Search

A hybrid computational method based on the extreme learning machine (ELM) neural network for classification and the evolutionary genetic algorithms (GA) for feature selection is presented in this paper. The dimension of the feature space is reduced by the GA in this scheme and only the appointed features are selected. The data is then passed to an ELM neural network for the classification phase. An automated system for the diagnosis of Parkinson's Disease (PD) based on gait data set is proposed by using the GA-ELM method. PD is a neurodegenerative disease that may cause change in the central nervous causing disturbance to the gait cycle duration. Our hybrid GA-ELM algorithm has produced an optimized diagnosis of PD from healthy subjects given in the gait dataset with accuracy 93.5%, and with five effective features that reduce the original dataset dimension. [ABSTRACT FROM AUTHOR]

An automated system for early diagnosis of type 2-diabetes mellitus is proposed in this paper, by using the Extreme Learning Machine neural network for classification and the evolutionary genetic algorithms for feature extraction, to be employed on a real data set from Saudi Arabian patients. The dimension of the feature space is reduced by the genetic algorithms and only the effective features are selected. The data is then fed to an Extreme Learning Machine neural network for classification. Diabetes is a major health problem in both industrial and developing countries, and when it appears in pregnancies it may cause many complications, hence its early diagnosis is beneficial for both mother and fetus. Our hybrid algorithm, the GA-ELM algorithm, has produced an optimized diagnosis of type 2-diabetes patients and classified the data set with an accuracy of 97.5% and with six effective features, out of the original eight features given in the dataset. Moreover, comparisons of the GA-ELM method with other available methods were conducted and the results are promising. [ABSTRACT FROM AUTHOR]

An automated system for the diagnosis of lung cancer is proposed in this paper, the system is designed by combining two major methodologies, namely the fuzzy base systems and the evolutionary genetic algorithms (GAs), to be employed on lung cancer data to assist physicians in the early detection of lung cancers, and hence obtain an early automated diagnosis complementary to that by physicians. Our hybrid algorithm, the genetic-fuzzy algorithm, has produced optimized diagnosis systems that attain high classification performance, in fact, our best six rule system obtained a 97.5% accuracy, with simple and well interpretive rules, with 93% degree of confidence, and without the need for dimensionality reduction. The results on real data indicate that the proposed system is very effective in the diagnosis of lung cancer and can be used for clinical applications. [ABSTRACT FROM AUTHOR]

To improve the understanding of the GA in dynamic environments we explore a set of test problems, the shaky ladder hyper-defined functions (sl-hdf), and extend these functions to create versions that are equivalent to many classical dynamic problems. We do this by constraining the space of all sl-hdfs to create representations of these classical functions. We have examined three classical problems, and compared sl-hdf versions of these problems with their standard representations. These results show that the sl-hdfs are representative of a larger class of problems, and can represent a larger class of test suite. Previous results on sl-hdf showed that GA performance is best in the Defined Cliffs variant of the sl-hdf. We build upon these results to improve GA performance in several classes of real world dynamic problems by modifying the problem representation. These results lend insight into dynamic problems where the GA will perform well. [ABSTRACT FROM AUTHOR]