-
[show abstract]
[hide abstract]
ABSTRACT: Ethanol production using hemicelluloses has recently become a focus of many researchers. In order to promote D: -xylose fermentation, we cloned the bacterial xylA gene encoding for xylose isomerase with 434 amino acid residues from Agrobacterium tumefaciens, and successfully expressed it in Saccharomyces cerevisiae, a non-xylose assimilating yeast. The recombinant strain S. cerevisiae W303-1A/pAGROXI successfully colonized a minimal medium containing D: -xylose as a sole carbon source and was capable of growth in minimal medium containing 2% xylose via aerobic shake cultivation. Although the recombinant strain assimilates D: -xylose, its ethanol productivity is quite low during fermentation with D: -xylose alone. In order to ascertain the key enzyme in ethanol production from D: -xylose, we checked the expression levels of the gene clusters involved in the xylose assimilating pathway. Among the genes classified into four groups by their expression patterns, the mRNA level of pyruvate decarboxylase (PDC1) was reduced dramatically in xylose media. This reduced expression of PDC1, an enzyme which converts pyruvate to acetaldehyde, may cause low ethanol productivity in xylose medium. Thus, the enhancement of PDC1 gene expression may provide us with a useful tool for the fermentation of ethanol from hemicellulose.
Bioprocess and Biosystems Engineering 01/2012; 35(1-2):183-9. · 1.81 Impact Factor
-
Pattern Recognition Letters. 01/2011; 32:1930-1935.
-
[show abstract]
[hide abstract]
ABSTRACT: The classification of biological samples measured by DNA microarrays has been a major topic of interest in the last decade, and several approaches to this topic have been investigated. However, till now, classifying the high-dimensional data of microarrays still presents a challenge to researchers. In this chapter, we focus on evaluating the performance of the training algorithms of the single hidden layer feedforward neural networks (SLFNs) to classify DNA microarrays. The training algorithms consist of backpropagation (BP), extreme learning machine (ELM) and regularized least squares ELM (RLS-ELM), and an effective algorithm called neural-SVD has recently been proposed. We also compare the performance of the neural network approaches with popular classifiers such as support vector machine (SVM), principle component analysis (PCA) and fisher discriminant analysis (FDA).
Advances in experimental medicine and biology 01/2011; 696:135-43. · 1.09 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: Training neural networks has attracted many researchers for a long time. Many training algorithms and their improvements have been proposed. However, up to now, improving performance of training algorithms for neural networks is still a challenge. In this paper, we investigate a new training method for single hidden layer feedforward neural networks (SLFNs) which use ‘tansig’ activation function. The proposed training algorithm uses SVD (Singular Value Decomposition) to calculate the network parameters. It is simple and has low computational complexity. Experimental results show that the proposed approach can obtain good performance with a compact network which has small number of hidden units.
Convergence Information Technology, International Conference on. 11/2009;
-
[show abstract]
[hide abstract]
ABSTRACT: Clonorchis sinensis, the parasite that causes clonorchiasis, is endemic in many Asian countries, and infection with the organism drives changes in the liver tissues of the host. However, information regarding the molecular events in clonorchiasis remains limited, and little is currently known about host-pathogen interactions in clonorchiasis. In this study, we assessed the gene expression profiles in mice livers via DNA microarray analysis 1, 2, 4, and 6 weeks after induced metacercariae infection. Functional clustering of the gene expression profile showed that the immunity-involved genes were induced in the livers of the mice at the early stage of metacercariae infection, whereas immune responses were reduced in the 6-week liver tissues after infection in which the metacercariae became adult flukes. Many genes involved in fatty acid metabolism, including Peci, Cyp4a10, Acat1, Ehhadh, Gcdh, and Cyp2 family were downregulated in the infected livers. On the other hand, the liver tissues infected with the parasite expressed Wnt signaling molecules such as Wnt7b, Fzd6, and Pdgfrb and cell cycle-regulating genes including cyclin-D1, Cdca3, and Bcl3. These investigations constitute an excellent starting point for increased understanding of the molecular mechanisms underlying host-pathogen interaction during the development of C. sinensis in the host liver.
Parasitology Research 11/2009; 106(1):269-78. · 2.15 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: Evolutionary algorithms (EAs) have been successfully applied in many complex optimization problems and engineering disciplines. Also, the single hidden-layer feedforward neural networks (SLFNs) have been widely used for machine learning due to their ability to form boundaries with arbitrary shape and to approximate any function with arbitrarily small error if the activation functions are chosen properly (Huang et al., 2000). Hematocrit density is an important factor for medical procedures and hemodialysis, and is the most highly affecting factor influencing the accuracy of glucose measurements with a hand-held device that uses the whole blood. Enzymatic reaction in glucose measurement with the electrochemical glucose biosensors is represented in the form of ion transfer to the electrode in the biosensor. Hematocrit density can be estimated while measuring the glucose value with the SLFN trained by combination of extreme learning machine (ELM) and differential evolution (DE) process. This ionization of enzymatic reaction along time produces the anodic current curve, and is presented to SLFNs as the input vector. SLFNs trained by ELM, RLS-ELM and ELS-ELM are compared for hematocrit density estimation. It shows that they can be a good method for estimating and reducing the effect of hematocrit density on glucose measurement by handheld devices. Since this approach can provide the hematocrit density while measuring the glucose value, it can be simply implemented in the handheld devices to enhance the accuracy of glucose measurement which has to use the whole blood.
10/2009; , ISBN: 978-953-307-008-7
-
International Conference on Networked Computing and Advanced Information Management, NCM 2009, Fifth International Joint Conference on INC, IMS and IDC: INC 2009: International Conference on Networked Computing, IMS 2009: International Conference on Advanced Information Management and Service, IDC 2009: International Conference on Digital Content, Multimedia Technology and its Applications, Seoul, Korea, August 25-27, 2009; 01/2009
-
Proceedings of the IEEE International Symposium on Computational Intelligence in Robotics and Automation, CIRA 2009, 15-18 December 2009, Daejeon, Korea; 01/2009
-
Bio-Science and Bio-Technology - International Conference, BSBT 2009 Held as Part of the Future Generation Information Technology Conference, FGIT 2009 Jeju Island, Korea, December 10-12, 2009 Proceedings; 01/2009
-
IEICE Transactions. 01/2009; 92-D:10-15.
-
[show abstract]
[hide abstract]
ABSTRACT: Recently, a novel learning algorithm called extreme learning machine (ELM) was proposed for efficiently training single-hidden-layer feedforward neural networks (SLFNs). It was much faster than the traditional gradient-descent-based learning algorithms due to the analytical determination of output weights with the random choice of input weights and hidden layer biases. However, this algorithm often requires a large number of hidden units and thus slowly responds to new observations. Evolutionary extreme learning machine (E-ELM) was proposed to overcome this problem; it used the differential evolution algorithm to select the input weights and hidden layer biases. However, this algorithm required much time for searching optimal parameters with iterative processes and was not suitable for data sets with a large number of input features. In this paper, a new approach for training SLFNs is proposed, in which the input weights and biases of hidden units are determined based on a fast regularized least-squares scheme. Experimental results for many real applications with both small and large number of input features show that our proposed approach can achieve good generalization performance with much more compact networks and extremely high speed for both learning and testing.
International Journal of Neural Systems 11/2008; 18(5):433-41. · 4.28 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: The development of functional Magnetic Resonance Imaging (fMRI) offers promising approaches in the study of human brain function. It dramatically improves an ability to collect large amount of data about brain activity in human subjects performing tasks. Analysis of fMRI is essential for successful detection of cognitive states. This paper presents the use of single hidden-layer feedforward neural networks (SLFNs) to decode cognitive states from fMRI data. The SLFNs are trained by an improved extreme learning machine (ELM) which is named as regularized least-squares ELM (RLS-ELM). Experimental results show that the proposed method can give better performance compared to the Gaussian Naïve Bayes (GNB) classifier that is known as one of the best classifiers for decoding cognitive states.
Networked Computing and Advanced Information Management, 2008. NCM '08. Fourth International Conference on; 10/2008
-
[show abstract]
[hide abstract]
ABSTRACT: An effective training algorithm called extreme learning machine (ELM) has recently proposed for single hidden layer feedforward neural networks (SLFNs). It randomly chooses the input weights and hidden layer biases, and analytically determines the output weights by a simple matrix-inversion operation. This algorithm can achieve good performance at extremely high learning speed However, it may require a large number of hidden units due to non-optimal input weights and hidden layer biases. In this paper, we propose a new approach, evolutionary least-squares extreme learning machine (ELS-ELM), to determine the input weights and biases of hidden units using the differential evolution algorithm in which the initial generation is generated not by random selection but by a least squares scheme. Experimental results for function approximation show that this approach can obtain good generalization performance with compact networks.
Neural Networks, 2008. IJCNN 2008. (IEEE World Congress on Computational Intelligence). IEEE International Joint Conference on; 07/2008
-
Proceedings of the IEEE Congress on Evolutionary Computation, CEC 2008, June 1-6, 2008, Hong Kong, China; 01/2008
-
Proceedings of the IEEE International Conference on Networking, Sensing and Control, ICNSC 2008, Hainan, China, 6-8 April 2008; 01/2008
-
IEICE Transactions. 01/2008; 91-D:1042-1049.
-
JDCTA. 01/2008; 2:40-46.
-
[show abstract]
[hide abstract]
ABSTRACT: Two-dimensional gel electrophoresis (2D-GE) is the key technique in large-scale protein identification from complex protein mixtures. The 2D-GE images, which represent protein signals as spots of various intensities and sizes, may yield a lot of information that can help the biologists for exploring the elements affecting human health. Automatic analysis for the gel images can help saving time and labor for biologist in identifying and matching the proteins across the 2D-GE images in which protein spot segmentation is a critical step. In this paper, we present a novel approach for protein spot detection, which is a marker-free watershed that does not require specification of predefined markers for the process of finding watershed contour lines. This approach includes a selective nonlinear filter and pixel intensity distribution analysis for removing local minima which causes over-segmentation when applying watershed transform. It then superimposes those true minima over the reconstructed gradient image before applying watershed transform for spot segmentation. The effectiveness of this marker-free approach was experimentally comparable with other methods.
Information Technology Convergence, 2007. ISITC 2007. International Symposium on; 12/2007
-
[show abstract]
[hide abstract]
ABSTRACT: Microarrays have been useful in the diagnosis and treatment due to their abilities to survey a large number of genes quickly and to study samples with small amount. With the development of microarray technology, the prospects for effective and reliable disease diagnosis and management can be significantly improved if the classification performance on microarray data is improved. This paper presents an application of the compact single hidden layer feedforward neural networks (C-SLFNs) trained by an improved extreme learning machine (ELM) algorithm to classify microarray data for cancer diagnosis. Experimental results show that the classification accuracy is higher than those achieved by the SLFNs trained by the original ELM and back-propagation (BP) algorithms, and other popular methods for microarray classification such as support vector machine (SVM) and Fisher discriminant analysis (FDA). Moreover, the trained C-SLFNs have a smaller number of hidden units than the SLFNs trained by the original ELM and BP, which results in quick response to new input patterns.
Frontiers in the Convergence of Bioscience and Information Technologies, 2007. FBIT 2007; 11/2007
-
[show abstract]
[hide abstract]
ABSTRACT: In medical diagnosis classification, we often face the unbalanced number of data samples between the classes in which there are not enough samples in rare classes. Conventional competitive learning methods are not suitable in this situation, because they usually tend to be biased to the classes that have the larger number of data samples. In this paper, we proposed a cost-sensitive extension of regularized least square(RLS) algorithm that penalizes errors of different samples with different weights and some rules of thumb to determine those weights. The significantly better classification accuracy of weighted RLS classifiers showed that it is promising substitution of other previous cost-sensitive classification methods for unbalanced data set.
Frontiers in the Convergence of Bioscience and Information Technologies, 2007. FBIT 2007; 11/2007
