution

Wojciechowski Marek

Archives of Civil Engineering

|

2023

|

Vol. 69, nr 4

507--518

EN

In the paper, an indirect method for the identification of the final shape of the freshly executed jet-grouted column is developed. The method relies on the backward analysis of the temperatures measured inside the column, along the trace of the injecting pipe. Temperature changes in the column are caused by the hydration process of the cementitious grout. 2D axisymmetric unsteady heat conduction initial-boundary value problem is solved for finding the column shape which fits best the reference temperature measurements. The model of the column is solved using the finite element method. The search is performed using the global evolutionary optimization algorithm called differential evolution. It is shown that the proposed method can provide an accurate prediction of the column shape if only the model reflects the physical reality well. The advantage over previous results is that the cylindrical shape of the column does not have to be assumed anymore, and the full profile of the column along its length can be accurately identified.

PL

W artykule przedstawiono metodę identyfikacji kształtu świeżo wykonanej kolumny typu jet-grouting. Metoda polega na wstecznej analizie temperatur mierzonych wewnątrz kolumny, wzdłuż śladu żerdzi iniekcyjnej. Zmiany temperatur w kolumnie są wynikiem hydratacji zaczynu cementowego. W celu określenia kształtu kolumny, który najlepiej pasuje do referencyjnych pomiarów temperatur, wykorzystano globalny algorytm optymalizacyjny zwany ewolucją różnicową. W ramach tego algorytmu formułowano próbne problemy początkowo-brzegowe, w postaci dwuwymiarowego, osiowo-symetrycznego zagadnienia nieustalonego przewodzenia ciepła, które rozwiązywano za pomocą metody elementów skończonych. Wykazano, że proponowana metoda pozwala na dokładne odwzorowanie kształtu kolumny, jeśli tylko model numeryczny poprawnie odwzorowuje rzeczywistość fizyczną. Zaletą metody w porównaniu do wcześniejszych rezultatów jest możliwość identyfikacji zmian średnicy kolumny wzdłuż jej długości, a nie tylko identyfikacja pojedynczej średnicy przy założonym kształcie walcowym kolumny.

4

Calibration of conceptual rainfall-runoff models by selected differential evolution and particle swarm optimization variants

Napiorkowski Jaroslaw J., Piotrowski Adam P., Karamuz Emilia, Senbeta Tesfaye B.

Acta Geophysica

|

2023

|

Vol. 71, no. 5

2325--2338

EN

The performance of conceptual catchment runoff models may highly depend on the specific choice of calibration methods made by the user. Particle Swarm Optimization (PSO) and Differential Evolution (DE) are two well-known families of Evolutionary Algorithms that are widely used for calibration of hydrological and environmental models. In the present paper, five DE and five PSO optimization algorithms are compared regarding calibration of two conceptual models, namely the Swedish HBV model (Hydrologiska Byrans Vattenavdelning model) and the French GR4J model (modèle du Génie Rural à 4 paramètres Journalier) of the Kamienna catchment runoff. This catchment is located in the middle part of Poland. The main goal of the study was to find out whether DE or PSO algorithms would be better suited for calibration of conceptual rainfall-runoff models. In general, four out of five DE algorithms perform better than four out of five PSO methods, at least for the calibration data. However, one DE algorithm constantly performs very poorly, while one PSO algorithm is among the best optimizers. Large differences are observed between results obtained for calibration and validation data sets. Differences between optimization algorithms are lower for the GR4J than for the HBV model, probably because GR4J has fewer parameters to optimize than HBV.

5

Multiobjective optimiaztion of microstructure parameters in a thermoelastic porous material by means of differential evolution and elements of game theory

Długosz Adam, Schlieter Tomasz

Computer Methods in Materials Science

|

2022

|

Vol. 22, No. 3

117--124

EN

The paper is devoted to the optimization of the microstructure parameters of a porous medium under thermo-mechanical loading. Four different criteria related to the properties of the porous material have been proposed and numerically implemented. To solve a multiobjective problem, a novel method based on the coupling of differential evolution and elements of game theory is used. The proposed algorithm features an appropriate balance between exploration and exploitation of objective space, which is necessary for the successful optimization of these types of tasks with the use of numerical simulations. The model of the thermo-elastic porous material is composed of two-scale direct analysis based on a numerical homogenization. Direct thermoelastic analysis with representative volume element (RVE) and finite element method (FEM) is performed. Numerical example of the optimization illustrating the usefulness of the proposed method is included.

6

Novel optimization method for mobile magnetostatic shield and test applications

Ralf Patrick Alexander, Kreischer Christian

Archives of Electrical Engineering

|

2022

|

Vol. 71, nr 3

627--639

EN

This article provides an optimized solution to the problem of passive shielding against static magnetic fields with any number of spherical shells. It is known, that the shielding factor of a layered structure increases in contrast to a single shell with the same overall thickness. For the reduction of weight and cost by given material parameters and available space the best system for the layer positions has to be found. Because classic magnetically shielded rooms are very heavy, this system will be used to develop a transportable Zero-Gauss-Chamber. To handle this problem, a new way was developed, in which for the first time the solution with regard to shielding and weight was optimized. Therefore, a solution for the most general case of spherical shells was chosen with an adapted boundary condition. This solution was expanded to an arbitrary number of layers and permeabilities. With this analytic solution a differential evolution algorithm is able to find the best partition of the shells. These optimized solutions are verified by numerical solutions made by the Finite Element Method (FEM). After that the solutions of different raw data are determined and investigated.

7

Colour Difference Classification for Dyed Fabrics Based on Differential Evolution with Dynamic Parameter Selection to Optimise the Output Regularisation Extreme Learning Machine

Zhou Zhiyu, Liu Dexin, Zhang Jianxin, Zhu Zefei, Yang Donghe, Jiang Likai

Fibres & Textiles in Eastern Europe

|

2021

|

Vol. 29, no. 3 (147)

97--102

EN

A novel optimisation technique based on the differential evolution (DE) algorithm with dynamic parameter selection (DPS-DE) is proposed to develop a colour difference classification model for dyed fabrics, improve the classification accuracy, and optimise the output regularisation extreme learning machine (RELM). The technique proposed is known as DPS-DE-RELM and has three major differences compared with DE-ELM: (1) Considering that the traditional ELM provides an illness solution based on the output weights, DE is proposed to optimise the output of the RELM. (2) Considering the simple parameter setting of the traditional algorithm, the DE algorithm with DPS is adopted. (3) For DPS, an optimal range of parameters is chosen, and the efficiency of the algorithm is significantly improved. This study analyses the colour difference classification of fabric images captured under standard lighting based on the DPS-DE-RELM algorithm. First, the colour difference of the fabric images is calculated and six color-difference-related features extracted, and second the features are classified into five different levels based on the perception of humans. Finally, a colour difference classification model is built based on the DPS-DERELM algorithm, and then the optimal classification model suitable for this study is selected. The experimental results show that the output method with regularisation parameters can achieve a maximum classification accuracy of 98.87%, which is higher compared with the aforementioned optimised original ELM algorithm, which can achieve a maximum accuracy of 84.67%. Therefore, the method proposed has the advantages of greater convergence speed, high classification accuracy, and robustness.

PL

W pracy zaproponowano nowatorską technikę optymalizacji opartą na algorytmie ewolucji różnicowej (DE) z doborem parametrów (DPS-DE) w celu opracowania modelu klasyfikacji różnicy kolorów dla tkanin barwionych, poprawy dokładności klasyfikacji i optymalizacji regularyzacji wyjściowej maszyny do uczącej się (RELM). Zaproponowana technika jest znana jako DPS-DE-RELM i cechuje się trzema głównymi różnicami w porównaniu do DE-ELM: (1) Biorąc pod uwagę, że tradycyjny ELM zapewnia rozwiązanie w oparciu o wagi wyjściowe, proponuje się DE w celu optymalizacji wydajności RELM. (2) Biorąc pod uwagę proste ustawienie parametrów tradycyjnego algorytmu, przyjęto algorytm DE z DPS. (3) W przypadku DPS wybierany jest optymalny zakres parametrów, a wydajność algorytmu znacznie się poprawia. Podczas badania przeanalizowano klasyfikację różnic kolorów obrazów tkanin zarejestrowanych w standardowym oświetleniu w oparciu o algorytm DPS-DE-RELM. Po pierwsze, obliczono różnicę kolorów obrazów tkanin i wyodrębniono sześć cech związanych z różnicą kolorów, a po drugie cechy te zaklasyfikowano na pięciu różnych poziomach w oparciu o percepcję ludzi. Na koniec zbudowano model klasyfikacji różnicy kolorów w oparciu o algorytm DPS-DE-RELM, a następnie wybrano optymalny model klasyfikacji odpowiedni do tego badania. Wyniki eksperymentalne pokazały, że metoda wyjściowa z parametrami regularyzacji może osiągnąć maksymalną dokładność klasyfikacji wynoszącą 98,87%, czyli wyższą w porównaniu z zoptymalizowanym oryginalnym algorytmem ELM, który może osiągnąć maksymalną dokładność na poziomie 84,67%. Stwierdzono, że zaproponowana metoda niesie ze sobą korzyści w postaci większej szybkości zbieżności, wysokiej dokładności klasyfikacji i odporności.

8

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.

9

Parameter determination of a solar cell model using differential evolution algorithm

Sredenšek Klemen, Seme Sebastijan

Przegląd Elektrotechniczny

|

2019

|

R. 95, nr 1

165--168

EN

This paper deals with determination of a double diode model parameters using the differential evolution algorithm. The importance of this method is the implementation of ohmic and shadow losses. Performance of the proposed approach shows high potential as a promising determination method for solar cell parameters.

PL

Przedmiotem artykułu jest określenie parametrów modelu z podwójną diodą przy wykorzystaniu ewolucyjnego algorytmu różniczkowego. Ważność tej metody tkwi w implementacji strat omowych i strat z zacienienia. Działanie zaproponowanego podejścia pokazuje jego duże możliwości w wyznaczaczaniu parametrów modułu fotowoltaicznego.

10

Determination of the photovoltaic system efficiency using the optimization method

Sredenšek Klemen, Štumberger Bojan, Hadžiselimović Miralem, Seme Sebastijan

Przegląd Elektrotechniczny

|

2019

|

R. 95, nr 12

216--219

EN

This paper deals with determination of photovoltaic system efficiency using the differential evolution algorithm. The significance of this method is to determine the efficiency of the photovoltaic system, taking into account the solar irradiance, photovoltaic module temperature and the air mass factor. The aim of the paper is to determine the functional dependence of the overall efficiency of photovoltaic system, efficiency of the PV module and efficiency of DC/AC inverter under real working conditions using the differential evolution algorithm. The results in this paper show that the smallest deviation is achieved by considering all three variables in the calculation of efficiency.

PL

Artykuł dotyczy określenia wydajności układu fotowoltaicznego przy użyciu algorytmu ewolucji różnicowej. Znaczenie tej metody polega na określeniu wydajności układu fotowoltaicznego z uwzględnieniem natężenia promieniowania słonecznego, temperatury modułu fotowoltaicznego i współczynnika masy powietrza. Celem artykułu jest określenie zależności funkcjonalnej ogólnej wydajności układu fotowoltaicznego, wydajności modułu fotowoltaicznego i wydajności falownika DC / AC w rzeczywistych warunkach pracy z wykorzystaniem algorytmu ewolucji różnicowej. Zgodnie z osiągniętymi wynikami najmniejsze odchylenie osiąga się, biorąc pod uwagę wszystkie trzy zmienne w obliczeniach wydajności.

11

Solution of linear and non-linear boundary value problems using population-distributed parallel differential evolution

Nasim Amnah, Burattini Laura, Fateh Muhammad Faisal, Zameer Aneela

Journal of Artificial Intelligence and Soft Computing Research

|

2019

|

Vol. 9, No. 3

205--218

EN

Cases where the derivative of a boundary value problem does not exist or is constantly changing, traditional derivative can easily get stuck in the local optima or does not factually represent a constantly changing solution. Hence the need for evolutionary algorithms becomes evident. However, evolutionary algorithms are compute-intensive since they scan the entire solution space for an optimal solution. Larger populations and smaller step sizes allow for improved quality solution but results in an increase in the complexity of the optimization process. In this research a population-distributed implementation for differential evolution algorithm is presented for solving systems of 2nd-order, 2-point boundary value problems (BVPs). In this technique, the system is formulated as an optimization problem by the direct minimization of the overall individual residual error subject to the given constraint boundary conditions and is then solved using differential evolution in the sense that each of the derivatives is replaced by an appropriate difference quotient approximation. Four benchmark BVPs are solved using the proposed parallel framework for differential evolution to observe the speedup in the execution time. Meanwhile, the statistical analysis is provided to discover the effect of parametric changes such as an increase in population individuals and nodes representing features on the quality and behavior of the solutions found by differential evolution. The numerical results demonstrate that the algorithm is quite accurate and efficient for solving 2nd-order, 2-point BVPs.

12

Optimization of the inverted pendulum controller with friction compensation by means of the new method of Lyapunov exponents estimation

Balcerzak M.

Mechanics and Mechanical Engineering

|

2018

|

Vol. 22, nr 4

959--965

EN

This text covers optimization of an inverted pendulum control system with friction compensator. The control system is tuned with respect to a performance index based on the novel method of the Largest Lyapunov Exponent estimation. The detailed description of the method is provided. Model of the control object is presented. A simple controller is proposed. Two control systems are compared: the one with compensator and the one without. Parameters of both controllers are optimized with respect to the novel criterion by means of the Differential Evolution method. Results of numerical simulations are presented. It is shown that the new criterion can be successfully applied to both: typical linear regulators and controllers with compensators.

13

Optimal control of an inverted pendulum based on the new method of Lyapunov exponents estimation

Balcerzak M.

Mechanics and Mechanical Engineering

|

2018

|

Vol. 22, nr 1

25--32

EN

This text covers optimization of an inverted pendulum control system according to the new control performance assessment criterion based on the optimal control theory. The novel control performance index is founded on the method of the Largest Lyapunov Exponent estimation. The detailed description of the new method is provided. Model of the control object is presented. A simple controller is proposed. Parameters of the controller are optimized with respect to the novel criterion by means of the Differential Evolution method. Results of numerical simulations are presented. It is shown that the new criterion can be successfully applied when the regulation time is crucial, whereas somewhat larger overshoot is acceptable.

14

Automatic calibration and sensitivity analysis of DISPRIN model parameters: A case study on Lesti watershed in East Java, Indonesia

Sulianto, Bisri M., Limantara L. M., Sisinggih D.

Journal of Water and Land Development

|

2018

|

no. 37

141--152

EN

The Dee Investigation Simulation Program for Regulating Network (DISPRIN) model consists of eight tanks that are mutually interconnected. It contains 25 parameters involved in the process of transforming rainfall into runoff data. This complexity factor is the appeal to be explored in order to more efficiently. Parameterization process in this research is done by using Differential Evolution (DE) algorithm while parameters sensitivity analysis is done by using Monte Carlo simulation method. Software application models of merging the two concepts are called DISPRIN25-DE model and compiled using code program M-FILE from MATLAB. Results of research on Lesti watershed at the control point Tawangrejeni automatic water level recorder (AWLR) station (319.14 km2) in East Java Indonesia indicate that the model can work effectively for transforming rainfall into runoff data series. Model performance at the calibration stage provide value of NSE = 0.871 and PME = 0.343 while in the validation stage provide value of NSE = 0.823 and PME = 0.180. Good performance in the calibration process indicates that DE algorithm is able to solve problems of global optimization of the equations system with a large number of variables. The results of the sensitivity analysis of 25 parameters showed that 3 parameters have a strong sensitivity level, 7 parameters with a medium level and 15 other parameters showed weak sensitivity level to performance of DISPRIN model.

PL

Model DISPRIN składa się z ośmiu zbiorników wzajemnie ze sobą połączonych. Zawiera 25 parametrów zaangażowanych w proces transformacji danych opadowych w dane odpływu. Ten czynnik złożoności skłania do podjęcia badań celem zwiększenia wydajności. W badaniach prezentowanych w niniejszej pracy proces parametryzacji zrealizowano, stosując algorytm zróżnicowanej ewolucji (DE), podczas gdy analizę czułości przeprowadzono z użyciem metody symulacji Monte Carlo. Modele aplikacji polegające na łączeniu dwóch koncepcji nazywane są DISPRIN25-DE i są kompilowane za pomocą programu M-FILE z MATLAB. Wyniki badań zlewni Lesti (319,14 km2) w punkcie kontrolnym stacji Tawangrejeni z automatycznym pomiarem poziomu wody w prowincji Jawa Wschodnia w Indonezji wskazują, że model może efektywnie działać w celu przekształcenia opadów w serie danych o odpływie. Na etapie kalibracji model dostarczył wartości NSE = 0,871 i PME = 0,343, a na etapie walidacji wartości NSE = 0.823 i PME = 0,180. Dobre rezultaty w procesie kalibracji wskazują, że algorytm DE jest zdolny rozwiązywać problemy globalnej optymalizacji systemu równań z dużą liczbą zmiennych. Wyniki analizy czułości 25 parametrów wykazały, że 3 parametry mają wysoką czułość, 7 – pośrednią, a 15 innych parametrów cechuje niski poziom czułości na zachowanie modelu DISPRIN.

15

Effect of strategy adaptation on differential evolution in presence and absence of parameter adaptation: an investigation

Dawar D., Ludwig S. A.

Journal of Artificial Intelligence and Soft Computing Research

|

2018

|

Vol. 8, No. 3

211--235

EN

Differential Evolution (DE) is a simple, yet highly competitive real parameter optimizer in the family of evolutionary algorithms. A significant contribution of its robust performance is attributed to its control parameters, and mutation strategy employed, proper settings of which, generally lead to good solutions. Finding the best parameters for a given problem through the trial and error method is time consuming, and sometimes impractical. This calls for the development of adaptive parameter control mechanisms. In this work, we investigate the impact and efficacy of adapting mutation strategies with or without adapting the control parameters, and report the plausibility of this scheme. Backed with empirical evidence from this and previous works, we first build a case for strategy adaptation in the presence as well as in the absence of parameter adaptation. Afterwards, we propose a new mutation strategy, and an adaptive variant SA-SHADE which is based on a recently proposed self-adaptive memory based variant of Differential evolution, SHADE. We report the performance of SA-SHADE on 28 benchmark functions of varying complexity, and compare it with the classic DE algorithm (DE/Rand/1/bin), and other state-of-the-art adaptive DE variants including CoDE, EPSDE, JADE, and SHADE itself. Our results show that adaptation of mutation strategy improves the performance of DE in both presence, and absence of control parameter adaptation, and should thus be employed frequently.

16

Optimum placement of multi type DG units for loss reduction in a radial distribution system considering the distributed generation

Shanmugapriyan J., Karuppiah N., Muthubalaji S., Tamilselvi S.

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2018

|

Vol. 66, nr 3

345--354

EN

Due to the increasing need for electricity, insertion of distributed generation (DG) into a distribution system attracts the attention of the deregulated power market. Placing DG in the distribution system inherently reduces the power loss and improves the system voltage profile. The choice of DG, proper placement and sizing of DG all play a vital role. This paper presents an effective methodology to identify the optimum location of multi type DG in the distribution system. The particle swarm optimization (PSO) algorithm and differential evolution (DE) are applied to identify the proper location and size of DG using the distributed generation suitability index (DGSI). The optimum location of DG is identified through DGSI and optimum sizing is done by means of the power loss minimization technique using evolutionary algorithms. The effective power loss reduction and improved system voltage profile are evaluated using sixteen combinations of different types of DGs with the standard IEEE 33-bus test system. The results reveal that power loss reduction and voltage profile improvement are effectively addressed by the DE algorithm.

17

Accurate prediction of continuous blood glucose based on support vector regression and differential evolution algorithm

Hamdi T., Ben Ali J., Di Costanzo V., Fnaiech F., Moreau E., Ginoux J. M.

Biocybernetics and Biomedical Engineering

|

2018

|

Vol. 38, no. 2

362--372

EN

Type 1 diabetes (T1D) is a chronic disease requiring patients to know their blood glucose values in order to ensure blood glucose levels as close to normal as possible. Hence, the ability to predict blood glucose levels is of a great interest for clinical researchers. In this sense, the literature is rich with several solutions that can predict blood glucose levels. Unfortunately, these methods require the patient to specific their daily activities: meal intake, insulin injection and emotional factors, which can be error prone. To reduce this burden on the patent, this work proposes to use only continuous glucose monitoring (CGM) data to predict blood glucose levels independently of other factors. To support this, support vector regression (SVR) and differential evolution (DE) algorithms were investigated. The proposed method is validated using real CGM data of 12 patients. The obtained average of root mean square error (RMSE) was 9.44, 10.78, 11.82 and 12.95 mg/dL for prediction horizon (PH) respectively equal to 15, 30, 45 and 60 min. The results of the present study and comparison with some previous works show that the proposed method holds promise. The SVR based on DE algorithm achieved high prediction accuracy while being robustness, automatic, and requiring no human intervention.

18

NURBS-based optimization of natural frequencies for bidirectional functionally graded beams

Kim N. I., Huynh T. A., Lieu Q. X., Lee J.

Archives of Mechanics

|

2018

|

Vol. 70, nr 4

337--364

EN

In this study, the nurbs-based isogeometric analysis is developed to optimize natural frequencies of bidirectional functionally graded (BFG) beams by tailoring their material distribution. One-dimensional Non-Uniform Rational B-Spline (NURBS) basis functions are utilized to construct the geometry of beam as well as approximate solutions, whereas the gradation of material property is represented by two-dimensional basis functions. To optimize the material composition, the spatial distribution of volume fractions of material constituents is defined using the higher order interpolation of volume fraction values that are specified at a finite number of control points. As an optimization algorithm, the differential evolution (DE) algorithm is employed to optimize the volume fraction distribution that maximizes each of the first three natural frequencies of BFG beams. A numerical analysis is performed on the examples of BFG beams with various boundary conditions and slenderness ratios. The obtained results are compared with the previously published results in order to show the accuracy and effectiveness of the present approach. The effects of number of elements, boundary conditions and slenderness ratios on the optimized natural frequencies of BFG beams are investigated.

19

Nature Inspired Techniques for Interference Management in Femtocells: A Survey

Deshmukh Shradha, Madankar Mangala

Annals of Computer Science and Information Systems

|

2017

|

Vol. 10

157--160

EN

In the wireless communication system the transmitter and receiver close to each other to improve the data rates and capacity. Therefore, the wireless networks are more popular than the traditional wired services. In the wireless networks, to cover cells the low power nodes such as macrocells, picocells, femtocells base stations (BSs) deployed to improve the indoor coverage. The femtocell base station reduces operators operational cost, maintainance and infrastructure. At the time of femtocell deployment, the femtocell base station deal with a number of technical challenges, among those all the interference management is more important. In femtocell network, one femtocell creates the interference to its neighboring femtocells.To deal with interference management challenge number of researchers have suggested different types of solutions. The survey shows that nature inspired metaheuristic algorithm has the powerful impact on interference cancellation and avoidance.This survey paper focuses on bat algorithm for the resource allocation problem in a femtocell.

20

The training of multiplicative neuron model based artificial neural networks with differential evolution algorithm for forecasting

Bas E.

Journal of Artificial Intelligence and Soft Computing Research

|

2016

|

Vol. 6, No. 1

5--11

EN

In recent years, artificial neural networks have been commonly used for time series forecasting by researchers from various fields. There are some types of artificial neural networks and feed forward artificial neural networks model is one of them. Although feed forward artificial neural networks gives successful forecasting results they have a basic problem. This problem is architecture selection problem. In order to eliminate this problem, Yadav et al. (2007) proposed multiplicative neuron model artificial neural network. In this study, differential evolution algorithm is proposed for the training of multiplicative neuron model for forecasting. The proposed method is applied to two well-known different real world time series data.