Wyniki wyszukiwania - BazTech

1

Enhanced decision tree induction using evolutionary techniques for Parkinson’s disease classification

Ghane Mostafa, Ang Mei Choo, Nilashi Mehrbakhsh, Sorooshian Shahryar

Biocybernetics and Biomedical Engineering

|

2022

|

Vol. 42, no. 3

902--920

EN

The diagnosis of Parkinson’s disease (PD) is important in neurological pathology for appropriate medical therapy. Algorithms based on decision tree induction (DTI) have been widely used for diagnosing PD through biomedical voice disorders. However, DTI for PD diagnosis is based on a greedy search algorithm which causes overfitting and inferior solutions. This paper improved the performance of DTI using evolutionary-based genetic algorithms. The goal was to combine evolutionary techniques, namely, a genetic algorithm (GA) and genetic programming (GP), with a decision tree algorithm (J48) to improve the classification performance. The developed model was applied to a real biomedical dataset for the diagnosis of PD. The results showed that the accuracy of the J48, was improved from 80.51% to 89.23% and to 90.76% using the GA and GP, respectively.

2

Genetic programming based identification of an overhead crane

Kusznir Tom, Smoczek Jarosław

Journal of KONBiN

|

2021

|

Vol. 51, iss. 3

123-133

EN

Overhead cranes carry out an important function in the transportation of loads in industry. The ability to transport a payload quickly and accurately without excessive oscillations could reduce the chance of accidents as well as increase productivity. Accurate modelling of the crane system dynamics reduces the plant-model mismatch which could improve the performance of model-based controllers. In this work the simulation model to be identified is developed using the Euler-Lagrange method with friction. A 5-step ahead predictor, as well as a 10-step ahead predictor, are obtained using multi-gene genetic programming (MGGP) using input-output data. The weights of the genes are obtained by using least squares. The results of 15 different genetic programming runs are plotted on a complexity-mean square error graph with the Pareto optimal solutions shown.

PL

Suwnice pomostowe pełnią istotną funkcję w transporcie technologicznym w różnych obszarach przemysłu. Podniesienie wydajności i zapewnienie bezpiecznej realizacji zadań transportowych przez suwnice wymaga zastosowania skutecznych układów sterowania. Opracowanie dokładnego modelu dynamiki suwnicy jest istotnym elementem projektowania systemu sterowania, w szczególności sterowania predykcyjnego. W niniejszej pracy wykorzystano programowanie genetyczne MGGP oraz metodę najmniejszych kwadratów do identyfikacji modeli predykcji pozycji i kąta wychylenia ładunku przemieszczanego przez suwnicę. W rezultacie przeprowadzonych badań uzyskano modele 5- i 10-krokowej predykcji dla modelu suwnicy wyprowadzonego z równań Eulera-Lagrange’a. Wyniki poddano analizie wielokryterialnej z uwzględnieniem złożoności modelu i błędu średniokwadratowego w celu wyznaczenia rozwiązania optymalnego w sensie Pareto.

3

Evolutionary data driven modelling and many objective optimization of non linear noisy data in the blast furnace iron making process

Mahanta Bashista Kumar, Chakraborti Nirupam

Computer Methods in Materials Science

|

2021

|

Vol. 21, No. 3

163--175

EN

Optimization of process parameters in modern blast furnace operation, where both control and accessing large data set with multiple variables and objectives is a challenging task. To handle such non-linear and noisy data set deep learning techniques have been used in recent time. In this study an evolutionary deep neural network algorithm (EvoDN2) has been applied to derive a data driven model for blast furnace. The optimal front generated from deep neural network is compared against the optimal models developed from bi-objective genetic programming algorithm (BioGP) and evolutionary neural network (EvoNN). The optimization process is applied to all the training models by using constraint based reference vector evolutionary algorithm (cRVEA).

4

Drought classification using gradient boosting decision tree

Danandeh Mehr Ali

Acta Geophysica

|

2021

|

Vol. 69, no. 3

909--918

EN

This paper compares the classification and prediction capabilities of decision tree (DT), genetic programming (GP), and gradient boosting decision tree (GBT) techniques for one-month ahead prediction of standardized precipitation index in Ankara province and standardized precipitation evaporation index in central Antalya region. The evolved models were developed based on multi-station prediction scenarios in which observed (reanalyzed) data from nearby stations (grid points) were used to predict drought conditions in a target location. To tackle the rare occurrence of extreme dry/wet conditions, the drought series at the target location was categorized into three classes of wet, normal, and dry events. The new models were trained and validated using the frst 70% and last 30% of the datasets, respectively. The results demonstrated the promising performance of GBT for meteorological drought classification. It provides better performance than DT and GP in Ankara; however, GP predictions for Antalya were more accurate in the testing period. The results also exhibited that the proposed GP model with a scaled sigmoid function at root can efortlessly classify and predict the number of dry, normal, and wet events in both case studies.

5

Computational Intelligence for Life Sciences

Besozzi Daniela, Manzoni Luca, Nobile Marco S., Spolaor Simone, Castelli Mauro, Vanneschi Leonardo, Cazzaniga Paolo, Ruberto Stefano, Rundo Leonardo, Tangherloni Andrea

Fundamenta Informaticae

|

2020

|

Vol. 171, nr 1-4

57--80

EN

Computational Intelligence (CI) is a computer science discipline encompassing the theory, design, development and application of biologically and linguistically derived computational paradigms. Traditionally, the main elements of CI are Evolutionary Computation, Swarm Intelligence, Fuzzy Logic, and Neural Networks. CI aims at proposing new algorithms able to solve complex computational problems by taking inspiration from natural phenomena. In an intriguing turn of events, these nature-inspired methods have been widely adopted to investigate a plethora of problems related to nature itself. In this paper we present a variety of CI methods applied to three problems in life sciences, highlighting their effectiveness: we describe how protein folding can be faced by exploiting Genetic Programming, the inference of haplotypes can be tackled using Genetic Algorithms, and the estimation of biochemical kinetic parameters can be performed by means of Swarm Intelligence. We show that CI methods can generate very high quality solutions, providing a sound methodology to solve complex optimization problems in life sciences.

6

Enhancing island model genetic programming by controlling frequent trees

Ono Keiko, Hanada Yoshiko, Kumano Masahito, Kimura Masahiro

Journal of Artificial Intelligence and Soft Computing Research

|

2019

|

Vol. 9, No. 1

51--65

EN

In evolutionary computation approaches such as genetic programming (GP), preventing premature convergence to local minima is known to improve performance. As with other evolutionary computation methods, it can be difficult to construct an effective search bias in GP that avoids local minima. In particular, it is difficult to determine which features are the most suitable for the search bias, because GP solutions are expressed in terms of trees and have multiple features. A common approach intended to local minima is known as the Island Model. This model generates multiple populations to encourage a global search and enhance genetic diversity. To improve the Island Model in the framework of GP, we propose a novel technique using a migration strategy based on textit frequent trees and a local search, where the frequent trees refer to subtrees that appear multiple times among the individuals in the island. The proposed method evaluates each island by measuring its activation level in terms of the fitness value and how many types of frequent trees have been created. Several individuals are then migrated from an island with a high activation level to an island with a low activation level, and vice versa. The proposed method also combines strong partial solutions given by a local search. Using six kinds of benchmark problems widely adopted in the literature, we demonstrate that the incorporation of frequent tree information into a migration strategy and local search effectively improves performance. The proposed method is shown to significantly outperform both a typical Island Model GP and the aged layered population structure method.

7

Computational intelligence for predicting biological effects of drug absorption in lungs

Pacławski Adam, Szlęk Jakub, Mendyk Aleksander

Computer Science

|

2019

|

Vol. 20 (1)

99--121

EN

Recently, the lungs have been extensively examined as a route for delivering drugs (active pharmaceutical ingredients, APIs) into the bloodstream; this is mainly due to the possibility of the noninvasive administration of macromolecules such as proteins and peptides. The absorption mechanisms of chemical compounds in the lungs are still not fully understood, which makes pulmonary formulation composition development challenging. This manuscript presents the development of an empirical model capable of predicting the excipients’ influence on the absorption of drugs in the lungs. Due to the complexity of the problem and the not-fully-understood mechanisms of absorption, computational intelligence tools were applied. As a result, a mathematical formula was established and analyzed. The normalized root-mean-squared error (NRMSE) and R2 of the model were 4.57%, and 0.83, respectively. The presented approach is beneficial both practically by developing an in silico predictive model and theoretically by gaining knowledge of the influence of APIs and excipient structure on absorption in the lungs.

8

Development and analysis of a cryptographic algorithm for genetically optimized wireless sensor

Benjamim X. C., Gama F., Semente R. O., Villarrea E., Salazar A.

Przegląd Elektrotechniczny

|

2018

|

R. 94, nr 8

79--84

EN

This article proposes a methodology for obtaining a cryptographic algorithm, optimized for wireless sensor networks, through genetic algorithm. With the objective of increasing the level of security, computational efficiency and highlighting the energy consumption, considering that the autonomy of the wireless sensor devices is directly influenced by this factor. In aptitude function of genetic algorithm, were used metrics of algorithm runtime, maximum deviation and irregular, space occupied in memory and correlation coefficient (a new proposed metric), in order to find a safe and fast algorithm. The results obtained through computational simulations show the efficiency of the proposed methodology, in terms of processing time, coefficient of correlation and occupation of memory.

PL

W tym artykule zaproponowano metodologię uzyskiwania algorytmu kryptograficznego, zoptymalizowanego dla bezprzewodowych sieci czujników, za pomoca˛ algorytmu genetycznego. W celu zwiększenia poziomu bezpieczeństwa, wydajności obliczeniowej i podkreślenia zużycia energii, biorąc pod uwagę fakt, że ten czynnik ma bezposśredni wpływ na autonomię bezprzewodowych czujników. W funkcji uzdatniania algorytmu genetycznego wykorzystano metryki czasu pracy algorytmu, maksymalnego odchylenia i nieregularności, miejsca zajmowanego w pamięci i współczynnika korelacji (nowa proponowana metryka), aby znaleźć bezpieczny i szybki algorytm. Wyniki uzyskane za pomocą symulacji obliczeniowych pokazują efektywność proponowanej metodologii, pod względem czasu przetwarzania, współczynnika korelacji i zajęcia pamięci.

9

Adaptive test selection for factorization-based surrogate fitness in genetic programming

Krawiec K., Liskowski P.

Foundations of Computing and Decision Sciences

|

2017

|

Vol. 42, No. 4

339--358

EN

Genetic programming (GP) is a variant of evolutionary algorithm where the entities undergoing simulated evolution are computer programs. A fitness function in GP is usually based on a set of tests, each of which defines the desired output a correct program should return for an exemplary input. The outcomes of interactions between programs and tests in GP can be represented as an interaction matrix, with rows corresponding to programs in the current population and columns corresponding to tests. In previous work, we proposed SFIMX, a method that performs only a fraction of interactions and employs non-negative matrix factorization to estimate the outcomes of remaining ones, shortening GP’s runtime. In this paper, we build upon that work and propose three extensions of SFIMX, in which the subset of tests drawn to perform interactions is selected with respect to test difficulty. The conducted experiment indicates that the proposed extensions surpass the original SFIMX on a suite of discrete GP benchmarks.

10

An analysis of the performance of genetic programming for realised volatility forecasting

Yin Z., O’Sullivan C., Brabazon A.

Journal of Artificial Intelligence and Soft Computing Research

|

2016

|

Vol. 6, No. 3

155--172

EN

Traditionally, the volatility of daily returns in financial markets is modeled autoregressively using a time-series of lagged information. These autoregressive models exploit stylised empirical properties of volatility such as strong persistence, mean reversion and asymmetric dependence on lagged returns. While these methods can produce good forecasts, the approach is in essence atheoretical as it provides no insight into the nature of the causal factors and how they affect volatility. Many plausible explanatory variables relating market conditions and volatility have been identified in various studies but despite the volume of research, we lack a clear theoretical framework that links these factors together. This setting of a theory-weak environment suggests a useful role for powerful model induction methodologies such as Genetic Programming (GP). This study forecasts one-day ahead realised volatility (RV) using a GP methodology that incorporates information on market conditions including trading volume, number of transactions, bid-ask spread, average trading duration (waiting time between trades) and implied volatility. The forecasting performance from the evolved GP models is found to be significantly better than those numbers of benchmark forecasting models drawn from the finance literature, namely, the heterogeneous autoregressive (HAR) model, the generalized autoregressive conditional heteroscedasticity (GARCH) model, and a stepwise linear regression model (SR). Given the practical importance of improved forecasting performance for realised volatility this result is of significance for practitioners in financial markets.

11

Forecasting the oecd fixed broadband penetration with genetic programming method, diffusion models and macro-economic indicators

Salpasaranis K., Stylianakis V.

Image Processing & Communications

|

2016

|

Vol. 21, no. 1

45--54

EN

This paper presents the implementation of a modiﬁed Genetic Programming (GP) metod in for casting ﬁxed broadband telecommunications penetration percentage in Organisation for Economic Co-operation and Development (OECD) countries. The speciﬁc GP method combines the use of known diffusion models for technological forecasting purposes, such as Logistic, Gompertz and Bass and the GP. The combination method produces both time dependant and causal models with high performance statistical indicators. Also, multiple approaches to forecasting can be implemented, mainly with no big datasets.

12

Is depth information and optical flow helpful for visual control?

Hansen J., Ebner M.

Bio-Algorithms and Med-Systems

|

2016

|

Vol. 12, no. 1

9--18

EN

The human visual system was shaped through natural evolution. We have used artificial evolution to investigate whether depth information and optical flow are helpful for visual control. Our experiments were carried out in simulation. The task was controlling a simulated racing car. We have used The Open Racing Car Simulator for our experiments. Genetic programming was used to evolve visual algorithms that transform input images (color, optical flow, or depth information) to control commands for a simulated racing car. We found that significantly better solutions were found when color, depth, and optical flow were available as input together compared with color, depth, or optical flow alone.

13

Cross-task code reuse in genetic programming applied to visual learning

Jaśkowski W., Krawiec K., Wieloch B.

International Journal of Applied Mathematics and Computer Science

|

2014

|

Vol. 24, no. 1

183--197

EN

We propose a method that enables effective code reuse between evolutionary runs that solve a set of related visual learning tasks. We start with introducing a visual learning approach that uses genetic programming individuals to recognize objects. The process of recognition is generative, i.e., requires the learner to restore the shape of the processed object. This method is extended with a code reuse mechanism by introducing a crossbreeding operator that allows importing the genetic material from other evolutionary runs. In the experimental part, we compare the performance of the extended approach to the basic method on a real-world task of handwritten character recognition, and conclude that code reuse leads to better results in terms of fitness and recognition accuracy. Detailed analysis of the crossbred genetic material shows also that code reuse is most profitable when the recognized objects exhibit visual similarity.

14

Evaluation of liquefaction potential of soil based on standard penetration test using multi-gene genetic programming model

Muduli P.K, Das S.K.

Acta Geophysica

|

2014

|

Vol. 62, no. 3

529--543

EN

This paper discusses the evaluation of liquefaction potential of soil based on standard penetration test (SPT) dataset using evolutionary artificial intelligence technique, multi-gene genetic programming (MGGP). The liquefaction classification accuracy (94.19%) of the developed liquefaction index (LI) model is found to be better than that of available artificial neural network (ANN) model (88.37%) and at par with the available support vector machine (SVM) model (94.19%) on the basis of the testing data. Further, an empirical equation is presented using MGGP to approximate the unknown limit state function representing the cyclic resistance ratio (CRR) of soil based on developed LI model. Using an independent database of 227 cases, the overall rates of successful prediction of occurrence of liquefaction and non-liquefaction are found to be 87, 86, and 84% by the developed MGGP based model, available ANN and the statistical models, respectively, on the basis of calculated factor of safety (Fs) against the liquefaction occurrence. Key words: liquefaction index, standard penetration test, limits state function, artificial intelligence, multi-gene genetic programming, factor of safety

15

Ocena podobieństwa drzew strategii generowanych za pomocą programowania genetycznego

Lach E., Hetman M.

Studia Informatica

|

2013

|

Vol. 34, nr 1

75--89

PL

W pracy zaprezentowano nowy algorytm oceny stopnia podobieństwa drzew strategii, opisujących zachowanie trójwymiarowych postaci wirtualnych. Algorytm został użyty w trakcie automatycznego generowania strategii postaci, za pomocą programowania genetycznego w celu otrzymania bardziej zróżnicowanych populacji strategii z większą liczbą dostępnych ścieżek poszukiwań.

EN

The paper proposes new algorithm for measuring a similarity of strategy trees, describing behaviors of the three-dimensional virtual characters. The obtain measure is used in automatic generation of characters’ strategies by means of genetic programming. The aim of the algorithm is to create more diversified populations with many different paths to explore.

16

Hindcasting global temperature by evolutionary computation

Stanisławska K., Kundzewicz Z. W., Krawiec K.

Acta Geophysica

|

2013

|

Vol. 61, no. 3

732--751

EN

Interpretation of changes of global temperature is important for our understanding of the climate system and for our confidence in projections for the future. Massive efforts have been devoted to improve the accuracy of reproducing the global temperature by the available climate models, but the hindcasts are still inaccurate. Notwithstanding the need to further advance climate models, one may consider data-driven approaches, providing practically useful results in a simpler and faster way. Without assuming any prior knowledge about physics and without imposing a model structure that encapsulates the existing knowledge about the underlying processes, we hindcast global temperature by automatically identified evolutionary computation models. We use 60 years of records of global temperature and climate drivers, with training and testing periods being 1950–1999 and 2000–2009, respectively. This paper demonstrates that the global temperature observed in the past is mimicked with reasonably good accuracy. Evolutionary computation holds promise for modeling the global climate system, which looks hopelessly complex in classical perspective.

17

Składowe oceny animacji wirtualnych postaci ludzkich

Lach E., Chaja T.

Studia Informatica

|

2012

|

Vol. 33, nr 1

47-58

PL

W artykule zaprezentowano składowe oceny animacji wirtualnych postaci ludzkich, które mają za zadanie wykrycie i usunięcie widocznych defektów obserwowanych w automatycznie generowanych animacjach. Składowe oceniają realizm animacji. W artykule zostały także przedstawione eksperymenty, które wykazały, że użycie proponowanych składników zwiększa realizm animacji generowanych za pomocą programowania genetycznego.

EN

The paper proposes evaluation methods for virtual humans behaviors, which are generated automatically. Presented methods measure realism of an animation. Experiments are described, which generate animations by means of genetic programming. Obtained results show that using proposed methods produces more realistic animations.

18

Genetic programming modeling of the critical size of inclusions

Kovačič M., Šarler B.

Computer Methods in Materials Science

|

2011

|

Vol. 11, No. 1

41-45

EN

Spring steel quality has a major impact on spring life. Spring steel quality depends also on the inclusions presence. 7 dynamically tested and broken springs (51CrV4) were analyzed. The dynamic test result is the number of the cycles before spring breakage. We were interested in dependency of the inclusion size and the distance from the surface of the inclusion on the spring tool life. In the paper the genetic programming method was used. In the proposed concept the mathematical models for spring life undergo adaptation. The results show that the proposed concept can be used in practice.

PL

Jakość stali sprężynowej decyduje o długości życia spręży-ny. Jakość tej stali zależy przede wszystkim od obecności wy-dzieleń. Analizowano 7 sprężyn ze stali 51CrV4 poddanych dynamicznym obciążeniom do zniszczenia. W próbach wy-znaczono liczbę cykli obciążenia do zniszczenia sprężyny. Celem pracy było wyznaczenie zależności pomiędzy wielkością cząstek wydzieleń i ich odległością od powierzchni a czasem życia sprężyny. Do wyznaczenia tej zależności wykorzystano programowanie genetyczne. W zaproponowanym rozwiązaniu pro-wadzona jest adaptacja modelu czasu życia sprężyny. Analiza wyników potwierdziła praktyczne zastosowanie opracowanego modelu.

19

Genetic programming for the prediction of tensile strength of cast iron

Duda J., Stawowy A.

Archives of Foundry Engineering

|

2011

|

Vol. 11, iss. 4

31-34

EN

In this paper we propose genetic programming (GP) to predict tensile strength of ductile cast iron. The chemical composition and pouring temperature were used as explanatory input variables (parameters), while tensile strength as dependent output variable (response). On the basis of real data set collected in a one of the Polish foundries, two different models for output variable were developed by genetic programming. Statistical analysis of obtained results and two test cases were employed to compare the accuracy of the GP model with the neural network (NN) model and a linear multiple regression model. The comparison demonstrated that the GP outperforms regress ion techniques, while it is generally worse than NN. Nevertheless GP can be a powerful tool for predicting the mechanical properties of cast iron as it provides a mathematical model, which can be further analyzed.

20

Adaptive switching of mutation rate for genetic algorithms and genetic programming

Spalek J., Gregor M.

Applied Computer Science

|

2011

|

Vol. 7, no 1

30-37

EN

The paper concerns the application of Genetic Algorithms and Genetic Programming to complex tasks such as automated design of control systems, where the space of solutions is non-trivial and may contain discontinuities. An adaptive value-switching mechanism for mutation rate control is proposed. It is shown that the proposed mechanism is useful in preventing the search from getting trapped in local extremes of the fitness landscape.