In the present work, existing empirical expressions for longitudinal dispersion coefficient of rivers (K) are evaluated. They are found inadequate primarily because these expressions ignore the channel sinuosity, an important parameter representing a river’s transverse irregularities that affect mixing process. Hence, a new expression for K is derived taking into account the sinuosity besides few of other hydraulic and geometric characteristics of a river. The model makes use of genetic algorithm (GA) on published field data. Based on several performance indices, the new expression is found superior to many existing expressions for estimating K. The sensitivity and error analysis conducted on parameters of the new expression show the channel sinuosity an important input for predicting K accurately. Any error in measurement of sinuosity would lead to significant deviation in the longitudinal dispersion coefficient in sinuous rivers.
The necessity to generate time series of runoff for planning and design purposes and environmental protection at ungauged sites is often the case in water resources studies. As in the case of the absence of measured runoff optimisation techniques cannot be used to estimate the parameters of rainfall-runoff models, regional estimation methods are used instead. In previous studies usually regression methods were used for relating the model parameters to the catchment characteristics in a given region. In the paper a different method for the regional calibration of a monthly water balance model is proposed for the case of sparse runoff data. Instead of using the regional regression, the method involves the regional calibration of a monthly water balance model to several gauged catchments in a given region simultaneously. These catchments were pooled together using cluster analysis of selected basin physiographic properties. For the model calibration a genetic programming algorithm was employed and two problem specific fitness functions were proposed. It is expected, that the regionally calibrated model parameters can be used in ungauged basins with similar physiographic conditions. The performance of such a regional calibration scheme was compared with two single site calibration methods in the Záhorie region of West Slovakia. and Článok sa zaoberá možnosťami využitia hydrologického modelovania pre účely určovania prietokov v povodiach bez ich pozorovaní. V takýchto prípadoch nemožno určiť parametre modelu klasickou kalibráciou, pri ktorej sa pri hľadaní parametrov modelu posudzuje čo najlepšia zhoda medzi simulovanými a pozorovanými prietokmi. Jednou z možností je zisťovanie parametrov modelu na základe posudzovania ich vzájomného vzťahu s hydrologickými, topografickými alebo fyzicko-geografickými vlastnosťami povodí, ktoré zohrávajú pri tvorbe odtoku dominantnú úlohu, ďalšia možnosť je určenie jednotných parametrov modelu kalibráciou modelu pre skupinu povodí (región alebo regionálny typ), vyčlenenú na základe podobných vlastností ovplyvňujúcich tvorbu odtoku. V článku je aplikovaná metodika určovania regionálnych parametrov hydrologického bilančného modelu v mesačnom časovom kroku na vybraných povodiach západného Slovenska. Namiesto prístupu regionálnej regresie je tu využitý spôsob regionálnej kalibrácie modelu pre regióny vyčlenené na základe podobnosti rôznych fyzicko-geografických vlastností. Pri regionálnej kalibrácii modelu boli využité metódy genetického algoritmu, pričom boli testované dve objektívne funkcie. Výsledky regionálnej kalibrácie sú porovnané s výsledkami kalibrácie modelu pre jednotlivé povodia. Regionálne určené parametre modelu môžu byť využité na modelovanie priemerných mesačných prietokov v povodiach bez pozorovaní, patriacich do príslušného regiónu alebo regionálneho typu.
This paper introduces a method how to transform one regular grammar to the second one. The transformation is based on regular grammar distance computation. Regular grammars are equivalent to finite states machines and they are represented by oriented graphs or by transition matrices, respectively. Thus, the regular grammar distance is defined analogously to the distance between two graphs. The distance is measured as the minimal count of elementary operations over the grammar which transform the first grammar to the second one. The distance is computed by searching an optimal mapping of non-terminal symbols of both grammars. The computation itself is done by the genetic algorithm because the exhaustive evaluation of mapping leads to combinatorial explosion. Transformation steps are derived from differences in matrices. Differences are identified during the computation of the distance.
learning machine (ELM), as a new learning mechanism for single hidden layer feedforward neural networks (SLFNs), has shown its advantages, such as fast computation speed and good generalization performance. However, the weak robustness of ELM is an unavoidable defect for image classification. To address the problem, we propose a novel ensemble method which combines rotation forest and selective ensemble model in this paper. Firstly, ELM and rotation forest are integrated to construct an ensemble classifier (RF-ELM), which combines the advantages of both rotation forest and ELM. The purpose of rotation forest here is to enhance the diversity of each base classifier which can improve the performance generalization. Then several ELMs are removed from the ensemble pool by using genetic algorithm (GA) based selective ensemble model to further enhance the robustness. Finally, the remaining ELMs are grouped as a selected ensemble classifier (RFSEN-ELM) for image classification. The performance is analyzed and compared with several existing methods on benchmark datasets and the experimental results demonstrate that the proposed algorithm substantially improves the accuracy and robustness of classification at an acceptable level of training cost.
A key stage in the design of an effective and efficient genetic algorithm is the utilisation of dornain specific knowledge. Once appropriate features have been identified, genetic operators can then be designed which inanipulate these features in well defined ways. In particular, the crossover operátor is designed so as to preserve in any offspring features cominon to both parental solutions and to guarantee that ordy features that appear in the parents appear in the offspring. Forma analysis [1] provides a well-defined frarnework for such a design process.
In this paper we consider the class of bisection problems. Features proposed for set recombination [2] are shown to be redundant when applied to bisection problems. Despite this inherent redundancy, approaches based on such features háve been successfully applied to graph bisection problems [3].
In order to overcome this redundancy and to obtain performance gains over previous genetic algorithm based approaches to graph bisection a natural choice of features is one based on node pairs. However, such features result in a crossover operator that displays degenerative behaviour and is of no practical use.